Intelligent Diagnosis of Pancreatic Biopsy From Endoscopic Ultrasound-Guided Fine-Needle Aspiration Via Stimulated Raman Histopathology

Tao Tan; Liyang Ma; Yuheng Guo; Tianyin Chen; Lili Meng; Kuan Luo; Pinghong Zhou; Mingyan Cai; Minbiao Ji; Hao Hu

doi:10.1016/j.labinv.2025.104182

Intelligent Diagnosis of Pancreatic Biopsy From Endoscopic Ultrasound-Guided Fine-Needle Aspiration Via Stimulated Raman Histopathology

Lab Invest. 2025 Apr 25;105(8):104182. doi: 10.1016/j.labinv.2025.104182. Online ahead of print.

Authors

Tao Tan¹, Liyang Ma², Yuheng Guo², Tianyin Chen³, Lili Meng⁴, Kuan Luo², Pinghong Zhou⁵, Mingyan Cai⁶, Minbiao Ji⁷, Hao Hu⁸

Affiliations

¹ Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai, China; Shanghai Collaborative Innovation Center of Endoscopy, Zhongshan Hospital, Fudan University, Shanghai, China; School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China.
² State Key Laboratory of Surface Physics and Department of Physics, Fudan University, Shanghai, China; Key Laboratory of Micro and Nano Photonic Structures (Ministry of Education), Academy for Engineering and Technology, Fudan University, Shanghai, China.
³ Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai, China; Shanghai Collaborative Innovation Center of Endoscopy, Zhongshan Hospital, Fudan University, Shanghai, China.
⁴ Pathology Center, Zhongshan Hospital, Fudan University, Shanghai, China.
⁵ Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai, China; Shanghai Collaborative Innovation Center of Endoscopy, Zhongshan Hospital, Fudan University, Shanghai, China. Electronic address: zhou.pinghong@zs-hospital.sh.cn.
⁶ Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai, China; Shanghai Collaborative Innovation Center of Endoscopy, Zhongshan Hospital, Fudan University, Shanghai, China. Electronic address: caimingyan@fudan.edu.cn.
⁷ Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai, China; Shanghai Collaborative Innovation Center of Endoscopy, Zhongshan Hospital, Fudan University, Shanghai, China; State Key Laboratory of Surface Physics and Department of Physics, Fudan University, Shanghai, China; Key Laboratory of Micro and Nano Photonic Structures (Ministry of Education), Academy for Engineering and Technology, Fudan University, Shanghai, China. Electronic address: minbiaoj@fudan.edu.cn.
⁸ Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai, China; Shanghai Collaborative Innovation Center of Endoscopy, Zhongshan Hospital, Fudan University, Shanghai, China. Electronic address: hu.hao1@zs-hospital.sh.cn.

PMID: 40288652
DOI: 10.1016/j.labinv.2025.104182

Abstract

Endoscopic ultrasound-guided fine-needle aspiration (EUS-FNA) has become one of the most important preoperative diagnostic methods for pancreatic tumors, but it often faces challenges of redundant sampling from patients and complex tissue processing that hinders timely diagnosis. Intraoperative rapid on-site evaluation is an auxiliary diagnostic technique that helps assess sample quality in real time, but it heavily depends on pathologists and involves subjectivity and complex procedures. Here, we developed a rapid and label-free approach for intraoperative histology on EUS-FNA specimen via deep learning-based stimulated Raman scattering microscopy, aimed at replacing rapid on-site evaluation and providing a more efficient and objective diagnostic approach. Fresh pancreatic EUS-FNA tissues were imaged with stimulated Raman scattering and compared with hematoxylin and eosin staining to identify key histologic features. Using images from 76 patients, a convolutional neural network model was established to identify benign, malignant, and nondiagnostic areas, achieving a validation accuracy >96% on an external test set of 33 cases. Furthermore, gradient-weighted class activation mapping was able to highlight histologic profiles within individual biopsy. Our approach has potential application in efficient intraoperative assessment of pancreatic biopsy through EUS-FNA.

Keywords: deep learning; endoscopic ultrasound–guided fine-needle aspiration; label-free histology; pancreatic tumors; stimulated Raman scattering microscopy.