Machine learning models integrating 2D and 3D intratumoral heterogeneity features from multi-sequence MRI: accurate prediction of perineural invasion in pancreatic ductal adenocarcinoma
7 affiliations
- 1Department of Radiology, Yan’an Hospital of Kunming City (Yanan Hospital Affiliated to Kunming Medical University) , ,
- 2Hepatobiliary and Pancreatic Surgery, Yunnan Cancer Hospital (The Third Affiliated Hospital of Kunming Medical University) , ,
- 3Department of Medical Imaging, Yunnan Cancer Hospital (The Third Affiliated Hospital of Kunming Medical University) , ,
- 4Department of Pathology, Yunnan Cancer Hospital (The Third Affiliated Hospital of Kunming Medical University) , ,
- 5Department of Nuclear Magnetic Resonance, The Second Hospital and Clinical Medical School, Lanzhou University , ,
- 6Department of Medical Imaging, The First People’s Hospital of Yunnan Province (The Affiliated Hospital of Kunming University of Science and Technology) , ,
- 7Department of Medical Imaging, The First Affiliated Hospital of Kunming Medical University , , ,
Abstract
Introduction: Perineural invasion (PNI) occurs in the majority of pancreatic ductal adenocarcinoma (PDAC) cases and is strongly associated with local recurrence, neuropathic pain, and poor survival, yet no reliable method exists for its preoperative identification. Here, we developed and externally validated a multi-sequence MRI-based intratumoral heterogeneity (ITH) scoring framework integrated with machine learning for the non-invasive prediction of PNI in PDAC.
Methods: Using preoperative T2-weighted, diffusion-weighted, and contrast-enhanced T1-weighted MRI from 205 surgically resected patients across four medical centers (100 training, 43 internal test, and 28 and 34 external validation patients), we extracted two-dimensional and three-dimensional ITH features via K-means clustering-based subregion partitioning and incorporated independent clinical predictors tumor location and clinical T-stage to construct combined predictive models. Eleven machine learning algorithms were systematically evaluated.
Results: The combined clinical-ITH model achieved an area under the curve (AUC) of 0.907 in the internal test set and AUCs of 0.860 and 0.869 in the two external validation cohorts. Corresponding AUCs were 0.881, 0.860, and 0.850 for the ITH model and 0.758, 0.342, and 0.700 for the clinical logistic regression model.
Discussion: SHAP analysis ranked three T2WI-derived features as the largest contributors to the combined model output, feature effects varied in direction and were not uniformly monotonic. These findings demonstrate that multi-sequence MRI-based ITH quantification provides an interpretable approach to preoperative PNI assessment with consistent discrimination across the two external surgical cohorts, offering a potential tool to guide surgical planning and adjuvant therapy selection in pancreatic cancer.
Related
- Explainable machine learning integrating CT-derived intratumoral heterogeneity for histological subtype prediction in pure ground-glass lung adenocarcinoma: multicenter validation and transcriptomic characterization
- Multi-b-value diffusion-weighted imaging-based habitat imaging for preoperative prediction of histological grade and prognosis in soft tissue sarcoma: focusing on intratumoral heterogeneity
- MRI-based intratumoral and peritumoral heterogeneity for predicting intracranial progression in EGFR-mutant lung adenocarcinoma patients with treatment-naive brain metastases receiving first-line third-generation EGFR-TKIs.
- Topologically distinct intratumoral heterogeneity scores for predicting high-risk pathological grades in invasive lung adenocarcinoma: A multicenter study across four institutions
- HepaKineticNet: Deep Learning of CT-Derived Intratumoral Heterogeneity for Overall Survival Prediction in BCLC Stage B-C Hepatocellular Carcinoma Treated with Locoregional Therapy Plus First-Line TKI and Anti-PD-1 Therapy.
BibTeX
@article{ouyang2026machine,
title = {{Machine learning models integrating 2D and 3D intratumoral heterogeneity features from multi-sequence MRI: accurate prediction of perineural invasion in pancreatic ductal adenocarcinoma}},
author = {Zhiqiang Ouyang and Zhengrui Song and Zhilin Li and Shulan Cui and Xin Liu and Wan Shen and Fangyu Zhu and Chengde Liao and Wanjun Hu and Shaonan He and Yi Lu and Qiuwen Ye},
journal = {Frontiers in artificial intelligence},
year = {2026},
month = oct,
doi = {10.3389/frai.2026.1975752},
url = {https://europepmc.org/article/PMC/PMC13727598},
note = {CC BY},
}
RIS
TY - JOUR
TI - Machine learning models integrating 2D and 3D intratumoral heterogeneity features from multi-sequence MRI: accurate prediction of perineural invasion in pancreatic ductal adenocarcinoma
AU - Zhiqiang Ouyang
AU - Zhengrui Song
AU - Zhilin Li
AU - Shulan Cui
AU - Xin Liu
AU - Wan Shen
AU - Fangyu Zhu
AU - Chengde Liao
AU - Wanjun Hu
AU - Shaonan He
AU - Yi Lu
AU - Qiuwen Ye
PY - 2026
DA - 2026/10/20
JO - Frontiers in artificial intelligence
DO - 10.3389/frai.2026.1975752
UR - https://europepmc.org/article/PMC/PMC13727598
AB - Introduction: Perineural invasion (PNI) occurs in the majority of pancreatic ductal adenocarcinoma (PDAC) cases and is strongly associated with local recurrence, neuropathic pain, and poor survival, yet no reliable method exists for its preoperative identification. Here, we developed and externally validated a multi-sequence MRI-based intratumoral heterogeneity (ITH) scoring framework integrated with machine learning for the non-invasive prediction of PNI in PDAC. Methods: Using preoperative T2-weighted, diffusion-weighted, and contrast-enhanced T1-weighted MRI from 205 surgically resected patients across four medical centers (100 training, 43 internal test, and 28 and 34 external validation patients), we extracted two-dimensional and three-dimensional ITH features via K-means clustering-based subregion partitioning and incorporated independent clinical predictors tumor location and clinical T-stage to construct combined predictive models. Eleven machine learning algorithms were systematically evaluated. Results: The combined clinical-ITH model achieved an area under the curve (AUC) of 0.907 in the internal test set and AUCs of 0.860 and 0.869 in the two external validation cohorts. Corresponding AUCs were 0.881, 0.860, and 0.850 for the ITH model and 0.758, 0.342, and 0.700 for the clinical logistic regression model. Discussion: SHAP analysis ranked three T2WI-derived features as the largest contributors to the combined model output, feature effects varied in direction and were not uniformly monotonic. These findings demonstrate that multi-sequence MRI-based ITH quantification provides an interpretable approach to preoperative PNI assessment with consistent discrimination across the two external surgical cohorts, offering a potential tool to guide surgical planning and adjuvant therapy selection in pancreatic cancer.
SN - 2624-8212
ER -