AI-assisted Early Detection of Pancreatic Ductal Adenocarcinoma on Contrast-enhanced CT

2025-03-13

AI Summary

Pancreatic ductal adenocarcinoma (PDAC) is frequently diagnosed at advanced stages due to the absence of early, specific symptoms, underscoring the urgent need for highly sensitive imaging screening methods. This work addresses the challenges of detecting and localizing small PDAC lesions in contrast-enhanced CT scans. We propose a coarse-to-fine two-stage deep learning framework: first, a multi-scale region-of-interest (ROI) localization network performs initial lesion screening; second, a refined segmentation network achieves precise lesion delineation. To enhance robustness—particularly for small lesions—we introduce a data-partitioning ensemble strategy and a domain-adaptive post-processing function. Evaluated on the PANORAMA challenge, our method achieves state-of-the-art performance with an AUROC of 0.9263 and an average precision (AP) of 0.7243, ranking first. The source code and pre-trained models are publicly available.

Technology Category

• Machine Learning: Ensemble Methods
• Computer Vision: Segmentation
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Pancreatic ductal adenocarcinoma (PDAC) is one of the most common and aggressive types of pancreatic cancer. However, due to the lack of early and disease-specific symptoms, most patients with PDAC are diagnosed at an advanced disease stage. Consequently, early PDAC detection is crucial for improving patients' quality of life and expanding treatment options. In this work, we develop a coarse-to-fine approach to detect PDAC on contrast-enhanced CT scans. First, we localize and crop the region of interest from the low-resolution images, and then segment the PDAC-related structures at a finer scale. Additionally, we introduce two strategies to further boost detection performance: (1) a data-splitting strategy for model ensembling, and (2) a customized post-processing function. We participated in the PANORAMA challenge and ranked 1st place for PDAC detection with an AUROC of 0.9263 and an AP of 0.7243. Our code and models are publicly available at https://github.com/han-liu/PDAC_detection.

Problem

• Early detection of pancreatic ductal adenocarcinoma (PDAC) using AI.
• Improving PDAC detection accuracy on contrast-enhanced CT scans.
• Developing a coarse-to-fine approach for PDAC localization and segmentation.

Innovation

• Coarse-to-fine PDAC detection on CT scans
• Data-splitting strategy for model ensembling
• Customized post-processing function for accuracy