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

@article{Arajo2020DRGRADUATEUD,
  title={DR|GRADUATE: uncertainty-aware deep learning-based diabetic retinopathy grading in eye fundus images},
  author={Teresa Ara{\'u}jo and Guilherme Aresta and Lu{\'i}s Mendonça and Susana Penas and Carolina Maia and {\^A}ngela Carneiro and Ana Maria Mendonça and Aur{\'e}lio J. C. Campilho},
  journal={Medical image analysis},
  year={2020},
  volume={63},
  pages={
          101715
        }
}
Diabetic retinopathy (DR) grading is crucial in determining the adequate treatment and follow up of patient, but the screening process can be tiresome and prone to errors. Deep learning approaches have shown promising performance as computer-aided diagnosis (CAD) systems, but their black-box behaviour hinders clinical application. We propose DR|GRADUATE, a novel deep learning-based DR grading CAD system that supports its decision by providing a medically interpretable explanation and an… Expand
Explainable artificial intelligence (XAI) in deep learning-based medical image analysis
TLDR
An overview of eXplainable Artificial Intelligence (XAI) used in deep learning-based medical image analysis and an outlook of future opportunities for XAI inmedical image analysis are presented. Expand
Cost-Sensitive Regularization for Diabetic Retinopathy Grading from Eye Fundus Images
TLDR
This paper proposes 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, and expands standard classification losses with an extra term that acts as a regularizer. Expand
A Review of Deep Learning in Medical Imaging: Imaging Traits, Technology Trends, Case Studies With Progress Highlights, and Future Promises
TLDR
This survey article presents traits of medical imaging, highlights both clinical needs and technical challenges in medical Imaging, and describes how emerging trends in DL are addressing these issues, including the topics of network architecture, sparse and noisy labels, federating learning, interpretability, uncertainty quantification, and so on. Expand
A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
TLDR
This study reviews recent advances in UQ methods used in deep learning and investigates the application of these methods in reinforcement learning (RL), and outlines a few important applications of UZ methods. Expand
An Efficient Framework for Automated Screening of Clinically Significant Macular Edema
TLDR
The results of this study convincingly demonstrate that by following these fundamental practices of machine learning, a basic k-NN based classifier could effectively accomplish the CSME screening. Expand
Applications of Deep Learning in Fundus Images: A Review
TLDR
In this review, 143 application papers with a carefully designed hierarchy of deep learning for fundus images are introduced and 33 publicly available datasets are presented. Expand
Assessment of Generative Adversarial Networks for Synthetic Anterior Segment Optical Coherence Tomography Images in Closed-Angle Detection
TLDR
The GAN synthetic AS-OCT images appeared to be of good quality, according to the glaucoma specialists, and the DL models, trained on all-synthetic AS- OCT images, can achieve high diagnostic performance. Expand
Automated Detection and Diagnosis of Diabetic Retinopathy: A Comprehensive Survey
TLDR
This review covers the literature dealing with AI approaches to DR that has been published in the open literature in five-years (2016-2021) and summarizes a total of 114 published articles which conformed to the scope of the review. Expand
Balanced-MixUp for Highly Imbalanced Medical Image Classification
TLDR
Experimental results demonstrate that applying Balanced-MixUp outperforms other conventional sampling schemes and loss functions specifically designed to deal with imbalanced data. Expand
Deep learning-based automated detection for diabetic retinopathy and diabetic macular oedema in retinal fundus photographs
TLDR
This study showed that the deep ensemble model exhibited excellent performance in detecting DR and DMO, and had good robustness and generalization, which could potentially help support and expand DR/DMO screening programs. Expand
...
1
2
...

References

SHOWING 1-10 OF 62 REFERENCES
Recognising and managing diabetic retinopathy how ilook for diabetic retinopathy: a vision technician’s experience
  • Community Eye Health
  • 2011
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
TLDR
This paper addresses the visualisation of image classification models, learnt using deep Convolutional Networks (ConvNets), and establishes the connection between the gradient-based ConvNet visualisation methods and deconvolutional networks. Expand
Diabetic Retinopathy Guidelines
  • 2012
New Effect Size Rules of Thumb
Recommendations to expand Cohen’s (1988) rules of thumb for interpreting effect sizes are given to include very small, very large, and huge effect sizes. The reasons for the expansion, andExpand
A Deep Learning Interpretable Classifier for Diabetic Retinopathy Disease Grading
TLDR
With this method, the generated visual maps can be easily interpreted by an ophthalmologist in order to find the underlying statistical regularities that help to the diagnosis of this eye disease. Expand
IDRiD: Diabetic Retinopathy - Segmentation and Grading Challenge
TLDR
The set-up and results of this challenge that is primarily based on Indian Diabetic Retinopathy Image Dataset (IDRiD), which received a positive response from the scientific community, have the potential to enable new developments in retinal image analysis and image-based DR screening in particular. Expand
Analysis of the performance of specialists and an automatic algorithm in retinal image quality assessment
TLDR
An inter-observer analysis for quality assessment that can be used as gold-standard for future studies is presented and a state-of-the-art algorithm for retinal image quality assessment is analyzed. Expand
EyeWeS: Weakly Supervised Pre-Trained Convolutional Neural Networks for Diabetic Retinopathy Detection
TLDR
It is shown that it is possible to convert any pre-trained convolutional neural network into a weakly-supervised model while increasing their performance and efficiency and to achieve 97.1% AUC in a cross-dataset experiment. Expand
A systematic study of the class imbalance problem in convolutional neural networks
TLDR
The effect of class imbalance on classification performance is detrimental; the method of addressing class imbalance that emerged as dominant in almost all analyzed scenarios was oversampling; and thresholding should be applied to compensate for prior class probabilities when overall number of properly classified cases is of interest. Expand
Automatic Detection of Retinal Lesions for Screening of Diabetic Retinopathy
  • S. Kar, S. Maity
  • Medicine, Computer Science
  • IEEE Transactions on Biomedical Engineering
  • 2018
TLDR
A novel and automated lesion detection scheme that highlights an improved performance over the existing methods with an average accuracy of $97.71\% and robustness in detecting the various types of DR lesions irrespective of their intrinsic properties. Expand
...
1
2
3
4
5
...