
Ravi HASSANALY
8
Documents
Affiliation actuelle
- Algorithms, models and methods for images and signals of the human brain = Algorithmes, modèles et méthodes pour les images et les signaux du cerveau humain [ICM Paris] (ARAMIS)
Identifiants chercheurs
Site web
Présentation
I am a postdoctoral researcher at the Paris Brain Institute, specializing in the application of deep generative models, particularly score-based generative models, for unsupervised anomaly detection in brain imaging.
My PhD at the Paris Brain Institute and Sorbonne University provided me with a strong foundation in AI and medical imaging, along with advanced programming skills in Python, deep learning frameworks, and high-performance computing.
Domaines de recherche
Intelligence artificielle [cs.AI]
Imagerie médicale
Publications
Publications
|
Leveraging healthy population variability in deep learning unsupervised anomaly detection in brain FDG PETSPIE Medical Imaging, Feb 2024, San Diego (California), United States. ⟨10.1117/12.2691683⟩
Communication dans un congrès
hal-04291561
v2
|
|
Recent advances in the open-source ClinicaDL software for reproducible neuroimaging with deep learningSPIE Medical Imaging, Feb 2024, San Diego, United States. pp.519-524, ⟨10.1117/12.3006039⟩
Communication dans un congrès
hal-04419141
v1
|
|
Unsupervised anomaly detection in 3D brain FDG PET: A benchmark of 17 VAE-based approachesDeep Generative Models workshop at the 26th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2023), Oct 2023, Vancouver, Canada
Communication dans un congrès
hal-04185304
v1
|
|
Simulation-based evaluation framework for deep learning unsupervised anomaly detection on brain FDG PETSPIE Medical Imaging, Feb 2023, San Diego, United States
Communication dans un congrès
hal-03835015
v2
|
|
ClinicaDL: an open-source deep learning software for reproducible neuroimaging processingOHBM 2022 - Annual meeting of the Organization for Human Brain Mapping, Jun 2022, Glasgow, United Kingdom
Communication dans un congrès
hal-04279014
v1
|
|
Evaluation of pseudo-healthy image reconstruction for anomaly detection with deep generative models: Application to brain FDG PETJournal of Machine Learning for Biomedical Imaging, 2024, Special Issue for Generative Models, 2, pp.611. ⟨10.59275/j.melba.2024-b87a⟩
Article dans une revue
hal-04315738
v2
|
|
Pseudo-healthy image reconstruction with deep generative models for the detection of dementia-related anomaliesMedical Imaging. Sorbonne Université, 2024. English. ⟨NNT : 2024SORUS118⟩
Thèse
tel-04681117
v1
|
|
Pseudo-healthy image reconstruction with variational autoencoders for anomaly detection: A benchmark on 3D brain FDG PET2024
Pré-publication, Document de travail
hal-04445378
v1
|
Chargement...
Chargement...