法医学杂志

法医学杂志 ›› 2022, Vol. 38 ›› Issue (2): 223-230.DOI: 10.12116/j.issn.1004-5619.2021.410923

• 论著 • 上一篇    下一篇

基于深度学习的颅脑损伤机制自动化鉴别

杨琦帆1,2(), 孙雪阳1,2, 王彦斌3, 田志岭2, 董贺文2, 万雷2, 邹冬华2, 于笑天2, 张广政1(), 刘宁国2()   

  1. 1.郑州大学基础医学院法医学系，河南 郑州 450000
    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.中国合格评定国家认可中心，北京 100062
  • 收稿日期:2021-09-26 发布日期:2022-04-25 出版日期:2022-04-28
  • 通讯作者: 张广政,刘宁国
  • 作者简介:张广政，男，博士，教授，主要从事法医临床学研究；E-mail：zgz@zzu.edu.cn
    刘宁国，男，研究员，主任法医师，主要从事法医病理学、医疗损害、环境损害研究；E-mail：liung@ssfjd.cn
    杨琦帆（1996—），女，硕士研究生，主要从事法医学研究；E-mail：yqf2022@126.com
  • 基金资助:
    中央级公益性科研院所项目(GY2020Z-4);2021年度中国科技期刊卓越行动选育高水平办刊人才子项目-青年人才支持项目(2021ZZ052807);国家自然科学基金资助项目(82171872);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(19DZ2292700);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暨司法部司法鉴定重点实验室开放课题(KF202120)

Automatic Identification of Brain Injury Mechanism Based on Deep Learning

Qi-fan YANG1,2(), Xue-yang SUN1,2, Yan-bin WANG3, Zhi-ling TIAN2, He-wen DONG2, Lei WAN2, Dong-hua ZOU2, Xiao-tian YU2, Guang-zheng ZHANG1(), Ning-guo LIU2()   

  1. 1.Department of Forensic Medicine, School of Basic Medical Sciences, Zhengzhou University, Zhengzhou 450000, 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.China National Accreditation Service for Conformity Assessment, Beijing 100062, China
  • Received:2021-09-26 Online:2022-04-25 Published:2022-04-28
  • Contact: Guang-zheng ZHANG,Ning-guo LIU

RichHTML

18

PDF (PC)

590

摘要： 目的

应用卷积神经网络Inception_v3模型进行基于颅脑CT图像的加、减速性损伤自动鉴别，探讨深度学习技术在法医学颅脑损伤成伤机制推断中的应用前景。

方法

收集190例加、减速性脑损伤的影像学资料作为实验组，另选取130例正常颅脑的影像学资料作为对照。将上述320例影像学资料根据随机抽样的方法分为训练验证集和测试集。采用准确率、精确率、召回率、F1值及AUC值评估模型分类性能。

结果

模型在训练过程和验证过程中对3种图像（加速性损伤、减速性损伤及正常颅脑）分类的最高准确率分别为99.00%、87.21%，满足要求。使用优化后的模型对测试集数据进行测试，该模型在测试集中的三分类准确率为87.18%，识别加速性损伤的精确率、召回率、F1值及AUC值分别为84.38%、90.00%、87.10%、0.98，识别减速性损伤的各值分别为86.67%、72.22%、78.79%、0.92，识别正常颅脑的各值分别为88.57%、89.86%、89.21%、0.93。

结论

Inception_v3模型在基于颅脑CT图像区分加、减速性损伤中具有应用潜力，有望成为推断头部致伤方式的一种辅助工具。

关键词: 法医学, 加速性脑损伤, 减速性脑损伤, 图像分类, 深度学习, 卷积神经网络, 受试者操作特征曲线, Inception_v3模型

Abstract: Objective

To apply the convolutional neural network （CNN） Inception_v3 model in automatic identification of acceleration and deceleration injury based on CT images of brain, and to explore the application prospect of deep learning technology in forensic brain injury mechanism inference.

Methods

CT images from 190 cases with acceleration and deceleration brain injury were selected as the experimental group, and CT images from 130 normal brain cases were used as the control group. The above-mentioned 320 imaging data were divided into training validation dataset and testing dataset according to random sampling method. The model classification performance was evaluated by the accuracy rate, precision rate, recall rate, F1-value and AUC value.

Results

In the training process and validation process, the accuracy rate of the model to classify acceleration injury, deceleration injury and normal brain was 99.00% and 87.21%, which met the requirements. The optimized model was used to test the data of the testing dataset, the result showed that the accuracy rate of the model in the test set was 87.18%, and the precision rate, recall rate, F1-score and AUC of the model to recognize acceleration injury were 84.38%, 90.00%, 87.10% and 0.98, respectively, to recognize deceleration injury were 86.67%, 72.22%, 78.79% and 0.92, respectively, to recognize normal brain were 88.57%, 89.86%, 89.21% and 0.93, respectively.

Conclusion

Inception_v3 model has potential application value in distinguishing acceleration and deceleration injury based on brain CT images, and is expected to become an auxiliary tool to infer the mechanism of head injury.

Key words: forensic medicine, acceleration brain injury, deceleration brain injury, image classification, deep learning, convolutional neural network, receiver operating characteristic （ROC） curve, Inception_v3 model

中图分类号: