法医学杂志 ›› 2022, Vol. 38 ›› Issue (1): 40-45.DOI: 10.12116/j.issn.1004-5619.2021.410719

所属专题: 水中尸体研究专题

• 论著 • 上一篇    下一篇

基于扫描电子显微镜硅藻人工智能搜索系统检验效能评估

余丹媛1,2(), 刘景建3, 刘超4, 杜宇坤5, 黄平6, 张吉6, 于伟敏7, 胡颖超8, 赵建1,4(), 成建定1()   

  1. 1.中山大学中山医学院法医学系,广东 广州 510080
    2.清远市公安局,广东 清远 511500
    3.昆明医科大学法医学院,云南 昆明 650500
    4.广州市刑事科学技术研究所 法医病理学公安部重点实验室,广东 广州 510442
    5.南方医科大学法医学院,广东 广州 510515
    6.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
    7.江苏集萃苏科思科技有限公司,江苏 苏州 215100
    8.兰波(苏州)智能科技有限公司,江苏 苏州 215100
  • 收稿日期:2021-07-27 发布日期:2022-02-25 出版日期:2022-02-28
  • 通讯作者: 赵建,成建定
  • 作者简介:成建定,男,博士,教授,博士研究生导师,主要从事法医病理学研究;E-mail:chengjd@mail.sysu.edu.cn
    赵建,男,博士研究生,副主任法医师,主要从事法医病理学鉴定和硅藻检验研究;E-mail:zhaojian0721@163.com
    余丹媛(1986—),女,硕士研究生,主要从事法医病理学鉴定和研究;E-mail:399794299@qq.com
  • 基金资助:
    广州市科技计划资助项目(2019030001);公安部科技强警基础工作专项资助项目(2020GABJC38)

Evaluation of Inspection Efficiency of Diatom Artificial Intelligence Search System Based on Scanning Electron Microscope

Dan-yuan YU1,2(), Jing-jian LIU3, Chao LIU4, Yu-kun DU5, Ping HUANG6, Ji ZHANG6, Wei-min YU7, Ying-chao HU8, Jian ZHAO1,4(), Jian-ding CHENG1()   

  1. 1.Department of Forensic Medicine, Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou 510080, China
    2.Qingyuan Public Security Bureau, Qingyuan 511500, Guangdong Province, China
    3.Department of Forensic Medicine, Kunming Medical University, Kunming 650500, China
    4.Guangzhou Forensic Science Institute & Key Laboratory of Forensic Pathology, Ministry of Public Security, Guangzhou 510442, China
    5.Department of Forensic Medicine, Southern Medical University, Guangzhou 510515, China
    6.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
    7.Jiangsu JITRI Sioux Technologies Co. , Ltd. , Suzhou 215100, Jiangsu Province, China
    8.Suzhou LabWorld Scientific Technology Ltd. , Suzhou 215100, Jiangsu Province, China
  • Received:2021-07-27 Online:2022-02-25 Published:2022-02-28
  • Contact: Jian ZHAO,Jian-ding CHENG

摘要: 目的

探讨硅藻人工智能(artificial intelligence,AI)搜索系统在溺死诊断中的应用价值。

方法

取12例溺死尸体的肝、肾组织进行硅藻检验,应用扫描电子显微镜获得视场图片,分别在硅藻AI搜索系统的0.5、0.7和0.9阈值下进行硅藻检测及人工识别,用硅藻召回率、查准率和图片排除比例检测并比较搜索系统的效能。

结果

硅藻AI搜索系统标注的目标中实际检出硅藻数与人工识别硅藻数之间差异无统计学意义(P>0.05);不同阈值下硅藻AI搜索系统检测硅藻的召回率差异具有统计学意义(P<0.05);不同阈值下硅藻AI搜索系统检测硅藻的查准率差异具有统计学意义(P<0.05),高可达53.15%;不同阈值下硅藻AI搜索系统的图片排除比例差异具有统计学意义(P<0.05),高可达99.72%。对于同一样品,硅藻AI搜索系统识别硅藻所用时间仅为人工识别的1/7。

结论

硅藻AI搜索系统在溺死案例诊断中具有良好的应用前景,其搜索硅藻能力与经验丰富的法医相当,同时可以极大地减少人工观察图片的工作量。

关键词: 法医病理学, 溺死, 硅藻检验, 人工智能, 自动搜索, 扫描电子显微镜, 人工识别

Abstract: Objective

To explore the application values of diatom artificial intelligence (AI) search system in the diagnosis of drowning.

Methods

The liver and kidney tissues of 12 drowned corpses were taken and were performed with the diatom test, the view images were obtained by scanning electron microscopy (SEM). Diatom detection and forensic expert manual identification were carried out under the thresholds of 0.5, 0.7 and 0.9 of the diatom AI search system, respectively. Diatom recall rate, precision rate and image exclusion rate were used to detect and compare the efficiency of diatom AI search system.

Results

There was no statistical difference between the number of diatoms detected in the target marked by the diatom AI search system and the number of diatoms identified manually (P>0.05); the recall rates of the diatom AI search system were statistically different under different thresholds (P<0.05); the precision rates of the diatom AI system were statistically different under different thresholds(P<0.05), and the highest precision rate was 53.15%; the image exclusion rates of the diatom AI search system were statistically different under different thresholds (P<0.05), and the highest image exclusion rate was 99.72%. For the same sample, the time taken by the diatom AI search system to identify diatoms was only 1/7 of that of manual identification.

Conclusion

Diatom AI search system has a good application prospect in drowning cases. Its automatic diatom search ability is equal to that of experienced forensic experts, and it can greatly reduce the workload of manual observation of images.

Key words: forensic pathology, drowning, diatom test, artificial intelligence, automatic searching, scanning electron microscope, manual identification

中图分类号: