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
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
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
Rethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
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
Self-citationChen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2016) · arXiv · doi:10.48550/arxiv.1606.00915 · Cited by 22,392
Self-citationProceedings of IEEE Conference on Computer Vision and Pattern Recognition
(1993) · doi:10.1109/cvpr.1993 · Cited by 17,989
Advances in Neural Information Processing Systems 19
(2007) · The MIT Press eBooks · doi:10.52202/085713 · Cited by 16,043
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate ShiftPreprint
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 15,273
Proceedings of IEEE International Conference on Computer Vision
(1995) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.1995.466933 · Cited by 13,117
Advances in Neural Information Processing Systems 25
Zhang, Y., Sutton, C. A., Storkey, A., & Zoubin Ghahramani, A. (2012) · Cited by 12,653
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
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
Context Encoders: Feature Learning by Inpainting
Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., & Efros, A. A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.278 · Cited by 5,691
Proceedings European Conference on Computer Vision 2002
Heyden, A., Sparr, G., Nielsen, M., & Johansen, P. (2002) · Lund University Publications (Lund University) · Cited by 5,153
Greedy layer-wise training of deep networks
Bengio, Y., Lamblin, P., Popovici, D., & Larochelle, H. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0024 · Cited by 4,841
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.11231 · Cited by 4,636
Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., & Summers, R. M. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.369 · Cited by 4,616
Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation
Kamnitsas, K., Ledig, C., Newcombe, V. F. J., Simpson, J. P., Kane, A. D., Menon, D. K., Rueckert, D., & Glocker, B. (2017) · Medical Image Analysis · doi:10.1016/j.media.2016.10.004 · Cited by 3,498
Self-citationZhang, R., Isola, P., & Efros, A. A. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46487-9_40 · Cited by 3,417
Bakas, S., Akbari, H., Sotiras, A., Bilello, M., Rozycki, M., Kirby, J. S., Freymann, J. B., Farahani, K., & Davatzikos, C. (2017) · Scientific Data · doi:10.1038/sdata.2017.117 · Cited by 3,049
Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
Krähenbühl, P., & Koltun, V. (2012) · arXiv · doi:10.48550/arxiv.1210.5644 · Cited by 2,908
Fast R-CNNPreprint
Girshick, R. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1504.08083 · Cited by 2,781
Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles
Noroozi, M., & Favaro, P. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46466-4_5 · Cited by 2,775
Unsupervised Visual Representation Learning by Context Prediction
Doersch, C., Gupta, A., & Efros, A. A. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.167 · Cited by 2,629
Proceedings of the British Machine Vision Conference 2014
(2014) · doi:10.5244/c.28 · Cited by 1,360
Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support
(2017) · Lecture notes in computer science · doi:10.1007/978-3-319-67558-9 · Cited by 1,149
Comparison and evaluation of methods for liver segmentation from CT datasets
Heimann, T., van Ginneken, B., Styner, M. A., Arzhaeva, Y., Aurich, V., Bauer, C., Beck, A., Becker, C., Beichel, R., Bekes, G., et al. (2009) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2009.2013851 · Cited by 1,135
Unsupervised Learning of Visual Representations Using Videos
Wang, X., & Gupta, A. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.320 · Cited by 1,005
Hierarchical Feature Representation and Multimodal Fusion with Deep Learning for AD/MCI Diagnosis
Suk, H.-I., Lee, S.-W., & Shen, D. (2014) · NeuroImage · doi:10.1016/j.neuroimage.2014.06.077 · Cited by 968
Shuffle and Learn: Unsupervised Learning Using Temporal Order Verification
Misra, I., Zitnick, C. L., & Hebert, M. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_32 · Cited by 779
Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks
Dosovitskiy, A., Fischer, P., Springenberg, J. T., Riedmiller, M., & Brox, T. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2496141 · Cited by 762
Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction
Zhang, R., Isola, P., & Efros, A. A. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.76 · Cited by 649
Multi-task Self-Supervised Visual Learning
Doersch, C., & Zisserman, A. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.226 · Cited by 637
3D U-Net: Learning Dense Volumetric Segmentation from Sparse AnnotationPreprint
Çiçek, Ö., Abdulkadir, A., Lienkamp, S. S., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.06650 · Cited by 488
Colorization as a Proxy Task for Visual Understanding
Larsson, G., Maire, M., & Shakhnarovich, G. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.96 · Cited by 481
Learning Features by Watching Objects Move
Pathak, D., Girshick, R., Dollár, P., Darrell, T., & Hariharan, B. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.638 · Cited by 458
Agrawal, P., Carreira, J., & Malik, J. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.13 · Cited by 438
Self-Supervised Video Representation Learning with Odd-One-Out Networks
Fernando, B., Bilen, H., Gavves, E., & Gould, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.607 · Cited by 421
SonoNet: Real-Time Detection and Localisation of Fetal Standard Scan Planes in Freehand Ultrasound
Baumgartner, C. F., Kamnitsas, K., Matthew, J., Fletcher, T. P., Smith, S., Koch, L. M., Kainz, B., & Rueckert, D. (2017) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2017.2712367 · Cited by 416
Self-citationAmbient Sound Provides Supervision for Visual Learning
Owens, A., Wu, J., McDermott, J. H., Freeman, W. T., & Torralba, A. B. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46448-0_48 · Cited by 391
DeepMedic for Brain Tumor Segmentation
Kamnitsas, K., Ferrante, E., Parisot, S., Ledig, C., Nori, A. V., Criminisi, A., Rueckert, D., & Glocker, B. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-55524-9_14 · Cited by 346
Self-citationDeep learning from temporal coherence in video
Mobahi, H., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553469 · Cited by 328
Unsupervised Visual Representation Learning by Context PredictionPreprint
Doersch, C., Gupta, A., & Efros, A. A. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1505.05192 · Cited by 311
Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks
Chen, L., Bentley, P., & Rueckert, D. (2017) · NeuroImage Clinical · doi:10.1016/j.nicl.2017.06.016 · Cited by 307
Self-citationSegmentation labels and radiomic features for the pre-operative scans of the TCGA-LGG collection
Bakas, S. (2024) · TIB Data Manager · doi:10.57702/9am8buow · Cited by 244
Learning Image Representations Tied to Ego-Motion
Jayaraman, D., & Grauman, K. L. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.166 · Cited by 236
Unsupervised Learning of Visual Representations using VideosPreprint
Wang, X., & Gupta, A. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1505.00687 · Cited by 194
Dense Optical Flow Prediction from a Static Image
Walker, J., Gupta, A., & Hebert, M. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.281 · Cited by 182
Discriminative dictionary learning for abdominal multi-organ segmentation
Tong, T., Wolz, R., Wang, Z., Gao, Q., Misawa, K., Fujiwara, M., Mori, K., Hajnal, J. V., & Rueckert, D. (2015) · Medical Image Analysis · doi:10.1016/j.media.2015.04.015 · Cited by 150
Self-citationLearning to See by MovingPreprint
Agrawal, P., Carreira, J., & Malik, J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1505.01596 · Cited by 138
Slow and Steady Feature Analysis: Higher Order Temporal Coherence in Video
Jayaraman, D., & Grauman, K. L. (2016) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2016.418 · Cited by 136
ConvNet-Based Localization of Anatomical Structures in 3-D Medical Images
de Vos, B. D., Wolterink, J. M., de Jong, P. A., Leiner, T., Viergever, M. A., & Isgum, I. (2017) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2017.2673121 · Cited by 133
Time-Contrastive Networks: Self-Supervised Learning from Multi-view Observation
Sermanet, P., Lynch, C., Hsu, J., & Levine, S. (2017) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.69 · Cited by 112
Time-Contrastive Networks: Self-Supervised Learning from VideoPreprint
Sermanet, P., Lynch, C., Chebotar, Y., Hsu, J., Jang, E., Schaal, S., & Levine, S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.06888 · Cited by 95
Son, J. S., & Zisserman, A. (2017) · British Machine Vision Conference (BMVC) · doi:10.5244/c.31.155 · Cited by 74
Self-supervised Learning for Spinal MRIs
Jamaludin, A., Kadir, T., & Zisserman, A. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-67558-9_34 · Cited by 74
Colorization as a Proxy Task for Visual UnderstandingPreprint
Larsson, G., Maire, M., & Shakhnarovich, G. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.04044 · Cited by 41
Semi-supervised and Task-Driven Data Augmentation
Chaitanya, K., Karani, N., Baumgartner, C. F., Becker, A. S., Donati, O. F., & Ender Konukoglu, A. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20351-1_3 · Cited by 34
Dense Optical Flow Prediction from a Static ImagePreprint
Walker, J., Gupta, A., & Hebert, M. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1505.00295 · Cited by 23
Shuffle and Learn: Unsupervised Learning using Temporal Order VerificationPreprint
Misra, I., Zitnick, C. L., & Hebert, M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.08561 · Cited by 19
Self-Supervised Learning for Spinal MRIsPreprint
Jamaludin, A., Kadir, T., & Zisserman, A. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1708.00367 · Cited by 15
Pose from Action: Unsupervised Learning of Pose Features based on MotionPreprint
Purushwalkam, S., & Gupta, A. K. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1609.05420 · Cited by 14
Cited by
Sorted by citations
Recent advances and clinical applications of deep learning in medical image analysis
Chen, X., Wang, X., Zhang, K., Fung, K.-M. A., Thai, T., Moore, K. N., Mannel, R. S., Liu, H., Zheng, B., & Qiu, Y. (2022) · Medical Image Analysis · doi:10.1016/j.media.2022.102444 · Cited by 1,180
CutPaste: Self-Supervised Learning for Anomaly Detection and Localization
Li, C.-L., Sohn, K., Yoon, J., & Pfister, T. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00954 · Cited by 1,107
COVIDX-Net: A Framework of Deep Learning Classifiers to Diagnose COVID-19 in X-Ray ImagesPreprint
Hemdan, E. E., Shouman, M. A., & Karar, M. E. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.11055 · Cited by 1,218
Using machine learning approaches for multi-omics data analysis: A review
Reel, P. S., Reel, S., Pearson, E., Trucco, E., & Jefferson, E. (2021) · Biotechnology Advances · doi:10.1016/j.biotechadv.2021.107739 · Cited by 903
Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysis
Tang, Y., Yang, D., Li, W., Roth, H. R., Landman, B., Xu, D., Nath, V., & Hatamizadeh, A. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.02007 · Cited by 849
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
