연구성과 홍보

Theranostics. 2025 Jun 20;15(15):7440-7453.

Title : AI-powered 3D pathology protocol enhances enteric nervous system visualization and quantification for clinical diagnostics

Authors : Young Hyun Yun1, Kee Young Chung2, Yunjoo Lee3, Tae Sik Sung4, Dayoung Ko5, Seung-Bum Ryoo4, Hyun-Young Kim5,6, Kyu Joo Park4, Jong Pil Im7, Byeong Gwan Kim7, Joo Sung Kim7, Seong-Joon Koh7*, Hyung Jin Choi1,2,8,9,10*

Affiliations :

1Department of Anatomy and Cell Biology, Seoul National University College of Medicine, Seoul, Republic of Korea.

2Department of Biomedical Sciences, Seoul National University College of Medicine, Seoul, Republic of Korea.

3Ragon Institute of Massachusetts General Hospital, Massachusetts Institute of Technology, and Harvard, Cambridge, Massachusetts, United States.

4Department of Surgery, Seoul National University College of Medicine, Seoul, Republic of Korea.

5Department of Pediatric Surgery, Seoul National University Children's Hospital, Seoul, Republic of Korea.

6Department of Pediatric Surgery, Seoul National University College of Medicine, Seoul, Republic of Korea.

7Department of Internal Medicine and Liver Research Institute, Seoul National University Hospital, Seoul, Republic of Korea.

8Neuroscience Research Institute, Seoul National University College of Medicine, Seoul, Republic of Korea.

9Wide River Institute of Immunology, Seoul National University, Seoul, Republic of Korea.

10Department of Brain and Cognitive Sciences, Seoul National University, Seoul, Republic of Korea.

DOI: 10.7150/thno.112024.

Abstract :

Rationale: Accurate diagnosis and understanding of gastrointestinal (GI) diseases such as ulcerative colitis and Hirschsprung's disease remain challenging due to the limitations of traditional two-dimensional (2D) histopathology in capturing the intricate three-dimensional (3D) architecture and dynamic microenvironment of GI tissues. This study explores the potential of integrating 3D imaging techniques with artificial intelligence (AI)-based analysis to improve histological evaluation and diagnostic accuracy. Methods: Using advanced imaging and computational tools, we identified critical structural and functional details of the enteric nervous system and associated tissues that are often missed by 2D approaches. Results: The results showed that 3D imaging coupled with AI significantly improves diagnostic accuracy and provides new insights into disease mechanisms, enabling earlier and more precise detection of pathological changes. In addition, this approach enhances our understanding of the pathophysiology of GI diseases, bridging gaps in both clinical and basic research. Conclusions: These findings underscore the transformative potential of 3D imaging and AI to revolutionize diagnostic workflows and advance our knowledge of GI diseases, ultimately contributing to improved patient outcomes and innovative research methodologies.