Improving the automatic diagnosis of hepatocellular carcinoma with contrastive learning

Emma Sarfati (1, 2, 3)

1 Laboratoire Guerbet / Guerbet Research
2 IMAGES - Image, Modélisation, Analyse, GEométrie, Synthèse
3 IDS - Département Images, Données, Signal

Several deep learning methods have been proposed to automatically classify liver lesions in MRI or CT, with good performance [1,2,3]. They all share a classical training procedure. Contrastive learning (CL) is a novel deep learning paradigm where pairs of cases, instead of cases taken in isolation, are leveraged to train the model. CL methods can be either trained without labels, in this case it learns global mathematical representations of the input images [4], or it can use labels during training in order to help to discriminate input images based on a specific characteristic [5]. In this study, we evaluate the potential of CL to improve the automatic classification of hepatocellular carcinoma (HCC) in CT-scans. We formulate it through a binary classification problem (HCC versus no HCC).

Mots clés: CT; Computer Applications-Detection; diagnosis; Cancer

Domaines: Informatique [cs]

Emma Sarfati. Improving the automatic diagnosis of hepatocellular carcinoma with contrastive learning. ECR 2024 : European Congress of Radiology, Feb 2024, Vienne (AUT), Austria. ⟨hal-04480600⟩