RFMiD: Retinal Image Analysis for multi-Disease Detection challenge.

In the last decades, many publicly available large fundus image datasets have been collected for diabetic retinopathy, glaucoma, and age-related macular degeneration, and a few other frequent pathologies. These publicly available datasets were used to develop a computer-aided disease diagnosis system by training deep learning models to detect these frequent pathologies. One challenge limiting the adoption of a such system by the ophthalmologist is, computer-aided disease diagnosis system ignores sight-threatening rare pathologies such as central retinal artery occlusion or anterior ischemic optic neuropathy and others that ophthalmologists currently detect. Aiming to advance the state-of-the-art in automatic ocular disease classification of frequent diseases along with the rare pathologies, a grand challenge on "Retinal Image Analysis for multi-Disease Detection" was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI - 2021). This paper, reports the challenge organization, dataset, top-performing participants solutions, evaluation measures, and results based on a new "Retinal Fundus Multi-disease Image Dataset" (RFMiD). There were two principal sub-challenges: disease screening (i.e. presence versus absence of pathology - a binary classification problem) and disease/pathology classification (a 28-class multi-label classification problem). It received a positive response from the scientific community with 74 submissions by individuals/teams that effectively entered in this challenge. The top-performing methodologies utilized a blend of data-preprocessing, data augmentation, pre-trained model, and model ensembling. This multi-disease (frequent and rare pathologies) detection will enable the development of generalizable models for screening the retina, unlike the previous efforts that focused on the detection of specific diseases.

A Cross-Domain Weakly Supervised Diabetic Retinopathy Lesion Identification Method Based on Multiple Instance Learning and Domain Adaptation.

Accurate identification of lesions and their use across different medical institutions are the foundation and key to the clinical application of automatic diabetic retinopathy (DR) detection. Existing detection or segmentation methods can achieve acceptable results in DR lesion identification, but they strongly rely on a large number of fine-grained annotations that are not easily accessible and suffer severe performance degradation in the cross-domain application. In this paper, we propose a cross-domain weakly supervised DR lesion identification method using only easily accessible coarse-grained lesion attribute labels. We first propose the novel lesion-patch multiple instance learning method (LpMIL), which leverages the lesion attribute label for patch-level supervision to complete weakly supervised lesion identification. Then, we design a semantic constraint adaptation method (LpSCA) that improves the lesion identification performance of our model in different domains with semantic constraint loss. Finally, we perform secondary annotation on the open-source dataset EyePACS, to obtain the largest fine-grained annotated dataset EyePACS-pixel, and validate the performance of our model on it. Extensive experimental results on the public dataset FGADR and our EyePACS-pixel demonstrate that compared with the existing detection and segmentation methods, the proposed method can identify lesions accurately and comprehensively, and obtain competitive results using only coarse-grained annotations.

Automatic Medical Report Generation Based on Cross-View Attention and Visual-Semantic Long Short Term Memorys.

Automatic medical report generation based on deep learning can improve the efficiency of diagnosis and reduce costs. Although several automatic report generation algorithms have been proposed, there are still two main challenges in generating more detailed and accurate diagnostic reports: using multi-view images reasonably and integrating visual and semantic features of key lesions effectively. To overcome these challenges, we propose a novel automatic report generation approach. We first propose the Cross-View Attention Module to process and strengthen the multi-perspective features of medical images, using mean square error loss to unify the learning effect of fusing single-view and multi-view images. Then, we design the module Medical Visual-Semantic Long Short Term Memorys to integrate and record the visual and semantic temporal information of each diagnostic sentence, which enhances the multi-modal features to generate more accurate diagnostic sentences. Applied to the open-source Indiana University X-ray dataset, our model achieved an average improvement of 0.8% over the state-of-the-art (SOTA) model on six evaluation metrics. This demonstrates that our model is capable of generating more detailed and accurate diagnostic reports.

Effective methods of diabetic retinopathy detection based on deep convolutional neural networks.

PURPOSE: Diabetic retinopathy (DR) has become the leading cause of blindness worldwide. In clinical practice, the detection of DR often takes a lot of time and effort for ophthalmologist. It is necessary to develop an automatic assistant diagnosis method based on medical image analysis techniques. METHODS: Firstly, we design a feature enhanced attention module to capture focus lesions and regions. Secondly, we propose a stage sampling strategy to solve the problem of data imbalance on datasets and avoid the CNN ignoring the focus features of samples that account for small parts. Finally, we treat DR detection as a regression task to keep the gradual change characteristics of lesions and output the final classification results through the optimization method on the validation set. RESULTS: Extensive experiments are conducted on open-source datasets. Our methods achieve 0.851 quadratic weighted kappa which outperforms first place in the Kaggle DR detection competition based on the EyePACS dataset and get the accuracy of 0.914 in the referable/non-referable task and 0.913 in the normal/abnormal task based on the Messidor dataset. CONCLUSION: In this paper, we propose three novel automatic DR detection methods based on deep convolutional neural networks. The results illustrate that our methods can obtain comparable performance compared with previous methods and generate visualization pictures with potential lesions for doctors and patients.