An integrated CT/MRI diagnostic system for pancreatic cystic lesions that supports pathological classification and risk stratification.
15 affiliations
- 1Department of Radiology, National Clinical Research Center for Cancer, Tianjin Clinical Research Center for Cancer, State Key Laboratory of Druggability Evaluation and Systematic Translational Medicine, Tianjin Key Laboratory of Digestive Cancer, Tianjin Key Laboratory of Cancer Prevention and Therapy, Tianjin Medical University Cancer Institute and Hospital, Tianjin 300060, China.
- 2Pancreas Center, National Clinical Research Center for Cancer, Tianjin Clinical Research Center for Cancer, State Key Laboratory of Druggability Evaluation and Systematic Translational Medicine, Tianjin Key Laboratory of Digestive Cancer, Tianjin Key Laboratory of Cancer Prevention and Therapy, Tianjin Medical University Cancer Institute and Hospital, Tianjin 300060, China.
- 3Queen Mary School Hainan, Beijing University of Posts and Telecommunications, Lingshui 570203, China.
- 4Department of Radiology, First Affiliated Hospital of Hainan Medical University, Haikou 570102, China.
- 5Center for Health Statistics and Information, National Health Commission of the PRC, Beijing 100044, China.
- 6School of Public Health, Tianjin University of Traditional Chinese Medicine, Tianjin 301617, China.
- 7Department of Medical Imaging, Jinan Third People's Hospital, Jinan 250101, China.
- 8Department of Radiology, Second Hospital of Tianjin Medical University, Tianjin 300211, China.
- 9Department of Radiology, Tianjin NanKai Hospital, Tianjin Medical University, Tianjin 300100, China.
- 10Department of Radiology, Tianjin First Central Hospital, Tianjin 300192, China.
- 11Department of Radiology, Tianjin Medical University General Hospital, Tianjin 300052, China.
- 12Department of Pathology, National Clinical Research Center for Cancer, Tianjin Clinical Research Center for Cancer, State Key Laboratory of Druggability Evaluation and Systematic Translational Medicine, Tianjin Key Laboratory of Digestive Cancer, Tianjin Key Laboratory of Cancer Prevention and Therapy, Tianjin Medical University Cancer Institute and Hospital, Tianjin 300060, China.
- 13Department of Eye and Vision Science, University of Liverpool, United Kingdom, Liverpool Centre for Cardiovascular Science at University of Liverpool, Liverpool John Moores University and Liverpool Heart & Chest Hospital, Liverpool L7 8TX, United Kingdom.
- 14Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hung Hom, Kowloon 999077, Hong Kong SAR, China.
- 15Department of Epidemiology, University of Groningen, University Medical Center Groningen, Groningen 9713 GZ, The Netherlands.
Abstract
Objective
To develop a pathology-based preoperative decision-support system (Structured Imaging Report System for Pancreatic Cystic Lesions, SIRS-PCL) for subtype classification and risk stratification of PCLs.Methods
We conducted a multicentre retrospective study involving 1,102 patients treated between 1 January 2011 and 31 December 2024. The study cohort was divided into a development dataset (n = 858) and a temporal validation dataset (n = 244) from the periods 2011-2022 and 2023-2024, respectively. Three logistic prediction models were used to classify the five PCL subtypes and to perform separate three-tier risk stratifications (benign/low, medium, and high) for intraductal papillary mucinous neoplasm (IPMN) and mucinous cystic neoplasm (MCN) cases. SIRS-PCL was prospectively implemented at Tianjin Medical University Cancer Institute and Hospital from 25 June 2025 to 25 June 2026, and the diagnostic accuracy, sensitivity, and specificity were evaluated in a cohort of 76 patients.Results
A total of 1,102 patients with PCLs were included in the study (median age 56 years, interquartile range 44-64), of whom 714 were female (64.8%). The five-category model included in SIRS-PCL achieved a mean area under the receiver operating characteristic curve (AUC) of 0.93 [95% confidence interval (CI) 0.91-0.95] in temporal validation. The IPMN model showed good discrimination for risk stratification (mean AUC 0.86, 95% CI 0.79-0.93), with the highest overall accuracy of 77.1% exceeding current guidelines (range 50.0%-58.6%). The MCN risk model also showed high performance (mean AUC 0.97, 95% CI 0.91-1.00). In comparison to current practice, SIRS-PCL use reduced unnecessary surgeries 11.5% vs. 23.1% and over-examinations 6.7% vs 33.7%. In the prospective implementation cohort, SIRS-PCL achieved accuracy of 86.2% for five-category pathological classification, 73.7% for IPMN risk stratification, and 100% for MCN risk stratification.Conclusions
SIRS-PCL is a pathology-based, quantitative decision-support system for preoperative pathological subtype classification and pathological risk stratification of surgically evaluated neoplastic PCLs.
Related
- Multimodal preoperative risk stratification of pancreatic mass lesions using clinical variables, imaging radiomics and plasma cfDNA methylation: protocol for an ambispective multicentre diagnostic prediction model study
- Integrated single-cell and proteomic profiling of pancreatic neoplasia identifies tissue markers that outperform established diagnostic markers in distinguishing cancer from precursor lesions.
- Integrated host-microbe biomarkers for early diagnostic classification of paediatric LRTI in mechanically ventilated children.
- Combined halp and GRIm scores for risk stratification in metastatic pancreatic ductal adenocarcinoma
- TiLCA-Net: nuclei segmentation and classification in pathological images via task-specialized attention and efficient decoding
BibTeX
@article{cui2026integrated,
title = {{An integrated CT/MRI diagnostic system for pancreatic cystic lesions that supports pathological classification and risk stratification.}},
author = {Xiaonan Cui and Houpu Liu and Sunyi Zheng and Hongwei Wang and Jiaxin Liu and Ziyi Gao and Tianye Liu and Jing Liang and Xiaoxu Wang and Xinru Zheng and Jing Wang and Keyi Bian and Xiaomeng Yang and Chunlin Zhang and Tianshuo Jiao and Yufei Yang and Shuxuan Fan and Xiuchao Wang and Song Gao and Chuntao Gao and Yukuan Feng and Hui Li and Guoping Xu and Xiang Zhang and Wen Shen and Haoran Sun and Baocun Sun and Yan Sun and Jianyu Xiao and Yalin Zheng and Michael Ying and Geertruida H de Bock and Zhaoxiang Ye and Jihui Hao},
journal = {Cancer biology \& medicine},
year = {2026},
month = oct,
doi = {10.20892/j.issn.2095-3941.2026.0566},
url = {https://europepmc.org/article/MED/42972650},
note = {CC BY-NC},
}
RIS
TY - JOUR
TI - An integrated CT/MRI diagnostic system for pancreatic cystic lesions that supports pathological classification and risk stratification.
AU - Xiaonan Cui
AU - Houpu Liu
AU - Sunyi Zheng
AU - Hongwei Wang
AU - Jiaxin Liu
AU - Ziyi Gao
AU - Tianye Liu
AU - Jing Liang
AU - Xiaoxu Wang
AU - Xinru Zheng
AU - Jing Wang
AU - Keyi Bian
AU - Xiaomeng Yang
AU - Chunlin Zhang
AU - Tianshuo Jiao
AU - Yufei Yang
AU - Shuxuan Fan
AU - Xiuchao Wang
AU - Song Gao
AU - Chuntao Gao
AU - Yukuan Feng
AU - Hui Li
AU - Guoping Xu
AU - Xiang Zhang
AU - Wen Shen
AU - Haoran Sun
AU - Baocun Sun
AU - Yan Sun
AU - Jianyu Xiao
AU - Yalin Zheng
AU - Michael Ying
AU - Geertruida H de Bock
AU - Zhaoxiang Ye
AU - Jihui Hao
PY - 2026
DA - 2026/10/01
JO - Cancer biology & medicine
DO - 10.20892/j.issn.2095-3941.2026.0566
UR - https://europepmc.org/article/MED/42972650
AB - Objective To develop a pathology-based preoperative decision-support system (Structured Imaging Report System for Pancreatic Cystic Lesions, SIRS-PCL) for subtype classification and risk stratification of PCLs.Methods We conducted a multicentre retrospective study involving 1,102 patients treated between 1 January 2011 and 31 December 2024. The study cohort was divided into a development dataset (n = 858) and a temporal validation dataset (n = 244) from the periods 2011-2022 and 2023-2024, respectively. Three logistic prediction models were used to classify the five PCL subtypes and to perform separate three-tier risk stratifications (benign/low, medium, and high) for intraductal papillary mucinous neoplasm (IPMN) and mucinous cystic neoplasm (MCN) cases. SIRS-PCL was prospectively implemented at Tianjin Medical University Cancer Institute and Hospital from 25 June 2025 to 25 June 2026, and the diagnostic accuracy, sensitivity, and specificity were evaluated in a cohort of 76 patients.Results A total of 1,102 patients with PCLs were included in the study (median age 56 years, interquartile range 44-64), of whom 714 were female (64.8%). The five-category model included in SIRS-PCL achieved a mean area under the receiver operating characteristic curve (AUC) of 0.93 [95% confidence interval (CI) 0.91-0.95] in temporal validation. The IPMN model showed good discrimination for risk stratification (mean AUC 0.86, 95% CI 0.79-0.93), with the highest overall accuracy of 77.1% exceeding current guidelines (range 50.0%-58.6%). The MCN risk model also showed high performance (mean AUC 0.97, 95% CI 0.91-1.00). In comparison to current practice, SIRS-PCL use reduced unnecessary surgeries 11.5% vs. 23.1% and over-examinations 6.7% vs 33.7%. In the prospective implementation cohort, SIRS-PCL achieved accuracy of 86.2% for five-category pathological classification, 73.7% for IPMN risk stratification, and 100% for MCN risk stratification.Conclusions SIRS-PCL is a pathology-based, quantitative decision-support system for preoperative pathological subtype classification and pathological risk stratification of surgically evaluated neoplastic PCLs.
SN - 2095-3941
ER -