CONTEXT AND GENERAL AIM
The tremendous progress of neuroimaging, genomic and biomarker technologies has allowed
capturing various characteristics of brain diseases in living patients. Collection of
multimodal data in large patient databases provides a comprehensive view of brain alterations,
biological processes, genetic risk factors and symptoms. The team aims to build numerical
models of brain diseases from multimodal patient based on appropriate data-driven approaches.
To this end, we develop new data representations and statistical learning approaches that can
integrate multiple types of data: neuroimaging, peripheral biomarkers, clinical and omics data
(genetics, transcriptomics).
In particular, we develop methods to highlight networks of interactions among multiple sources
of data, to track data changes during disease progression, and to automatically predict current
or future clinical outcomes from these data. We apply these models to neurodegenerative diseases
(Alzheimer's disease and other dementias, multiple sclerosis, Parkinson's disease, etc.). They shall
allow deepening our understanding of neurological diseases and developing new decision support
systems for diagnosis, prognosis and design of clinical trials.
PIs involved: N. Burgos, O. Colliot
Neuroimaging provides critical information on anatomical and functional alterations as well as on
specific molecular and cellular processes. Our work is focused on the development of computational
approaches to extract biomarkers and build computer-aided diagnosis (CAD) systems from MRI and PET
data. More specifically, we develop: i) image translation models that can generate biomarkers of
specific pathological processes from unspecific routine imaging data; ii) approaches for detecting
local abnormalities; iii) frameworks for reproducible and reliable evaluation of CAD systems; iv)
methods for training and validating from large-scale hospital data warehouses.
PIs involved: S. Tezenas du Montcel, S. Durrleman
Longitudinal data sets contain observations of multiple subjects observed at multiple time-points.
They offer a unique opportunity to understand temporal processes such as ageing or disease progression.
We develop a new generation of statistical methods to infer the dynamics of changes of a series of data
such as biomarkers, images or clinical endpoints, together with the variability of such multivariate
trajectories within a population of reference. We apply these new models across an array of neurodegenerative
diseases to i) understand the heterogeneity in disease progression, in particular how genetic factors may
control variations in disease progression, ii) forecast the progression of a new patient at entry of a clinical
trial for stratification purposes and iii) the design of new clinical scales for use as outcomes in trials.
PIs involved: B. Couvy-Duchesne, O. Colliot
The field of neuroimaging is at a turning point, owing to the availability of several large research datasets
such as the UKBiobank, which comprises more than 50,000 volunteers from the general population with deep phenotyping,
multimodal MRI and genotyping data. Such large data promise a finer understanding of the brain association with
phenotypic data and disorders as well as improved risk prediction, though they also raise computational and methodological
challenges. We work on introducing new efficient algorithms and models that can scale up to the data and that can combine
information of different nature (genetic, environment, neuroimaging) and from several independent samples.
PIs involved: D. Racoceanu, S. Durrleman
Computational approaches can help characterize diseases at the microscopic level, from whole slide images
in histopathology to high-content microscopy. Benefiting from state-of-the-art deep learning approaches
with an increasing interest in explainable and responsible models, these modalities are likely to generate
a whole new systemic knowledge. Analyzing morphological and topological micro-heterogeneity allows a deeper
understanding of the disease, by providing novel quantitative insights allowing designing multi-scale and
multimodal algorithms, able to generate new morphological and topological correlations with patient's
stratification. Combined with omics signature, such multi-scale prints (pathomics, radiomics) open the path
towards a systemic understanding of complex processes, by providing a knowledgeable assessment, as well as
more efficient and reliable predictive simulations. Examples of applications include the characterization of
pathological protein aggregates in Alzheimer disease and the study of microglia-like cells integrated into
brain organoids.