法医学杂志 ›› 2023, Vol. 39 ›› Issue (2): 129-136.DOI: 10.12116/j.issn.1004-5619.2022.220505

• 论著 • 上一篇    下一篇

基于深度学习实现成人坐骨耻骨支内侧缘的性别推断

马永刚1(), 曹永杰2,3(), 赵益花4, 周新军1, 黄斌1, 张高潮1, 黄平2, 王亚辉2, 马开军5, 陈峰3, 张东川5(), 张吉2()   

  1. 1.西安交通大学附属三二〇一医院,陕西 汉中 723000
    2.司法鉴定科学研究院 上海市法医学重点实验室 司法部司法鉴定重点实验室 上海市司法鉴定专业技术服务平台,上海 200063
    3.南京医科大学基础医学院法医学系,江苏 南京 211166
    4.福建科胜司法鉴定所,福建 莆田 351100
    5.上海市公安局物证鉴定中心,上海 200083
  • 收稿日期:2022-05-10 发布日期:2023-06-06 出版日期:2023-04-25
  • 通讯作者: 张东川,张吉
  • 作者简介:张吉,男,主检法医师,主要从事法医病理学研究;E-mail:zhangj@ssfjd.cn
    张东川,男,主检法医师,主要从事法医病理学研究;E-mail:zhangdch5@mail2.sysu.edu.cn
    马永刚(1978—),男,副主任医师,主要从事医学与法医学影像诊断与研究;E-mail:myg98@163.com
    曹永杰(1996—),男,硕士研究生,主要从事法医人类学研究;E-mail:1017824284@qq.com第一联系人:马永刚和曹永杰为共同第一作者
  • 基金资助:
    国家重点研发计划资助项目(2022YFC3302002);国家自然科学基金资助项目(81722027);中央级公益性科研院所资助项目(GY2020G-2);上海市法医学重点实验室资助项目(21DZ2270800);司法部司法鉴定重点实验室资助项目;上海市司法鉴定专业技术服务平台资助项目

Sex Estimation of Medial Aspect of the Ischiopubic Ramus in Adults Based on Deep Learning

Yong-gang MA1(), Yong-jie CAO2,3(), Yi-hua ZHAO4, Xin-jun ZHOU1, Bin HUANG1, Gao-chao ZHANG1, Ping HUANG2, Ya-hui WANG2, Kai-jun MA5, Feng CHEN3, Dong-chuan ZHANG5(), Ji ZHANG2()   

  1. 1.3201 Hospital Affiliated to Xi’an Jiaotong University, Hanzhong 723000, Shaanxi Province, China
    2.Shanghai Key Laboratory of Forensic Medicine, Key Laboratory of Forensic Science, Ministry of Justice, Shanghai Forensic Service Platform, Academy of Forensic Science, Shanghai 200063, China
    3.Department of Forensic Medicine, School of Basic Medical Sciences, Nanjing Medical University, Nanjing 211166, China
    4.Fujian Kesheng Judicial Expertise Center, Putian 351100, Fujian Province, China
    5.Institute of Forensic Science, Shanghai Public Security Bureau, Shanghai 200083, China
  • Received:2022-05-10 Online:2023-06-06 Published:2023-04-25
  • Contact: Dong-chuan ZHANG,Ji ZHANG

摘要:

目的 探究深度学习技术在中国汉族人群CT三维重建图像自动性别识别中的可靠性和准确率。 方法 收集20~85岁汉族人群骨盆CT影像学数据700例(男性350例,女性350例),将其重建为三维虚拟骨骼模型,并截取坐骨耻骨支内侧缘(medial aspect of the ischiopubic ramus,MIPR)特征区域图像。采用Inception v4作为图像识别模型,以初始化学习和迁移学习两种方式进行训练。随机选取80%的图像作为训练验证集,20%的图像作为测试集。将左右两侧MIPR图像进行单独以及合并训练。之后使用总准确率、女性准确率、男性准确率等指标进行模型的性能评价。 结果 将左右两侧MIPR图像单独进行初始化学习训练,右侧MIPR模型的总准确率为95.7%,其中女性准确率为95.7%、男性准确率为95.7%;左侧MIPR模型的总准确率为92.1%,其中女性准确率为88.6%、男性准确率为95.7%。将左右两侧MIPR图像合并以初始化学习进行训练,模型的总准确率为94.6%,其中女性准确率为92.1%、男性准确率为97.1%。将左右两侧MIPR图像合并以迁移学习进行训练,模型的总准确率为95.7%,其中女性准确率为95.7%,男性准确率为95.7%。 结论 利用Inception v4深度学习模型和迁移学习算法对中国汉族人群骨盆MIPR图像构建性别推断模型,可对成人骨骼遗骸开展有效性别鉴定,具有较高的准确率及泛化能力。

关键词: 法医人类学, 深度学习, 性别推断, 三维重建, 骨盆, 坐骨耻骨支内侧缘, 迁移学习

Abstract:

Objective To investigate the reliability and accuracy of deep learning technology in automatic sex estimation using the 3D reconstructed images of the computed tomography (CT) from the Chinese Han population. Methods The pelvic CT images of 700 individuals (350 males and 350 females) of the Chinese Han population aged 20 to 85 years were collected and reconstructed into 3D virtual skeletal models. The feature region images of the medial aspect of the ischiopubic ramus (MIPR) were intercepted. The Inception v4 was adopted as the image recognition model, and two methods of initial learning and transfer learning were used for training. Eighty percent of the individuals’ images were randomly selected as the training and validation dataset, and the remaining were used as the test dataset. The left and right sides of the MIPR images were trained separately and combinedly. Subsequently, the models’ performance was evaluated by overall accuracy, female accuracy, male accuracy, etc. Results When both sides of the MIPR images were trained separately with initial learning, the overall accuracy of the right model was 95.7%, the female accuracy and male accuracy were both 95.7%; the overall accuracy of the left model was 92.1%, the female accuracy was 88.6% and the male accuracy was 95.7%. When the left and right MIPR images were combined to train with initial learning, the overall accuracy of the model was 94.6%, the female accuracy was 92.1% and the male accuracy was 97.1%. When the left and right MIPR images were combined to train with transfer learning, the model achieved an overall accuracy of 95.7%, and the female and male accuracies were both 95.7%. Conclusion The use of deep learning model of Inception v4 and transfer learning algorithm to construct a sex estimation model for pelvic MIPR images of Chinese Han population has high accuracy and well generalizability in human remains, which can effectively estimate the sex in adults.

Key words: forensic anthropology, deep learning, sex estimation, three-dimensional reconstruction, pelvis, medial aspect of the ischiopubic ramus, transfer learning

中图分类号: