法医学杂志 ›› 2024, Vol. 40 ›› Issue (2): 154-163.DOI: 10.12116/j.issn.1004-5619.2023.231003

• 法医人类学年龄推断专题 • 上一篇    下一篇

CT三维重建技术结合深度学习算法推断成人坐骨年龄

张怀瀚1,2(), 曹永杰2,3(), 张吉2, 熊剪2,4, 马继伟2,5, 杨孝通1,2, 黄平2(), 马永刚6()   

  1. 1.山西医科大学法医学院,山西 太原 030001
    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.贵州医科大学法医学院,贵州 贵阳 550004
    5.内蒙古医科大学法医学教研室,内蒙古 呼和浩特 010030
    6.西安交通大学医学部附属三二〇一医院医学影像科,陕西 汉中 723000
  • 收稿日期:2023-10-30 发布日期:2024-06-07 出版日期:2024-04-25
  • 通讯作者: 黄平,马永刚
  • 作者简介:张怀瀚(1999—),男,硕士研究生,主要从事法医人类学研究;E-mail:victorgo24@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:张怀瀚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);上海市自然科学基金资助项目(23ZR1464400)

Adults Ischium Age Estimation Based on Deep Learning and 3D CT Reconstruction

Huai-han ZHANG1,2(), Yong-jie CAO2,3(), Ji ZHANG2, Jian XIONG2,4, Ji-wei MA2,5, Xiao-tong YANG1,2, Ping HUANG2(), Yong-gang MA6()   

  1. 1.School of Forensic Medicine, Shanxi Medical University, Taiyuan 030001, 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.School of Forensic Medicine, Guizhou Medical University, Guiyang 550004, China
    5.Department of Forensic Medicine, Inner Mongolia Medical University, Hohhot 010030, China
    6.Medical Imaging Department, 3201 Hospital of Xi’an Jiaotong University Health Science Center, Hanzhong 723000, Shaanxi Province, China
  • Received:2023-10-30 Online:2024-06-07 Published:2024-04-25
  • Contact: Ping HUANG, Yong-gang MA

摘要:

目的 探索适用于中国西部汉族人群的CT三维重建图像年龄自动推断深度学习模型,评估其可行性与可靠性。 方法 收集20.0~80.0岁中国西部汉族人群骨盆CT回顾性影像学数据1 200例(男性600例,女性600例),重建为三维虚拟骨骼模型,区分性别、左右截取坐骨结节特征区域图像建立样本库。使用ResNet34模型,随机抽取不同性别各500例样本作为训练及验证集,剩余样本作为测试集,使用初始学习及迁移学习对区分性别、左右的图像进行训练,以平均绝对误差(mean absolute error,MAE)、均方根误差(root mean square error,RMSE)作为主要指标评价模型。 结果 不同性别组成中预测结果存在差异,双侧模型预测结果优于左、右单侧模型,迁移模型预测结果优于初始模型。不同性别组成的双侧迁移模型预测结果中,男性MAE为7.74岁、RMSE为9.73岁,女性MAE为6.27岁、RMSE为7.82岁,混合性别MAE为6.64岁,RMSE为8.43岁。 结论 基于中国西部汉族人群坐骨结节图像应用ResNet34结合迁移学习算法构建的骨龄推断模型可以有效推断成人坐骨骨龄。

关键词: 法医人类学, 年龄推断, 深度学习, 三维重建, 骨盆, 坐骨结节, 迁移学习, 汉族

Abstract:

Objective To develop a deep learning model for automated age estimation based on 3D CT reconstructed images of Han population in western China, and evaluate its feasibility and reliability. Methods The retrospective pelvic CT imaging data of 1 200 samples (600 males and 600 females) aged 20.0 to 80.0 years in western China were collected and reconstructed into 3D virtual bone models. The images of the ischial tuberosity feature region were extracted to create sex-specific and left/right site-specific sample libraries. Using the ResNet34 model, 500 samples of different sexes were randomly selected as training and verification set, the remaining samples were used as testing set. Initialization and transfer learning were used to train images that distinguish sex and left/right site. Mean absolute error (MAE) and root mean square error (RMSE) were used as primary indicators to evaluate the model. Results Prediction results varied between sexes, with bilateral models outperformed left/right unilateral ones, and transfer learning models showed superior performance over initial models. In the prediction results of bilateral transfer learning models, the male MAE was 7.74 years and RMSE was 9.73 years, the female MAE was 6.27 years and RMSE was 7.82 years, and the mixed sexes MAE was 6.64 years and RMSE was 8.43 years. Conclusion The skeletal age estimation model, utilizing ischial tuberosity images of Han population in western China and employing the ResNet34 combined with transfer learning, can effectively estimate adult ischium age.

Key words: forensic anthropology, age estimation, deep learning, three-dimensional reconstruction, pelvis, ischial tuberosity, transfer learning, Han population

中图分类号: