DR|GRADUATE: Uncertainty-aware deep learning-based diabetic retinopathy grading in eye fundus images

Araújo, Teresa; Aresta, Guilherme; Mendonça, Luís; Penas, Susana; Maia, Carolina; Carneiro, Ângela; Mendonça, Ana Maria; Campilho, Aurélio

doi:10.1016/j.media.2020.101715

Cited by 85 publications

(40 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model is now capable of detecting NVs in eye fundus images, as shown in Fig. 7a,7b and 7c, which were initially not being detected by DR|Graduate [16]. However, in some cases other structures are counfounded with NVs and mistakenly detected as PDR signs (Fig.…”

Section: B Results and Discussionmentioning

confidence: 93%

“…DR grading was obtained using the methodology proposed by T. Araújo et al [16]. DR|Graduate is a deep learningbased DR grading computer-aided diagnosis system that supports its decision by providing an interpretable explanation and an estimation of the uncertainty of that prediction, which gives the ophthalmologist a measure of how much that decision can be trusted.…”

Section: E Dr Grading 1) Methods -Dr|graduatementioning

confidence: 99%

“…The training scheme was kept the same as in [16], in order to assess only the influence of the NV augmentation in the results. Note that the original data augmentation scheme, used in [16] (flips, rotations, brightness adjustments and contrast normalization), were still performed in the new training, together with the newly proposed NV augmentation.…”

Section: ) Newly Proposed Data Augmentationmentioning

confidence: 99%

“…Generaly, DR is classified accordingly to the international DR scale as mild non-proliferative DR (NPDR) (R1), moderate NPDR (R2), severe NPDR (R3) or PDR (R4) [1], ordered according to their risk of progression [13]. Despite the task's complexity, several works have shown promising performance [14]- [16]. Namely, Araújo et al [16] proposed a model (DR|Graduate) that not only produces a grade but also an uncertainty associated with the prediction and an attention map that explains the decision.…”

Section: Introductionmentioning

confidence: 99%

“…Despite the task's complexity, several works have shown promising performance [14]- [16]. Namely, Araújo et al [16] proposed a model (DR|Graduate) that not only produces a grade but also an uncertainty associated with the prediction and an attention map that explains the decision. However, the proposed model tends to fail to detect R4 graded images.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Data Augmentation for Improving Proliferative Diabetic Retinopathy Detection in Eye Fundus Images

et al. 2020

Self Cite

View full text Add to dashboard Cite

Proliferative diabetic retinopathy (PDR) is an advanced diabetic retinopathy stage, characterized by neovascularization, which leads to ocular complications and severe vision loss. However, the available DRlabeled retinal image datasets have a small representation of images of the severest DR grades, and thus there is lack of PDR cases for training DR grading models. Additionally, the criteria for labelling these images in the publicly available datasets is not always clear, with some images which do not show typical PDR lesions being labeled as PDR due to the presence of photo-coagulation treatment and laser marks. This problem, together with the datasets' high class imbalance, leads to a limited variability of the samples, which the typical data augmentation and class balancing cannot fully mitigate. We propose a heuristicbased data augmentation scheme based on the synthesis of neovessel (NV)-like structures that compensates for the lack of PDR cases in DR-labeled datasets. The proposed neovessel generation algorithm relies on the general knowledge of common location and shape of these structures. NVs are generated and introduced in pre-existent retinal images which can then be used for enlarging deep neural networks' training sets. The data augmentation scheme was tested on multiple datasets, and allows to improve the model's capacity to detect NVs.

show abstract

Section: B Results and Discussionmentioning

confidence: 93%

Section: E Dr Grading 1) Methods -Dr|graduatementioning

confidence: 99%

Section: ) Newly Proposed Data Augmentationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Data Augmentation for Improving Proliferative Diabetic Retinopathy Detection in Eye Fundus Images

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

Cost-Sensitive Regularization for Diabetic Retinopathy Grading from Eye Fundus Images

Galdrán

Dolz²,

Chakor³

et al. 2020

Medical Image Computing and Computer Assisted Intervention – MICCAI 2020

View full text Add to dashboard Cite

Assessing the degree of disease severity in biomedical images is a task similar to standard classification but constrained by an underlying structure in the label space. Such a structure reflects the monotonic relationship between different disease grades. In this paper, we propose a straightforward approach to enforce this constraint for the task of predicting Diabetic Retinopathy (DR) severity from eye fundus images based on the well-known notion of Cost-Sensitive classification. We expand standard classification losses with an extra term that acts as a regularizer, imposing greater penalties on predicted grades when they are farther away from the true grade associated to a particular image. Furthermore, we show how to adapt our method to the modelling of label noise in each of the sub-problems associated to DR grading, an approach we refer to as Atomic Sub-Task modeling. This yields models that can implicitly take into account the inherent noise present in DR grade annotations. Our experimental analysis on several public datasets reveals that, when a standard Convolutional Neural Network is trained using this simple strategy, improvements of 3-5% of quadratic-weighted kappa scores can be achieved at a negligible computational cost. Code to reproduce our results is released at github.com/agaldran/cost_sensitive_loss_classification.

show abstract

Balanced-MixUp for Highly Imbalanced Medical Image Classification

Galdrán

Carneiro

Ballester

2021

Medical Image Computing and Computer Assisted Intervention – MICCAI 2021

View full text Add to dashboard Cite

Highly imbalanced datasets are ubiquitous in medical image classification problems. In such problems, it is often the case that rare classes associated to less prevalent diseases are severely under-represented in labeled databases, typically resulting in poor performance of machine learning algorithms due to overfitting in the learning process. In this paper, we propose a novel mechanism for sampling training data based on the popular MixUp regularization technique, which we refer to as Balanced-MixUp. In short, Balanced-MixUp simultaneously performs regular (i.e., instance-based) and balanced (i.e., class-based) sampling of the training data. The resulting two sets of samples are then mixed-up to create a more balanced training distribution from which a neural network can effectively learn without incurring in heavily under-fitting the minority classes. We experiment with a highly imbalanced dataset of retinal images (55K samples, 5 classes) and a long-tail dataset of gastro-intestinal video frames (10K images, 23 classes), using two CNNs of varying representation capabilities. Experimental results demonstrate that applying Balanced-MixUp outperforms other conventional sampling schemes and loss functions specifically designed to deal with imbalanced data. Code is released at https://github.com/agaldran/balanced_mixup .

show abstract

DR|GRADUATE: Uncertainty-aware deep learning-based diabetic retinopathy grading in eye fundus images

Cited by 85 publications

References 33 publications

Data Augmentation for Improving Proliferative Diabetic Retinopathy Detection in Eye Fundus Images

Data Augmentation for Improving Proliferative Diabetic Retinopathy Detection in Eye Fundus Images

Cost-Sensitive Regularization for Diabetic Retinopathy Grading from Eye Fundus Images

Balanced-MixUp for Highly Imbalanced Medical Image Classification

Contact Info

Product

Resources

About