Journal
COMPUTERS IN BIOLOGY AND MEDICINE
Volume 151, Issue -, Pages -Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.compbiomed.2022.106301
Keywords
Multi-class classification; Corneal photographs; Infectious keratitis; Attention mechanism; Convolutional neural network
Categories
Funding
- Natural Science Foundation of Shandong Province
- Natural Science Foundation of Jiangsu Province
- National Natural Science Founda-tion of China
- National Natural Science Foundation Regional Innovation and Development Joint Fund
- [2022HWYQ-041]
- [BK20220266]
- [62201323]
- [U20A20386]
Ask authors/readers for more resources
This paper proposes a novel method, CAA-Net, for automatically diagnosing infectious keratitis using corneal photographs. The method combines class-awareness and attention strategies, and has been verified to be effective in diagnosing different types of infectious keratitis.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available