Enhancing Clinically Significant Prostate Cancer Prediction in T2-weighted Images through Transfer Learning from Breast Cancer

TL;DR

This paper explores using transfer learning from breast cancer imaging to improve the accuracy of prostate cancer prediction in T2-weighted MRI images, achieving significant performance gains with limited prostate data.

Contribution

It introduces a novel transfer learning approach from breast to prostate cancer imaging, enhancing prediction accuracy in prostate cancer diagnosis.

Findings

Over 30% improvement in cross-validation accuracy

Effective transfer learning reduces data requirements

Demonstrates potential for cross-domain medical imaging applications

Abstract

In 2020, prostate cancer saw a staggering 1.4 million new cases, resulting in over 375,000 deaths. The accurate identification of clinically significant prostate cancer is crucial for delivering effective treatment to patients. Consequently, there has been a surge in research exploring the application of deep neural networks to predict clinical significance based on magnetic resonance images. However, these networks demand extensive datasets to attain optimal performance. Recently, transfer learning emerged as a technique that leverages acquired features from a domain with richer data to enhance the performance of a domain with limited data. In this paper, we investigate the improvement of clinically significant prostate cancer prediction in T2-weighted images through transfer learning from breast cancer. The results demonstrate a remarkable improvement of over 30% in leave-one-out cross-validation accuracy.