利用医学相似性指数评价放疗中靶区自动勾画效果的可行性研究  

Feasibility of Evaluating Result of Auto-segmentation of Target Volumes in Radiotherapy with Medical Consideration Index

作　　者：何奕松 余行 张盛元 罗勇[1] 傅玉川[1] HE Yisong;YU Hang;ZHANG Shengyuan;LUO Yong;FU Yuchuan(Department of Radiation Oncology,West China Hospital of Sichuan University,Chengdu,610041;Key Laboratory of Radiation Physics and Technology of Ministry of Education,Institute of Nuclear Science and Technology,Sichuan University,Chengdu,610064)

机构地区：[1]四川大学华西医院放疗科,成都市610041 [2]四川大学核科学技术研究所,辐射物理与技术教育部重点实验室,成都市610064

出　　处：《中国医疗器械杂志》2021年第5期573-579,共7页Chinese Journal of Medical Instrumentation

基　　金：四川省科技计划重点研发项目(2020YFS0274)。

摘　　要：目的探究使用基于双向局部距离的医学相似指数(medical similarity index,MSI)评价医学影像自动分割结果的可行性。方法以医生手动勾画的鼻咽癌中低危临床靶区为感兴趣区.分别利用基于图集和基于深度学习的方法获得自动勾画轮廓.计算自动勾画与手动勾画在多种惩罚系数下的MSI和Dice相似性系数(Dice similarity coefficient,DSC).对比分析MSI和DSC的差异。结果基于图集和基于深度学习的自动勾画的DSC分别为0.73和0.84.不同惩罚系数下的MSI可分别在0.29~0.78和0.44~0.91之间变动。结论使用MSI评估自动勾画结果是可行的.通过惩罚系数的设置.能反映欠勾画和过勾画等现象.提高医学影像轮廓相似度评估的敏感度。Objective To explore the feasibility of using the bidirectional local distance based medical similarity index(MSI)to evaluate automatic segmentation on medical images.Methods Taking the intermediate risk clinical target volume for nasopharyngeal carcinoma manually segmented by an experience radiation oncologist as region of interest,using Atlas-based and deep-learning-based methods to obtain automatic segmentation respectively,and calculated multiple MSI and Dice similarity coefficient(DSC)between manual segmentation and automatic segmentation.Then the difference between MSI and DSC was comparatively analyzed.Results DSC values for Atlas-based and deep-learning-based automatic segmentation were 0.73 and 0.84 respectively.MSI values for them varied between 0.29~0.78 and 0.44~0.91 under different inside-outside-level.Conclusion It is feasible to use MSI to evaluate the results of automatic segmentation.By setting the penalty coefficient,it can reflect phenomena such as under-delineation and over-delineation,and improve the sensitivity of medical image contour similarity evaluation.

关 键 词：轮廓相似性 医学相似性指数 Dice相似性系数 自动勾画 放射治疗 

分 类 号：R318[医药卫生—生物医学工程] TH774[医药卫生—基础医学]