Using multi-task learning to improve diagnostic performance of convolutional neural networks | |
Fang, Mengjie2,4; Dong, Di2,4; Sun, Ruijia3; Fan, Li1; Sun, Yingshi3; Liu, Shiyuan1; Tian, Jie2,4 | |
2019 | |
会议日期 | 2019-2 |
会议地点 | San Diego, California, USA |
英文摘要 | Due to the complex biological and physical mechanisms, the correlations between the classification objects of clinical tasks and the medical imaging phenotype are always ambiguous and implied, which makes it difficult to train a powerful diagnostic convolutional neural network (CNN) model efficiently. In this study, we propose a generic multi-task learning (MTL) CNN framework to achieve higher classification accuracy and better generalization. The proposed framework is designed to carry out the major diagnostic task and several auxiliary tasks simultaneously. It encourages the models to learn more beneficial representation following the underlying relation among patients’ clinical characteristics, obvious imaging findings and quantitative imaging phenotype. We evaluate our approach on two clinical applications, namely advanced gastric cancer (AGC) serosa invasion diagnosis and discrimination of lung invasive adenocarcinoma manifesting as ground-glass nodule (GGN). Two datasets are utilized, which contain 357 AGC patients’ venous phase contrast-enhanced CT volumes and 236 GGN patients’ non-contrast CT volumes respectively. Several subjective CT morphology characteristics and common clinical characteristics are collected and used as the auxiliary tasks. To evaluate the generality of our strategy, CNNs with and without natural image-based pre-training are successively incorporated into the framework. The experimental results demonstrate that the proposed MTL CNN framework is able to improve the diagnostic performance significantly (7.4%-12.8% AUC increase and 3.5%-7.9% accuracy increase). |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/48553] |
专题 | 自动化研究所_中国科学院分子影像重点实验室 |
通讯作者 | Tian, Jie |
作者单位 | 1.Department of Radiology, Changzheng Hospital, Second Military Medical University, Shanghai 200003, China 2.University of Chinese Academy of Sciences, Beijing 100049, China 3.Radiology Department, Peking University Cancer Hospital & Institute, Beijing 100142, China 4.CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China |
推荐引用方式 GB/T 7714 | Fang, Mengjie,Dong, Di,Sun, Ruijia,et al. Using multi-task learning to improve diagnostic performance of convolutional neural networks[C]. 见:. San Diego, California, USA. 2019-2. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论