Non-Redundant Combination of Hand-Crafted and Deep Learning Radiomics: Application to the Early Detection of Pancreatic Cancer - Equipe Image, Modélisation, Analyse, GEométrie, Synthèse Access content directly
Conference Papers Year : 2023

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

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.
Fichier principal
Vignette du fichier
fbfpkxxgvsyhmrrmqrvnsvbrwbvvrxsb.pdf (2.28 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04185207 , version 1 (22-08-2023)

Identifiers

  • HAL Id : hal-04185207 , version 1

Cite

Rebeca Vétil, Clément Abi Nader, Alexandre Bône, Marie-Pierre Vullierme, Marc-Michel Rohe, et al.. Non-Redundant Combination of Hand-Crafted and Deep Learning Radiomics: Application to the Early Detection of Pancreatic Cancer. Cancer Prevention through early detecTion - CaPTion workshop @ MICCAI2023, Oct 2023, Vancouver, Canada. ⟨hal-04185207⟩
86 View
25 Download

Share

Gmail Facebook X LinkedIn More