基于深度学习宫颈癌靶区自动分割勾画临床研究  

Clinical evaluation of deep learning-based clinical target volume auto-segmentation algorithm for cervical cancer

作　　者：马辰莺[1] 周菊英[1] 徐晓婷[1] 郭建[1] 韩妙飞 高耀宗 王章龙 周婧劼 Ma Chenying;Zhou Juying;Xu Xiaoting;Guo Jian;Han Miaofei;Gao Yaozong;Wang Zhanglong;Zhou Jingjie(Department of Radiation Oncology,First Affiliated Hospital of Soochow University,Suzhou 215006,China;Shanghai Lianying Intelligent Medical Technology Co.,Ltd,Shanghai 200232,China;Shanghai Lianying Medical Technology Co.,Ltd,Shanghai 201807,China)

机构地区：[1]苏州大学附属第一医院放疗科,215006 [2]上海联影智能医疗科技有限公司,200232 [3]上海联影医疗科技有限公司,201807

出　　处：《中华放射肿瘤学杂志》2020年第10期859-865,共7页Chinese Journal of Radiation Oncology

基　　金：国家自然科学基金(81602792);苏州市科技发展计划项目(SS201628)。

摘　　要：目的验证基于深度学习的宫颈癌靶区自动分割勾画临床适用性。方法选取535例宫颈癌CT影像,参照RTOG及JCOG标准勾画宫颈癌临床靶区(CTV),经专家审查后作为参考勾画,用于自动分割勾画训练和测试。另从测试组中随机挑选根治4例及术后6例,分别由初、中、高级医师手动勾画CTV。统计Dice系数(DSC)、平均表面距离(MSD)和豪斯多夫距离(HD)用于自动分割勾画测试,以及比较医师手动勾画和自动勾画相对于参考勾画的准确性。同时,分别记录算法和手动勾画耗时。结果数据经VB-Net网络训练得到根治CTV1(dCTV1)、dCTV2、术后CTV1(pCTV1)自动分割模型,自动勾画结果与参考勾画具有较好的一致性(DSC:0.88、0.70、0.86;MSD:1.32、2.42、1.15 mm;HD:21.6、22.4、20.8 mm)。dCTV1算法与三组医师勾画相近(P>0.05);dCTV2及pCTV1算法均优于初中级医师勾画(P<0.05),自动分割勾画耗时较手动勾画显著缩短。结论基于深度学习的宫颈癌靶区自动分割勾画准确性与高级医师手动勾画相当,应用于临床中将有助于大幅提高工作效率,具有提高勾画一致性和准确性的潜能。Objective To validate the feasibility of a deep learning-based clinical target volume(CTV)auto-segmentation algorithm for cervical cancer in clinical settings.Methods CT data sets from 535 cervical cancer patients were collected.CTVs were delineated according to RTOG and JCOG guidelines,reviewed by experts,and then used as reference contours for training(definitive 177,post-operative 302)and test(definitive 23,post-operative 33).Four definitive and 6 post-operative cases were randomly selected from the testing cohort to be manually delineated by junior,intermediate,senior doctors,respectively.Dice coefficient(DSC),mean surface distance(MSD)and Hausdorff distance(HD)were used for test and comparison between auto-segmentation and RO delineation.Meantime,auto-segmentation time and manual delineation time were recorded.Results Auto-segmentation models of dCTV1,dCTV2 and pCTV1 were trained with VB-Net and showed good agreement with reference contours in the testing cohorts(DSC,0.88,0.70,0.86 mm;MSD,1.32,2.42,1.15 mm;HD,21.6,22.4,20.8 mm).For dCTV1,the difference between auto-segmentation and all three groups of doctors was not significant(P>0.05).For dCTV2 and pCTV1,auto-segmentation was better than the junior and intermediate doctors(both P<0.05).Auto-segmentation time consumption was considerably shorter than that of manual delineation.Conclusions Deep learning-based CTV auto-segmentation algorithm for cervical cancer achieves comparable accuracy to manual delineation of senior doctors.Clinical application of the algorithm can contribute to shortening doctors′manual delineation time and improving clinical efficiency.Furthermore,it may serve as a guide for junior doctors to improve the consistency and accuracy of cervical cancer CTV delineation in clinical practice.

关 键 词：深度学习 临床靶体积勾画 自动分割算法 宫颈肿瘤 

分 类 号：R737.33[医药卫生—肿瘤] TP391.41[医药卫生—临床医学] TP18[自动化与计算机技术—计算机应用技术]