PhD position in Self-Supervised Learning for Anomaly Detection in Medical Neuroimaging

France Life Imaging; Villeurbanne, Grenoble; Sur place; EUR 40 000 - 60 000; Plein temps

Résumé du poste

An innovative research opportunity awaits in a stimulating environment focused on deep learning for medical image analysis. This PhD position aims to tackle the challenges of supervised models by exploring self-supervised learning techniques, which do not require extensive annotated datasets. Candidates will engage in cutting-edge research that targets critical issues in neuroimaging, particularly in detecting subtle lesions and changes in brain pathologies. Joining a collaborative team of experts, you will contribute to advancements in machine learning and neuroimaging, making a significant impact in the field. If you are passionate about pushing the boundaries of technology in healthcare, this opportunity is perfect for you.

Qualifications

• PhD position focusing on deep self-supervised learning for medical image analysis.
• Experience in machine learning and neuroimaging is essential.

Responsabilités

• Develop and evaluate self-supervised detection and segmentation approaches.
• Work collaboratively with supervisors from multiple research teams.

Connaissances

Machine Learning

Deep Learning

Neuroimaging

Self-supervised Learning

Anomaly Detection

Unsupervised Representation Learning

Formation

PhD in Neurosciences or related field

Outils

Visual Transformers

Gaussian Mixture Models

Auto-encoders

Description du poste

Type de structure : We offer a stimulating research environment gathering experts in Image processing, Neurosciences & Neuroimaging, Advanced Statistical and Machine Learning methods from CREATIS, Grenoble Institute of Neurosciences (GIN) and INRIA. The PhD position is granted by the “Défi IA” program sponsored by la Région Auvergne Rhône-Alpes.
The position is available in the framework of DAISIES project.

Contexte et mission : Scientific context

The vast majority of deep learning architectures for medical image analysis are based on supervised models requiring the collection of large datasets of annotated examples. Building such annotated datasets, which requires skilled medical experts, is time-consuming and hardly achievable, especially for some specific tasks, including the detection of small and subtle lesions that are sometimes impossible to visually detect and thus manually outline. This critical aspect significantly impairs performances of supervised models and hampers their deployment in clinical neuroimaging applications, especially for brain pathologies that require the detection of small size lesions (e.g. multiple sclerosis, microbleeds) or subtle structural or morphological changes (e.g. Parkinson disease).

OBJECTIVE AND RESEARCH PROGRAM :

To solve this challenging issue, the objective of this thesis is to develop and evaluate deep self-supervised detection and segmentation approaches whose training does not require any fine semantic annotations of the anomalies localization. We will explore different categories of self-supervised methods, including: novel unsupervised auto-encoder based anomaly detection models leveraging on the recent developments in visual transformers blocks (ViT) or vector quantized variational autoencoders (VQ-VAE), scalability of Gaussian mixture models as well as weakly supervised models based on scarce annotations.

Key words: Machine learning, Deep Learning; Multidimensional data, Segmentation, Neuroimaging, Self-supervised learning, Anomaly detection, Unsupervised representation learning.

Starting date: Autumn 2022

How to apply: Send an email directly to three supervisors with your CV and persons to contact. Interviews of the selected applicants will be done on an ongoing basis. Applications will be accepted up to the 30th of June.

Lieu : Location: Grenoble Neurosciences Institute: https://neurosciences.univ-grenoble-alpes.fr & CREATIS - Villeurbanne: https://www.creatis.insa-lyon.fr/. Time sharing in the two laboratories will be discussed with the selected candidates.

Contact : The PhD candidate will be co-supervised by: - GIN - team «Functional neuroimaging and brain perfusion»: Michel Dojat ([e-mail]), - CREATIS - team Myriad : Carole Lartizien ([e-mail]) - INRIA - team Statify: Florence Forbes ([e-mail])