[1]陈瑶,高永彬,熊玉洁.基于Transformer与Vector Loss模块的椎骨Cobb角点定位网络[J].中国医学物理学杂志,2022,39(11):1393-1400.[doi:DOI:10.3969/j.issn.1005-202X.2022.11.012]
　CHEN Yao,GAO Yongbin,XIONG Yujie.Vertebral Cobb corner localization using neural network with Transformer and Vector Loss modules[J].Chinese Journal of Medical Physics,2022,39(11):1393-1400.[doi:DOI:10.3969/j.issn.1005-202X.2022.11.012]
点击复制

基于Transformer与Vector Loss模块的椎骨Cobb角点定位网络()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
39卷
期数:
2022年第11期
页码:
1393-1400
栏目:
医学影像物理
出版日期:
2022-11-25

文章信息/Info

Title:
Vertebral Cobb corner localization using neural network with Transformer and Vector Loss modules
文章编号:
1005-202X（2022）11-1393-08
作者:
陈瑶; 高永彬; 熊玉洁
上海工程技术大学电子电气工程学院， 上海 201620
Author(s):
CHEN Yao;  GAO Yongbin;  XIONG Yujie
School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China
关键词:
X光图像; Cobb角; Transformer; Vector Loss; 神经网络; 辅助诊断
Keywords:
X-ray image Cobb angle Transformer Vector Loss neural network auxiliary diagnosis
分类号:
R318
DOI:
DOI:10.3969/j.issn.1005-202X.2022.11.012
文献标志码:
A
摘要:
目的：通过定位脊椎骨角点计算Cobb角度数。方法：使用神经网络的方法进行脊椎骨角点坐标的定位，通过嵌入Transformer与Vector Loss模块解决了在清晰度不高、拍摄角度不同的X光图像上计算Cobb角度数精确不高的问题。结果：在MICCAI 2019公开脊椎挑战赛数据集中，本文方法的平均对称百分比（SMAPE）高达9.01。相较于最新的方法，该方法在SMAPE值上提高了1.80。结论：本文所提出的算法嵌入Transformer与Vector Loss模块，与现有的诸多算法相比，具有较高的准确率和稳健性，可以辅助临床医生选择适合患者的治疗方案。
Abstract:
Objective To calculate the Cobb angle by locating the vertebral corners. Methods Neural network was used to locate the coordinates of the vertebral corners. By embedding Transformer and Vector Loss modules, the problem of the poor accuracy in calculating the Cobb angle in X-ray images with low definition and different shooting angles was solved. Results In the MICCAI 2019 Open Spine Challenge data set, the proposed method achieved a symmetric mean absolute precentage error (SMAPE) as high as 9.01. Compared with the latest methods, the proposed method improved the SMAPE by 1.80. Conclusion The proposed algorithm with Transformer and Vector Loss modules is superior to the existing algorithms in accuracy and robustness, and can assist clinicians in selecting the treatment schemes suitable for patients.

相似文献/References:

[1]王伟,蔡裕兴,陈卫国,等. 数字化全脊柱拼接结合核磁共振成像在青少年脊柱侧弯诊治的应用[J].中国医学物理学杂志,2017,34(6):594.[doi:DOI:10.3969/j.issn.1005-202X.2017.06.011]
　[J].Chinese Journal of Medical Physics,2017,34(11):594.[doi:DOI:10.3969/j.issn.1005-202X.2017.06.011]

备注/Memo

备注/Memo:
【收稿日期】2022-01-15 【基金项目】上海市科委重点项目（18411952800） 【作者简介】陈瑶，硕士研究生，研究方向：计算机视觉、智慧医疗，E-mail: chenyao9635@163.com
更新日期/Last Update: 2022-11-25