Artificial Intelligence Accurately Identifies Bacterial Infections in Decomposed Tissue

Strategic Insights -

Research at Xi'an Jiaotong University has successfully demonstrated the use of artificial intelligence (AI) in identifying bacterial infections in decomposed tissue under varying temperature conditions. The study utilized pathology images and AI algorithms to classify bacterial infections, showing strong classification efficacy across all tested temperatures. The findings have significant implications for forensic pathology and infection prevention during autopsies.

Key Takeaways:

  • The research at Xi'an Jiaotong University used pathology images and AI algorithms to classify bacterial infections in decomposed tissue, demonstrating strong classification efficacy across all tested temperatures (25 °C, 37 °C, and 4 °C).
  • The model exhibited robustness and generalizability, with an overall area under the curve (AUC) value exceeding 0.920 and 0.820 at the patch and whole slide image (WSI) levels, respectively, in the training and testing sets.
  • The research concluded that the AI-driven computational pathology can reliably distinguish bacterial infection types, even in decomposition states.
  • The method offers a novel approach for bacterial diagnosis in forensic pathology and supports infection prevention during autopsies.
  • The research was peer-reviewed and published in the Journal of Microbiological Methods (2025;236:107180).
  • The authors of the study include Gongji Wang, Xinggong Liang, Zhengyang Zhu, Wanqing Zhang, Yuqian Li, Jianliang Luo, Han Wang, Shuo Wu, Run Chen, Mingyan Deng, Hao Wu, Chen Shen, Gengwang Hu, Kai Zhang, Qinru Sun, and Zhenyuan Wang.

Statistics:

  • The AUC values exceeded 0.920 and 0.820 at the patch and whole slide image (WSI) levels, respectively, in the training and testing sets.
  • The model's classification efficacies at the patch level in the external validation set surpassed 0.990.
  • The study was conducted at Xi'an Jiaotong University, College of Forensic Medicine, Xi'an 710061, Shaanxi, People's Republic of China.
  • The research has been peer-reviewed and published in the Journal of Microbiological Methods (2025;236:107180).

Sources:

  • Identification of bacterial infection types in decomposition stages at various temperatures using pathology images and artificial intelligence algorithms. Journal of Microbiological Methods, 2025;236:107180.
  • Gongji Wang, Dept. of Forensic Pathology, College of Forensic Medicine, Xi'an Jiaotong University, Xi'an 710061, Shaanxi, People's Republic of China.
  • Elsevier, Radarweg 29, 1043 Nx Amsterdam, Netherlands.