Journal of Forensic Medicine ›› 2026, Vol. 42 ›› Issue (2): 102-111.DOI: 10.12116/j.issn.1004-5619.2025.451106

• Original Articles • Previous Articles     Next Articles

Construction of a Multimodal Forensic Pathology Database and Implementation of Model-Augmented Retrieval

Haojie QIN1(), Enhao FU1,2, Yongchao YANG1,2, Yawen LIU2,3, Mingzhu JIA2,4, Zhiling TIAN2, Zhe ZHENG1, Siyun GUO5(), Ningguo LIU2()   

  1. 1.College of Basic Medicine and Forensic Medicine, Henan University of Science and Technology, Institute of Medical Aspects of Specific Environments, Judicial Expertise Center, Luoyang 471000, Henan Province, 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.School of Forensic Medicine, Shanxi Medical University, Jinzhong 030600, Shanxi Province, China
    4.Department of Pathology and Forensic Medicine, School of Basic Medical Sciences, Zhengzhou University, Zhengzhou 450001, China
    5.Guangdong Nantian Institute of Forensic Science, Shenzhen 518003, Guangdong Province, China
  • Received:2025-11-16 Online:2026-07-08 Published:2026-04-25
  • Contact: Siyun GUO, Ningguo LIU

Abstract:

Objective To construct a multimodal forensic pathology database based on artificial intelligence (AI) technology and explore methods for integrating pre-trained models into multimodal databases. Methods A hybrid storage architecture consisting of MySQL, Redis and OSS was employed to manage desensitized multimodal data. Data entry was optimized using optical character recognition (OCR) and natural language processing (NLP) technologies. OCR performance was evaluated and optimized using cosine distance, character error rate (CER), and word error rate (WER) to meet practical operational requirements. An intelligent retrieval model was developed using the ChatGLM3-6B model and retrieval-augmented generation (RAG) technology. Model performance was evaluated using ranking metrics including Precision@K, Recall@K, discounted cumulative gain (DCG), and normalized discounted cumulative gain (NDCG). Results The database demonstrated satisfactory baseline performance. The response times were maintained within 150 ms for single-query condition and within 2 s for multiple-query conditions. The average disk read throughput reached 950 MB/s. In concurrent performance tests, the database achieved a maximum throughput of 1 200 queries per second (QPS), meeting multimodal data management demands. OCR evaluation showed high recognition accuracy; for high-quality documents, the cosine distance, CER, and WER achieved 0.02, 1.5%, and 3.2%, respectively. Intelligent retrieval results indicated that Precision@K remained consistently high (0.69-1.00), while NDCG values remained above 0.87 for all evaluations. When K=100, the NDCG surpassed 0.95 for all queries, meeting expected performance requirements. Conclusion The multimodal forensic pathology database constructed in this study demonstrates good stability and operational efficiency and can meet the requirements of routine forensic practice for multimodal data storage, management, and analysis. The intelligent retrieval capabilities, based on pre-trained large language models (LLMs), can be applied to conversational information retrieval from forensic reports and related documents, providing a novel approach to the management and analysis of multimodal databases.

Key words: forensic pathology, multimodal data, database, artificial intelligence (AI), large language model (LLM), information retrieval

CLC Number: