Deep image mining for diabetic retinopathy screening

By Gwenolé Quellec, Katia Charrière, Yassine Boudi, Béatrice Cochener, Mathieu Lamard. 2016

500 citations recorded by the source corpus.

HighlightsA ConvNet is trained to detect images with referable diabetic retinopathy (DR).Training is supervised with image‐level annotations only (referable DR or not).Thanks to a modified training procedure, pathological pixels can also be detected.This solution outperforms DR screening systems in a public dataset of 90,000 images.It also outperforms lesion detectors in the DiaretDB1 dataset, for all lesion types. Graphical abstract Figure. No Caption available. ABSTRACT Deep learning is quickly becoming the leading methodology for medical image analysis. Given a large medical archive, where each image is associated with a diagnosis, efficient pathology detectors or classifiers can be trained with virtually no expert knowledge about the target pathologies. However, deep learning algorithms, including the popular ConvNets, are black boxes: little is known about the local patterns analyzed by ConvNets to make a decision at the image level. A solution is proposed in this paper to create heatmaps showing which pixels in images play a role in the image‐level predictions. In other words, a ConvNet trained for image‐level classification can be used to detect lesions as well. A generalization of the backpropagation method is proposed in order to train ConvNets that produce high‐quality heatmaps. The proposed solution is applied to diabetic retinopathy (DR) screening in a dataset of almost 90,000 fundus photographs from the 2015 Kaggle Diabetic Retinopathy competition and a private dataset of almost 110,000 photographs (e‐ophtha). For the task of detecting referable DR, very good detection performance was achieved: Symbol in Kaggle’s dataset and Symbol in e‐ophtha. Performance was also evaluated at the image level and at the lesion level in the DiaretDB1 dataset, where four types of lesions are manually segmented: microaneurysms, hemorrhages, exudates and cotton‐wool spots. For the task of detecting images containing these four lesion types, the proposed detector, which was trained to detect referable DR, outperforms recent algorithms trained to detect those lesions specifically, with pixel‐level supervision. At the lesion level, the proposed detector outperforms heatmap generation algorithms for ConvNets. This detector is part of the Messidor® system for mobile eye pathology screening. Because it does not rely on expert knowledge or manual segmentation for detecting relevant patterns, the proposed solution is a promising image mining tool, which has the potential to discover new biomarkers in images. Symbol. No Caption available. Symbol. No Caption available.

Subfields: Computer Vision and Pattern Recognition, Ophthalmology, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Ophthalmology

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Distributed deep learning networks among institutions for medical imaging (2018, methodology): “In addition, the resolutions ranged from 433 289 pixels to 5184 3456 pixels.(14) The images were preprocessed via the method detailed in the competition report by the winner, Ben Graham.”
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications (2021, background): “Further applications of DNN explanation techniques for medical images include the detection of lesions in diabetic retinopathy data [145], pixelwise analysis of microscopy images from global image annotations [98], the validation of predictions in dermatology [199], and analysis of X-ray images [48]”
Applications of Deep Learning in Fundus Images: A Review (2021, methodology): “Quellec et al. (2020) used few-shot learning to perform rare pathologies detection.”
Fundus Image Classification Using VGG-19 Architecture with PCA and SVD (2018, methodology): “Quellec et al. [32], proposed a pixel based ConvNets DNN technique for earlier diagnosis of retinal fundus images.”
A Deep Learning Ensemble Approach for Diabetic Retinopathy Detection (2019, methodology): “The computer vision-based methods are divided into hand-on engineering [4]–[7] and end-to-end learning [8]–[10].”
IDRiD: Diabetic Retinopathy - Segmentation and Grading Challenge. (2020, background): “A step further, researchers ( Quellec et al., 2017 ) demonstrated an ability of lesion segmentation based on CNN trained for image-level classiﬁcation.”
Weakly-supervised localization of diabetic retinopathy lesions in retinal fundus images (2017, methodology): “To the best of our knowledge, [25] is the only approach proposed so far to detect the lesion areas within retina images which is trained in weaklysupervised fashion using only image-level labels to conclude the lesion areas.”
Toward Interpretable Machine Learning: Transparent Deep Neural Networks and Beyond (2020, methodology): “Interpretable and non-linear models have been successfully applied to many other tasks, including the detection of lesions in diabetic retinopathy data [115], the validation of predictions in dermatology [157], plant stress classiﬁcation [41], or the analysis of galaxy morphologies [164].”
Certifiably Robust Interpretation in Deep Learning (2019, background): “Figures are borrowed from Quellec et al. (2017). Signs of lesions indicative of diabetic retinopathy are automatically highlighted.”