中北大学学报（自然科学版）2025，Vol.46Issue(4)：422-429,8.DOI:10.62756/jnuc.issn.1673-3193.2024.07.0011
基于深度学习的椎体分割和Cobb角计算方法
Vertebral Segmentation and Cobb Angle Calculation Based on Deep Learning
摘要
Abstract
In order to meet the clinical need for automatic calculation of Cobb angle in scoliosis disease,it is necessary to segment each vertebra of the spine.In this paper,a vertebra segmentation model combin-ing HRNet and VP-UNet was proposed to achieve accurate vertebra segmentation and automatic calcula-tion of Cobb angle.Firstly,the bone direction loss function(BD-Loss)was designed,and the spinal pos-ture was used as a prior knowledge to guide the training of HRNet,so as to improve the adaptability of HRNet to the complex spinal morphology.Secondly,a position information perception module(PIPM)was proposed to integrate HRNet localization features into VP-UNet segmentation network to obtain multi-level information of spinal image.VP-UNet added Dropout layer and dense unit on the basis of VGG-Net to extract more global image information while reducing parameters.Finally,based on the results of vertebral localization and segmentation,a method of spine type judgment and Cobb angle calcula-tion was proposed.The experimental results show that compared with VGG-Net,the improved segmenta-tion model has improved Recall by 2.18 percentage points,Precision by 1.7 percentage points,Dice by 0.69 percentage points and IoU by 3.09 percentage points,which can accurately locate and segment each vertebra.The calculated results of Cobb angle meet the clinical needs and provide the technical support for the diagnosis of scoliosis.关键词
深度学习/椎体定位/椎体分割/Cobb角Key words
deep learning/vertebral localization/vertebral segmentation/Cobb angle分类
信息技术与安全科学引用本文复制引用
肖亚婷,陈燕,张勇,张润杰,宋宇锋,张权..基于深度学习的椎体分割和Cobb角计算方法[J].中北大学学报（自然科学版）,2025,46(4):422-429,8.基金项目
山西省基础研究计划项目(202103021224204) （202103021224204）
