Utility of Pancreas Surface Lobularity as a CT Biomarker for Opportunistic Screening of Type 2 Diabetes

2025-11-13

AI Summary

Pancreatic surface lobulation (PSL) remains uncharacterized as a potential computed tomography (CT) imaging biomarker for type 2 diabetes mellitus (T2DM). Method: We developed an automated deep learning pipeline integrating four pancreatic segmentation models—including PancAP—to quantify pancreatic volume, fat content, and PSL features from routine abdominal CT scans, followed by a multivariate machine learning model for T2DM prediction. Contribution/Results: This study is the first to identify PSL as a significant opportunistic CT biomarker for T2DM: PSL was significantly elevated in T2DM patients (p = 0.01). The optimal model achieved an AUC of 0.90, with 66.7% sensitivity and 91.9% specificity. Critically, the method requires no additional imaging or patient cooperation—leveraging only standard-of-care abdominal CTs. It enables passive, early, and scalable T2DM screening, establishing a novel, clinically deployable paradigm for opportunistic metabolic disease detection in radiology practice.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Medical and Biological Imaging
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• User Modeling, Personalization and Recommendation: ML for personalized search and recommendations
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Type 2 Diabetes Mellitus (T2DM) is a chronic metabolic disease that affects millions of people worldwide. Early detection is crucial as it can alter pancreas function through morphological changes and increased deposition of ectopic fat, eventually leading to organ damage. While studies have shown an association between T2DM and pancreas volume and fat content, the role of increased pancreatic surface lobularity (PSL) in patients with T2DM has not been fully investigated. In this pilot work, we propose a fully automated approach to delineate the pancreas and other abdominal structures, derive CT imaging biomarkers, and opportunistically screen for T2DM. Four deep learning-based models were used to segment the pancreas in an internal dataset of 584 patients (297 males, 437 non-diabetic, age: 45$pm$15 years). PSL was automatically detected and it was higher for diabetic patients (p=0.01) at 4.26 $pm$ 8.32 compared to 3.19 $pm$ 3.62 for non-diabetic patients. The PancAP model achieved the highest Dice score of 0.79 $pm$ 0.17 and lowest ASSD error of 1.94 $pm$ 2.63 mm (p$<$0.05). For predicting T2DM, a multivariate model trained with CT biomarkers attained 0.90 AUC, 66.7% sensitivity, and 91.9% specificity. Our results suggest that PSL is useful for T2DM screening and could potentially help predict the early onset of T2DM.

Problem

• Investigating pancreatic surface lobularity as a CT biomarker for diabetes screening
• Developing automated deep learning models to segment pancreas from CT scans
• Validating CT imaging biomarkers for early Type 2 Diabetes detection

Innovation

• Automated pancreas segmentation using deep learning models
• Detection of pancreatic surface lobularity from CT scans
• Multivariate model with CT biomarkers predicts Type 2 Diabetes