文献类型： 会议论文

第一作者： Wenxi Yu

作者： Wenxi Yu ¹ ; Hua Zhou ² ; Youngwon Choi ³ ; Jonathan G. Goldin ¹ ; Grace Hyun J. Kim ¹ ;

作者机构： 1.Center for Computer Vision and Imaging Biomarkers, University of California, Los Angeles

2.Department of Biostatistics, University of California, Los Angeles

3.Department of Statistics, Seoul National University

关键词： Attention models;Domain knowledge;Idiopathic pulmonary fibrosis;Medical imaging

会议名称： IEEE International Symposium on Biomedical Imaging

主办单位：

页码： 1777-1780

摘要： We propose a Multi-scale, domain knowledge-Guided Attention model (MGA-Net) for a weakly supervised problem - disease diagnosis with only coarse scan-level labels. The use of guided attention models encourages the deep learning-based diagnosis model to focus on the area of interests (in our case, lung parenchyma), at different resolutions, in an end-to-end manner. The research interest is to diagnose subjects with idiopathic pulmonary fibrosis (IPF) among subjects with interstitial lung disease (ILD) using an axial chest high resolution computed tomography (HRCT) scan. Our dataset contains 279 IPF patients and 423 non-IPF ILD patients. The network's performance was evaluated by the area under the receiver operating characteristic curve (AUC) with standard errors (SE) using stratified five-fold cross validation. We observe that without attention modules, the IPF diagnosis model performs unsatisfactorily (AUC±SE =0.690 ± 0.194); by including unguided attention module, the IPF diagnosis model reaches satisfactory performance (AUC±SE =0.956±0.040), but lack explainability; when including only guided high- or medium- resolution attention, the learned attention maps highlight the lung areas but the AUC decreases; when including both high- and medium- resolution attention, the model reaches the highest AUC among all experiments (AUC± SE =0.971 ± 0.021) and the estimated attention maps concentrate on the regions of interests for this task. Our results suggest that, for a weakly supervised task, MGA-Net can utilize the population-level domain knowledge to guide the training of the network in an end-to-end manner, which increases both model accuracy and explainability.

分类号： tp391.41-53