The DOI matches its Crossref record; 74 of the 74 references it cites were found in a registry or an index; none of the 23 sources its claims cite is checked for support yet.
Self-supervised learning for medical image analysis using image context restoration
Open accessAbstract
Machine learning, particularly deep learning has boosted medical image analysis over the past years. Training a good model based on deep learning requires large amount of labelled data. However, it is often difficult to obtain a sufficient number of labelled images for training. In many scenarios the dataset in question consists of more unlabelled images than labelled ones. Therefore, boosting the performance of machine learning models by using unlabelled as well as labelled data is an important but challenging problem. Self-supervised learning presents one possible solution to this problem. However, existing self-supervised learning strategies applicable to medical images cannot result in significant performance improvement. Therefore, they often lead to only marginal improvements. In this paper, we propose a novel self-supervised learning strategy based on context restoration in order to better exploit unlabelled images. The context restoration strategy has three major features: 1) it learns semantic image features; 2) these image features are useful for different types of subsequent image analysis tasks; and 3) its implementation is simple. We validate the context restoration strategy in three common problems in medical imaging: classification, localization, and segmentation. For classification, we apply and test it to scan plane detection in fetal 2D ultrasound images; to localise abdominal organs in CT images; and to segment brain tumours in multi-modal MR images. In all three cases, self-supervised learning based on context restoration learns useful semantic features and lead to improved machine learning models for the above tasks.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
The paper proposes context restoration as a self-supervised pretraining task for medical images: randomly swap image patches and train a CNN to restore the original context. Across fetal ultrasound classification, abdominal CT organ localization, and brain MR tumor segmentation, context restoration pretraining outperformed autoencoder, relative-position, context-prediction, and no self-supervision.
Key findings
- Context restoration pretraining improved CNNs in all three evaluated tasks: fetal standard scan plane classification, abdominal multi-organ localization, and brain tumor segmentation. It outperformed other self-supervised strategies and no self-supervision in the reported comparisons.
- For fetal ultrasound classification, when using only a quarter of the training data, context restoration pretraining improved the SonoNet performance the most among the compared pretraining strategies.
- For abdominal CT localization, context restoration pretraining produced more localization improvements than other pretraining methods; in some cases it was comparable to or better than no pretraining on more annotated training data.
- For BraTS 2017 brain tumor segmentation, U-Nets initialized by context restoration pretraining achieved the best performance in total; using 50% of the training set gave similar performance to using the whole training set, with Dice in enhanced tumor core, sensitivity in non-enhanced and enhanced tumor cores, and Hausdorff distances even slightly better.
Methods
- Self-supervised task: given an unlabelled image, randomly select two isolated patches and swap them; repeat T times to disorder context, then train a CNN to restore the original image using an L2 loss.
- Evaluated on three datasets/tasks: fetal 2D ultrasound classification with 2694 examinations and SonoNet-64; abdominal CT multi-organ localization with 150 subjects and a SonoNet-like CNN; BraTS 2017 brain tumor segmentation with 285 subjects, 142 for training/validation and 143 for testing, using a 2D U-Net on 64×64 patches.
- Compared pretraining strategies: autoencoder, relative position prediction, local context prediction, and context restoration; subsequent tasks used whole, half, or quarter of the training set. Training details include 58K iterations for ultrasound classification, 55K for CT localization, and 50K for segmentation.
Limitations
- The paper states that the L2 loss used for context restoration results in blurry restored images.
- The paper reports that data augmentation did not consistently improve performance and sometimes decreased segmentation accuracy; it also notes that self-supervised pretraining was not compared against supervised pretraining because supervised pretraining is difficult in medical imaging due to annotation requirements.
- Evident from the text: evaluation is limited to three medical imaging tasks and datasets, and the paper notes that in brain tumor segmentation the performance differences among self-supervision strategies were not always significant.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
26 Own interpretation · 25 Own result · 21 No basis given · 20 Not checked yet
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
“Balancing the numbers of instances in each class significantly improves the performance in all three metrics.”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Fetal standard scan plane classification
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
“Initialising by pretrained features, particularly those from context restoration tasks, improves the CNN performance.”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Abdominal multi-organ localization
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 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
“A shortcoming is that the L2 loss results in image blur.”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Context restoration results
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
“In all three cases, self-supervised learning based on context restoration learns useful semantic features and lead to improved machine learning models for the above tasks.”
§ Self-supervised learning for medical image analysis using image context restoration > Abstract
plaindirectn = 3- 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
“On quarter of training data, the data augmentation techniques can be advantageous over some self-supervised learning methods such as the CP method.”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Fetal standard scan plane classification
plainconditional- 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
“when learning on half of training images, the F1-scores keep stable in most cases except where the SonoNet is pretrained based on context restoration.”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Fetal standard scan plane classification
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.
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
“Our context restoration pretraining improves the SonoNet performance the most.”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Fetal standard scan plane classification
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
“In all cases, the image context restoration achieve qualitatively good results.”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Context restoration results
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.
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
“Data augmentation did not offer performance improvement in many cases.”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Abdominal multi-organ localization
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
“using 50% of the training set, the proposed self-supervision strategy offers similar performance to using the whole training set.”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Brain tumour segmentation
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. 18
- The quote only partly states this claim. 1
- Probably not a substantial claim. 21
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
“when the SonoNet is trained on quarter of the training data, the precision decreases significantly while there is only slight decrease in terms of the recall.”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Fetal standard scan plane classification
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 all three tasks, the pretraining based on our context restoration strategy is superior to other self-supervised learning strategies, as well as no self-supervised training.”
§ Self-supervised learning for medical image analysis using image context restoration > Introduction
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
“When the SonoNet is trained on half of the training data, the precision and recall both decrease, which lead to the decrease of the F1-score.”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Fetal standard scan plane classification
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
“Data augmentation does not lead to improvement when the SonoNet is trained on half data; while it lead to obvious improvement when the SonoNet is trained on quarter of data.”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Fetal standard scan plane classification
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
“The SonoNet pretrained using context restoration can only offers marginal improvement.”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Fetal standard scan plane classification
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 quote only partly states this claim.
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
“When learning using only a quarter of training images, the SonoNet with feature initialisation from the auto-encoder pretraining still cannot improve the baseline; while SonoNets using other pretraining strategies perform better than the baseline.”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Fetal standard scan plane classification
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.
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 terms of the liver, the CNN performance decreases sharply with half training data; while it remains stable with quarter training data.”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Abdominal multi-organ localization
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
“Although the CNN pretrained using the RP method on quarter training data outperforms that using context restoration pretraining, it performs much worse in left kidney.”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Abdominal multi-organ localization
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
“The Dice score in enhanced tumour core, the sensitivity in non-enhanced and enhanced tumour cores, and the Hausdorff distances in all aspects are even slightly better.”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Brain tumour segmentation
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
“pretraining based on relative positions and context prediction tasks improves the segmentations but they are not as good as the pretraining based on the context restoration task.”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Brain tumour segmentation
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
“For many common problems in medical imaging such as classification, localization, and segmentation, learning image context is key.”
§ Self-supervised learning for medical image analysis using image context restoration > Self-supervision based on context restoration > Context restoration
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.
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 case of subsequent segmentation tasks, the whole CNN architecture can be shared by the pretraining network and the subsequent segmentation network. As a result, almost all the weights of the subsequent segmentation CNN can be initialised using those learned in the self-supervised pretraining. This results in better segmentation results.”
§ Self-supervised learning for medical image analysis using image context restoration > Self-supervision based on context restoration > Network architectures
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
“However, the removal of context changes the image intensity distribution. Thus the resulting images belong to another domain and the learned features may not be useful for images in the original domain.”
§ Self-supervised learning for medical image analysis using image context restoration > Related work
What the sources say
- Not checked yetcites Pathak et al., 2016
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.
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
“The pretrained models from the natural image domain are not useful in the medical imaging domain since the intensity distribution of natural images is different from that of medical images.”
§ Self-supervised learning for medical image analysis using image context restoration > Introduction
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.
In the paper
“Since each data instance is regarded as one class, the exemplar learning method is difficult to apply to large datasets.”
§ Self-supervised learning for medical image analysis using image context restoration > Related work
What the sources say
- Not checked yetcites Dosovitskiy et al., 2016 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
“More precisely, the CNN weights learned in the CP method can be used to initialise subsequent CNNs for classification and segmentation; while CNN weights learned in the RP method can initialise subsequent classification CNNs and only the analysis part of the subsequent segmentation CNNs.”
§ Self-supervised learning for medical image analysis using image context restoration > Related work
What the sources say
- Not checked yetcites Pathak et al., 2016
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
“In case of subsequent classification tasks, simple CNN layers with a few deconvolution layers are sufficient (see Fig. 3) (Doersch and Zisserman, 2017). In this condition, the analysis part makes most contributions to the context restoration. Therefore, the feature maps resulting from the analysis part are more useful.”
§ Self-supervised learning for medical image analysis using image context restoration > Self-supervision based on context restoration > Network architectures
What the sources say
- Not checked yetcites Doersch and Zisserman, 2017
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 may because the augmented images do not cover the variance of organ shapes and positions and introduce additional variance to pixel intensities.”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Abdominal multi-organ localization
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.
In the paper
“The disadvantage of multi-task self-supervised learning is the training requires significant computational resources, i.e. 64 GPUs for approximately 16.8K GPU hours.”
§ Self-supervised learning for medical image analysis using image context restoration > Related work
What the sources say
- Not checked yetcites Doersch and Zisserman, 2017
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 many medical image analysis problems, localization anatomical structures is a prerequisite.”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Abdominal multi-organ localization
What the sources say
- Not checked yetcites Heimann et al., 2009 source
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.
In the paper
“As suggested by Pathak et al. (2016), the L2 loss is sufficient for feature learning although the outputs from context restoration outputs may be blurry.”
§ Self-supervised learning for medical image analysis using image context restoration > Self-supervision based on context restoration > Network architectures
What the sources say
- Not checked yetcites Pathak et al., 2016
hedgeddirect- 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
“In this scenario, the baseline (i.e. random initialisation) is not far away from the ceiling (i.e. SonoNet on the whole training set). Therefore, it is difficult to obtain improvements.”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Fetal standard scan plane classification
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
“de Vos et al. (2017) proposed a novel approach which can localize anatomical structures in 3D medical images.”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Abdominal multi-organ localization
What the sources say
- Not checked yetcites de Vos et al., 2017 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.
Probably not a substantial claim.
In the paper
“The results showed that multitask self-supervised learning improves subsequent tasks more than single-task self-supervised learning.”
§ Self-supervised learning for medical image analysis using image context restoration > Related work
What the sources say
- Not checked yetcites Doersch and Zisserman, 2017
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
“However, existing self-supervised learning strategies applicable to medical images cannot result in significant performance improvement. Therefore, they often lead to only marginal improvements.”
§ Self-supervised learning for medical image analysis using image context restoration > Abstract
What the sources say
- Not checked yetcites Doersch et al., 2015
- Not checked yetcites Pathak et al., 2016
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
“the CNNs for context restoration can be structured in flexible architectures depending on subsequent tasks.”
§ Self-supervised learning for medical image analysis using image context restoration > 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.
In the paper
“They are routinely assessed using MR imaging (Bakas et al., 2017b).”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Brain tumour segmentation
What the sources say
- Not checked yetcites Bakas et al., 2017b
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
“In computer vision, many CNNs are pretrained before the main task.”
§ Self-supervised learning for medical image analysis using image context restoration > Discussion and conclusion
What the sources say
- Not checked yetcites Ren et al., 2015
- Not checked yetcites Simonyan and Zis-serman, 2014
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
“the implementation of the context restoration task is simple and straightforward, meaning that it can be widely used.”
§ Self-supervised learning for medical image analysis using image context restoration > Discussion and conclusion
plaindirect- 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: fails — The paper may give no 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. 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
“2) The augmentation does not introduce any more useful variance in terms of tumour appearance.”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Brain tumour segmentation
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: 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
“3) The augmentation introduces additional intensity variations which are not meaningful.”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Brain tumour segmentation
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.
None of the sources cited for this claim have been checked yet.
In the paper
“the Faster R-CNN (Ren et al., 2015) is based on the pretraining of the VGG-Net (Simonyan and Zis-serman, 2014).”
§ Self-supervised learning for medical image analysis using image context restoration > Discussion and conclusion
What the sources say
- Not checked yetcites Ren et al., 2015
- Not checked yetcites Simonyan and Zis-serman, 2014
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
“which may because of three reasons: 1) The segmentation is based on patches so a large number of image patches can be sampled.”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Brain tumour segmentation
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
“We conclude from the existing self-supervised feature learning literature that the ideal pretraining task should have similar goal to the subsequent task.”
§ Self-supervised learning for medical image analysis using image context restoration > Discussion and conclusion
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check 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. It may be too vague to check against evidence. The paper may give no reason why it holds.
In the paper
“This type of pretraining leads to good detection results in the Faster R-CNN.”
§ Self-supervised learning for medical image analysis using image context restoration > Discussion and conclusion
What the sources say
- Not checked yetcites Ren et al., 2015
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
“It is noteworthy that if less training data leads to significant decrease of results, self-supervised learning is likely to improve the results significantly.”
§ Self-supervised learning for medical image analysis using image context restoration > Experiments and results > Abdominal multi-organ localization
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: 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
“if the reduction of training data causes significant performance decrease, the context restoration pretraining can offer significant performance improvement over the baselines.”
§ Self-supervised learning for medical image analysis using image context restoration > Discussion and conclusion
plainconditional- 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
“Compared with the existing strategies such as relative positions and context prediction, solving the context restoration task requires pattern recognition and prediction, which ensures the context restoration task offers more efficient image semantics.”
§ Self-supervised learning for medical image analysis using image context restoration > Discussion and conclusion
plaindirect- 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: fails — The paper may give no 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. The paper may give no reason why it holds.
The paper relies on this without support.
Training CNNs only using a small number of labelled images cannot always achieve satisfactory results and does not exploit the potentially large number of unlabelled images that may be available.
“Training CNNs only using the small number of labelled images cannot always achieve satisfactory results and does not exploit the potentially large number of unlabelled images that may be available.”
The paper relies on this without support.
It is usually easier to access a large number of unlabelled medical images rather than a large number of annotated images.
“This means it is usually easier to access a large number of unlabelled medical images rather than a large number of annotated images.”
The paper relies on this without support.
In medical imaging, most images are in greyscale so that no colour information is available.
“In medical imaging, most images are in greyscale so that no colour information is available.”
The paper relies on this without support.
The key challenge for self-supervised learning is identifying a suitable self-supervision task, i.e. generating input and output instance pairs from data.
“The key challenge for self-supervised learning is identifying a suitable self supervision task, i.e. generating input and out-put instance pairs from data.”
The paper relies on this without support.
Manual cropping requires expert knowledge and is costly.
“However, manual cropping requires expert knowledge and costly.”
The paper relies on this without support.
Not all patients have two kidneys.
“This is because not all patients have two kidneys.”
The paper relies on this without support.
Gliomas are the major brain tumours occurring in adults.
“Gliomas are the major brain tumours occurring in adults.”
The paper relies on this without support.
Accurate segmentation of gliomas on MR image is a key step for quantification.
“Accurate segmentation of gliomas on MR image is a key step for quantification.”
The paper relies on this without support.
In medical image analysis, the image context is the common feature for classification, localization/detection, and segmentation tasks.
“Particularly, in medical image analysis, the image context is the common feature for classification, localization/detection, and segmentation tasks.”
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
§ Self-supervised learning for medical image analysis using image context restoration > Self-supervision based on context restoration > Context restoration
“a new dataset (1)χ˜=f(χ˜) is generated.”
§ Self-supervised learning for medical image analysis using image context restoration > Self-supervision based on context restoration > Context restoration
“xi=g(x˜i)=f−1(x˜i)”
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
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
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
Densely Connected Convolutional Networks
Huang, G., Liu, Z., van der Maaten, L., & Weinberger, K. Q. (2016) · arXiv · doi:10.48550/arxiv.1608.06993 · Cited by 48,960
Densely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Cited by
Sorted by citations
Items 301–400 of 573
Knowing What to Label for Few Shot Microscopy Image Cell Segmentation
Dawoud, Y., Bouazizi, A., Ernst, K., Carneiro, G., & Belagiannis, V. (2023) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv56688.2023.00356 · Cited by 7
SCL-FExR: supervised contrastive learning approach for facial expression Recognition
Vasudeva, K., Dubey, A., & Chandran, S. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-14803-5 · Cited by 7
Self-supervised Semantic Segmentation: Consistency over Transformation
Karimijafarbigloo, S., Azad, R., Kazerouni, A., Velichko, Y., Bağcı, U., & Merhof, D. (2023) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw60793.2023.00280 · Cited by 7
Self-supervised Domain Adaptation for Diabetic Retinopathy Grading Using Vessel Image Reconstruction
Nguyen, M.-D., Mai, T. T. N., Than, N. T. T., Prange, A., & Sonntag, D. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87626-5_26 · Cited by 7
Self-supervised Learning of Inter-label Geometric Relationships for Gleason Grade Segmentation
Mahapatra, D., Kuanar, S. P., Bozorgtabar, B., & Ge, Z. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87722-4_6 · Cited by 7
Online Unsupervised Learning For Domain Shift In Covid-19 CT Scan Datasets
Ewen, N., & Khan, N. (2021) · 2021 IEEE International Conference on Autonomous Systems (ICAS) · doi:10.1109/icas49788.2021.9551146 · Cited by 5
Srivastava, S., Vidyarthi, A., & Jain, S. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-09148-x · Cited by 6
Chilumukuru, N. S., Priyadarshini, P., & Ezunkpe, Y. (2025) · JMIR Formative Research · doi:10.2196/62996 · Cited by 6
Gong, R., Ying, S., & Shi, J. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897885 · Cited by 6
A novel artificial intelligence-based predictive analytics technique to detect skin cancer
Balaji, P., Hùng, B. T., Chakrabarti, P., Jin, X., Chakrabarti, T., & Aluvalu, R. (2023) · PeerJ Computer Science · doi:10.7717/peerj-cs.1387 · Cited by 7
Exploring Self-Supervised Representation Learning for Low-Resource Medical Image Analysis
Chattopadhyay, S., Ganguly, S., Chaudhury, S., Nag, S., & Chattopadhyay, S. (2023) · Proceedings - International Conference on Image Processing · doi:10.1109/icip49359.2023.10222058 · Cited by 7
ThyroidNet: A Deep Learning Network for Localization and Classification of Thyroid Nodules
Chen, L., Chen, H., Pan, Z., Xu, S., Lai, G., Chen, S., Wang, S., Gu, X., & Zhang, Y. (2023) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2023.031229 · Cited by 6
Self-citationRevisiting segmentation-guided denoising student–teacher in anomaly detection
Zang, Y., Lu, A., Li, B., & Hu, W. (2024) · The Visual Computer · doi:10.1007/s00371-024-03412-4 · Cited by 7
AnatoMask: Enhancing Medical Image Segmentation with Reconstruction-Guided Self-masking
Li, Y., Luan, T., Wu, Y., Pan, S., Chen, Y., & Yang, X. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73027-6_9 · Cited by 6
T3D: Advancing 3D Medical Vision-Language Pre-Training by Learning Multi-View Visual Consistency
Liu, C., Ouyang, C., Chen, Y., Quilodrán-Casas, C., Ма, Л., Fu, J., Guo, Y., Shah, A., Bai, W., & Arcucci, R. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00698 · Cited by 12
Deep Learning Research Directions in Medical Imaging
Simionescu, C., & Iftene, A. (2022) · Mathematics · doi:10.3390/math10234472 · Cited by 6
Self-supervised Learning Based on Max-tree Representation for Medical Image Segmentation
Tang, Q., Du, B., & Xu, Y. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892853 · Cited by 6
Automatic classification of heart failure based on Cine-CMR images
Xie, Y., Zhong, H., Wu, J., Zhao, W., Hou, R., Zhao, L., Xu, X., Zhang, M., & Zhao, J. (2023) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-023-03028-4 · Cited by 6
Self-supervised learning-leveraged boosting ultrasound image segmentation via mask reconstruction
Sang, Q., Hou, Y., Qian, P., & Wu, Q. (2023) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-023-02014-1 · Cited by 6
Xie, Y., Yang, Z., Yang, Q., Liu, D., Tang, S., Yang, L., Duan, X., Hu, C., Lu, Y., & Wang, J. (2024) · Health Information Science and Systems · doi:10.1007/s13755-023-00266-3 · Cited by 6
Seth, P., & Pai, A. K. (2024) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw60836.2024.00067 · Cited by 6
Longitudinal Correlation Analysis for Decoding Multi-modal Brain Development
Zhao, Q., Adeli, E., & Pohl, K. M. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87234-2_38 · Cited by 6
A Multi-Stage Attentive Transfer Learning Framework for Improving COVID-19 DiagnosisPreprint
Liu, Y., & Ji, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.05410 · Cited by 8
Gao, Y., Zhou, H.-Y., Wang, X., Zhang, T., Beets‐Tan, R. G. H., Han, L., Estacio, L., D'Angelo, A. R., Teuwen, J., Mann, R. M., et al. (2023) · Research Square · doi:10.21203/rs.3.rs-2924701/v1 · Cited by 6
Domain Aware Multi-task Pretraining of 3D Swin Transformer for T1-Weighted Brain MRI
Kim, J., Kim, M., & Park, H. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0901-7_8 · Cited by 6
Singh, Y., Ünal, O., Ali, F., Salehi, S., Kuanar, S. P., Elhanashi, A., Hathaway, Q. A., Chaudhary, A., Huo, Y., Younis, K., et al. (2026) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-025-01823-w · Cited by 5
Learning with less: A survey of deep learning in medical imaging under varying supervision levels
Kumari, S., & Singh, P. P. (2026) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2026.103375 · Cited by 7
Meng, X., Yu, H., Fan, J., Mu, J., Huang, C., Luan, J., Xu, M., Gu, Y., Ma, G., & Yang, J. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.107757 · Cited by 5
Diabetic Retinopathy Grading Base on Contrastive Learning and Semi-supervised Learning
Gu, Y., Wang, X., Pan, J., & Zhou, Z. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-91415-8_7 · Cited by 5
Zhong, H., Wu, J., Zhao, W., Xu, X., Hou, R., Zhao, L., Deng, Z., Zhang, M., & Zhao, J. (2021) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc46164.2021.9630228 · Cited by 5
Navarro, F., Watanabe, C., Shit, S., Sekuboyina, A., Peeken, J. C., Combs, S. E., & Menze, B. H. (2022) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc48229.2022.9870911 · Cited by 5
Boundary-Enhanced Self-supervised Learning for Brain Structure Segmentation
Feng, C., Wu, C., Wang, Y., Zhang, Y., Chen, X., & Tian, Q. C. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-16431-6_2 · Cited by 5
Boosting few-shot confocal endomicroscopy image recognition with feature-level MixSiam
Zhou, J., Dong, X., & Liu, Q. (2023) · Biomedical Optics Express · doi:10.1364/boe.478832 · Cited by 5
Self-supervised zero-shot dehazing network based on dark channel prior
Xiao, X., Ren, Y., Li, Z., Zhang, N., & Zhou, W. (2023) · Frontiers of Optoelectronics · doi:10.1007/s12200-023-00062-7 · Cited by 5
Coarse-to-fine visual representation learning for medical images via class activation maps
Yap, B. P., & Ng, B. K. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108203 · Cited by 5
Ghazi, F., Benkuider, A., Ayoub, F., & Ibrahimi, K. (2024) · BioMedInformatics · doi:10.3390/biomedinformatics4020066 · Cited by 5
Artificial Intelligence in Cancer Diagnosis: A Game-changer in Healthcare
Sahoo, P., Kundu, M., & Begum, J. (2024) · Current Pharmaceutical Biotechnology · doi:10.2174/0113892010298852240528123911 · Cited by 8
SIAM: Spatial and Intensity Awareness Module for cerebrovascular segmentation
Chen, Y., Chen, C., Li, X., & Xiao, R. (2024) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2024.108511 · Cited by 5
SimCLR-based Self-Supervised Learning Approach for Limited Brain MRI and Unlabeled Images
Fırıldak, K., Çelik, G., & Talu, M. F. (2024) · Bitlis Eren Üniversitesi Fen Bilimleri Dergisi · doi:10.17798/bitlisfen.1558069 · Cited by 5
MOSMOS: Multi-organ segmentation facilitated by medical report supervision
Tian, W., Huang, X., Hou, J., Ren, C., Jiang, L., Zhao, R.-W., Jin, G., Zhang, Y., & Geng, D. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.107743 · Cited by 6
Adaptive batch-fusion self-supervised learning for ultrasound image pretraining
Zhang, J., Wu, X., Liu, S., Fan, Y., Chen, Y., Lyu, G., Liu, P., Liu, Z., & He, S. (2025) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2025.102599 · Cited by 6
Hong, L. T. T., Thành, N. C., & Long, T. Q. (2021) · NAFOSTED Conference on Information and Computer Science (NICS) · doi:10.1109/nics54270.2021.9701580 · Cited by 5
Francis, S., Pooloth, G., Singam, S. B. S., Puzhakkal, N., Pournami, P. N., & Balakrishnan, J. P. (2022) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.22802 · Cited by 5
Higashi, T., Ogawa, N., Maeda, K., Ogawa, T., & Haseyama, M. (2023) · Sensors · doi:10.3390/s23031657 · Cited by 5
Sparse annotation learning for dense volumetric MR image segmentation with uncertainty estimation
Osman, Y. B. M., Li, C., Huang, W., & Wang, S. (2023) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ad111b · Cited by 5
A large-scale curated and filterable dataset for cryo-EM foundation model pre-training
Chen, Q., Xu, Z., Dai, H., Shen, Y., Zhang, J., Liu, Z., Pei, Y., & Jingyi Yu, A. (2025) · Scientific Data · doi:10.1038/s41597-025-05179-2 · Cited by 7
Brain-Aware Replacements for Supervised Contrastive Learning in Detection of Alzheimer’s Disease
Seyfioğlu, M. S., Liu, Z., Kamath, P. A., Gangolli, S., Wang, S., Grabowski, T. J., & Shapiro, L. G. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-16431-6_44 · Cited by 19
Haq, I., He, L., Li, J., Chen, B., Yang, X., & Li, Y. (2025) · Physica Scripta · doi:10.1088/1402-4896/adedce · Cited by 5
Zou, Y., & Yin, Z. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00023 · Cited by 4
A self-supervised framework for improved generalisability in ultrasound B-mode image segmentation
Ellis, E., Bulpitt, A. J., Parsa, N., Byrne, M. F., & Ali, S. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.109089 · Cited by 5
Ahmed, A., Imran, A. S., Kastrati, Z., Daudpota, S. M., Ullah, M., & Noor, W. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.109044 · Cited by 6
Adaptive Vehicle Detection in Urban Environments: A Self-learning Approach
Guerrero-Contreras, G., Balderas-Díaz, S., García-Pascual, A., & Muñoz, A. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-83117-1_3 · Cited by 4
Flexible ConvNext Block Based Multi-task Learning Framework for Liver MRI Images Analysis
Sui, D., Liu, W., Guo, M., Li, Y., Zhang, L., Luo, G., & Wang, K. (2022) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm55620.2022.9994956 · Cited by 4
Chen, L., & Zhang, Z. (2023) · Medical Physics · doi:10.1002/mp.16736 · Cited by 5
Self-citationReview on self supervised learning in medical image analysis
Kumari, N., & Agrawal, S. (2023) · IEEE Conference on Information and Communication Technology (CICT) · doi:10.1109/cict59886.2023.10455714 · Cited by 4
A Study on Self-Supervised Pretraining for Vision Problems in Gastrointestinal Endoscopy
Sanderson, E., & Matuszewski, B. J. (2024) · IEEE Access · doi:10.1109/access.2024.3381517 · Cited by 7
Arabi, H., & Zaidi, H. (2024) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-024-01159-x · Cited by 4
Zeng, T., Lv, H., Ashraf, M. A., Ling, M., Chen, Y., Liu, Y., Chen, X., Li, Y., & Huang, J. (2024) · Journal of Radiation Research and Applied Sciences · doi:10.1016/j.jrras.2024.101022 · Cited by 4
Gao, R., Peng, A., Duan, Y., Chen, M., Zheng, T., Zhang, M., Chen, L., & Sun, H. (2025) · Journal of Magnetic Resonance Imaging · doi:10.1002/jmri.29734 · Cited by 4
Self-citationZhu, Q., Wentland, A. L., & Li, S. (2025) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2025.3540711 · Cited by 4
Deadlift Recognition and Application based on Multiple Modalities using Recurrent Neural Network
Sun, S.-W., Mou, T.-C., & Chang, P.-C. (2020) · Electronic Imaging · doi:10.2352/issn.2470-1173.2020.17.3dmp-002 · Cited by 4
Context encoder self-supervised approaches for eye fundus analysis
Moris, D. I., Hervella, Á. S., Rouco, J., Novo, J., & Ortega, M. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9533567 · Cited by 4
Multiview Long-Short Spatial Contrastive Learning For 3D Medical Image Analysis
Cao, G., Wang, Y., Zhang, M., Zhang, J., Kang, G., & Xu, X. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9747913 · Cited by 4
Qayyum, A., Mazher, M., Niederer, S., & Razzak, I. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-27324-7_7 · Cited by 4
Joint Representation Learning from French Radiological Reports and Ultrasound Images
Dadoun, H., Delingette, H., Rousseau, A.-L., de Kerviler, É., & Ayache, N. (2023) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi53787.2023.10230642 · Cited by 5
SADIR: Shape-Aware Diffusion Models for 3D Image Reconstruction
Jayakumar, N., Hossain, T., & Zhang, M. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-46914-5_23 · Cited by 4
Sun, Y., Wang, F., Shu, J., Wang, H., Wang, L., Meng, D., & Lian, C. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01931 · Cited by 4
Universal Model for 3D Medical Image Analysis.Preprint
Zhang, X., Zhang, Y., Zhang, X., & Wang, Y. (2020) · arXiv (Cornell University) · Cited by 4
Targeted Self Supervision for Classification on a Small COVID-19 CT Scan DatasetPreprint
Ewen, N., & Khan, N. (2023) · doi:10.32920/22734284 · Cited by 4
Qiu, Y., Zhang, H., Yang, K., Zhai, T., Lu, Y., Cao, Z., & Zhang, Z. (2024) · Photonics · doi:10.3390/photonics11020106 · Cited by 3
Automated Brain Tumor Detection Using Convolutional Neural Network
Chaudhary, R., Chaudhary, P., Singh, C., Kumar, K., Singh, S., Arora, R., Kaur, S., Vaarshney, D., Acharya, P., & Mishra, U. (2025) · Biotechnology and Applied Biochemistry · doi:10.1002/bab.70060 · Cited by 3
A foundation model for brain tumor MRI analysis: WHO grading and subtype classification
Li, J., Liu, R., Xing, Y., Gao, X., Yin, Q., & Su, Q. (2025) · Radiotherapy and Oncology · doi:10.1016/j.radonc.2025.111297 · Cited by 3
Clustering-enhanced active learning with dynamic sampling for brain tumor classification
Fan, Y., Wang, X., Yue, Z., Zhang, X., Chen, M., & Chen, J. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109715 · Cited by 3
MG-3D: Multi-grained knowledge-enhanced vision-language pre-training for 3D medical image analysis
Ni, X., Wu, L., Zhuang, J., Wang, Q., Wu, M., Vardhanabhuti, V., Zhang, L., Gao, H., & Chen, H. (2026) · Medical Image Analysis · doi:10.1016/j.media.2026.104027 · Cited by 5
Learning with less supervision: A survey of label-efficient learning for medical image analysis
Jin, C., Guo, Z., Lin, Y., Luo, L., & Chen, H. (2026) · Medical Image Analysis · doi:10.1016/j.media.2026.104062 · Cited by 49
Pawar, A. B., Priya, C., Krishnaiah, V. V. J. R., Daniel, V. A. A., El–Ebiary, Y. A. B., & Taloba, A. I. (2023) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2023.0141088 · Cited by 3
Ghazi, F., Benkuider, A., Zraidi, M., Ayoub, F., & Ibrahimi, K. (2023) · International Conference on Wireless Networks and Mobile Communications (WINCOM) · doi:10.1109/wincom59760.2023.10323028 · Cited by 3
An Attention Network With Self-Supervised Learning for Rheumatoid Arthritis Scoring
Ling, D., Yu, W., Zhang, Z., & Zou, J. (2024) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas58744.2024.10558434 · Cited by 3
The Application of Convolutional Neural Networks in Organ-on-a-Chip Technology: A Review
Anderson, W., & Sarmadi, M. (2024) · Journal of Student Research · doi:10.47611/jsrhs.v13i1.6102 · Cited by 3
Sun, K., Shi, J., Jin, G., Li, J., Wang, J., Du, J., & Shi, J. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106684 · Cited by 3
SDSL: Spectral Distance Scaling Loss Pretraining SwinUNETR for 3D Medical Image Segmentation
Lee, J., Vu, D. T., Yu, G.-H., Kim, J., Kim, K., & Kim, J. Y. (2024) · IEEE Access · doi:10.1109/access.2024.3450961 · Cited by 3
Rasaee, H., Samuel, M., Behboodi, B., Afilalo, J., & Rivaz, H. J. (2025) · IEEE Open Journal of Engineering in Medicine and Biology · doi:10.1109/ojemb.2025.3537560 · Cited by 4
Abbas, T., Linjawi, M., Iqbal, I., Alghushairy, O., Alsini, R. A. I., & Daud, A. Y. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.108391 · Cited by 3
Test Time Training for 4D Medical Image Interpolation
Zhang, Q., Lei, Y., Zheng, Z., Chen, Z., & Xie, Z. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227329 · Cited by 3
Xu, Z., Ali, S., Celik, N., Bailey, A. A., Braden, B., & Rittscher, J. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-17979-2_2 · Cited by 3
Yan, J., Gan, H., Xu, X., Yang, Z. Q., & Ye, Z. (2022) · China Automation Congress (CAC) · doi:10.1109/cac57257.2022.10055587 · Cited by 3
Zheng, H., Bao, J., Dong, Z., & Wan, X. (2023) · Applied Intelligence · doi:10.1007/s10489-023-05088-0 · Cited by 3
Efficient 3D Representation Learning for Medical Image Analysis
Tang, Y., Liu, J., Zhou, Z., Yu, X., & Huo, Y. (2024) · World Scientific Annual Review of Artificial Intelligence · doi:10.1142/s2811032324500024 · Cited by 3
Multiple representation contrastive self-supervised learning for pulmonary nodule detection✰
Torki, A., Adibi, P., & Kashani, H. B. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112307 · Cited by 2
Semantic structure preservation for accurate multi-modal glioma diagnosis
Shi, C., Zhang, X., Zhao, R., Zhang, W., & Chen, F. (2025) · Scientific Reports · doi:10.1038/s41598-025-88458-7 · Cited by 3
Self-supervised Multi-scale Consistency for Weakly Supervised Segmentation Learning
Valvano, G., Leo, A., & Tsaftaris, S. A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87722-4_2 · Cited by 3
Self-supervised 3D Out-of-Distribution Detection via Pseudoanomaly Generation
Cho, J., Kang, I., & Park, J. (2022) · Lecture notes in computer science · doi:10.1007/978-3-030-97281-3_15 · Cited by 3
Wang, J., Li, H., Liu, H., Hu, D., Lu, D., Yoon, K., Barter, K. M., Bagnato, F. R., & Oğuz, İ. (2023) · SPIE Medical Imaging: Image Processing · doi:10.1117/12.2654522 · Cited by 3
Sital, C., Brosch, T., Tio, D., Raaijmakers, A. J. E., & Weese, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.07923 · Cited by 3
Bootstrap Representation Learning for Segmentation on Medical Volumes and SequencesPreprint
Chen, Z., Zhuo, W., Wang, T., Xue, W., & Ni, D. (2021) · arXiv (Cornell University) · doi:10.13140/rg.2.2.15943.83364 · Cited by 3
Self-supervised Tumor Segmentation through Layer DecompositionPreprint
Zhang, X., Xie, W., Huang, C., Wang, Y., Zhang, Y., Chen, X., & Tian, Q. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.03230 · Cited by 3
A Machine Learning Framework for Oncological Margin Detection
Santilli, A. (2021) · QSpace (Queen's University Library) · Cited by 3
Nezhad, A. P., Ghatee, M., & Sajedi, H. (2021) · doi:10.36227/techrxiv.14806290 · Cited by 3
Self-supervised learning for early detection of neurodegenerative diseases with small data
Jiang, H. (2023) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/166402 · Cited by 3
Cornelissen, S., van der Putten, J. A., Boers, T. G. W., Jukema, J. B., Fockens, K. N., Bergman, J. J. G. H. M., van der Sommen, F., & de With, P. H. N. (2021) · 2021 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip42928.2021.9506121 · Cited by 2
Metadata
- Authors
- Chen, L., Bentley, P., Mori, K., Misawa, K., Fujiwara, M., & Rueckert, D.
- Affiliations
- Imperial College London (GB)
- Nagoya University (JP)
- Aichi Cancer Center (JP)
- Nagoya University Hospital (JP)
- Corresponding author
- Chen, Liang
- Venue
- Medical Image Analysis
- Publisher
- Elsevier BV
- Published
- 2019-12
- Volume
- 58
- Pages
- 101539
- ISSN
- 1361-8415 (ISSN-L)
- PMC
- PMC7613987
- OpenAlex
- W2964744899
- Semantic Scholar
- d6e78069dbbb35592f013187ef3432286def8f18
- Cited by
- 575
- References
- 73
- Citations by year
- 2026: 44 · 2025: 85 · 2024: 99 · 2023: 133 · 2022: 105 · 2021: 74 · 2020: 34 · 2019: 1
- FWCI
- 24.53
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Locations
- Medical Image Analysis (publishedVersion)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- Spiral (Imperial College London) (submittedVersion, cc-by-nc-nd)
- Funders
- Wellcome Trust (102431)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- self-supervised learning, unlabeled data, CT images, brain tumor segmentation, multimodal MRI, image classification, image localization, image segmentation
- MeSH terms
- Abdomen, Supervised Machine Learning, Brain Neoplasms, Humans, Magnetic Resonance Imaging, Tomography, X-Ray Computed, Ultrasonography, Prenatal
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 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (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
