Pediatric Pancreas Segmentation from MRI Scans with Deep Learning

2025-06-18

AI Summary

This study addresses the challenging task of automatic pancreatic segmentation in pediatric T2-weighted MRI, encompassing both healthy children and those with acute or chronic pancreatitis. We propose PanSegNet—the first clinically validated, pathology-agnostic deep learning model specifically designed for this purpose. Built upon a U-Net architecture, it integrates multi-center, multi-field-strength (1.5T/3T) data and incorporates Dice loss with boundary-aware optimization. On an independent test set, PanSegNet achieves a mean Dice score of 88% (HD95 = 3.98 mm) in healthy controls and >80% in acute/chronic pancreatitis cohorts. Volumetric measurements show strong agreement with manual annotations (R² ≥ 0.77), and inter-observer consistency is excellent (Cohen’s κ ≥ 0.81). To our knowledge, this is the first work enabling unified, accurate pancreatic segmentation across diverse pediatric physiological and pathological states. We publicly release both the trained model and expert-annotated dataset, thereby filling a critical gap in pediatric pancreatic AI research and advancing radiation-free, clinically deployable quantitative assessment.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Objective: Our study aimed to evaluate and validate PanSegNet, a deep learning (DL) algorithm for pediatric pancreas segmentation on MRI in children with acute pancreatitis (AP), chronic pancreatitis (CP), and healthy controls. Methods: With IRB approval, we retrospectively collected 84 MRI scans (1.5T/3T Siemens Aera/Verio) from children aged 2-19 years at Gazi University (2015-2024). The dataset includes healthy children as well as patients diagnosed with AP or CP based on clinical criteria. Pediatric and general radiologists manually segmented the pancreas, then confirmed by a senior pediatric radiologist. PanSegNet-generated segmentations were assessed using Dice Similarity Coefficient (DSC) and 95th percentile Hausdorff distance (HD95). Cohen's kappa measured observer agreement. Results: Pancreas MRI T2W scans were obtained from 42 children with AP/CP (mean age: 11.73 +/- 3.9 years) and 42 healthy children (mean age: 11.19 +/- 4.88 years). PanSegNet achieved DSC scores of 88% (controls), 81% (AP), and 80% (CP), with HD95 values of 3.98 mm (controls), 9.85 mm (AP), and 15.67 mm (CP). Inter-observer kappa was 0.86 (controls), 0.82 (pancreatitis), and intra-observer agreement reached 0.88 and 0.81. Strong agreement was observed between automated and manual volumes (R^2 = 0.85 in controls, 0.77 in diseased), demonstrating clinical reliability. Conclusion: PanSegNet represents the first validated deep learning solution for pancreatic MRI segmentation, achieving expert-level performance across healthy and diseased states. This tool, algorithm, along with our annotated dataset, are freely available on GitHub and OSF, advancing accessible, radiation-free pediatric pancreatic imaging and fostering collaborative research in this underserved domain.

Problem

• Segmentation of pediatric pancreas in MRI scans
• Evaluation of deep learning for acute/chronic pancreatitis
• Validation of PanSegNet algorithm accuracy and reliability

Innovation

• Deep learning algorithm for pediatric pancreas segmentation
• Validated with Dice Similarity Coefficient and Hausdorff distance
• Freely available on GitHub and OSF for collaboration