Explainable AI for sharp injury identification using transfer learning with pre-trained deep neural networks.

Journal: Forensic science international
Published Date:

Abstract

OBJECTIVE: To investigate an AI-based method for automatically identifying and classifying sharp injuries using deep learning models, evaluate its effectiveness (e.g., accuracy and explainability), and support forensic injury classification.

Authors

  • Shoutao Ni
    School of Investigation, People's Public Security University of China, Beijing 100000, PR China; Institute of Forensic Science, Ministry of Public Security, Beijing 100038, PR China; Department of Qingdao Railway Public Security, Qingdao, Shandong, 266000, PR China.
  • Fangmao Ju
    School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an, Shanxi 710049, PR China; Research Center for intelligent Medical Equipment and Devices (IMED), Xi'an Jiaotong University, Xi'an, Shanxi 710049, China.
  • Jiaxin Zhang
    School of Chinese Medicine, Hong Kong Traditional Chinese Medicine Phenome Research Center, State Key Laboratory of Environmental and Biological Analysis, Hong Kong Baptist University, Hong Kong 999077, China.
  • Miaogen Xuan
    Public Security Bureau of Hangzhou, Hangzhou, Zhejiang 310000, PR China.
  • Liang Chen
    Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai, China.
  • Shutao Zhang
    School of Design Art, Lanzhou University of Technology, Lanzhou 730050, China.
  • Wenzhi Guo
    College of Mechanical and Vehicle Engineering, Taiyuan University of Technology, Taiyuan 030024, China.
  • Chunfeng Lian
    Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA. Electronic address: chunfeng_lian@med.unc.edu.
  • Yang Li
    Occupation of Chinese Center for Disease Control and Prevention, Beijing, China.