Using Out-of-Distribution Detection for Model Refinement in Cardiac Image Segmentation - Archive ouverte HAL Accéder directement au contenu
Chapitre D'ouvrage Année : 2022

Using Out-of-Distribution Detection for Model Refinement in Cardiac Image Segmentation

Francesco Galati
  • Fonction : Auteur
  • PersonId : 1128335
Maria A. Zuluaga

Résumé

We introduce a new learning framework that builds upon the recent progress achieved by methods for quality control (QC) of image segmentation to address the poor generalisation of deep learning models in Out-of-Distribution (OoD) data. Under the assumption that the label space is consistent across data coming from different distributions, we use the information provided by a QC module as a proxy of the segmentation model's performance in unseen data. If the model's performance is poor, the QC information is used as feedback to refine the training of the segmentation model, thus adapting to the OoD data. Our method was evaluated in the context of the Multi-Disease, Multi-View & Multi-Center Right Ventricular Segmentation in Cardiac MRI Challenge reporting average Dice Score and Hausdorff distance of 0.905 and 10.472, respectively.
Fichier principal
Vignette du fichier
M_Ms(2).pdf (980.02 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03590799 , version 1 (28-02-2022)

Identifiants

Citer

Francesco Galati, Maria A. Zuluaga. Using Out-of-Distribution Detection for Model Refinement in Cardiac Image Segmentation. Statistical Atlases and Computational Models of the Heart. Multi-Disease, Multi-View, and Multi-Center Right Ventricular Segmentation in Cardiac MRI Challenge, 13131, Springer International Publishing, pp.374-382, 2022, Lecture Notes in Computer Science, ⟨10.1007/978-3-030-93722-5_40⟩. ⟨hal-03590799⟩
40 Consultations
72 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More