رسالة جامعية
Statistical learning on heterogeneous medical data with bayesian latent variable models : application to neuroimaging dementia studies ; Apprentissage statistique sur des données médicales hétérogènes avec des modèles Bayésiens à variables latentes : application aux études de neuroimagerie pour les maladies neurodégénératives
| العنوان: | Statistical learning on heterogeneous medical data with bayesian latent variable models : application to neuroimaging dementia studies ; Apprentissage statistique sur des données médicales hétérogènes avec des modèles Bayésiens à variables latentes : application aux études de neuroimagerie pour les maladies neurodégénératives |
|---|---|
| المؤلفون: | Antelmi, Luigi |
| المساهمون: | E-Patient : Images, données & mOdèles pour la médeciNe numériquE (EPIONE), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Université Côte d'Azur, Nicholas Ayache, Philippe Robert |
| المصدر: | https://theses.hal.science/tel-03474169Test ; Statistics [math.ST]. Université Côte d'Azur, 2021. English. ⟨NNT : 2021COAZ4050⟩. |
| بيانات النشر: | HAL CCSD |
| سنة النشر: | 2021 |
| المجموعة: | HAL Université Côte d'Azur |
| مصطلحات موضوعية: | Alzheimer’s disease, Neuro-imaging, Magnetic resonance imaging, Positron emission tomography, Variational autoencoder, Multi-task learning, High dimensional data, Maladie d’Alzheimer, Neuro-imagerie, Imagerie par résonnance magnétique, Tomographie par émission de positrons, Auto-encodeur variationnel, Apprentissage multi-tâche, Données de haute dimension, Données multimodales, [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST], [INFO.INFO-IM]Computer Science [cs]/Medical Imaging |
| الوصف: | This thesis presents new computational tools for the joint modeling of multi-modal biomedical data,robust to missing data, with application to neuroimaging studies in dementia. The theoretical base for this work is the Variational Autoencoder (VAE), a latent variable generative model well suited for working with complex data as it forces them into a simpler low-dimensional space, able to model data non-linearities. The core of this Thesis consists in the Multi-Channel Variational Autoencoder (MCVAE), an extension of the VAE to jointly model latent relationships across multi-modal observations. This is achieved by: 1) constraining the latent distribution of each data modality to a common target prior, 2) forcing these latent distribution to generate all the data modalities through their associated generative functions. Moreover, we adapt the MCVAE to a Multi-Task setting, where the problem of dealing with missing data is addressed with a specific optimization scheme following these steps: 1) defining tasks across datasets based on the identification of data subsets presenting compatible modalities, 2) stacking multiple instances of the MCVAE, where each instance models a specific task, 3) sharing the models parameters of common modalities between modeling tasks.Thanks to these actions, the Multi-Task MCVAE allows to learn a joint model for all the data points leveraging on all the available information. Overall, this thesis provides a novel investigation of flexible approaches to account for data heterogeneity in the analysis of biomedical information.This work enables new research directions in which medical information can be consistently modeled within a joint probabilistic framework accounting for multiple data modalities, missing information, and biases across different datasets. Lastly, thanks to their general formulation, the methodologies here proposed can find applications beyond the neuroimaging research field. ; Cette thèse présente de nouveaux outils informatiques pour la modélisation conjointe de ... |
| نوع الوثيقة: | doctoral or postdoctoral thesis |
| اللغة: | English |
| العلاقة: | NNT: 2021COAZ4050; tel-03474169; https://theses.hal.science/tel-03474169Test; https://theses.hal.science/tel-03474169v2/documentTest; https://theses.hal.science/tel-03474169v2/file/2021COAZ4050.pdfTest |
| الإتاحة: | https://theses.hal.science/tel-03474169Test https://theses.hal.science/tel-03474169v2/documentTest https://theses.hal.science/tel-03474169v2/file/2021COAZ4050.pdfTest |
| حقوق: | info:eu-repo/semantics/OpenAccess |
| رقم الانضمام: | edsbas.3EE7BD9 |
| قاعدة البيانات: | BASE |
| الوصف غير متاح. |