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

Cancers

John Hermans¹  Geke Litjens¹  Henkjan Huisman²  Natália Alves²  Megan Schuurmans²  Joeran S. Bosma² 

[1] Department of Medical Imaging, Radboud Institute for Health Sciences, 6500 HB Nijmegen, The Netherlands;Diagnostic Image Analysis Group, Department of Medical Imaging, Radboud University Medical Center, 6500 HB Nijmegen, The Netherlands;

关键词: pancreatic ductal adenocarcinoma;    deep-learning;    early detection;   

DOI  :  10.3390/cancers14020376

来源: DOAJ

【 摘 要 】

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 (<2 cm) 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 the 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), and (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 <2 cm, showing that state-of-the-art deep learning can detect small PDAC and benefits from anatomy information.

【 授权许可】

Unknown