Pseudo-healthy image reconstruction with variational autoencoders for anomaly detection: A benchmark on 3D brain FDG PET - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2024

Pseudo-healthy image reconstruction with variational autoencoders for anomaly detection: A benchmark on 3D brain FDG PET

Résumé

Many deep generative models have been proposed to reconstruct pseudo-healthy images for anomaly detection. Among these models, the variational autoencoder (VAE) has emerged as both simple and efficient. While significant progress has been made in refining the VAE within the field of computer vision, these advancements have not been extensively applied to medical imaging applications. We present a benchmark that assesses the ability of multiple VAEs to reconstruct pseudo-healthy neuroimages for anomaly detection in the context of dementia. We first propose a rigorous methodology to define the optimal architecture of the vanilla VAE and select the best hyper-parameters of the VAE variants. Relying on a simulation-based evaluation framework, we thoroughly assess the ability of 20 VAE models to reconstruct pseudo-healthy images for the detection of dementia-related anomalies in 3D brain FDG PET and compare their performance. This benchmark demonstrated that the majority of the VAE models tested were able to reconstruct images of good quality and generate healthy looking images from simulated images presenting anomalies. Even if no model clearly outperformed all the others, the benchmark allowed identifying a few models that perform slightly better than the vanilla VAE. It further showed that many VAE-based models can generalize to the detection of anomalies of various intensities, shapes and locations in 3D brain FDG PET.
Fichier principal
Vignette du fichier
Hassanaly-VAE_benchmark-v1.pdf (10.69 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04445378 , version 1 (07-02-2024)

Licence

Paternité

Identifiants

  • HAL Id : hal-04445378 , version 1

Citer

Ravi Hassanaly, Maëlys Solal, Olivier Colliot, Ninon Burgos. Pseudo-healthy image reconstruction with variational autoencoders for anomaly detection: A benchmark on 3D brain FDG PET. 2024. ⟨hal-04445378⟩
76 Consultations
25 Téléchargements

Partager

Gmail Facebook X LinkedIn More