The DOI matches its Crossref record; 68 of the 77 references it cites were found in a registry or an index, and 1 are not checked yet; none of the 90 sources its claims cite is checked for support yet.
Explainable AI in medical imaging: An overview for clinical practitioners – Beyond saliency-based XAI approaches
Open accessAbstract
Driven by recent advances in Artificial Intelligence (AI) and Computer Vision (CV), the implementation of AI systems in the medical domain increased correspondingly. This is especially true for the domain of medical imaging, in which the incorporation of AI aids several imaging-based tasks such as classification, segmentation, and registration. Moreover, AI reshapes medical research and contributes to the development of personalized clinical care. Consequently, alongside its extended implementation arises the need for an extensive understanding of AI systems and their inner workings, potentials, and limitations which the field of eXplainable AI (XAI) aims at. Because medical imaging is mainly associated with visual tasks, most explainability approaches incorporate saliency-based XAI methods. In contrast to that, in this article we would like to investigate the full potential of XAI methods in the field of medical imaging by specifically focusing on XAI techniques not relying on saliency, and providing diversified examples. We dedicate our investigation to a broad audience, but particularly healthcare professionals. Moreover, this work aims at establishing a common ground for cross-disciplinary understanding and exchange across disciplines between Deep Learning (DL) builders and healthcare professionals, which is why we aimed for a non-technical overview. Presented XAI methods are divided by a method's output representation into the following categories: Case-based explanations, textual explanations, and auxiliary explanations.
Checked 2026-10-09 · 1 reference not checked yet
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
This review provides a non-technical overview of non-saliency XAI methods for medical imaging, categorizing them into case-based, textual, and auxiliary explanations. It argues these methods diversify XAI beyond visual saliency maps and can help uncover model flaws, data outliers, distributional discrepancies, and biases, though clinical integration and empirical assessment remain under-researched.
Key findings
- Non-visual XAI methods are grouped by output representation into case-based explanations (e.g., TCAV, ACE, Network Dissection, influence functions, GANterfactuals), textual explanations (e.g., VQA, Visual Dialog, image captioning), and auxiliary explanations (e.g., t-SNE, UMAP, ProtoTree, TreeView, uncertainty quantification with BNNs and Deep Ensembles).
- The paper cites limitations of saliency-based methods: Adebayo et al. found saliency methods can be insensitive; Ghorbani et al. demonstrated vulnerability to image perturbations and adversarial attacks; Tomsett et al. noted inconsistent evaluation metrics in sanity-check studies.
- Textual explanation datasets include VQA with ~0.25 million images, ~0.76 million questions, and ~10 million answers, and VisDial with ten question-answer pairs on ~140k COCO images, totaling ~1.4M question-answer pairs.
- Uncertainty quantification is highlighted: BNNs were applied to BraTS 2017 with 285 subjects with high- or low-grade gliomas; Deep Ensembles can distinguish aleatoric from epistemic uncertainty, but low diversity between ensemble members can negatively affect uncertainty estimates and out-of-distribution detection.
Methods
- Design: narrative, non-technical review aimed at healthcare professionals and DL practitioners, focusing on XAI techniques not relying on saliency in medical imaging.
- Data/sample: literature and method examples rather than a primary patient cohort; cited datasets include MedNIST, ImageCLEF 2019 VQA-Med, BraTS 2017 (285 subjects), COCO/VisDial, ROCO, and IU X-Ray.
- Main analysis: methods are categorized by expected output into case-based, textual, and auxiliary explanations; Table 1 summarizes strengths, weaknesses, explanation target (data, internals, predictions), and explanation perspective (global, local).
Limitations
- Stated: there are no recommendations or restrictions for selecting appropriate XAI methods; assessment guidelines are relatively sparse; clinical integration and empirical assessment of XAI impact are little researched.
- Stated: non-visual XAI techniques may seem more specific and in some cases rely on method-specific knowledge for correct interpretation.
- Evident: this is a narrative review without a stated systematic search strategy, inclusion criteria, or quantitative synthesis; many examples rely on non-medical or limited medical datasets, so clinical generalizability is not established.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
83 Not checked yet · 18 Own interpretation · 15 No basis given
In the paper
“A prominent example is Influence Functions (IF) [30] proposed by Koh and Liang which approximate this during upweighting a specific sample by an infinitesimally small amount and measuring the change in loss and parameters.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Automated Concept-based Explanations (ACE)
What the sources say
- Not checked yetcites [30]
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“However, this leads to a challenging requirement of textual explanations, namely the dependence on sophisticated datasets, including images alongside descriptive semantic information.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.2. Textual explanations
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“Because of that, selecting an appropriate XAI method for the task at hand remains a challenge, especially considering the subjective perceptions of end-users alongside their individual needs [18,19] and relatively sparse assessment guidelines.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2. Non-Visual XAI methods in medical imaging
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“Consequently, apart from visual explanations, three subgroups of non-visual XAI methods were identified according to the type of result a user can expect when applying an XAI technique [17]: auxiliary explanations, case-based explanations, and textual explanations.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2. Non-Visual XAI methods in medical imaging
What the sources say
- Not checked yetcites [17]
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“Tomsett et al. [16] pointed out a lack of consistency concerning evaluation metrics in sanity-check studies concluding that despite the increasing effort, it remains challenging to evaluate visual explanations fully.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2. Non-Visual XAI methods in medical imaging
What the sources say
- Not checked yetcites [16] source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“Moreover, there is no agreed-upon threshold separating influential from non-influential instances.”
- Also stated in: § Table 1 · plain
“No agreed-upon threshold separating influential from non-influential instances”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Automated Concept-based Explanations (ACE)
What the sources say
- Not checked yetcites [30]
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § Table 1 · plain
In the paper
“A mandatory condition is for the loss function to be 2nd-order differentiable.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Automated Concept-based Explanations (ACE)
What the sources say
- Not checked yetcites [30]
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Compared to visual and auxiliary explanations, this explanatory method is less explored.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.1. Case-based explanations
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Moreover, visual XAI methods represent only a minor subset of all possible methods.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2. Non-Visual XAI methods in medical imaging
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
In the paper
“The inability to explain a model prediction in semantically and visually meaningful ways is a well-known shortcoming of several existing computer-aided diagnosis approaches [1].”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.2. Textual explanations
What the sources say
- Not checked yetcites [1] source
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- The quote only partly states this claim. 1
- It may state two separate claims as one. 33
- Probably not a substantial claim. 63
In the paper
“The authors stated that counterfactual explanations led to significantly better results regarding mental models, explanation satisfaction, and trust.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Automated Concept-based Explanations (ACE)
What the sources say
- Not checked yetcites [32] source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The quote only partly states this claim.
In the paper
“Conclusively, IF allow for understanding model behavior and detecting outliers in training data.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Automated Concept-based Explanations (ACE)
What the sources say
- Not checked yetcites [30]
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“A significant advantage of ACE, compared to TCAV, is that it mitigates the need for human supervision, as manual labeling is not required.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.1. Case-based explanations
What the sources say
- Not checked yetcites [24]
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“because humans tend to devalue explanations that contradict their prior beliefs.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2. Non-Visual XAI methods in medical imaging
What the sources say
- Not checked yetcites [7] source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“A somewhat different approach called Network Dissection [26] is a general framework designed to quantify the interpretability of individual units (e.g., neurons or channels) within a neural network.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Automated Concept-based Explanations (ACE)
What the sources say
- Not checked yetcites [26] source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“Even though visual XAI methods are considered easy to interpret and intuitive, some studies pointed out significant limitations.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2. Non-Visual XAI methods in medical imaging
What the sources say
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“TCAV determines a model's sensitivity to an underlying high-level concept for a given class by training a linear classifier to separate the images containing the defined concept from those that do not.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.1. Case-based explanations
What the sources say
- Not checked yetcites [23]
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Ghorbani et al. [15] demonstrated saliency maps' vulnerability to image perturbations and fragility to adversarial attacks”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2. Non-Visual XAI methods in medical imaging
What the sources say
- Not checked yetcites [15] source
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Since medical imaging is mainly associated with visual tasks, most explainability approaches incorporate visual XAI methods, including attribution and heat maps [9].”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2. Non-Visual XAI methods in medical imaging
What the sources say
- Not checked yetcites [9] source
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Miller argues that a good explanation is contrastive, selective, and truthful.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2. Non-Visual XAI methods in medical imaging
What the sources say
- Not checked yetcites [7] source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“However, channels are often not fully disentangled and can not be interpreted in isolation, so the interpretation ability of units activating to certain concepts should not be over-interpreted.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Automated Concept-based Explanations (ACE)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“For example, so-called counterfactual explanations aim to enable contrastive reasoning by altering the input image so that a given classifier would make a different prediction than its actual label.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Automated Concept-based Explanations (ACE)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“However, some research asserts that this approach is the most intuitive for human users to comprehend [7].”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.1. Case-based explanations
What the sources say
- Not checked yetcites [7] source
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“However, a limitation of this method is its lack of flexibility and strong model-specificity since a slight change in the task would require the acquisition of a new dataset alongside another training of the CycleGAN and the binary classifier.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Automated Concept-based Explanations (ACE)
What the sources say
- Not checked yetcites [32] source
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“However, the method relies on the manual setting of parameters, which can affect the outcome, e.g., resulting in duplicated or mixed concepts [25].”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.1. Case-based explanations
What the sources say
- Not checked yetcites [25] source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“With this technique, the authors confirmed that representations at different layers disentangle distinct categories of meaning and that different training techniques can significantly impact the representation learned by hidden units.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Automated Concept-based Explanations (ACE)
What the sources say
- Not checked yetcites [26] source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Moreover, applying these methods does not require an in-depth understanding or method-specific interpretation.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Visual Explanations
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
In the paper
“Moreover, as the authors of [75] pointed out, uncertainty modeling in DL systems makes such models safer for clinical use.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.3. Auxiliary explanations
What the sources say
- Not checked yetcites [75]
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This challenge is specifically present in medical imaging, where several imaging modalities, anatomical areas, and disease entities must be considered.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.2. Textual explanations
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“In general, diagnostic report generation is a time-consuming and knowledge-intensive task [45].”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.2. Textual explanations
What the sources say
- Not checked yetcites [45] source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Human classification of images or objects strongly relies on a subconscious comparison with prototypical parts or characteristics associated with certain objects.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.3. Auxiliary explanations
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
In the paper
“Uncertainty may appear in two forms, aleatoric uncertainty and epistemic uncertainty [67], with the former being caused by data or label noise and the latter being caused by sparsity or out-of-data distribution.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.3. Auxiliary explanations
What the sources say
- Not checked yetcites [67] source
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In contrast, there are also other methods for uncertainty estimation, justified by the fact that Bayesian approaches usually require complex modifications of the training process and can be computationally expensive.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.3. Auxiliary explanations
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: Bayesian approaches typically require complex modifications to the training process and can be computationally expensive.
In the paper
“It builds upon conditional probabilities to express the distances between data points and find similarities.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.3. Auxiliary explanations
What the sources say
- Not checked yetcites [12]
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Coupled with visualizations, systems encompassing image captioning can even pose as an educative, as findings described within generated captions can be projected directly onto the initial image, justifying which image area is responsible for the generation of a specific caption part.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Even though uncertainty quantification is often treated as a distinct topic separated from explainability, its contribution to this area speaks against separation and, on the contrary, promotes the incorporation of uncertainty estimation as an intrinsic part of XAI research [17].”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.3. Auxiliary explanations
What the sources say
- Not checked yetcites [17]
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“However, an interpretation may be challenging without a thorough understanding of how this method works.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.3. Auxiliary explanations
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Explanation methods involving this uncertainty category enable the identification of model limitations and provide information about possible optimization approaches.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.3. Auxiliary explanations
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Moreover, high precision is mandatory, and generated reports must focus on normal and abnormal findings related to medical characteristics rather than general descriptions [45,46].”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.2. Textual explanations
What the sources say
- Not checked yetcites [45] source
- Not checked yetcites [46]
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“as such explanations arise from deceiving the model by applying minimally required changes to the input, simultaneously revealing models' susceptibility to attacks [82].”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 3. Summary
What the sources say
- Not checked yetcites [82] source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“For example, in [41], Visual Dialog was deployed in radiology specific to chest X-ray images bringing forth RadVisDial, the first publicly available dataset for visual dialog in radiology.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.2. Textual explanations
What the sources say
- Not checked yetcites [41] source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Its hierarchical structure is intended to increase interpretability and lead to more insights regarding clusters in the data by exploiting the positive and the negative reasoning process.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.3. Auxiliary explanations
What the sources say
- Not checked yetcites [62] source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“Uniform Manifold Approximation and Projection (UMAP) [58] is a successor of t-SNE, superior in run time performance, scalability regarding larger datasets, and perseverance of data structure.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.3. Auxiliary explanations
What the sources say
- Not checked yetcites [58] source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For these reasons, systems such as VQA or VisualDialog are clinically limited and rely on further optimization research that takes the presented requirements into account.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“In simpler terms, t-SNE provides a depiction or intuition of how the data is arranged in a highdimensional space.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.3. Auxiliary explanations
What the sources say
- Not checked yetcites [12]
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Great potential is attributed to the quantification of uncertainty.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Also, their interpretation usually does not rely on a thorough understanding of the underlying internal functioning, as generated texts are easily interpretable.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
In the paper
“However, they also pointed out that X-rays are only one of the many data points available (e.g., medications, lab data, clinical data) for a patient's diagnosis and emphasize the importance of including these additional parameters in AI agents to overcome diagnostic limitations.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.2. Textual explanations
What the sources say
- Not checked yetcites [41] source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As has been shown, these categories are often very different regarding their individual contribution to explainability and the underlying methodology.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 3. Summary
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In relation to the generated output of the methods, textual explanations are less diversified than case-based explanations.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 3. Summary
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The differentiation between epistemic and aleatoric uncertainty can be used by DL engineers, in particular, to determine whether, and if so, model or training adjustments are necessary.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“The networks predict a voxel's probability of belonging to each segmentation class and generate calibrated confidence intervals of downstream biomarkers.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.3. Auxiliary explanations
What the sources say
- Not checked yetcites [75]
plaindirectn = 285- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“which can be particularly helpful for inexperienced or in-training healthcare professionals who want to confirm their diagnostic findings with the help of a support system.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Among other things, these considerations are also important for differentiating whether a model acts according to an open-world or closed-world assumption.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Ultimately, the distribution form characterizes the range of a system's behavior [69].”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.3. Auxiliary explanations
What the sources say
- Not checked yetcites [69] source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“Bayesian Neural Networks (BNNs) [68,71,72] are stochastic ANNs trained using Bayesian inference.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.3. Auxiliary explanations
What the sources say
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“Eaton-Rosene et al. [75] proposed a generalizable technique for quantifying uncertainty with Bayesian Neural Networks for semantic segmentation on the BraTS 2017 dataset [76], including 285 subjects with high-or low-grade gliomas.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.3. Auxiliary explanations
What the sources say
- Not checked yetcites [75]
- Not checked yetcites [76] source
plainn = 285- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Overall, a visualization using TreeView enables a convenient transition between factors, class labels, and an input data space.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.3. Auxiliary explanations
What the sources say
- Not checked yetcites [65]
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“A major disadvantage of UMAP is its lack of maturity, as it is a relatively new technique, and best practices are not yet established [60].”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.3. Auxiliary explanations
What the sources say
- Not checked yetcites [60]
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Secondly, t-SNE plots cannot always visualize the relative sizes of clusters appropriately; hence, cluster size and distance should not be over-interpreted.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.3. Auxiliary explanations
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“An essential advantage of Deep Ensembles is the possibility to distinguish between aleatoric and epistemic uncertainty: The arrangements' mean can be interpreted as aleatoric uncertainty, while the agreements' standard deviation represents epistemic uncertainty, which is low if all mean estimates yield a similar value and grows if the mean estimates differ strongly.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.3. Auxiliary explanations
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“While epistemic uncertainty is reducible by acquiring more data or optimizing the training process, aleatoric uncertainty is not because of a task's intrinsic randomness and the fact that a model is only an approximation of it [13,17].”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.3. Auxiliary explanations
What the sources say
- Not checked yetcites [13] source
- Not checked yetcites [17]
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“A significant advantage is that the interpretation of images, and thus, the generation of diagnostic reports or documentation, can also be automated”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“BNNs can be designed in different ways regarding the selection of stochastic components, distribution approximation, and inference approaches [74].”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.3. Auxiliary explanations
What the sources say
- Not checked yetcites [74] source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Overall, it is noteworthy that systems like VQA or Image Captioning are not XAI methods as such but rather serve as an example of how an interplay between semantic and visual elements could serve as a rectification within the diagnostic process.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Visual Explanations
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Altering tunable hyperparameters, such as the perplexity (balancing the attention t-SNE gives to local and global aspects of the data), can drastically change the plot.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > 2.3. Auxiliary explanations
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Dependence on complex datasets including images and textual annotations”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
What the sources say
- Not checked yetcites [43] source
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Possibility of ambiguous result”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
What the sources say
- Not checked yetcites [62] source
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Semantic relationship between images and textual descriptions is intuitive, even for nonexperts”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
What the sources say
- Not checked yetcites [43] source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Especially with medical questions, it would be incorrect to state that the patient does not suffer from a specific disease if there is no record reporting this unless more information is given to confirm this assumption.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
In the paper
“Interplay between an image's semantic content description and a visual explanation”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
What the sources say
- Not checked yetcites [47]
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Interactive and context-related dialog”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
What the sources say
- Not checked yetcites [40] source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“An aspect that has so far been little researched is the clinical integration and empirical assessment of the impact of such XAI methods.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
In the paper
“Requires complex modifications to training process”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
What the sources say
- Not checked yetcites [71] source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Lack of maturity”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
What the sources say
- Not checked yetcites [58] source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“No manual labeling required”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
What the sources say
- Not checked yetcites [24]
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Detection of concepts beyond classes in classification task”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
What the sources say
- Not checked yetcites [26] source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Only applicable to models with a 2ndorder differentiable loss”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
What the sources say
- Not checked yetcites [30]
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Conclusively, even though non-visual XAI methods may appear less intuitive compared to prominent saliency-based approaches such as GradCAM [11], they significantly contribute to the diversification of XAI, allowing for the systematic uncovering of model flaws, data outliers, distributional discrepancies, and biases.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
What the sources say
- Not checked yetcites [11] source
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Only positive activations are considered”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
What the sources say
- Not checked yetcites [26] source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Differentiation of these assumptions can be crucial as open-world systems have the ability to denote low confidence when answering questions to which the answer is unknown, whereas closed-world systems would simply answer with the most likely answer (class) of a given subset as the opposite cannot be confirmed.”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“Cluster size and distance should not be over-interpreted”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
What the sources say
- Not checked yetcites [12]
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Allows for explorative interpretation of activations within a neural network but also investigation”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
What the sources say
- Not checked yetcites [12]
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“Dependence on binary classifier”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
What the sources say
- Not checked yetcites [32] source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Free-form and open-ended”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
What the sources say
- Not checked yetcites [37] source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Interpretation requires a thorough understanding of the method”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
What the sources say
- Not checked yetcites [65]
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Transition between factors, class labels, and input data space”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
What the sources say
- Not checked yetcites [65]
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“No manual formulation of prototypes/ concepts is required”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
What the sources say
- Not checked yetcites [62] source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Communication of inner workings in a nontechnical way”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
What the sources say
- Not checked yetcites [26] source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Improved time performance, Better perseverance of data structure”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
What the sources say
- Not checked yetcites [58] source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“Explorative explanations beyond feature attribution”
§ Explainable AI in medical imaging: An overview for clinical practitioners -Beyond saliency-based XAI approaches > Table 1
What the sources say
- Not checked yetcites [23]
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper relies on this without support.
A gap exists in non-technical overviews of non-visual XAI methods for medical imaging aimed at healthcare professionals.
“This review aims to fill that gap by providing a non-technical overview of common non-visual XAI methods that apply to medical imaging, along with their advantages, pitfalls, and limitations.”
The authors state this as an assumption.
The main need of the intended end-users, namely radiologists, clinicians, and doctors, is linking knowledge and confirming diagnosis.
“In this paper, we primarily refer to end-users as radiologists, clinicians, and doctors whose main need presumably might be the linking of knowledge and confirmation of diagnosis.”
The paper relies on this without support.
There is no mathematical or standardized definition of explainability and interpretability.
“Since there is neither a mathematical nor a standardized definition of explainability and interpretability, in this paper, a non-mathematical definition from the social sciences perspective will be used as given by Miller [7]”
The paper relies on this without support.
Models are typically not equipped to reject an input during training or inference if it is poorly represented by the underlying data or falls out of distribution.
“as models are usually not equipped with the ability to reject an input during training or inference if it is not represented well by the underlying data or falls out of distribution.”
The paper relies on this without support.
Bayesian approaches typically require complex modifications to the training process and can be computationally expensive.
“justified by the fact that Bayesian approaches usually require complex modifications of the training process and can be computationally expensive.”
The paper relies on this without support.
The agreement among models in an ensemble represents confidence in the overall ensemble.
“The models' agreement represents the confidence in the overall model ensemble.”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Recent developments include interactive dashboards that allow clinicians to explore how individual variables contribute to patient-specific risk scores364,424.”
From Artificial intelligence-driven multi-omics approaches in Alzheimer's disease: Progress, challenges, and future directions (2025) · cites this paper as [364]
Experimental — accuracy not yet measuredIn the citing paper
“These methods help us discern if confounders or biases are present in the model, allowing for their control or removal.107”
From Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects (2024) · cites this paper as [107]
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.74 · Cited by 24,513
Unpaired image-to-image translation using cycle-consistent adversarial networks
Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.244 · Cited by 23,602
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Barredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., et al. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.12.012 · Cited by 10,423
UMAP: Uniform Manifold Approximation and Projection
McInnes, L., Healy, J., Saul, N., & Großberger, L. (2018) · Journal of Open Source Software · doi:10.21105/joss.00861 · Cited by 9,826
The multimodal brain tumor image segmentation benchmark (BRATS)
Menze, B. H., Jakab, A., Bauer, S., Kalpathy-Cramer, J., Farahani, K., Kirby, J., Burren, Y., Porz, N., Slotboom, J., Wiest, R., et al. (2015) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2014.2377694 · Cited by 6,781
Show and tell: A neural image caption generator
Vinyals, O., Toshev, A., Bengio, S., & Erhan, D. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298935 · Cited by 6,318
Explanation in artificial intelligence: Insights from the social sciences
Miller, T. (2019) · Artificial Intelligence · doi:10.1016/j.artint.2018.07.007 · Cited by 5,302
Research works printed but not linked: 11
- Van der Maaten, Laurens, Hinton, Geoffrey, Visualizing data using t-SNE., ., vol. 9, no. 86, pp. 2579–2605, 2008.
- J. Adebayo, J. Gilmer, M. Muelly, I. Goodfellow, M. Hardt, B. Kim, Sanity checks for saliency maps, in: Proceedings of the 32nd International Conference on Neural Information Processing Systems.
- B. Kim et al., Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV), in: Proceedings of the 35th International Conference on Machine Learning, Jul. 2018, pp. 2668–2677. Accessed: Feb. 14, 2022. [Online]. Available: https://proceedings.mlr.press/v80/kim18d.html.
- A. Ghorbani, J. Wexler, J.Y. Zou, B. Kim, Towards Automatic Concept-based Explanations, in: Advances in Neural Information Processing Systems, 2019, vol. 32. Accessed: Jun. 03, 2022. [Online]. Available: https://proceedings.neurips.cc/paper/2019/hash/77d2afcb31f6493e350fca61764efb9a-Abstract.html.
- P.W. Koh, P. Liang, Understanding Black-box Predictions via Influence Functions, in: Proceedings of the 34th International Conference on Machine Learning, Jul. 2017, pp. 1885–1894. Accessed: Sep. 20, 2022. [Online]. Available: https://proceedings.mlr.press/v70/koh17a.html.
- K. Xu et al., Show, attend and tell: neural image caption generation with visual attention, in: Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37, Lille, France, Jul. 2015, pp. 2048–2057.
- T. Pearce, A. Brintrup, M. Zaki, A. Neely, High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach, in: Proceedings of the 35th International Conference on Machine Learning, Jul. 2018, pp. 4075–4084. Accessed: Dec. 12, 2022. [Online]. Available: https://proceedings.mlr.press/v80/pearce18a.html.
- M.S. Ayhan, P. Berens, Test-time Data Augmentation for Estimation of Heteroscedastic Aleatoric Uncertainty in Deep Neural Networks, presented at the Medical Imaging with Deep Learning, Apr. 2018. Accessed: Apr. 07, 2022. [Online]. Available: https://openreview.net/forum?id=rJZz-knjz.
- Y. Gal, Z. Ghahramani, Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning, in: Proceedings of The 33rd International Conference on Machine Learning, Jun. 2016, pp. 1050–1059. Accessed: Jul. 08, 2022. [Online]. Available: https://proceedings.mlr.press/v48/gal16.html.
- M.E.E. Khan, A. Immer, E. Abedi, M. Korzepa, Approximate Inference Turns Deep Networks into Gaussian Processes, in: Advances in Neural Information Processing Systems, 2019, vol. 32. Accessed: Jun. 08, 2022. [Online]. Available: https://proceedings.neurips.cc/paper/2019/hash/b3bbccd6c008e727785cb81b1aa08ac5-Abstract.html.
- F. D’Angelo, V. Fortuin, “Repulsive Deep Ensembles are Bayesian,” presented at the Neural Information Processing Systems, Jun. 2021. Accessed: Dec. 18, 2022. [Online]. Available: https://www.semanticscholar.org/paper/Repulsive-Deep-Ensembles-are-Bayesian-D'Angelo-Fortuin/be5491660a61d60606aaec8dc0e7e046fb930110.
Cited by
Sorted by citations
A Review of Explainable Artificial Intelligence in Healthcare
Sadeghi, Z., Alizadehsani, R., CIFCI, M. A., Kausar, S., Rehman, R., Mahanta, P., Bora, P. K., Almasri, A., Alkhawaldeh, R. S., Hussain, S., et al. (2024) · Computers and Electrical Engineering · doi:10.1016/j.compeleceng.2024.109370 · Cited by 598
Muhammad, D., & Bendechache, M. (2024) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2024.08.005 · Cited by 325
Mienye, I. D., Obaido, G., Jere, N., Mienye, E., Aruleba, K., Emmanuel, I. D., & Ogbuokiri, B. (2024) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2024.101587 · Cited by 212
Koçak, B., Ponsiglione, A., Stanzione, A., Bluethgen, C., Santinha, J., Ugga, L., Huisman, M., Klontzas, M. E., Cannella, R., & Cuocolo, R. (2024) · Diagnostic and Interventional Radiology · doi:10.4274/dir.2024.242854 · Cited by 168
“107 In general, XAI methods can be categorized into two main groups: pertur-bation-based and backpropagation-based explanations.”
Mathew, D. E., Ebem, D. U., Ikegwu, A. C., Ukeoma, P. E., & Dibiaezue, N. F. (2025) · Neural Processing Letters · doi:10.1007/s11063-025-11732-2 · Cited by 168
“Incorporating explainability into AI disease diagnosis not only assists healthcare professionals but also addresses concerns regarding safety, accountability, and ethical utilization of AI in healthcare [21].”
Metadata
- Authors
- Borys, K., Schmitt, Y. A., Nauta, M., Seifert, C., Krämer, N., Friedrich, C. M., & Nensa, F.
- Affiliations
- Essen University Hospital (DE)
- University of Duisburg-Essen (DE)
- Dortmund University of Applied Sciences and Arts (DE)
- Corresponding author
- Borys, Katarzyna
- ORCID
- Venue
- European Journal of Radiology
- Publisher
- Elsevier BV
- Published
- 2023-05
- Volume
- 162
- Pages
- 110786
- ISSN
- 0720-048X (ISSN-L)
- OpenAlex
- W4327919044
- Semantic Scholar
- b08ce42005c672f681c6ab4cff96f830ce0bf9fc
- Cited by
- 233
- References
- 77
- Citations by year
- 2026: 77 · 2025: 101 · 2024: 46 · 2023: 9
- FWCI
- 4.87
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- European Journal of Radiology (publishedVersion, other-oa)
- PubMed (publishedVersion)
- University of Twente Research Information (submittedVersion, other-oa)
- University of Twente Research Information (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › COVID-19 diagnosis using AI
- Keywords
- explainable AI, diagnostic imaging, case-based explanation, textual explanations, deep learning interpretability, clinicians, computer-aided diagnosis, image classification, image segmentation, image registration
- MeSH terms
- Artificial Intelligence, Health Personnel, Humans
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-09, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-09 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
