基于自适应联合损失函数的新型冠状病毒感染病灶分割网络  

Corona virus disease 2019 lesion segmentation network based on an adaptive joint loss function

作　　者：肖汉光 李焕琪 冉智强 张启航 张勃龙 韦羽佳 祝秀红 XIAO Hanguang;LI Huanqi;RAN Zhiqiang;ZHANG Qihang;ZHANG Bolong;WEI Yujia;ZHU Xiuhong(School of Artificial Intelligence,Chongqing University of Technology,Chongqing 401135,P.R.China)

机构地区：[1]重庆理工大学两江人工智能学院,重庆401135

出　　处：《生物医学工程学杂志》2023年第4期743-752,共10页Journal of Biomedical Engineering

基　　金：国家自然科学(面上)基金项目(61971078);重庆市科学技术局自然科学基金面上项目(CSTB2022NSCQMSX0923);重庆理工大学全额资助一般项目(gzlcx20232107)。

摘　　要：新型冠状病毒感染是一种传染性强、变异性强、潜伏期长的急性呼吸道传染病。基于电子计算机断层扫描成像的新型冠状病毒感染病灶自动分割可以辅助医生进行快速诊断和精确治疗,能有效地减少误诊漏诊的风险。针对新型冠状病毒感染病灶征象复杂且边界模糊难以分割等痛点,本文在新型冠状病毒感染病灶分割网络的基础上结合水平集分割方法引入了水平集广义骰子损失函数(LGDL),提出了双路径新型冠状病毒感染病灶分割网络(Dual-SAUNet++),其中LGDL是由掩膜路径的广义骰子损失和水平集路径的均方误差联合所得的自适应权重损失。本文所提模型在测试集上取得的戴斯相似系数为(87.81±10.86)%,交并比为(79.20±14.58)%,敏感度为(94.18±13.56)%,特异度为(99.83±0.43)%,豪斯多夫距离为(18.29±31.48) mm。实验证明,Dual-SAUNet++能够同时关注病灶的面积和边界信息,可以有效分割出多尺度病灶且具有较强的抗噪能力。综上,本文所提方法通过精确分割病灶区域,可辅助医生判断新型冠状病毒感染的严重程度,为后续临床治疗提供可靠依据。Corona virus disease 2019(COVID-19)is an acute respiratory infectious disease with strong contagiousness,strong variability,and long incubation period.The probability of misdiagnosis and missed diagnosis can be significantly decreased with the use of automatic segmentation of COVID-19 lesions based on computed tomography images,which helps doctors in rapid diagnosis and precise treatment.This paper introduced the level set generalized Dice loss function(LGDL)in conjunction with the level set segmentation method based on COVID-19 lesion segmentation network and proposed a dual-path COVID-19 lesion segmentation network(Dual-SAUNet++)to address the pain points such as the complex symptoms of COVID-19 and the blurred boundaries that are challenging to segment.LGDL is an adaptive weight joint loss obtained by combining the generalized Dice loss of the mask path and the mean square error of the level set path.On the test set,the model achieved Dice similarity coefficient of(87.81±10.86)%,intersection over union of(79.20±14.58)%,sensitivity of(94.18±13.56)%,specificity of(99.83±0.43)%and Hausdorff distance of 18.29±31.48 mm.Studies indicated that Dual-SAUNet++has a great anti-noise capability and it can segment multi-scale lesions while simultaneously focusing on their area and border information.The method proposed in this paper assists doctors in judging the severity of COVID-19 infection by accurately segmenting the lesion,and provides a reliable basis for subsequent clinical treatment.

关 键 词：新型冠状病毒感染 病灶分割 电子计算机断层扫描 水平集距离图 水平集广义骰子损失函数 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] R563.1[自动化与计算机技术—计算机科学与技术]