Large-vocabulary forensic pathological analyses via prototypical cross-modal contrastive learning
Chen Shen, Chunfeng Lian, Wanqing Zhang, Fan Wang, Jianhua Zhang, Shuanliang Fan, Xin Wei, Gongji Wang, Kehan Li, Hongshu Mu, Hao Wu, Xinggong Liang, Jianhua Ma, Zhenyuan Wang
Abstract
Forensic pathology plays a vital role in determining the cause and manner of death through macroscopic and microscopic post-mortem examinations. However, the field faces challenges such as variability in outcomes, labor-intensive processes, and a shortage of skilled professionals. This paper introduces SongCi, a visual-language model tailored for forensic pathology. Leveraging advanced prototypical cross-modal self-supervised contrastive learning, SongCi improves the accuracy, efficiency, and generalizability of forensic analyses. Pre-trained and validated on a large multi-center dataset comprising over 16 million high-resolution image patches, 2, 228 vision-language pairs from post-mortem whole slide images, gross key findings, and 471 unique diagnostic outcomes, SongCi demonstrates superior performance over existing multi-modal models and computational pathology foundation models in forensic tasks. It matches experienced forensic pathologists’ capabilities, significantly outperforms less experienced practitioners, and offers robust multi-modal explainability. To overcome various challenges in forensic pathology, the authors present SongCi, a visual-language AI trained on multi-modal autopsy cases of various cohorts. SongCi detects diverse post-mortem diseases and injuries and gives clear image-text explanations for forensic analysis, rivaling senior pathologists.