法医学杂志 ›› 2020, Vol. 36 ›› Issue (2): 239-242.DOI: 10.12116/j.issn.1004-5619.2020.02.017

• 技术与应用 • 上一篇    下一篇

基于人工智能硅藻自动化识别系统的实际案例应用

周圆圆1,2, 曹永杰3, 杨越1, 王亚丽1, 邓恺飞2, 马开军4, 陈忆九2, 秦志强2, 张建华2, 黄平2, 张吉2, 陈丽琴1   

  1. 1. 内蒙古医科大学法医学教研室,内蒙古 呼和浩特 010030; 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. 南京医科大学法医学教研室,江苏 南京 210000; 4. 上海市刑事科学技术研究院,上海 200083
  • 发布日期:2020-04-25 出版日期:2020-04-28
  • 通讯作者: 陈丽琴,女,教授,硕士研究生导师,主要从事法医遗传学和法医病理学研究;E-mail:lqchenyj@163.com 张吉,男,助理研究员,主要从事法医病理学研究;E-mail:zhangj@ssfjd.cn
  • 作者简介:周圆圆(1993—),女,硕士研究生,主要从事法医病理学研究;E-mail:zyy601263281@163.com
  • 基金资助:
    国家自然科学基金资助项目(81601645,81722027,81801873);“十三五”国家重点研发计划资助项目(2016YFC0800702);上海市法医学重点实验室资助项目(17DZ2273200);上海市司法鉴定专业技术服务平台资助项目(19DZ2290900);上海市法医学重点实验室基金资助项目(KF1802)

Application of Artificial Intelligence Automatic Diatom Identification System in Practical Cases

ZHOU Yuan-yuan1,2, CAO Yong-jie3, YANG Yue1, WANG Ya-li1, DENG Kai-fei2, MA Kai-jun4, CHEN Yi-jiu2, QIN Zhi-qiang2, ZHANG Jian-hua2, HUANG Ping2, ZHANG Ji2, CHEN Li-qin1   

  1. 1. Department of Forensic Medicine, Inner Mongolia Medical University, Hohhot 010030, 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, Nanjing Medical University, Nanjing 210000, China; 4. Shanghai Research Institute of Criminal Science and Technology, Shanghai 200083, China
  • Online:2020-04-25 Published:2020-04-28

摘要: 目的 探讨人工智能硅藻自动化识别系统在实际案例中的应用,为应用该系统进行硅藻定量分析提供参考,并对该系统所搭载的深度学习模型进行验证。 方法 收集10例水中尸体的器官进行硅藻硝酸消解,利用数字化切片扫描仪将涂片数字化扫描后,使用人工智能硅藻自动化识别系统进行硅藻的定性定量检测。 结果 该人工智能硅藻自动化识别系统所搭载的深度学习模型的受试者操作特征(receiver operator characteristic,ROC)曲线的曲线下面积(area under the curve,AUC)达到98.22%,硅藻识别的查准率达到92.45%。 结论 该人工智能硅藻自动化识别系统实现了硅藻的自动化识别,可用于实际案例中硅藻的辅助检验,并为水中尸体的死因鉴定提供参考依据。

关键词: 法医病理学, 人工智能, 硅藻类, 溺死

Abstract: Objective To discuss the application of artificial intelligence automatic diatom identification system in practical cases, to provide reference for quantitative diatom analysis using the system and to validate the deep learning model incorporated into the system. Methods Organs from 10 corpses in water were collected and digested with diatom nitric acid; then the smears were digitally scanned using a digital slide scanner and the diatoms were tested qualitatively and quantitatively by artificial intelligence automatic diatom identification system. Results The area under the curve (AUC) of the receiver operator characteristic (ROC) curve of the deep learning model incorporated into the artificial intelligence automatic diatom identification system, reached 98.22% and the precision of diatom identification reached 92.45%. Conclusion The artificial intelligence automatic diatom identification system is able to automatically identify diatoms, and can be used as an auxiliary tool in diatom testing in practical cases, to provide reference to drowning diagnosis.

Key words: forensic pathology, artificial intelligence, diatoms, death from drowning