The DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index; 1 of the 15 sources its claims cite were checked for support.
Interactive Medical Image Segmentation Using Deep Learning With Image-Specific Fine Tuning
Open accessAbstract
Convolutional neural networks (CNNs) have achieved state-of-the-art performance for automatic medical image segmentation. However, they have not demonstrated sufficiently accurate and robust results for clinical use. In addition, they are limited by the lack of image-specific adaptation and the lack of generalizability to previously unseen object classes (a.k.a. zero-shot learning). To address these problems, we propose a novel deep learning-based interactive segmentation framework by incorporating CNNs into a bounding box and scribble-based segmentation pipeline. We propose image-specific fine tuning to make a CNN model adaptive to a specific test image, which can be either unsupervised (without additional user interactions) or supervised (with additional scribbles). We also propose a weighted loss function considering network and interaction-based uncertainty for the fine tuning. We applied this framework to two applications: 2-D segmentation of multiple organs from fetal magnetic resonance (MR) slices, where only two types of these organs were annotated for training and 3-D segmentation of brain tumor core (excluding edema) and whole brain tumor (including edema) from different MR sequences, where only the tumor core in one MR sequence was annotated for training. Experimental results show that: 1) our model is more robust to segment previously unseen objects than state-of-the-art CNNs; 2) image-specific fine tuning with the proposed weighted loss function significantly improves segmentation accuracy; and 3) our method leads to accurate results with fewer user interactions and less user time than traditional interactive segmentation methods.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
40 Own result · 26 Own interpretation · 9 Own method · 7 Not checked yet · 7 No basis given · 5 Sources not found · 1 Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Deep learning with convolutional neural networks (CNNs) has achieved state-of-the-art performance for automated medical image segmentation [1].”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Introduction
What the sources say
- Supportedcites [1] Litjens G Kooi T Bejnordi BE Setio AAA Ciompi F Ghafoorian M van der Laak JA Ginneken BV Sánchez CI A survey on deep learning in medical image analysis Medical Image Analysis 2017 42 60 88 28778026 source
The survey reports excellent segmentation results from neural networks (Section 3.3.1, p. 12). It also reports that CNN-based systems were the highest-performing in the EM 2012 neuronal segmentation challenge and the highest-ranked in the GLAS gland segmentation challenge (Section 4.4, p. 19), supporting the state-of-the-art characterization. (LLM, conf=0.90)
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.
- Supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“2) image-specific fine-tuning with the proposed weighted loss function significantly improves segmentation accuracy;”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Abstract
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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Experimental results show that 1) our model is more robust to segment previously unseen objects than state-of-the-art CNNs;”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Abstract
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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It shows that BIFSeg achieves a larger improvement of accuracy from the initial segmentation when compared with the use of CRF or BIFSeg(-w).”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 2D Segmentation of Multiple Organs from Fetal MRI
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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“BIFSeg achieves significantly better accuracy (p-value < 0.05) for the placenta, and previously unseen fetal lungs and maternal kidneys compared with P-Net + CRF and BIFSeg(-w).”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 2D Segmentation of Multiple Organs from Fetal MRI
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.
A result the paper reports from its own data — 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 the placenta and fetal brain, FCN, U-Net and P-Net achieve visually similar results that are close to the ground truth.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 2D Segmentation of Multiple Organs from Fetal MRI
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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“After image-specific fine-tuning, most pixels in the outputs of BIFSeg(-w) and BIFSeg have a probability close to 0.0 or 1.0.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 2D Segmentation of Multiple Organs from Fetal MRI
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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It can be observed that CRF and BIFSeg(-w) correct the initial segmentation moderately.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 3D Segmentation of Brain Tumors from T1c and FLAIR
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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, for fetal lungs and maternal kidneys that are previously unseen in the training set, FCN and U-Net lead to a large region of under-segmentation.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 2D Segmentation of Multiple Organs from Fetal MRI
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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Since the central region of the tumor has a low intensity that is similar to the background, 3D GrabCut obtains large under-segmentations.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 3D Segmentation of Brain Tumors from T1c and FLAIR
plaindirectSingle case- 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. 39
- Probably not a substantial claim. 13
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
“3) our method leads to accurate results with fewer user interactions and less user time than traditional interactive segmentation methods.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Abstract
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.
A result the paper reports from its own data — 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 contrast, BIFSeg achieves better results with the same set of scribbles.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 2D Segmentation of Multiple Organs from Fetal MRI
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.
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
“It shows that the performance of DeepMedic is low for T1c but high for FLAIR, and that of HighRes3DNet is the opposite.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 3D Segmentation of Brain Tumors from T1c and FLAIR
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.
A result the paper reports from its own data — 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 average machine time for 3D GrabCut, DeepMedic, and PC-Net is 3.87s, 65.31s and 3.83s, respectively (on the laptop), and that for HighRes3DNet is 1.10s (on the cluster).”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 3D Segmentation of Brain Tumors from T1c and FLAIR
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.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“CRF improves the segmentation to some degree, but large areas of under-segmentation still exist.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 3D Segmentation of Brain Tumors from T1c and FLAIR
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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It shows that BIFSeg takes noticeably less user time with similar or higher accuracy compared with the other three interactive segmentation methods.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 2D Segmentation of Multiple Organs from Fetal MRI
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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It can be observed that GrabCut achieves a poor segmentation except for the fetal brain where there is a good contrast between the target and the background.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 2D Segmentation of Multiple Organs from Fetal MRI
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 result the paper reports from its own data — 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 this 2D case, BIFSeg takes 0.72s in average for unsupervised image-specific fine-tuning.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 2D Segmentation of Multiple Organs from Fetal MRI
plainSingle case- 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 result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“HighRes3DNet and PC-Net obtain similar results, but PC-Net is less complex and has lower memory consumption.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 3D Segmentation of Brain Tumors from T1c and FLAIR
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.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It shows that P-Net achieves the best accuracy for unseen fetal lungs and maternal kidneys with average machine time 0.16s.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 2D Segmentation of Multiple Organs from Fetal MRI
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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“and the CNNs outperform 3D GrabCut, with DeepMedic and PC-Net performing better than HighRes3DNet.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 3D Segmentation of Brain Tumors from T1c and FLAIR
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.
A result the paper reports from its own data — 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 contrast, BIFSeg performs better than CRF and BIFSeg(-w).”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 3D Segmentation of Brain Tumors from T1c and FLAIR
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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“BIFSeg improves the average Dice score from 82.66% to 86.13% for the tumor core, and from 83.52% to 86.29% for the whole tumor.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 3D Segmentation of Brain Tumors from T1c and FLAIR
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.
A result the paper reports from its own data — 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 acts as a post-processing step after the initial segmentation and out-performs CRF.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Discussion and Conclusion
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.
None of the sources cited for this claim have been checked yet.
In the paper
“Since the scribbles are provided only in mis-segmented areas, the variations of position and length of scribbles are limited and much smaller than that of freely drawn scribbles used in traditional methods such as Random Walks [18] and Slic-Seg [21], and the output of BIFSeg also varies slightly with varying scribbles, as shown in Fig. 8.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Discussion and Conclusion
What the sources say
- Not checked yetcites [18] Grady L Schiwietz T Aharon S Westermann R Random walks for interactive organ segmentation in two and three dimensions: implementation and validation MICCAI 2005 773 780 16686030 source
- Not checked yetcites [21] Wang G Zuluaga MA Pratt R Aertsen M Doel T Klusmann M David AL Deprest J Vercauteren T Ourselin S Slic-Seg: A minimally interactive segmentation of the placenta from sparse and motion-corrupted fetal MRI in multiple views Medical Image Analysis 2016 34 137 147 27179367 PMC5052128 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.
It may state two separate claims as one.
A result the paper reports from its own data — 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 contrast, BIFSeg achieves better refined results for both the tumor core in T1c and the whole tumor in FLAIR.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 3D Segmentation of Brain Tumors from T1c and FLAIR
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.
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
“DeepMedic takes over 60 seconds for inference, while HighRes3DNet has too large a memory consumption to work on a laptop.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Discussion and Conclusion
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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Experiments on segmenting multiple organs from 2D fetal MRI and brain tumors from 3D MRI show that our method performs well on previously unseen objects and the image-specific fine-tuning outperforms CRF.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Discussion and Conclusion
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.
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
“BIFSeg achieves similar or higher accuracy with fewer user interactions and less user time than traditional interactive segmentation methods.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Discussion and Conclusion
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.
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
“Our framework is general, flexible and can handle both 2D and 3D segmentations with few assumptions of network structures.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Method
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.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Note that the energy optimization problem of Eq. (1) remains well-posed with Eq. (9), (10), and (11).”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Method > Weighted Loss Function during Network Update Step
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
“First, user-provided scribbles have much higher confidence than the other pixels, and they should have a higher impact on the loss function, leading to a weighted version of Eq. (3):”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Method > Weighted Loss Function during Network Update Step
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: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
In the paper
“HighRes3DNet [8] works on 3D whole images with relatively fast inference but needs a large amount of GPU memory, leading to high hardware requirements.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Introduction
What the sources say
- Not matchedcites [8] Li W Wang G Fidon L Ourselin S Cardoso MJ Vercauteren T On the compactness, efficiency, and representation of 3D convolutional networks: brain parcellation as a pretext task IPMI 2017 348 360
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
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.
- Not matched
In the paper
“For example, DeepMedic [7] works on 3D local patches to reduce memory requirements but results in a slow inference.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Introduction
What the sources say
- Not checked yetcites [7] Kamnitsas K Ledig C Newcombe VFJ Simpson JP Kane AD Menon DK Rueckert D Glocker B Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation Medical Image Analysis 2017 36 61 78 27865153
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.
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 is based on the fact that our CNNs are designed and trained to learn some common features, such as saliency, contrast and hyper-intensity, across different objects, which helps to generalize to unseen objects.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Method
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: unclear — It is unclear why the paper says it holds.
It may state two separate claims as one.
- Rests on an assumption: Current CNNs do not generalize well to previously unseen object classes that are absent from the training set.
In the paper
“DeepIGeoS [5] combines CNNs with user interactions and has demonstrated good interactivity.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Introduction
What the sources say
- Not checked yetcites [5] Wang G Zuluaga MA Li W Pratt R Patel PA Aertsen M Doel T Klusmann M David AL Deprest J Ourselin S DeepIGeoS: A deep interactive geodesic framework for medical image segmentation arXiv preprint arXiv:1707.00652 2017 PMC6594450 29993532
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.
Probably not a substantial claim. It may state two separate claims as one.
In the paper
“It has been shown that image-specific adaptation of a pre-trained Gaussian Mixture Model (GMM) helps to improve segmentation accuracy [6].”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Introduction
What the sources say
- Not matchedcites [6] Ribeiro HL Gonzaga A Hand image segmentation in video sequence by GMM: a comprarative analysis SIBGRAPI 2006 357 364
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
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.
Probably not a substantial claim.
- Not matched
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Here the tumor core in T1c images was previously seen while the whole tumor in FLAIR images was previously unseen for the CNNs.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 3D Segmentation of Brain Tumors from T1c and FLAIR
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.
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 is because DeepMedic has a small receptive field and tends to rely on local features. It is difficult to use local features to deal with T1c due to its complex appearance but easier to deal with FLAIR since the appearance is less complex.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 3D Segmentation of Brain Tumors from T1c and FLAIR
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.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Parameter setting was λ = 10.0, σ = 0.1, t0 = 0.2, t1 = 0.6, ϵ = 0.2, ω = 5.0 based on a grid search with the training data (i.e., whole tumor images were not used for parameter learning).”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 3D Segmentation of Brain Tumors from T1c and FLAIR
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.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Here the fetal brain and the placenta were previously seen objects, and the fetal lungs and maternal kidneys were previously unseen objects.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 2D Segmentation of Multiple Organs from Fetal MRI
plainn = 18- 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.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“We performed data splitting at patient level and used images from 10, 2, 6 patients for training, validation and testing, respectively.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 2D Segmentation of Multiple Organs from Fetal MRI
plainn = 18- 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.
Probably not a substantial claim.
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
“HighRes3DNet has a more complex model and tends to over-fit the tumor core.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 3D Segmentation of Brain Tumors from T1c and FLAIR
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.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Parameter setting was λ = 3.0, σ = 0.1, t0 = 0.2, t1 = 0.7, ϵ = 0.2, ω = 5.0 based on a grid search with the training data (i.e., fetal lungs and maternal kidneys were not used for parameter learning).”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Experiments and Results > 2D Segmentation of Multiple Organs from Fetal MRI
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.
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
“Table IV shows that DeepMedic achieves higher accuracy for the whole tumor. The reason is that our 3D experiment tends to learn to recognize hyper-intensity regions where local features have a higher influence than global features, and the relatively smaller receptive field of DeepMedic is more suitable for this task compared with the PC-Net and HighRes3DNet.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Discussion and Conclusion
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.
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
“First, these four organs were imaged with the same protocol. They have similar signal to noise ratio and share some common features, such as saliency, contrast and hyper-intensity.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Discussion and Conclusion
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
“Applying pre-trained models to previously unseen objects is a zero-shot learning problem [33].”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Discussion and Conclusion
What the sources say
- Not matchedcites [33] Zhang Z Saligrama V Zero-shot learning via semantic similarity embedding ICCV 2015 4166 4174
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
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.
- Not matched
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
“It therefore reduces the efforts needed for gathering and annotating training data and can be applied to some unseen organs directly.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Discussion and Conclusion
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.
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
“Similarly, the tumor core and whole tumor have some common features, e.g., lower or higher intensity than the remaining brain regions.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Discussion and Conclusion
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.
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
“Though unsupervised fine-tuning helps to correct small mis-segmentations when the initial fully-automated performance is satisfactory, it may lead to under-performance when dealing with some complex cases, considering the distribution mismatch between the training and testing data.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Discussion and Conclusion
hedgedconditional- 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.
None of the sources cited for this claim have been checked yet.
In the paper
“Dealing with unseen objects is a major advantage compared with traditional CNNs and even transfer learning [25] or weakly supervised learning [3], since for some objects it does not require annotated instances for training at all.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Discussion and Conclusion
What the sources say
- Not checked yetcites [25] Tajbakhsh N Shin JY Gurudu SR Hurst RT Kendall CB Gotway MB Liang J Convolutional neural networks for medical image analysis: full training or fine tuning? TMI 2016 35 5 1299 1312 26978662 source
- Not checked yetcites [3] Rajchl M Lee M Oktay O Kamnitsas K Passerat-Palmbach J Bai W Rutherford M Hajnal J Kainz B Rueckert D DeepCut: Object segmentation from bounding box annotations using convolutional neural networks TMI 2017 36 2 674 683 PMC7115996 27845654 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.
It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“To ensure that PC-Net was suitable for the brain tumor segmentation task despite the gain in efficiency, we compared the initial fully automated output of PC-Net, DeepMedic and HighRes3D. Then, we only used PC-Net for the interactive segmentation pipeline of BIFSeg.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Discussion and Conclusion
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.
Probably not a substantial claim. 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
“PC-Net is more compact than HighRes3DNet and less likely to achieve over-fitting, leading to better ability to deal with the unseen whole tumor.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Discussion and Conclusion
hedgeddirect- 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.
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
“Second, compared with FCN and U-Net, P-Net has far fewer parameters without reduction of the receptive field. Therefore, it can generalize better to previously unseen objects.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Discussion and Conclusion
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.
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
“Our BIFSeg framework is theoretically applicable to different CNN models.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Discussion and Conclusion
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
“It uses a bounding box-based CNN for binary segmentation and can segment previously unseen objects.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Discussion and Conclusion
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.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“In our experiments, hyper-parameters of BIFSeg (e.g., λ) were fixed globally in the testing stage.”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Discussion and Conclusion
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.
Interactive segmentation remains the state of the art for existing commercial surgical planning and navigation products.
“As such, interactive segmentation remains the state of the art for existing commercial surgical planning and navigation products.”
The paper relies on this without support.
Current CNNs do not generalize well to previously unseen object classes that are absent from the training set.
“The first challenge of using CNNs for interactive segmentation is that current CNNs do not generalize well to previously unseen object classes that are not present in the training set.”
The paper relies on this without support.
Current CNNs are not adaptive to different test images because their parameters are learned from training images and then fixed during testing.
“but current CNNs are not adaptive to different test images, as parameters of the model are learned from training images and then fixed in the testing stage, without image-specific adaptation.”
The paper relies on this without support.
Interactive segmentation often requires image-specific learning to handle large context variations among different images.
“Second, interactive segmentation often requires image-specific learning to deal with large context variations among different images”
The paper relies on this without support.
Annotations for medical images are often expensive to acquire.
“For medical images, annotations are often expensive to acquire as both expertise and time are needed to produce accurate annotations.”
The paper relies on this without support.
Transitioning from GMMs to CNNs for image-specific adaptation has not yet been demonstrated.
“However, transitioning from simple GMMs to powerful but complex CNNs in this context has not yet been demonstrated.”
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 cited source doesn’t support the claim as written.
In the citing paper
“McClure al. [667] | et | 2018 | CL | Segmentation | Brain segmentation | 5 | DWC: Distributed weight consolidation”
From A review of uncertainty quantification in deep learning: Techniques, applications and challenges (2021) · cites this paper as [667]
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“while existing deep learning-based interactive segmentation methods focus mainly on limited tasks and image modalities.”
From Segment anything in medical images (2024) · cites this paper as [9]
Experimental — accuracy not yet measuredIn the citing paper
“We found that for all of these three networks, the segmentation accuracy of TTD remains close to that of the single-prediction baseline.”
From Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks (2019) · cites this paper as [4]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Method > Unsupervised and Supervised Image-specific Fine-tuning
“(6)ϕ′(y^i|X^,θ)={+∞ifi∈Sandy^i=si0ifi∈Sandy^i≠si−logP(y^i|X^,θ)otherwise”
§ Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning > Method > Unsupervised and Supervised Image-specific Fine-tuning
“(4)argminY^{E(θ)=∑iϕ(y^i|X^,θ)+λ∑i,jψ(y^i,y^j|X^)}subjectto:y^i=siifi∈S”
Citations
Cites
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Fully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2699184 · Cited by 22,392
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2016) · arXiv · doi:10.48550/arxiv.1606.00915 · Cited by 22,392
A survey on deep learning in medical image analysis
Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.07.005 · Cited by 15,332
V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
Milletari, F., Navab, N., & Ahmadi, S.-A. (2016) · 2016 Fourth International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2016.79 · Cited by 11,931
Fully convolutional networks for semantic segmentation
Shelhamer, E., Long, J., & Darrell, T. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2572683 · Cited by 11,898
Caffe: Convolutional Architecture for Fast Feature Embedding
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014) · Proceedings of the 22nd ACM international conference on Multimedia · doi:10.1145/2647868.2654889 · Cited by 11,077
3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
Çiçek, Ö., Abdulkadir, A., Lienkamp, S. S., Brox, T., & Ronneberger, O. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46723-8_49 · Cited by 7,945
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
Research works printed but not linked: 2
- sermanet, 2014, Overfeat Integrated Recognition Localization and Detection Using Convolutional Networks
- vezhnevets, 2005, GrowCut: Interactive multi-label ND image segmentation by cellular automata, Proc GraphiCon, 150
Cited by
Sorted by citations
Items 601–700 of 842
Cell Segmentation by Modified U-Net Architecture for Biomedical Images
Kumar, C., N, M. K. T., & Narasimhadhan, A. V. (2020) · IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT) · doi:10.1109/conecct50063.2020.9198530 · Cited by 3
Interactive Medical Image Segmentation with Self-Adaptive Confidence CalibrationPreprint
Li, W., Xu, Q., Shen, C., Hu, B., Zhu, F., Li, Y., Jin, B., & Wang, X. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.07716 · Cited by 3
Self-citation3D Quantum-inspired Self-supervised Tensor Network for Volumetric Segmentation of Medical ImagesPreprint
Konar, D., Bhattacharyya, S., Gandhi, T. K., Panigrahi, B. K., & Jiang, R. (2020) · doi:10.36227/techrxiv.12909860 · Cited by 3
Li, G., Zhang, G., & Qin, C. (2021) · Sensors · doi:10.3390/s21186100 · Cited by 2
“As one of the fundamental problems in computer vision, it has obtained remarkable results in broad applications, such as medical image analysis [1], image editing [2], and especially pixel-level annotation [3].”
BackgroundGasmi, K., Ammar, L. B., Elshammari, H., & Yahya, F. (2023) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2023.033270 · Cited by 2
A decoder-free feature aggregation network for medical image segmentation
Ni, J., Mu, W., Pan, A., & Chen, Z. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18847-z · Cited by 2
Zhang, H., Zhu, P., Song, X., Ali, M. S., Li, Z., Liao, Z., Ruan, D., & Li, T. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3543198 · Cited by 2
SA-Seg: Annotation-Efficient Segmentation for Airway Tree Using Saliency-Based Annotation
Zhou, K., Chen, N., Zhang, Y., & Xu, X. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2025.3568855 · Cited by 2
A Review of Critical Deep Learning-Based Image Guidance Technologies for Surgical Robots
Cao, Y., Zhang, J., Li, H., Ren, B., Zhao, Y. H., Gao, C., & Zhou, Y. (2025) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2025.3584339 · Cited by 2
Hassan, F., Aslam, S., Ajibade, S.-S. M., Cho, J., & Easwaramoorthy, S. V. (2025) · Digital Health · doi:10.1177/20552076251380645 · Cited by 2
A general framework for interactive semantic segmentation refinement of point clouds
Zhang, P., Wu, T., Sun, J., Li, W., & Su, Z. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112919 · Cited by 2
Self-citationLinear Transformer Based U-Shaped Lightweight Segmentation Network
He, H., Editorial Office, Sun, C., Wang, Z., & Dan, Y. (2025) · Journal of Advanced Computational Intelligence and Intelligent Informatics · doi:10.20965/jaciii.2025.p1319 · Cited by 2
Shvetsov, N., Kilvaer, T. K., Tafavvoghi, M., Sildnes, A., Møllersen, K., Busund, L., & Bongo, L. A. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.111326 · Cited by 4
Applications of artificial intelligence in fetal MRI: a systematic review
Hai, Y., Le, D. C. P., & Duy, Q. V. (2025) · The Egyptian Journal of Radiology and Nuclear Medicine · doi:10.1186/s43055-025-01643-6 · Cited by 2
Wu, Y., Zhang, W., Ren, Y., Hu, J., Hu, W., & Qin, Q. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.115709 · Cited by 2
Wang, Q., Li, Z., Zhao, W., Wu, H., Xie, F., Guan, Z., & Zhao, W. Z. (2021) · IET Computer Vision · doi:10.1049/cvi2.12051 · Cited by 2
Advances in the application of artificial intelligence in solid tumor imaging
Shao, Y., Zhang, Y., Chen, H., Lu, S.-S., Zhang, S.-C., & Zhang, J. (2021) · WArtificial Intelligence in Cancer · doi:10.35713/aic.v2.i2.12 · Cited by 2
Machine Learning-based Image Processing in Support of Discus Hernia Diagnosis
Geroski, T., Ranković, V., Kovačević, V., Milovanovic, V., Rasulić, L., & Filipović, N. (2021) · IEEE International Conference on Bioinformatics and Bioengineering (BIBE) · doi:10.1109/bibe52308.2021.9635305 · Cited by 2
Few-Shot Learning For Auromatic Intracranial Hematoma Segmentation
Liu, X., Zhu, S., Yang, W., & Zhou, S. (2021) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm52615.2021.9669426 · Cited by 2
Generative Deep Belief Model for Improved Medical Image Segmentation
Balaji, P. (2022) · Intelligent Automation & Soft Computing · doi:10.32604/iasc.2023.026341 · Cited by 2
Computational Modelling and Machine Learning Based Image Processing in Spine Research
Šušteršič, T., Kovačević, V., Ranković, V., Rasulić, L., & Filipović, N. (2022) · Springer eBooks · doi:10.1007/978-3-030-98279-9_16 · Cited by 2
Barnawi, A., Thakur, N., Kumar, N., Kumar, K., Alzahrani, B. A., & AlMansour, A. A. (2023) · International Conference on Consumer Electronics · doi:10.1109/icce56470.2023.10043580 · Cited by 2
STC-Net: Fusing Swin Transformer and Convolution Neural Network for 2D Medical Image Segmentation
Wang, X., & Li, Y. (2022) · International Conference on Electronic Information Engineering and Computer Technology (EIECT) · doi:10.1109/eiect58010.2022.00069 · Cited by 2
Pixel Diffuser: Practical Interactive Medical Image Segmentation without Ground Truth
Ju, M., Yang, J.-W., Lee, J.-Y., Lee, M., Ji, J., & Kim, Y. (2023) · Bioengineering · doi:10.3390/bioengineering10111280 · Cited by 2
Autoencoder and CNN for Content-based Retrieval of Multimodal Medical Images
S, S. K. J., & Vigila, S. M. C. (2024) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2024.0150429 · Cited by 2
Asymmetric Source-Free Unsupervised Domain Adaptation for Medical Image Diagnosis
Zhang, Y., Huang, Z.-A., Wu, J., & Tan, K. C. (2024) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai59869.2024.00051 · Cited by 2
Brain Tumor Prediction Using CNN Architecture and Augmentation Techniques: Analytical Results
Mishra, S., Elappila, M., & Yogish, D. (2024) · IEEE International Conference on Contemporary Computing and Communications (InC4) · doi:10.1109/inc460750.2024.10649368 · Cited by 2
Artificial Intelligence to Reshape the Healthcare Ecosystem
Reali, G., & Femminella, M. (2024) · Future Internet · doi:10.3390/fi16090343 · Cited by 4
Huang, Y., Shen, C., Li, W., Wang, X., Jin, B., & Cai, H. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72111-3_45 · Cited by 2
Self-citationAlpar, O., Soukup, O., Ryška, P., Paluska, P., Vališ, M., & Krejcar, O. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112580 · Cited by 2
Fu, G., Cui, W., Yang, M., Si, M., Cui, W., Wang, H., Fu, S., & Zhang, Y. F. (2025) · Optics Communications · doi:10.1016/j.optcom.2025.131615 · Cited by 2
FPGA-Accelerated Sparse Subset Segmentation Using ADMM for High-Resolution Imagery
Karthikeyan, R., Lodaya, D. A., Yanamala, R. M. R., Raj, R. D. A., Prakash, K., Subeesh, T. S., Anandkumar, V., & Pallakonda, A. (2025) · IEEE Access · doi:10.1109/access.2025.3590167 · Cited by 2
Adaptive Enhancement Method for Multimode Remote Sensing Image Based on LiDAR
Zhang, X., & Muhammad, K. (2020) · Mobile Networks and Applications · doi:10.1007/s11036-020-01616-1 · Cited by 2
Ramasamy, J., Doshi, R., & Hiran, K. K. (2023) · International Journal on Recent and Innovation Trends in Computing and Communication · doi:10.17762/ijritcc.v11i3s.6155 · Cited by 2
Bibliometric trend analysis on global image processing research
Chen, S., Wang, Y., & Qiu, S. (2018) · Optical Sensing and Imaging Technologies and Applications · doi:10.1117/12.2505675 · Cited by 2
ContourNet: Salient Local Contour Identification for Blob Detection in Plasma Fusion Simulation Data
Imre, M., Han, J., Dominski, J., Churchill, R. M., Kube, R., Chang, C. S., Peterka, T., Guo, H., & Wang, C. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-33720-9_22 · Cited by 2
Retracted: Integration of Wavelet and ROI based Fuzzy K-Means for Mri-Ct Segmentation
Sumithra, M. G., & Malathi, S. (2020) · International Conference on Smart Systems and Inventive Technology (ICSSIT) · doi:10.1109/icssit48917.2020.9214145 · Cited by 2
RetractedSemi-automated weak annotation for deep neural network skin thickness measurement
Jin, F. Q., Knight, A. E., Cardones, A. R., Nightingale, K. R., & Palmeri, M. L. (2021) · Ultrasonic Imaging · doi:10.1177/01617346211014138 · Cited by 2
T-MIS: Transparency Adaptation in Medical Image Segmentation
Somani, A., Singh, D., Prasad, D. K., & Horsch, A. (2021) · Nordic Machine Intelligence · doi:10.5617/nmi.9120 · Cited by 2
Interactive Segmentation Using U-Net with Weight Map and Dynamic User Interactions
Pirabaharan, R., & Khan, N. (2022) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc48229.2022.9871361 · Cited by 2
Hurricane Damage Prediction based on Convolutional Neural Network Models
Guo, T. (2021) · International Conference on Artificial Intelligence and Computer Engineering (ICAICE) · doi:10.1109/icaice54393.2021.00065 · Cited by 2
Derin öğrenme mimarilerini kullanarak göğüs BT görüntülerinden otomatik Covid-19 tahmini
Turk, V., Reis, H. Ç., & Kaya, S. (2022) · Gümüşhane Üniversitesi Fen Bilimleri Enstitüsü Dergisi · doi:10.17714/gumusfenbil.1002738 · Cited by 3
A Survey of Convolutional Neural Network and Its Variants
Song, H., & Wen, Y. (2022) · International Conference on Computer and Communications Management (ICCCM) · doi:10.1145/3556223.3556229 · Cited by 2
Devi, K. G., & Balasubramanian, K. (2023) · Recent Advances in Computer Science and Communications · doi:10.2174/2666255816666230601150351 · Cited by 2
Learning to Correct Sloppy Annotations in Electron Microscopy Volumes
Chen, M., Renuka, M. B., Mi, L., Lichtman, J. W., Shavit, N., & Meirovitch, Y. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00450 · Cited by 2
Bibliometric Analysis of Image Segmentation with Deep Learning: An Analytical Study
Windarto, A. P., Yuhandri, Y., & Bukhori, S. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-99-8498-5_6 · Cited by 2
Zhang, L., Zhu, Y., Ni, Q., Zheng, X., Gao, Z., & Zhao, Q. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106457 · Cited by 2
Deep Kernel Learning with Application to Medical Image Annotation
Zhang, G., Zhong, L., Xiao, M., & Huang, Y. (2018) · International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD) · doi:10.1109/fskd.2018.8686904 · Cited by 2
Cross-View Label Transfer in Knee MR Segmentation Using Iterative Context Learning
Li, T., Xuan, K., Xue, Z., Chen, L., Zhang, L., & Qian, D. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-60548-3_10 · Cited by 2
A Fuzzy Adaptive Firefly Algorithm for Multilevel Color Image Thresholding Based on Fuzzy Entropy
Wang, Y., & Li, K. (2021) · International Journal of Cognitive Informatics and Natural Intelligence · doi:10.4018/ijcini.20211001.oa44 · Cited by 2
A Path-based Fuzzy Approach to Color Image Segmentation
Chamorro-Martínez, J., Mengíbar-Rodríguez, M., & Martínez-Jiménez, P. M. (2021) · IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) · doi:10.1109/fuzz45933.2021.9494488 · Cited by 2
Interactive user interface based on Convolutional Auto-encoders for annotating CT-scansPreprint
Längkvist, M., Widell, J., Thunberg, P., Loutfi, A., & Lidén, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.11701 · Cited by 2
Iterative Interaction Training for Segmentation Editing NetworksPreprint
Bredell, G., Tanner, C., & Konukoğlu, E. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.08555 · Cited by 2
3D Quantum-inspired Self-supervised Tensor Network for Volumetric Segmentation of Medical ImagesPreprint
Konar, D., Bhattacharyya, S., Gandhi, T. K., Panigrahi, B. K., & Jiang, R. (2021) · doi:10.36227/techrxiv.12909860.v3 · Cited by 2
LAFEAT: Piercing Through Adversarial Defenses with Latent FeaturesPreprint
Yu, Y., Gao, X., & Xu, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.09284 · Cited by 2
Quality-Aware Memory Network for Interactive Volumetric Image SegmentationPreprint
Zhou, T., Li, L., Bredell, G., Li, J., & Ender Konukoglu, A. (2021) · arXiv (Cornell University) · doi:10.3929/ethz-b-000521601 · Cited by 2
Entropy-Based Locally Adaptive Thresholding for Image SegmentationPreprint
Zhang, M., Cheng, S., Cao, X., Chen, H., & Xu, X. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4010416 · Cited by 2
Tseng, L.-A., Lin, H.-C., Bai, M., Li, M., Lee, Y., Chiang, K., Wang, Y., & Guo, J.-M. (2024) · Research Square · doi:10.21203/rs.3.rs-3828259/v1 · Cited by 2
Qian, C., Yang, H., & Li, J. (2023) · 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC) · doi:10.1109/smc53992.2023.10393973 · Cited by 1
Research on the algorithm of organ segmentation in chest X-ray images
Lyu, Y., & Tian, X. (2021) · IEEE International Conference on Advances in Electrical Engineering and Computer Applications (AEECA) · doi:10.1109/aeeca52519.2021.9574238 · Cited by 1
SWOSBC: A Novel Optimizer for Learning Convolutional Neural Network
Bhakta, S., Nandi, U., Mahapatra, K. R., Singh, M. M., & Noorwali, A. (2024) · IEEE Access · doi:10.1109/access.2024.3481640 · Cited by 2
Fairness in artificial intelligence‐driven multi‐organ image segmentation
Li, Q., Zhang, Y., Sun, L., Sun, M., Liu, M., Wang, Z., Wang, Q., Wang, S., & Wang, C. (2024) · iRadiology · doi:10.1002/ird3.101 · Cited by 2
Cai, W., Tang, T., Balachander., J., Kong, L., Zhou, Y., Wang, Q., & Li, J. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888624 · Cited by 1
The AI Evolution in Nuclear Medicine by Enhancing Precision and Personalization
Renugadevi, R. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-1275-0.ch017 · Cited by 1
DiffClick: Click-differentiated enhancement network for interactive segmentation
Song, S., Yu, S., Zhou, H., Huang, X., Yu, L., & Xiao, J. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.112217 · Cited by 1
Graph neural network-based interactive clustering enhanced by human knowledge
Wang, Y., Li, Y., Fu, Q., Ji, C., Lu, Y., & Chen, J. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113595 · Cited by 1
Roddan, A., Czempiel, T., Xu, C., Elson, D. S., & Giannarou, S. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05114-1_46 · Cited by 1
Lu, X., Zhou, Q., Xiao, Z., Guo, Y., Peng, Q., Zhao, S., Liu, S., Huang, J., Yang, C. F., & Yuan, Y. (2025) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-025-01690-5 · Cited by 1
Zhang, R., Sun, Y., Zhang, Z., Li, J., Liu, X., Au, H. F., Guo, H., & Yan, P. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755147 · Cited by 4
Zhang, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-08970-0_1 · Cited by 1
Transductive few-shot adapters for medical image segmentation
Silva-Rodriguez, J.-J., Dolz, J., & Ayed, I. B. (2025) · Elsevier eBooks · doi:10.1016/b978-0-32-395674-1.00020-2 · Cited by 1
Foundation Models for Zero-Shot Segmentation of Scientific Images without AI-Ready Data
Mukherjee, S., Lang, J. T., Kwon, O., Zenyuk, I. V., Brogden, V., Weber, A. Z., & Ushizima, D. M. (2025) · International Conference on Parallel Processing Workshops (ICPPW) · doi:10.1145/3750720.3757283 · Cited by 1
Xie, M., Xiao, Q., Wu, H., Zhang, Y., Han, H., Xie, X., Zhang, W., Cheng, J., & Xu, J. (2026) · npj Digital Medicine · doi:10.1038/s41746-026-02347-5 · Cited by 1
Teng, P., Yu, S., Zhang, B., Yang, F., Zhang, T., Wang, B., Yang, Y., & Liu, G. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109610 · Cited by 1
Few-shot medical image segmentation via CLIP-driven dual contrastive learning
Zou, M., Yuan, W., Liu, Y., Zeng, D., & Zhao, G. L. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.132815 · Cited by 1
The U-Net Architecture for MRI Brain Tumor Segmentation, Detection, and Classification: A Survey
Benchari, M., Totaro, M. W., Bayoumi, M., & Mokhtari, S. (2026) · Biomedical Materials & Devices · doi:10.1007/s44174-026-00660-x · Cited by 1
Kim, H., Jeong, M. J., Koo, K., Choi, Y. J., Heo, E. S., Nam, W., Kang, S., Lee, U., Kim, Y., Lee, K. H., et al. (2026) · Frontiers in Oncology · doi:10.3389/fonc.2026.1687859 · Cited by 1
Krishnaveni, T., & Kollem, S. (2026) · Computational Biology and Chemistry · doi:10.1016/j.compbiolchem.2026.109084 · Cited by 1
MFSleepNet: An Interactive Multimodal Fusion Framework for Automatic Sleep Staging
Gui, R., Wang, C., Niu, Q., & Wang, L. (2026) · Sensors · doi:10.3390/s26103085 · Cited by 1
Privacy preserved federated deep learning for disease classification of patients medical images
Dachepalli, V., & Gavini, S. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.115512 · Cited by 1
Shapes Similarity and Feature Reconstruction Comparison Based Active Contour Model
Ni, B., Cai, X., & Chen, J. (2018) · IEEE International Conference on e-Business Engineering (ICEBE) · doi:10.1109/icebe.2018.00026 · Cited by 1
Rail image segmentation based on neighborhood-mean weighed valley-emphasis enhancement algorithm
Cao, Y., Duan, Y., & Wu, D. (2019) · Journal of Computational Methods in Sciences and Engineering · doi:10.3233/jcm-193909 · Cited by 1
Guo, B., Zhou, F., Liu, B., & Bai, X. (2021) · Frontiers in Neuroscience · doi:10.3389/fnins.2021.756536 · Cited by 1
Koçer, S., Jama, B. S. A., & DÜNDAR, Ö. (2022) · Fivezero · doi:10.54486/fivezero.2022.11 · Cited by 1
Weakly Supervised Nucleus Segmentation Using Point Annotations via Edge Residue Assisted Network
Zhang, W., Chen, X., Du, S., Fan, H., & Tang, Y. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-13822-5_42 · Cited by 1
Deformable convolution infrared tracking algorithm based on improved SiamRPN++
Yang, L., Ma, J., Zhao, Z., & Ma, C. (2022) · International Conference on Automation and Computing (ICAC) · doi:10.1109/icac55051.2022.9911118 · Cited by 1
Segmentation of Fetal 2D Images with Deep Learning: A Review
CEDRI, P. R., Rehman, M. A. U., & CEDRI, G. I. (2022) · International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) · doi:10.1109/iceccme55909.2022.9988625 · Cited by 1
MRI Segmentation Using Deep Neural Network-based Unet Architecture for Brain Tumor
Pingat, S. P., Mali, N. D., Jha, P., Gupt, D., Yadav, P. S., Gujar, S. N., & Bhargava, C. P. (2023) · International Conference on Intelligent Technologies (CONIT) · doi:10.1109/conit59222.2023.10205576 · Cited by 1
PIMedSeg: Progressive interactive medical image segmentation
Gong, X., Wang, L., Miao, L., Chen, N., & Li, J. (2023) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2023.107776 · Cited by 1
Classifying Fetal Health Using Neural Networks by Boosting Imbalanced Classes
Anoosha, P., Parlapalli, R. D., Reddy, E. S., & Menaga, P. (2023) · Lecture notes in networks and systems · doi:10.1007/978-981-99-3734-9_28 · Cited by 1
DCO-Net: Deformable convolution-based O-shape network for fully automated placenta segmentation
Ma, Q., Song, P., Yan, C., & Wang, Y. (2023) · Digital Signal Processing · doi:10.1016/j.dsp.2023.104337 · Cited by 1
A Systematic Review on Detection and Classification of Melanoma
Jayasankar, S., & Brindha, T. (2023) · IEEE International Conference on Recent Advances in Systems Science and Engineering (RASSE) · doi:10.1109/rasse60029.2023.10363597 · Cited by 1
Deep Learning Segmentation of Protein EM Maps
Zumbado-Corrales, M., & Esquivel‐Rodríguez, J. (2023) · IEEE International Conference on BioInspired Processing (BIP) · doi:10.1109/bip60195.2023.10379274 · Cited by 1
Angelina, C. L., Lee, T., Wang, H., Rerknimitr, R., Han, M., Kongkam, P., & Chang, H.-T. (2024) · Communications in computer and information science · doi:10.1007/978-981-97-1714-9_8 · Cited by 1
A Multi-Model Framework to Explore ADHD Diagnosis from Neuroimaging Data
Ozdemir, Y. Y., Nukala, N. C. P., Molinari, R., & Deshpande, G. (2024) · Journal of Data Science · doi:10.6339/24-jds1128 · Cited by 1
Brain Tumour Detection and Classification Using Deep Learning
Kuntan, S. S., Sidgiddi, V. A., Jaganur, S. S., & K, R. B. (2024) · International Research Journal on Advanced Engineering Hub (IRJAEH) · doi:10.47392/irjaeh.2024.0242 · Cited by 1
Unsupervised high-throughput segmentation of cells and cell nuclei in quantitative phase images
Sistermanns, J., Emken, E., Hayden, O., Weirich, G., & Utschick, W. (2024) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi56570.2024.10635287 · Cited by 1
HiSEG: Human assisted instance segmentation
Korkmaz, M., Sezgin, T. M., & Buyukyazi, T. (2024) · Computers & Graphics · doi:10.1016/j.cag.2024.104061 · Cited by 2
Classification of Melanoma Cancer Using Deep Convolutional Neural Networks
Güneş, A., & Dönmez, E. (2024) · Journal of Advanced Research in Natural and Applied Sciences · doi:10.28979/jarnas.1505804 · Cited by 1
Pan, C., Qi, L., Zhao, L., & Wei, Y. (2025) · International Journal of Cognitive Computing in Engineering · doi:10.1016/j.ijcce.2025.01.003 · Cited by 1
Metadata
- Authors
- Wang, G., Li, W., Zuluaga, M. A., Pratt, R., Patel, P. A., Aertsen, M., Doel, T., David, A. L., Deprest, J., Ourselin, S., & Vercauteren, T.
- Affiliations
- Wellcome / EPSRC Centre for Interventional and Surgical Sciences (GB)
- KU Leuven (BE)
- Corresponding author
- Wang, Guotai
- ORCID
- Venue
- IEEE Transactions on Medical Imaging
- Published
- 2018-07
- Volume
- 37
- Issue
- 7
- Pages
- 1562-1573
- ISSN
- 0278-0062 (ISSN-L)
- 1558-254X
- PMC
- PMC6051485
- OpenAlex
- W2763160469
- Cited by
- 843
- References
- 42
- Citations by year
- 2026: 37 · 2025: 82 · 2024: 102 · 2023: 112 · 2022: 132 · 2021: 146 · 2020: 130 · 2019: 76 · 2018: 26
- FWCI
- 47.27
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- IEEE Transactions on Medical Imaging (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Lirias (submittedVersion, other-oa)
- UCL Discovery (University College London) (submittedVersion)
- Research Portal (King's College London) (submittedVersion, cc-by)
- arXiv (Cornell University)
- Funders
- Wellcome Trust (WT101957, WT97914, HICF-T4-275)
- Engineering and Physical Sciences Research Council (NS/A000027/1, EP/H046410/1, EP/J020990/1, EP/K005278, NS/A000050/1, 203145Z/16/Z)
- Royal Society (RG160569)
- University College London
- Great Ormond Street Hospital Charity
- Nvidia
- Emerald, a GPU-accelerated High Performance Computer, made available by the Science and Engineering South Consortium operated in partnership with the STFC Rutherford-Appleton Laboratory
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Brain Tumor Detection and Classification
- Keywords
- zero-shot learning, scribble-based segmentation, weighted loss function, uncertainty estimation, brain tumor segmentation, magnetic resonance imaging, convolutional neural networks
- MeSH terms
- Deep Learning, Brain, Brain Neoplasms, Female, Fetus, Humans, Image Interpretation, Computer-Assisted, Magnetic Resonance Imaging, Pregnancy, Prenatal Diagnosis
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 2026-10-05, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-05 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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
