基于半监督多头网络的腰椎CT图像分割  

Lumbar CT Image Segmentation Based on Semi-supervised Multi-head Network

作　　者：何越 杜钦红 杜钰堃 杨环 西永明[2] HE Yue;DU Qin-hong;DU Yu-kun;YANG Huan;XI Yong-ming(College of Computer Science and Technology,The Affiliated Hospital of Qingdao University,Qingdao University,Qingdao 266071,China;Department of Spine Surgery,Laoshan Hospital,The Affiliated Hospital of Qingdao University,Qingdao University,Qingdao 266071,China)

机构地区：[1]青岛大学计算机科学技术学院,青岛266071 [2]青岛大学附属医院崂山院区脊柱外科,青岛266071

出　　处：《青岛大学学报（自然科学版）》2023年第2期36-42,共7页Journal of Qingdao University(Natural Science Edition)

基　　金：山东省泰山学者项目(批准号:ts20190985)资助。

摘　　要：针对医学图像分割任务中医学数据标注困难以及CT图像强度不均匀问题,提出一种基于半监督的多头分割网络SSMH-Net。SSMH-Net网络采用教师—学生训练架构,基于相同的分割模型V-Net,通过指数移动平均算法完成教师与学生模型的交互训练;采用Multi-Head方法估计模型预测的不确定性信息,指导分割模型在更可靠的目标中学习。在CTspine分割数据集上,SSMH-Net网络平均分割Dice系数达到95.70%,表现出较为优异的分割性能。Aiming at the difficulty of medical data labeling in the tasks of medical image segmentation and the uneven intensity in CT images,semi-supervised multi-head segmentation network SSMH-Net was proposed.Teacher-student training architecture was adopted,based on the same segmentation model V-Net,and completed the interactive training of teacher-student models through the exponential moving average algorithm.Multi-Head method was adopted to estimate the uncertainty information of model predictions,which guided the segmentation model to learn from more reliable targets.On the CTspine segmentation dataset,the SSMH-Net network shows excellent segmentation performance,which has an average segmentation Dice coefficient of 95.70%.

关 键 词：椎体分割 半监督学习 注意力模块 V-Net multi-head 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]