Prognostic Value of Transfer Learning Based Features in Resectable Pancreatic Ductal Adenocarcinoma

TL;DR

This study demonstrates that CNN-based transfer learning significantly improves prognostic predictions for resectable pancreatic ductal adenocarcinoma over traditional radiomics and CNNs trained from scratch, especially with small datasets.

Contribution

The paper introduces a CNN-based transfer learning approach that outperforms traditional radiomics and from-scratch CNN models in predicting PDAC patient survival.

Findings

Transfer learning achieved AUC of 0.74 in prognosis.

Traditional radiomics model had AUC of 0.56.

CNN trained from scratch had AUC of 0.50.

Abstract

Pancreatic Ductal Adenocarcinoma (PDAC) is one of the most aggressive cancers with an extremely poor prognosis. Radiomics has shown prognostic ability in multiple types of cancer including PDAC. However, the prognostic value of traditional radiomics pipelines, which are based on hand-crafted radiomic features alone is limited. Convolutional neural networks (CNNs) have been shown to outperform these feature-based models in computer vision tasks. However, training a CNN from scratch needs a large sample size which is not feasible in most medical imaging studies. As an alternative solution, CNN-based transfer learning has shown potential for achieving reasonable performance using small datasets. In this work, we developed and validated a CNN-based transfer learning approach for prognostication of PDAC patients for overall survival using two independent resectable PDAC cohorts. The proposed deep transfer learning model for prognostication of PDAC achieved the area under the receiver operating characteristic curve of 0.74, which was significantly higher than that of the traditional radiomics model (0.56) as well as a CNN model trained from scratch (0.50). These results suggest that deep transfer learning may significantly improve prognosis performance using small datasets in medical imaging.