Dual-branch combination network (DCN): Towards accurate diagnosis and lesion segmentation of COVID-19 using CT images.
Dual-branch combination network (DCN): Towards accurate diagnosis and lesion segmentation of COVID-19 using CT images.
复制标题
双分支组合网络 (DCN)：利用 CT 图像实现 COVID-19 的准确诊断和病灶分割
DOI：
10.1016/j.media.2020.101836
复制
发表时间：
2021-01
影响因子：
10.9
通讯作者：
Hu D
中科院分区：
文献类型：
--
作者：
Gao K;Su J;Jiang Z;Zeng LL;Feng Z;Shen H;Rong P;Xu X;Qin J;Yang Y;Wang W;Hu D
最近，冠状病毒病（COVID-19）在全球爆发和传播，随着医疗资源日益紧张，开发准确、高效的疾病诊断工具势在必行。人工智能 (AI) 辅助工具已展现出理想的潜力；例如，胸部计算机断层扫描 (CT) 已被证明在 COVID-19 的诊断和评估中发挥着重要作用。然而，开发基于CT的疾病检测AI诊断系统面临着相当大的挑战，这主要是由于缺乏足够的人工描绘样本进行训练，以及在感染早期阶段对细微病变有足够的敏感性。在本研究中，我们开发了一种用于COVID-19诊断的双分支组合网络（DCN），可以同时实现个体级别的分类和病变分割。为了将分类分支更集中于病变区域，开发了一种新颖的病变注意模块来整合中间分割结果。此外，为了管理各个设施不同成像参数的潜在影响，提出了一种切片概率映射方法来学习从切片级分类到个体级分类的转换。我们对来自中国 10 个研究所的 1202 名受试者的大型数据集进行了实验。结果表明：1）所提出的 DCN 在内部数据集上达到了 96.74% 的分类精度，在外部验证数据集上达到了 92.87% 的分类精度，从而优于其他模型； 2）DCN以更少的样本获得了可比的性能，并表现出更高的灵敏度，特别是在细微病变检测方面； 3）与其他深度模型相比，DCN 由于其分类由高级语义信息引导，因此在感染位点上提供了良好的可解释性。基于我们提出的框架的基于 CT 的 COVID-19 在线诊断平台现已推出。
The recent global outbreak and spread of coronavirus disease (COVID-19) makes it an imperative to develop accurate and efficient diagnostic tools for the disease as medical resources are getting increasingly constrained. Artificial intelligence (AI)-aided tools have exhibited desirable potential; for example, chest computed tomography (CT) has been demonstrated to play a major role in the diagnosis and evaluation of COVID-19. However, developing a CT-based AI diagnostic system for the disease detection has faced considerable challenges, which is mainly due to the lack of adequate manually-delineated samples for training, as well as the requirement of sufficient sensitivity to subtle lesions in the early infection stages. In this study, we developed a dual-branch combination network (DCN) for COVID-19 diagnosis that can simultaneously achieve individual-level classification and lesion segmentation. To focus the classification branch more intensively on the lesion areas, a novel lesion attention module was developed to integrate the intermediate segmentation results. Furthermore, to manage the potential influence of different imaging parameters from individual facilities, a slice probability mapping method was proposed to learn the transformation from slice-level to individual-level classification. We conducted experiments on a large dataset of 1202 subjects from ten institutes in China. The results demonstrated that 1) the proposed DCN attained a classification accuracy of 96.74% on the internal dataset and 92.87% on the external validation dataset, thereby outperforming other models; 2) DCN obtained comparable performance with fewer samples and exhibited higher sensitivity, especially in subtle lesion detection; and 3) DCN provided good interpretability on the loci of infection compared to other deep models due to its classification guided by high-level semantic information. An online CT-based diagnostic platform for COVID-19 derived from our proposed framework is now available.
登录
查看更多内容
影响因子：
168.9
作者：
Huang, Chaolin;Wang, Yeming;Cao, Bin
通讯作者：
Cao, Bin
影响因子：
168.9
作者：
Chan, Jasper Fuk-Woo;Yuan, Shuofeng;Yuen, Kwok-Yung
通讯作者：
Yuen, Kwok-Yung
影响因子：
4.8
作者：
Armato, SG;Sensakovic, WF
通讯作者：
Sensakovic, WF
影响因子：
10.9
作者：
Li, Lei;Wu, Fuping;Zhuang, Xiahai
通讯作者：
Zhuang, Xiahai
影响因子：
19.7
作者：
Li, Lin;Qin, Lixin;Xia, Jun
通讯作者：
Xia, Jun