Class-Aware Attention Network for infectious keratitis diagnosis using corneal photographs. (December 2022)

• Record Type: Journal Article
• Authors: Li, Jinhao; Wang, Shuai; Hu, Shaodan; Sun, Yiming; Wang, Yaqi; Xu, Peifang; Ye, Juan
• Is Part Of: Computers in biology and medicine. Volume 151:Part A(2022)
• Publication Date: 2022-12
• Subjects: Multi-class classification -- Corneal photographs -- Infectious keratitis -- Attention mechanism -- Convolutional neural network; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2022.106301
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Infectious keratitis is one of the common ophthalmic diseases and also one of the main blinding eye diseases in China, hence rapid and accurate diagnosis and treatment for infectious keratitis are urgent to prevent the progression of the disease and limit the degree of corneal injury. Unfortunately, the traditional manual diagnosis accuracy is usually unsatisfactory due to the indistinguishable visual features. In this paper, we propose a novel end-to-end fully convolutional network, named Class-Aware Attention Network (CAA-Net), for automatically diagnosing infectious keratitis (normal, viral keratitis, fungal keratitis, and bacterial keratitis) using corneal photographs. In CAA-Net, a class-aware classification module is first trained to learn class-related discriminative features using separate branches for each class. Then, the learned class-aware discriminative features are fed into the main branch and fused with other feature maps using two attention strategies to assist the final multi-class classification performance. For the experiments, we have built a new corneal photograph dataset with 1886 images from 519 patients and conducted comprehensive experiments to verify the effectiveness of our proposed method. The code is available at https://github.com/SWF-hao/CAA-Net_Pytorch . Graphical abstract: Highlights: The traditional manual diagnosis accuracy of infectious keratitis is usually unsatisfactory due to the indistinguishable visual features. We proposed a novel end-to-end fully convolutional network with a class-related feature learning module and two attention strategies. We designed a novel loss function to make the prediction margin between the true class of one sample and other classes larger. We have built a new corneal photograph dataset with 1, 886 images collected from 519 patients and compared with other state-of-the-art methods.