基于深度学习的计算机辅助诊断系统检出DR胸部正位片中的骨折  

Deep-learning based computer aided diagnosis system in detecting fractures on anteroposterior chest DR films

作　　者：吴育鑫 薛蕴菁[2] 段青[2] 孙斌[2] 刘柏韵 陈玉仙[2] WU Yuxin;XUE Yunjing;DUAN Qing;SUN Bin;LIU Baiyun;CHEN Yuxian(Graduate School, Fujian Medical University, Fuzhou 350000, China;Department of Imaging, Fujian Medical University Union Hospital, Fuzhou 350000, China;InferVision, Beijing 100025, China)

机构地区：[1]福建医科大学研究生院,福建福州350000 [2]福建医科大学附属协和医院影像科,福建福州350000 [3]北京推想科技有限公司,北京100025

出　　处：《中国介入影像与治疗学》2020年第11期675-678,共4页Chinese Journal of Interventional Imaging and Therapy

摘　　要：目的观察基于深度学习的计算机辅助诊断系统(DL-CAD)检出DR胸部正位片中骨折的效能及其对低年资放射科医师的辅助作用。方法①试验1:回顾性收集547例DR胸部正位片,其中361例存在胸部骨折(共983处骨折)、186例无胸部骨折,评估DL-CAD对骨折的预测性能。②试验2:随机选取试验1中的397例DR胸片,其中211例存在胸部骨折(共604处骨折)、186例无胸部骨折,记录并比较单独DL-CAD(1组)、单独低年资医师(2组)、DL-CAD辅助低年资医师(3组)、单独高年资医师(4组)的检出结果。结果①试验1:983处骨折中,DL-CAD识别出672处,正确识别641处,误诊31处,敏感度65.21%(641/983),F值为77.46%;361例骨折患者中,DL-CAD识别出320例,正确识别314例,误诊6例,敏感度86.98%(314/361),F值92.22%。②试验2:1、2、3、4组观察者检出骨折的敏感度分别为62.09%(375/604)、61.59%(372/604)、86.75%(524/604)和83.44%(504/604),F值分别为75.38%、74.62%、90.74%及89.84%;3、4组检测效能均高于1、2组(P均<0.001),而1组与2组间、3组与4组间差异均无统计学意义(P均>0.05)。结论DL-CAD对DR胸部正位片中骨折的检出效果较好,且可有效提高低年资放射科医师对胸部骨折的检出效能。Objective To evaluate the efficiency of deep-learning based computer aided diagnosis system(DL-CAD)in detecting fractures on DR chest anteroposterior films,and to explore its capability of assisting the junior radiologist.Methods①Experiment 1:A total of 547 DR chest anteroposterior films,including 361 patients with 983 chest fractures and 186 without chest fractures were retrospectively analyzed.The predictive performance of DL-CAD for fracture was evaluated.②Experiment 2:Totally 397 patients were randomly selected from experiment 1,including 211 cases with 604 chest fractures and 186 cases without chest fractures.The results of DL-CAD alone(group 1),a junior radiology resident alone(group 2),a junior radiology resident aided with DL-CAD(group 3)and a senior radiologist alone(group 4)were recorded and compared,respectively.Results①For experiment 1:Among 983 fractures,DL-CAD identified 672 fractures,641 were correctly identified and 31 were misdiagnosed,with a sensitivity of 65.21%(641/983)and F-measure of 77.46%.Out of a total of 361 fracture cases,DL-CAD identified 314 cases,misdiagnosed 6 cases,with a sensitivity of 86.98%(314/361)and F-measure of 92.22%.②Experiment 2:The sensitivity of fracture detection was 62.09%(375/604),61.59%(372/604),86.75%(524/604)and 83.44%(504/604),and the F-measure was 75.38%,74.62%,90.74%,89.84%for group 1,2,3 and 4,respectively.The detection efficacy of group 3 and 4 were both higher than that of group 1 and 2(all P<0.001).There was no significant difference between group 1 and group 2,nor group 3 and group 4(both P>0.05).Conclusion DL-CAD software showed good detection effect of fractures on DR chest anteroposterior films,which could effectively improve the diagnostic performance of junior radiologist in fracture detection.

关 键 词：骨折 放射摄影术 胸部 X线透视检查 深度学习 计算机辅助诊断系统 

分 类 号：R683.1[医药卫生—骨科学] R816.8[医药卫生—外科学]