Fully Automatic Deep Learning Framework for Pancreatic Ductal Adenocarcinoma Detection on Computed Tomography

TL;DR

This study develops a deep learning framework that effectively detects small pancreatic ductal adenocarcinoma lesions on CT scans, significantly improving early diagnosis by integrating surrounding anatomical information.

Contribution

The paper introduces a novel deep learning approach that incorporates surrounding anatomy to enhance detection of small PDAC lesions on CT scans, outperforming existing models.

Findings

nnUnet_MS achieved AUC of 0.91 for all tumors

AUC of 0.88 for tumors <2cm

Anatomy integration improves detection performance

Abstract

Early detection improves prognosis in pancreatic ductal adenocarcinoma (PDAC) but is challenging as lesions are often small and poorly defined on contrast-enhanced computed tomography scans (CE-CT). Deep learning can facilitate PDAC diagnosis, however current models still fail to identify small (<2cm) lesions. In this study, state-of-the-art deep learning models were used to develop an automatic framework for PDAC detection, focusing on small lesions. Additionally, the impact of integrating surrounding anatomy was investigated. CE-CT scans from a cohort of 119 pathology-proven PDAC patients and a cohort of 123 patients without PDAC were used to train a nnUnet for automatic lesion detection and segmentation (nnUnet_T). Two additional nnUnets were trained to investigate the impact of anatomy integration: (1) segmenting the pancreas and tumor (nnUnet_TP), (2) segmenting the pancreas, tumor, and multiple surrounding anatomical structures (nnUnet_MS). An external, publicly available test set was used to compare the performance of the three networks. The nnUnet_MS achieved the best performance, with an area under the receiver operating characteristic curve of 0.91 for the whole test set and 0.88 for tumors <2cm, showing that state-of-the-art deep learning can detect small PDAC and benefits from anatomy information.