法医学杂志

• 综述 •    

人工智能技术在肋骨骨折CT影像诊断中的法医学研究前沿及展望

孙亚宁1,2(), 李丹阳2,3,4(), 夏晴2, 高妍1,2, 徐宗诗1,2, 夏文涛2, 周慧明2,3, 韩晓梦1, 俞晓英2(), 盛延良1()   

  1. 1.佳木斯大学基础医学院 微生态-免疫调节网络与相关疾病重点实验室,黑龙江 佳木斯 154007
    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.山西医科大学医学科学院,山西 太原 030000
    4.山西医科大学公共卫生学院,山西 太原 030000
  • 收稿日期:2024-07-16
  • 通讯作者: 俞晓英,盛延良
  • 作者简介:孙亚宁(1999—),男,硕士研究生,主要从事法医临床影像与人工智能技术融合应用研究;E-mail:synsfjd@163.com
    李丹阳(1999—),女,硕士研究生,主要从事法医人类学研究;E-mail:lidanyang19990304@163.com
    第一联系人:孙亚宁和李丹阳为共同第一作者
  • 基金资助:
    国家重点研发计划资助项目(2022YFC3302001);上海市司法鉴定协会项目(SHSFJD2023-001);司法部司法鉴定重点实验室资助项目;上海市法医学重点实验室资助项目(21DZ2270800);上海市司法鉴定专业技术服务平台资助项目

Frontiers and Perspectives of Artificial Intelligence in Forensic Research on CT Imaging Diagnosis of Rib Fractures

Ya-ning SUN1,2(), Dan-yang LI2,3,4(), Qing XIA2, Yan GAO1,2, Zong-shi XUN1,2, Wen-tao XIA2, Hui-ming ZHOU2,3, Xiao-meng HAN1, Xiao-ying YU2(), Yan-liang SHENG1()   

  1. 1.Key Laboratory of Microecology-Immune Regulatory Network and Related Diseases, School of Basic Medicine, Jiamusi University, Jiamusi 154007, Heilongjiang 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.Academy of Medical Sciences, Shanxi Medical University, Taiyuan 030000, China
    4.School of Public Health, Shanxi Medical University, Taiyuan 030000, China
  • Received:2024-07-16
  • Contact: Xiao-ying YU, Yan-liang SHENG

摘要:

肋骨骨折在胸部外伤中较为常见,其骨折数量及畸形愈合情况与定罪量刑和民事赔偿密切相关,具有重要的法医学意义。目前,鉴定实践中对肋骨骨折的诊断主要依赖CT检查,但获得准确结果往往需要经验丰富的司法鉴定人耗费大量时间与精力,诊断效率与一致性均存在一定局限。近年来,随着人工智能(artificial intelligence,AI)技术的迅猛发展,多种具备实际应用价值的AI影像诊断辅助模型相继问世,有效提高了肋骨骨折的识别效率和准确程度。本文系统总结了当前AI技术在肋骨骨折CT影像诊断中的最新应用进展,重点涵盖AI在肋骨骨折自动识别、分类、定位、多任务联合及形成时间推断等方向的研究成果,通过梳理现有文献与方法,旨在揭示AI技术在提升诊断效率与准确度方面的潜力,为构建更具法医学实用价值的智能诊断模型提供参考。

关键词: 法医学, 人工智能, 肋骨骨折, CT影像, 综述

Abstract:

Rib fractures are relatively common in thoracic trauma, and the number of fractured ribs as well as the presence of malunion are closely associated with criminal sentencing and civil compensation, thereby holding significant forensic significance. At present, the diagnosis of rib fractures in forensic practice primarily relies on computed tomography (CT) examinations. However, achieving accurate results often demands substantial time and effort from experienced forensic experts, with limitations in diagnostic efficiency and consistency. In recent years, the rapid advancement of artificial intelligence (AI) has led to the emergence of multiple AI-assisted imaging diagnostic models with practical applicability, effectively improving the efficiency and accuracy of rib fracture identification. This review systematically summarizes the latest application progress of AI in CT diagnosis of rib fractures, with a particular focus on recent advances in automatic detection, classification, localization, multitask integration, and fracture age estimation. By synthesizing existing literature and methodologies, this work aims to reveal the potential of AI in improving diagnostic efficiency and accuracy, and to provide a reference for the future development of intelligent diagnostic models with greater forensic utility.

Key words: forensic medicine, artificial intelligence (AI), rib fractures, CT imaging, review

中图分类号: