Non-Redundant Combination of Hand-Crafted and Deep Learning Radiomics: Application to the Early Detection of Pancreatic Cancer

TL;DR

This paper proposes a method to extract non-redundant deep learning radiomics features that complement hand-crafted features, improving early pancreatic cancer detection by combining both feature types and validating on large datasets.

Contribution

It introduces a novel approach to enforce independence between deep learning and hand-crafted radiomics features using mutual information minimization, enhancing early cancer detection.

Findings

Improved AUC in early pancreatic cancer detection

Non-redundant feature combination outperforms baseline methods

Validated on large independent test set

Abstract

We address the problem of learning Deep Learning Radiomics (DLR) that are not redundant with Hand-Crafted Radiomics (HCR). To do so, we extract DLR features using a VAE while enforcing their independence with HCR features by minimizing their mutual information. The resulting DLR features can be combined with hand-crafted ones and leveraged by a classifier to predict early markers of cancer. We illustrate our method on four early markers of pancreatic cancer and validate it on a large independent test set. Our results highlight the value of combining non-redundant DLR and HCR features, as evidenced by an improvement in the Area Under the Curve compared to baseline methods that do not address redundancy or solely rely on HCR features.