Decoupled conditional contrastive learning with variable metadata for prostate lesion detection - Equipe Image, Modélisation, Analyse, GEométrie, Synthèse
Conference Papers Year : 2023

Decoupled conditional contrastive learning with variable metadata for prostate lesion detection

Abstract

Early diagnosis of prostate cancer is crucial for efficient treatment. Multi-parametric Magnetic Resonance Images (mp-MRI) are widely used for lesion detection. The Prostate Imaging Reporting and Data System (PI-RADS) has standardized interpretation of prostate MRI by defining a score for lesion malignancy. PI-RADS data is readily available from radiology reports but is subject to high inter-reports variability. We propose a new contrastive loss function that leverages weak metadata with multiple annotators per sample and takes advantage of inter-reports variability by defining metadata confidence. By combining metadata of varying confidence with unannotated data into a single conditional contrastive loss function, we report a 3% AUC increase on lesion detection on the public PI-CAI challenge dataset.
Fichier principal
Vignette du fichier
Workshop_MICCAI_2023 (1).pdf (480.37 Ko) Télécharger le fichier
Origin Files produced by the author(s)
licence
Copyright

Dates and versions

hal-04183841 , version 1 (21-08-2023)

Licence

Copyright

Identifiers

Cite

Camille Ruppli, Pietro Gori, Roberto Ardon, Isabelle Bloch. Decoupled conditional contrastive learning with variable metadata for prostate lesion detection. MILLanD - MICCAI Workshop, Oct 2023, Vancouver, Canada. ⟨hal-04183841⟩
148 View
45 Download

Altmetric

Share

More