基于LSTM与注意力结构的肺结节多特征抽取方法  

Multi-Feature Extraction of Pulmonary Nodules Based on LSTM and Attention Structure

作　　者：倪扬帆 杨媛媛 谢哲 郑德重 王卫东[3] NI Yangfan;YANG Yuanyuan;XIE Zhe;ZHENG Dezhong;WANG Weidong(Laboratory for Medical Imaging Informatics,Shanghai Institution of Technical Physics,Chinese Academy of Sciences,Shanghai 200080,China;University of Chinese Academy of Sciences,Beijing 100049,China;Chinese PLA General Hospital,Beijing 100089,China)

机构地区：[1]中国科学院上海技术物理研究所医学影像信息学实验室,上海200080 [2]中国科学院大学,北京100049 [3]中国人民解放军总医院,北京100089

出　　处：《上海交通大学学报》2022年第8期1078-1088,共11页Journal of Shanghai Jiaotong University

基　　金：科技部重点研发计划(2019YFC0118803)。

摘　　要：对肺结节的形状特征、边缘特征和内部特征进行准确分类,能够辅助影像科医生的日常诊断工作,提高影像报告的书写效率.针对这一问题,提出一种基于长短时记忆(LSTM)结构与注意力结构的多任务分类模型.该模型通过注意力机制融合各个任务间的共享特征,提高当前任务的特征抽取效果.LSTM结构分类器能够有效地筛选任务间的共享特征,提高模型的信息传递效率.实验表明,相较于传统多任务结构,所提模型在公开数据集LIDC-IDRI上能够取得更好的多特征分类效果,辅助医生快捷地获取肺结节特征信息.The accurate classification of shape, edge, and internal features of pulmonary nodules can not only assist the radiologists in their daily diagnosis, but also improve the writing efficiency of imaging reports. This paper proposes a multi-task classification model based on long-short term memory(LSTM) and attention structure, which merges the shared features among different classification tasks through attention mechanism to improve the feature extraction performance of the current task. The classifier based on temporal sequence LSTM structure can effectively screen the shared features and improve the efficiency of information transmission in the multi-task model. Experimental results show that compared with the traditional multi-task structure, the proposed model can achieve better classification results on the public dataset LIDC-IDRI, and assist doctors to quickly obtain nodule characteristics.

关 键 词：肺结节 注意力结构 长短时记忆网络 多任务分类 

分 类 号：R318[医药卫生—生物医学工程] TP181[医药卫生—基础医学]