期刊
IEEE TRANSACTIONS ON MEDICAL IMAGING
卷 41, 期 5, 页码 1208-1218出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMI.2021.3134270
关键词
COVID-19; X-ray imaging; Convolution; Feature extraction; Pulmonary diseases; Routing; Deep learning; COVID-19; capsule networks; multi-head attention; chest X-ray images
类别
资金
- Fundamental Research Funds for the Central Universities [XDJK2020B033]
The outbreak of COVID-19 has posed great challenges to global healthcare systems, particularly in terms of efficient detection methods. This study proposes a capsule network model with a multi-head attention routing algorithm for fast and accurate diagnostics of COVID-19 diseases from chest X-ray images.
The outbreak of COVID-19 threatens the lives and property safety of countless people and brings a tremendous pressure to health care systems worldwide. The principal challenge in the fight against this disease is the lack of efficient detection methods. AI-assisted diagnosis based on deep learning can detect COVID-19 cases for chest X-ray images automatically, and also improve the accuracy and efficiency of doctors' diagnosis. However, large scale annotation of chest X-ray images is difficult because of limited resources and heavy burden on the medical system. To meet the challenge, we propose a capsule network model with multi-head attention routing algorithm, called MHA-CoroCapsule, to provide fast and accurate diagnostics for COVID-19 diseases from chest X-ray images. The MHA-CoroCapsule consists of convolutional layers, two capsule layers, and a non-iterative, parameterized multi-head attention routing algorithm is used to quantify the relationship between the two capsule layers. The experiments are performed on a combined dataset constituted by two publicly available datasets including normal, non-COVID pneumonia and COVID-19 images. The model achieves the accuracy of 97.28%, recall of 97.36%, and precision of 97.38% even with a limited number of samples. The experimental results demonstrate that, contrary to the transfer learning and deep feature extraction approaches, the proposed MHA-CoroCapsule has an encouraging performance with fewer trainable parameters and does not require pretraining and plenty of training samples.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据