AccuLearning自动勾画临床靶区和危及器官用于宫颈癌术后放疗的可行性研究  

Feasibility of automatic segmentation of CTV and OARs in postoperative radiotherapy for cervical cancer using AccuLearning

作　　者：陈飞[1] 龚筱钦 余云鹏[1] 游涛[1] 王旭[1] 戴春华[1] 胡静[1] CHEN Fei;GONG Xiaoqin;YU Yunpeng;YOU Tao;WANG Xu;DAI Chunhua;HU Jing(Department of Radiotherapy,Affiliated Hospital of Jiangsu University,Zhenjiang 212000,China)

机构地区：[1]江苏大学附属医院放疗科,江苏镇江212000

出　　处：《实用医学杂志》2024年第2期153-157,共5页The Journal of Practical Medicine

基　　金：江苏省卫生健康委员会医学科研重点项目(编号:ZDB2020022);镇江市重点研发计划(社会发展)项目(编号:SH2023002);镇江市社会发展指导性科技计划项目(编号:FZ2020031)。

摘　　要：目的从几何学和剂量学探讨AccuLearning(AL)建立宫颈癌术后临床靶区(CTV)和危及器官(OARs)自动勾画模型应用于临床的可行性。方法选取75例宫颈癌术后手动勾画CT数据,60例应用AL训练生成自动勾画模型,并对剩余15例进行自动勾画,同时将自动勾画图像上的放疗计划导入到手动勾画结构上,比较两种勾画方式的效率、戴斯相似系数(DSC)、豪斯多夫距离(HD)和剂量学差异。结果自动勾画时间明显小于手动勾画(P<0.05);各结构DSC值≥0.87;肠袋和直肠的HD值在10 mm左右,其余结构小于5 mm;剂量学评估CTV(D98、V90%、V95%、Dmean、HI)、肠袋(V50)和膀胱(V50)有显著性差异(P<0.05)。结论基于AL形成的宫颈癌术后自动勾画模型提高了放疗效率,OARs具有直接应用于临床的可能性,CTV仍需进一步修改。Objective To explore the feasibility of automatic segmentation of clinical target volume(CTV)and organs at risk(OARs)for cervical cancer using AccuLearning(AL)based on geometric and dosimetric indices.Methods Seventy-five CT localization images with manual contouring data of postoperative cervical cancer were enrolled in this study.Sixty cases were randomly selected to trained to generate automatic segmentation model by AL,and the CTV and OARs of the remaining 15 cases were automatically contoured.Radiotherapy plans on the automatic segmentation contours were imported on the CT images of manual contours.The efficiency,Dice similarity coefficient(DSC),Hausdorff distance(HD)and dosimetric parameters were compared between the two methods.Results The time of automatic segmentation was significantly shorter than that of the manual contour(P<0.05).The DSC of all structures were≥0.87.The HD of bowel bag and rectum were about 10 mm,and that of the rest of OARs were less than 5 mm.CTV(D98,V90%,V95%,Dmean,HI),bowel bag(V50)and bladder(V50)had significant differences in dosimetric comparison(P<0.05).Conclusion The automatic segmentation model based on AL can improve the efficiency of radiotherapy.Automatic segmentation of OARs has the potential of clinical application,while that of CTV still needs to be further modified.

关 键 词：自动勾画 宫颈癌 临床靶区 危及器官 剂量学 

分 类 号：R811.1[医药卫生—放射医学] R737.33[医药卫生—临床医学]