2.1 Context

ARAMIS is an Inria project-team within the Paris Brain Institute (ICM) at the Pitié-Salpêtrière hospital (AP-HP) in Paris. ARAMIS was created as a team of the Inria Paris Center in 2012 and became a project-team in 2014. ARAMIS has a joint affiliation to Inria, CNRS, Inserm and Sorbonne University.

The Pitié-Salpêtrière hospital is the largest adult hospital in Europe. It is a leading center for neurological diseases: in terms of size (around 20,000 neurological patients each year), level of clinical expertise and quality of the technical facilities. Created in 2010, the Paris Brain Institute (ICM) gathers all research activities in neuroscience and neurology of the Pitié-Salpêtrière hospital. The ICM is both a private foundation and a public research unit (affiliated to CNRS, Inserm and Sorbonne University). It hosts about 25 research teams as well as various high level technical facilities (neuroimaging, genotyping/sequencing, cell culture, cellular imaging, bioinformatics ...), and gathers over 700 personnel. In addition, the ICM hosts one of the six IHU (Instituts Hospitalo-Universitaires).

ARAMIS is thus located both within a leading neuroscience institute and within a large hospital. This unique position has several advantages: direct contact with neuroscientists and clinicians allows us to foresee the emergence of new problems and opportunities for new methodological developments, provides access to unique datasets, and eases the transfer of our results to clinical research and clinical practice.

2.2 General aim

The ARAMIS team is devoted to the design of computational, mathematical and statistical approaches for the analysis of multimodal patient data, with an emphasis on neuroimaging data. The core methodological domains of our team are: machine learning, statistical modeling of complex geometric data, connectivity and network analysis. These new approaches are applied to clinical research in neurological diseases in collaboration with other teams of the ICM, clinical departments of the Pitié-Salpêtrière hospital and external partners. The team has a pluridisciplinary composition, bringing together researchers in mathematics, computer science and engineering (N. Burgos, O. Colliot, B. Couvy-Duchesne, F. De Vico Fallani, S. Durrleman, D. Racoceanu) and clinicians (D. Dormont, S. Epelbaum, S. Tezenas du Montcel).

We develop various clinical applications of our research, in particular in neurodegenerative disorders (Alzheimer's disease and other dementias, Parkinson's disease), multiple sclerosis, developmental disorders, stroke and to design brain-computer interfaces for rehabilitation.

3.1 From geometrical data to multimodal imaging

Brain diseases are associated to alterations of brain structure that can be studied in vivo using anatomical and diffusion MRI. The anatomy of a given subject can be represented by sets of anatomical surfaces (cortical and subcortical surfaces) and curves (white matter tracks) that can be extracted from anatomical and diffusion MRI respectively. We aim to develop approaches that can characterize the variability of brain anatomy within populations of subjects. To that purpose, we propose methods to estimate population atlases that provide an average model of a population of subjects together with a statistical model of their variability. Finally, we aim to introduce representations that can integrate geometrical information (anatomical surfaces, white matter tracts) together with functional (PET, ASL, EEG/MEG) and microstructural information.

3.2 Models of brain networks

Functional imaging techniques (EEG, MEG and fMRI) allow characterizing the statistical interactions between the activities of different brain areas, i.e. functional connectivity. Functional integration of spatially distributed brain regions is a well-known mechanism underlying various cognitive tasks, and is disrupted in brain disorders. Our team develops a framework for the characterization of brain connectivity patterns, based on connectivity descriptors from the theory of complex networks. More specifically, we propose analytical tools to infer brain networks, chacterize their structure and integrate multiple networks (for instance from multiple frequency bands or multiple modalities). The genericity of this approach allows us to apply it to various types of data including functional and structural neuroimaging, as well as genomic data.

3.3 Spatiotemporal modeling from longitudinal data

Longitudinal data sets are collected to capture variable temporal phenomena, which may be due to ageing or disease progression for instance. They consist in the observation of several individuals, each of them being observed at multiple points in time. The statistical exploitation of such data sets is notably difficult since data of each individual follow a different trajectory of changes and at its own pace. This difficulty is further increased if observations take the form of structured data like images or measurements distributed at the nodes of a mesh, and if the measurements themselves are normalized data or positive definite matrices for which usual linear operations are not defined. We aim to develop a theoretical and algorithmic framework for learning typical trajectories from longitudinal data sets. This framework is built on tools from Riemannian geometry to describe trajectories of changes for any kind of data and their variability within a group both in terms of the direction of the trajectories and pace.

3.4 Decision support systems

We then aim to develop tools to assist clinical decisions such as diagnosis, prognosis or inclusion in therapeutic trials. To that purpose, we leverage the tools developed by the team, such as multimodal representations, network indices and spatio-temporal models which are combined with advanced classification and regression approaches. We also dedicate strong efforts to rigorous, transparent and reproducible validation of the decision support systems on large clinical datasets.

3.5 Clinical research studies

Finally, we aim to apply advanced computational and statistical tools to clinical research studies. These studies are often performed in collaboration with other researchers of the ICM, clinicians of the Pitié -Salpêtrière hospital or external partners. Notably, our team is very often involved ”ex-ante” in clinical research studies. As co-investigators of such studies, we contribute to the definition of objectives, study design and definition of protocols. This is instrumental to perform clinically relevant methodological development and to maximize their medical impact.

The studied clinical applications include neurodegenerative disorders (Alzheimer's disease and other dementias, Parkinson's disease), multiple sclerosis, developmental disorders, stroke and the design of brain-computer interfaces for rehabilitation.

4.1 Introduction

We develop different applications of our new methodologies to brain pathologies, mainly neurodegenerative diseases. These applications aim at:

• better understanding the pathophysiology of brain disorders;
• designing systems to support clinical decisions such as diagnosis, prognosis and design of clinical trials;
• developing brain computer interfaces for clinical applications.

4.2 Understanding brain disorders

Computational and statistical approaches have the potential to help understand the pathophysiology of brain disorders. We first aim to contribute to better understand the relationships between pathological processes, anatomical and functional alterations, and symptoms. Moreover, within a single disease, there is an important variability between patients. The models that we develop have the potential to identify more homogeneous disease subtypes, that would constitute more adequate targets for new treatments. Finally, we aim to establish the chronology of the different types of alterations. We focus these activities on neurodegeneratives diseases: dementia (Alzheimer's disease, fronto-temporal dementia), Parkinson's disease, multiple sclerosis.

4.3 Supporting clinical decisions

We aim to design computational tools to support clinical decisions, including diagnosis, prognosis and the design of clinical trials. The differential diagnosis of neurodegenerative diseases can be difficult. Our tools have the potential to help clinicians by providing automated classification that can integrate multiple types of data (clinical/cognitive tests, imaging, biomarkers). Predicting the evolution of disease in individual patients is even more difficult. We aim to develop approaches that can predict which alterations and symptoms will occur and when. Finally, new approaches are needed to select participants in clinical trials. Indeed, it is widely recognized that, to have a chance to be successful, treatments should be administered at a very early stage.

4.4 Brain computer interfaces for clinical applications

A brain computer interface (BCI) is a device aiming to decode brain activity, thus creating an alternate communication channel between a person and the external environment. BCI systems can be categorized on the basis of the classification of an induced or evoked brain activity. The central tenet of a BCI is the capability to distinguish different patterns of brain activity, each being associated to a particular intention or mental task. Hence adaptation, as well as learning, is a key component of a BCI because users must learn to modulate their brainwaves to generate distinct brain patterns. Usually, a BCI is considered a technology for people to substitute some lost functions. However, a BCI could also help in clinical rehabilitation to recover motor functions. Indeed, in current neuroscience-based rehabilitation it is recognized that protocols based on mental rehearsal of movements (like motor imagery practicing) are a way to access the motor system because they can induce an activation of sensorimotor networks that were affected by lesions. Hence, a BCI based on movement imagery can objectively monitor patients’ progress and their compliance with the protocol, monitoring that they are actually imagining movements. It also follows that feedback from such a BCI can provide patients with an early reinforcement in the critical phase when there is not yet an overt sign of movement recovery.

6.1 New software

6.2 New platforms

Platform Brain-computer interface

Participants: Marie-Constance Corsi [Correspondant], Arthur Desbois [Correspondant], Fabrizio De Vico Fallani [Correspondant].

Our team coordinates the developments of the Brain-Computer Interface (BCI) platform at the Centre EEG/MEG of the neuroimaging core facility of the ICM. Several projects, including our NETBCI NNIH/ANR and ATTACK Big-brain theory funded projects, as well as experiments by different researchers of the Institute (ANR BETAPARK Project), and the BCINET ERC Consolidator grant are currently being run. To reinforce the impact of the platform we have recently recruited an Inria ADT engineer, who has significantly contributed to the extension of the Inria software OpenVibe allowing for new functionalities based on our methodological development on brain connectivity (A. Desbois)

7.1 Automatic quality control of brain T1-weighted magnetic resonance images for a clinical data warehouse

Participants: Simona Bottani [Correspondant], Ninon Burgos [Correspondant], Aurelien Maire [Correspondant], Didier Dormont [Correspondant], Olivier Colliot [Correspondant].

We published the first paper on AI for medical imaging based on the data warehouse of the Greater Paris hospitals (AP-HP). We developed and validated an automatic quality control system for brain MRI data. This is an important step to allow fast data curation and thus perform very-large scale studies using this data warehouse which comprises several million of participants. More details about the paper below.

Many studies on machine learning (ML) for computer-aided diagnosis have so far been mostly restricted to high-quality research data. Clinical data warehouses, gathering routine examinations from hospitals, offer great promises for training and validation of ML models in a realistic setting. However, the use of such clinical data warehouses requires quality control (QC) tools. Visual QC by experts is time-consuming and does not scale to large datasets. In this paper, we propose a convolutional neural network (CNN) for the automatic QC of 3D T1-weighted brain MRI for a large heterogeneous clinical data warehouse. To that purpose, we used the data warehouse of the hospitals of the Greater Paris area (Assistance Publique-Hôpitaux de Paris [AP-HP]). Specifically, the objectives were: 1) to identify images which are not proper T1-weighted brain MRIs; 2) to identify acquisitions for which gadolinium was injected; 3) to rate the overall image quality. We used 5000 images for training and validation and a separate set of 500 images for testing. In order to train/validate the CNN, the data were annotated by two trained raters according to a visual QC protocol that we specifically designed for application in the setting of a data warehouse. For objectives 1 and 2, our approach achieved excellent accuracy (balanced accuracy and F1-score > 90%), similar to the human raters. For objective 3, the performance was good but substantially lower than that of human raters. Nevertheless, the automatic approach accurately identified (balanced accuracy and F1-score > 80%) low quality images, which would typically need to be excluded. Overall, our approach shall be useful for exploiting hospital data warehouses in medical image computing.

More details in 6.

7.2 Anomaly detection for the individual analysis of brain PET images

Participants: Ninon Burgos [Correspondant], Jorge Cardoso, Stanley Durrleman, Sébastien Ourselin, Olivier Colliot.

In clinical practice, positron emission tomography (PET) images are mostly analysed visually, but the sensitivity and specificity of this approach greatly depends on the observer's experience. Quantitative analysis of PET images would alleviate this problem by helping define an objective limit between normal and pathological findings. We present an anomaly detection framework for the individual analysis of PET images. We created subject-specific abnormality maps that summarise the pathology's topographical distribution in the brain by comparing the subject's PET image to a model of healthy PET appearance that is specific to the subject under investigation. This model was generated from demographically and morphologically-matched PET scans from a control dataset. We generated abnormality maps for healthy controls, patients at different stages of Alzheimer's disease and with different frontotemporal dementia syndromes. We showed that no anomalies were detected for the healthy controls and that the anomalies detected from the patients with dementia coincided with the regions where abnormal uptake was expected. We also validated the proposed framework using the abnormality maps as inputs of a classifier and obtained higher classification accuracies than when using the PET images themselves as inputs. The proposed method was able to automatically locate and characterise the areas characteristic of dementia from PET images. The abnormality maps are expected to i) help clinicians in their diagnosis by highlighting, in a data-driven fashion, the pathological areas, and ii) improve the interpretability of subsequent analyses, such as computer-aided diagnosis or spatio-temporal modelling.

More details in 8.

7.3 Multilevel survival modeling with structured penalties for disease prediction from imaging genetics data

Participants: Pascal Lu [Correspondant], Olivier Colliot [Correspondant].

We introduced a framework for disease prediction from multimodal genetic and imaging data. We propose a multilevel survival model which allows predicting the time of occurrence of a future disease state in patients initially exhibiting mild symptoms. This new multilevel setting allows modeling the interactions between genetic and imaging variables. This is in contrast with classical additive models which treat all modalities in the same manner and can result in undesirable elimination of specific modalities when their contributions are unbalanced. Moreover, the use of a survival model allows overcoming the limitations of previous approaches based on classification which consider a fixed time frame. Furthermore, we introduce specific penalties taking into account the structure of the different types of data, such as a group lasso penalty over the genetic modality a a l2-penalty over the imaging modality. Finally, we propose a fast optimization algorithm, based on a proximal gradient method. The approach was applied to the prediction of Alzheimer’s disease (AD) among patients with mild cognitive impairment(MCI) based on genetic (single nucleotide polymorphisms) and imaging (anatomical MRI measures) data from the ADNI database. The experiments demonstrate the effectiveness of the method for predicting the time of conversion to AD. It revealed how genetic variants and brain imaging alterations interact in the prediction of future disease status. The approach is generic and could potentially be useful for the prediction of other diseases.

More details in 59.

7.4 Clinica: an open source software platform for reproducible clinical neuroscience studies

Participants: Alexandre Routier [Correspondant], Ninon Burgos [Correspondant], Mauricio Diaz-Melo [Correspondant], Simona Bottani [Correspondant], Omar El-Rifai [Correspondant], Ravi Hassanaly [Correspondant], Arnaud Marcoux [Correspondant], Jorge Samper-Gonzalez [Correspondant], Elina Thibeau-Sutre [Correspondant], Ghislain Vaillant [Correspondant], Junhao Wen [Correspondant], Stanley Durrleman [Correspondant], Olivier Colliot [Correspondant].

We present Clinica (www.clinica.run), an open-source software platform designed to make clinical neuroscience studies easier and more reproducible. Clinica aims for researchers to i) spend less time on data management and processing, ii) perform reproducible evaluations of their methods, and iii) easily share data and results within their institution and with external collaborators. The core of Clinica is a set of automatic pipelines for processing and analysis of multimodal neuroimaging data (currently, T1-weighted MRI, diffusion MRI and PET data), as well as tools for statistics, machine learning and deep learning. It relies on the brain imaging data structure (BIDS) for the organization of raw neuroimaging datasets and on established tools written by the community to build its pipelines. It also provides converters of public neuroimaging datasets to BIDS (currently ADNI, AIBL, OASIS and NIFD). Processed data include image-valued scalar fields (e.g. tissue probability maps), meshes, surface-based scalar fields (e.g. cortical thickness maps) or scalar outputs (e.g. regional averages). These data follow the ClinicA Processed Structure (CAPS) format which shares the same philosophy as BIDS. Consistent organization of raw and processed neuroimaging files facilitates the execution of single pipelines and of sequences of pipelines, as well as the integration of processed data into statistics or machine learning frameworks. The target audience of Clinica is neuroscientists or clinicians conducting clinical neuroscience studies involving multimodal imaging, and researchers developing advanced machine learning algorithms applied to neuroimaging data.

More details in 26.

7.5 Deep learning for brain disorders: from data processing to disease treatment

Participants: Ninon Burgos [Correspondant], Simona Bottani [Correspondant], Johann Faouzi [Correspondant], Elina Thibeau-Sutre [Correspondant], Olivier Colliot [Correspondant].

We were invited to publish a review paper on "Deep learning for brain disorders" in the high impact journal Briefings in Bioinformatics.

In order to reach precision medicine and improve patients' quality of life, machine learning is increasingly used in medicine. Brain disorders are often complex and heterogeneous, and several modalities such as demographic, clinical, imaging, genetics and environmental data have been studied to improve their understanding. Deep learning, a subpart of machine learning, provides complex algorithms that can learn from such various data. It has become state of the art in numerous fields, including computer vision and natural language processing, and is also growingly applied in medicine. In this article, we review the use of deep learning for brain disorders. More specifically, we identify the main applications, the concerned disorders and the types of architectures and data used. Finally, we provide guidelines to bridge the gap between research studies and clinical routine.

More details in 39.

7.6 Converting disease maps into heavyweight ontologies: general methodology and application to Alzheimer’s disease

Participants: Vincent Henry [Correspondant], Ivan Moszer [Correspondant], Olivier Dameron [Correspondant], Marie-Claude Potier [Correspondant], Martin Hoffman-Apitius [Correspondant], Olivier Colliot [Correspondant].

Omics technologies offer great promises for improving our understanding of diseases. The integration and interpretation of such data pose major challenges, calling for adequate knowledge models. Disease maps provide curated knowledge about disorders' pathophysiology at the molecular level adapted to omics measurements. However, the expressiveness of disease maps could be increased to help avoiding ambiguities and misinterpretations and to reinforce their interoperability with other knowledge resources. Ontologies are an adequate framework to overcome this limitation, through their axiomatic definitions and logical reasoning properties. We introduce the Disease Map Ontology (DMO), an ontological upper model based on systems biology terms. We then propose to apply DMO to Alzheimer's disease (AD). Specifically, we use it to drive the conversion of AlzPathway, a disease map devoted to Alzheimer's disease, into a formal ontology: AD Map Ontology (ADMO). We demonstrate that it allows one to deal with issues related to redundancy, naming, consistency, process classification and pathway relationships. Furthermore, we show that it can store and manage multi-omics data. Finally, we expand the model using elements from other resources, such as clinical features contained in the ADO (AD Ontology), resulting in an enriched model called ADMO-plus. The current versions of DMO, ADMO and ADMOplus are freely available here.

More details in 55.

7.7 Exploratory analysis of the genetics of impulse control disorders in Parkinson's disease using genetic risk scores

Participants: Johann Faouzi [Correspondant], Baptiste Couvy-Duchesne, Samir Bekadar, Olivier Colliot, Jean-Christophe Corvol.

We studied the association between impulse control disorders (ICDs) in Parkinsons disease (PD) and genetic risk scores (GRS) for 40 known or putative risk factors (e.g. depression, personality traits). In absence of published genome-wide association studies (GWAS), little is known about the genetics of ICDs in PD. GRS of related phenotypes, for which large GWAS are available, may help shed light on the genetic contributors of ICDs in PD. We searched for GWAS on European ancestry populations with summary statistics publicly available for a broad range of phenotypes, including other psychiatric disorders, personality traits, and simple phenotypes. We separately tested their predictive ability in two of the largest PD cohorts with clinical and genetic available: the Parkinsons Progression Markers Initiative database (N = 368, 33% female) and the Drug Interaction With Genes in Parkinsons Disease study (N = 373, 40% female). We considered 40 known or putative risk factors for ICDs in PD for which large GWAS had been published. After Bonferroni correction for multiple comparisons, no GRS or the combination of the 40 GRS were significantly associated with ICDs from the analyses in each cohort separately and from the meta-analysis. Albeit unsuccessful, our approach will gain power in the coming years with increasing availability of genotypes in clinical cohorts of PD, but also from future increase in GWAS sample sizes of the phenotypes we considered. Our approach may be applied to other complex disorders, for which GWAS are not available or limited.

More details in 50.

7.8 Association and prediction of phenotypic traits from neuroimaging data using a multi-component mixed model excluding the target vertex

Participants: Baptiste Couvy-Duchesne [Correspondant], Naomi Wray, Peter Visscher, Jian Yang, Olivier Colliot.

Mass-univariate association analyses aim at mapping the brain regions associated with a trait/disorder. The correlation between vertices may cause a true association to spread locally (cluster of association) or distally (false positive cluster). We previously showed that controlling for all vertices in the model (using a linear mixed model: LMM), could greatly reduce the probability of false positive and improve mapping precision. Here, we investigated a new LMM called MOMENT which reduces false positive rate in methylome-wide association studies. Compared to LMM, MOMENT had enhanced power and mapping precision but failed at reducing the rates of false positives clusters.The increasing sample sizes from neuroimaging studies should allow detection of image measures are associated with phenotypic traits with smaller effect sizes, which will advance progress in the mapping of the brain regions associated with traits and diseases. The UK Biobank (UKB) is one of the best example of this new generation of samples. Multimodal Brain MRI collection is currently ongoing, with tens of thousands of individuals already imaged out of a target of 100,000. The large sample size, together with the breadth of phenotyping (incl. self-reports, in lab assessments, prescription and medical history), should allow new insights into the factors contributing to brain differences between older adults.

More details in 70.

7.9 Primary Progressive Aphasia Associated With GRN Mutations: New Insights Into the Non-amyloid Logopenic Variant

Participants: Dario Saracino [Correspondant], Sophie Ferrieux, Simona Bottani, Olivier Colliot, Marc Teichmann, Raphaella Migliaccio, Isabelle Le Ber.

We aimed to determine relative frequencies and linguistic profiles of primary progressive aphasia (PPA) variants associated with progranulin (GRN) mutations, and study their neuroanatomical correlates. PPA patients carrying GRN mutations (PPA-GRN) were selected amongst a national prospective research cohort of 1,696 frontotemporal dementia (FTD) patients, including 235 patients with PPA. All PPA patients with amyloid-positive CSF biomarkers were excluded. In this cross-sectional study, speech/language and cognitive profiles were characterized with standardized evaluations, and grey matter (GM) atrophy patterns using voxel-based morphometry. Comparisons were performed with controls, and sporadic PPA patients. Among the overall population of 235 patients, 45 (19%) carried GRN mutations. We studied 32 of these and showed that logopenic PPA (lvPPA) was the most frequent linguistic variant (13, 41%), followed by non-fluent/agrammatic (nfvPPA: 9, 28%) and mixed forms (8, 25%). Semantic variant was rather rare (2, 6%). LvPPA patients, qualified as non-amyloid-lvPPA, presented canonical logopenic deficit. Seven out of 13 had a pure form, six showed subtle additional linguistic deficits not fitting criteria for mixed PPA, hence labelled as "logopenic-spectrum variant". GM atrophy primarily involved left posterior temporal gyrus, mirroring neuroanatomical changes of amyloid-positive-lvPPA. NfvPPA patients presented agrammatism (89%) rather than apraxia of speech (11%). This study shows that most frequent PPA variant associated with GRN mutations is non-amyloid lvPPA, preceding nfvPPA and mixed forms, and illustrates that language network may be affected at different levels. GRN testing is indicated for PPA patients, whether familial or sporadic. This finding is important for upcoming GRN gene-specific therapies.

7.10 A diffeomorphic vector field approach to analyze the thickness of the hippocampus from 7T MRI

Participants: Alexis Guyot [Correspondant], Ana Graciano-Fouquier [Correspondant], Emilie Gerardin [Correspondant], Marie Chupin [Correspondant], Joan Glaunès [Correspondant], Linda Marrakchi-Kacem [Correspondant], Johanne Germain [Correspondant], Claire Boutet [Correspondant], Claire Cury [Correspondant], Lucie Hertz-Pannier [Correspondant], Alexandre Vignaud [Correspondant], Stanley Durrleman [Correspondant], Thomas Henry [Correspondant], Pierre-Francois van de Moortele [Correspondant], Alain Trouvé [Correspondant], Olivier Colliot [Correspondant].

7-Tesla MRI of the hippocampus enhances the visualization of its internal substructures. Among these substructures, the cornu Ammonis and subiculum form a contiguous folded ribbon of gray matter. We have proposed a method to analyze local thickness measurements of this ribbon. We introduced an original approach based upon the estimation of a diffeomorphic vector field that traverses the ribbon. The method was designed to handle specificities of the hippocampus and corresponding 7-Tesla acquisitions: highly convoluted surface, non closed ribbon, incompletely defined inner/outer boundaries, anisotropic acquisitions. We furthermore proposed to conduct group comparisons using a population template built from the central surfaces of individual subjects. We first assessed the robustness of our approach to anisotropy, as well as to inter-rater variability, on a post-mortem scan and on in vivo acquisitions respectively. We then conducted a group study on a dataset of in vivo MRI from temporal lobe epilepsy (TLE) patients and healthy controls. The method detected local thinning patterns in patients, predominantly ipsilaterally to the seizure focus, which is consistent with medical knowledge. This new technique allows measuring the thickness of the hippocampus from 7-Tesla MRI. It shows good robustness with respect to anisotropy and inter-rater variability and has the potential to detect local atrophy in patients. As 7-Tesla MRI is increasingly available, this new method may become a useful tool to study local alterations of the hippocampus in brain disorders. It is made freely available to the community (code: here, postmortem segmentation: here).

More details in 54.

7.11 Reproducible evaluation of diffusion MRI features for automatic classification of patients with Alzheimer's disease

Participants: Junhao Wen [Correspondant], Jorge Samper-Gonzalez, Simona Bottani, Alexandre Routier, Ninon Burgos, Thomas Jacquemont, Sabrina Fontanella, Stanley Durrleman, Stéphane Epelbaum, Anne Bertrand, Olivier Colliot.

Diffusion MRI is the modality of choice to study alterations of white matter. In past years, various works have used diffusion MRI for automatic classification of AD. However, classification performance obtained with different approaches is difficult to compare and these studies are also difficult to reproduce. In the present paper, we first extend a previously proposed framework to diffusion MRI data for AD classification. Specifically, we add: conversion of diffusion MRI ADNI data into the BIDS standard and pipelines for diffusion MRI preprocessing and feature extraction. We then apply the framework to compare different components. First, FS has a positive impact on classification results: highest balanced accuracy (BA) improved from 0.76 to 0.82 for task CN vs AD. Secondly, voxel-wise features generally gives better performance than regional features. Fractional anisotropy (FA) and mean diffusivity (MD) provided comparable results for voxel-wise features. Moreover, we observe that the poor performance obtained in tasks involving MCI were potentially caused by the small data samples, rather than by the data imbalance. Furthermore, no extensive classification difference exists for different degree of smoothing and registration methods. Besides, we demonstrate that using non-nested validation of FS leads to unreliable and over-optimistic results: 0.05 up to 0.40 relative increase in BA. Lastly, with proper FR and FS, the performance of diffusion MRI features is comparable to that of T1w MRI. All the code of the framework and the experiments are publicly available: general-purpose tools have been integrated into the Clinica software package) and the paper-specific code is available here.

More details in 67.

7.12 Step-wise target controllability identifies dysregulated pathways of macrophage networks in multiple sclerosis

Participants: Bassignana Giulia [Correspondant], Fransson Jennifer [Correspondant], Henry Vincent [Correspondant], Colliot Olivier [Correspondant], Zujovic Violetta [Correspondant], De Vico Fallani Fabrizio [Correspondant].

Identifying the nodes able to drive the state of a network is crucial to understand, and eventually control, biological systems. Despite recent advances, such identification remains difficult because of the huge number of equivalent controllable configurations, even in relatively simple networks. Based on the evidence that in many applications it is essential to test the ability of individual nodes to control a specific target subset, we develop a fast and principled method to identify controllable driver-target configurations in sparse and directed networks. We demonstrate our approach on simulated networks and experimental gene networks to characterize macrophage dysregulation in human subjects with multiple sclerosis.

More details in 37.

7.13 Predicting the Progression of Mild Cognitive Impairment Using Machine Learning: A Systematic, Quantitative and Critical Review

Participants: Manon Ansart, Stéphane Epelbaum, Ninon Burgos, Didier Dormont, Olivier Colliot, Stanley Durrleman.

We performed a systematic review of studies focusing on the automatic prediction of the progression of mild cognitive impairment to Alzheimer’s disease (AD) dementia, and a quantitative analysis of the methodological choices impacting performance. This review included 172 articles, from which 234 experiments were extracted. For each of them, we reported the used data set, the feature types, the algorithm type, performance and potential methodological issues. The impact of these characteristics on the performance was evaluated using a multivariate mixed effect linear regressions. We found that using cognitive, fluorodeoxyglucose-positron emission tomography or potentially electroencephalography and magnetoencephalography variables significantly improved predictive performance compared to not including them, whereas including other modalities, in particular T1 magnetic resonance imaging, did not show a significant effect. The good performance of cognitive assessments questions the wide use of imaging for predicting the progression to AD and advocates for exploring further fine domain-specific cognitive assessments. We also identified several methodological issues, including the absence of a test set, or its use for feature selection or parameter tuning in nearly a fourth of the papers. Other issues, found in 15 percent of the studies, cast doubts on the relevance of the method to clinical practice. We also highlight that short-term predictions are likely not to be better than predicting that subjects stay stable over time. These issues highlight the importance of adhering to good practices for the use of machine learning as a decision support system for the clinical practice.

More details in 33.

7.14 Gaussian Graphical Model exploration and selection in high dimension low sample size setting

Participants: Thomas Lartigue, Simona Bottani, Olivier Colliot, Stanley Durrleman, Stéphanie Allassonnière.

Gaussian Graphical Models (GGM) are often used to describe the conditional correlations between the components of a random vector. In this article, we compare two families of GGM inference methods: nodewise edge selection and penalised likelihood maximisation. We demonstrate on synthetic data that, when the sample size is small, the two methods produce graphs with either too few or too many edges when compared to the real one. As a result, we propose a composite procedure that explores a family of graphs with an nodewise numerical scheme and selects a candidate among them with an overall likelihood criterion. We demonstrate that, when the number of observations is small, this selection method yields graphs closer to the truth and corresponding to distributions with better KL divergence with regards to the real distribution than the other two. Finally, we show the interest of our algorithm on two concrete cases: first on brain imaging data, then on biological nephrology data. In both cases our results are more in line with current knowledge in each field.

More details in 57.

7.15 Enhanced Methods for Lymphocyte Detection and Segmentation on H&E-Stained Images using eXclusive Autoencoders

Participants: Chao-Hui Huang, Daniel Racoceanu.

We propose a generalized solution for lymphocyte detection and segmentation, based on a novel image feature extraction method, named exclusive autoencoder (XAE). XAE is compatible with conventional autoencoder (AE) and able to provide additional information about the categorization in the feature space. For the task of lymphocyte detection, XAE was able to reach the an F-score of 99.96%, outperforming the state-of-the-art methods (reporting an F-score of 90%). Further, based on the integration of XAE+FCN (fully connected network) and conventional image processing function blocks provided in CellProfiler, we propose a lymphocyte segmentation pipeline. The obtained Dice coefficient reached 88.31% while the cutting-edge approach was at 74%.

More details in 16.

7.16 Tau Protein Discrete Aggregates in Alzheimer’s Disease: Neuritic Plaques and Tangles Detection and Segmentation using Computational Histopathology

Participants: Kristina Maňoušková [Correspondant], Valentin Abadie [Correspondant], Mehdi Ounissi [Correspondant], Gabriel Jimenez [Correspondant], Lev Stimmer [Correspondant], Benoit Delatour [Correspondant], Stanley Durrleman [Correspondant], Daniel Racoceanu [Correspondant].

Tau proteins in the gray matter are widely known to be a part of Alzheimer's disease symptoms. They can aggregate in three different structures within the brain: neurites, tangles, and neuritic plaques. The morphology and spatial disposition of these three aggregates are hypothesised to be correlated to the advancement of the disease. In order to establish a behavioural disease model related to the Tau proteins aggregates, it is necessary to develop algorithms to detect and segment them automatically. We present a 4-folded pipeline aiming to perform with clinically operational results. This pipeline is composed of a non-linear colour normalisation, a CNN-based image classifier, an Unet-based image segmentation stage, and a morphological analysis of the segmented objects. The tangle detection and segmentation algorithms improve state-of-the-art performances (75.8% and 91.1% F1-score, respectively), as well as for neuritic plaques detection and segmentation (81.3% and 78.2% F1-score, respectively). These results constitute an initial baseline in an area where no prior results exist, as far as we know. Even if overall, the results need to be robustified to fully meet biologists' expectations, the pipeline is complete and based on a promising state-of-the-art architecture. Therefore, we consider this study a handy baseline of an impactful extension to support new advances in Alzheimer's disease. Moreover, building a fully operational pipeline will be crucial to create a 3D histology map for a deeper understanding of clinico-pathological associations in Alzheimer's disease and the histology-based evidence of disease stratification among different sub-types.

More details in 18

7.17 Phase/Amplitude Synchronization of Brain Signals During Motor Imagery BCI Tasks

Participants: Tiziana Cattai [Correspondant], Stefania Colonnese [Correspondant], Dani Bassett [Correspondant], MarieConstance Corsi [Correspondant], De Vico Fallani Fabrizio [Correspondant].

In the last decade, functional connectivity (FC) has been increasingly adopted based on its ability to capture statistical dependencies between multivariate brain signals. However, the role of FC in the context of brain-computer interface applications is still poorly understood. To address this gap in knowledge, we considered a group of 20 healthy subjects during an EEG-based hand motor imagery (MI) task. We studied two well-established FC estimators, i.e. spectral- and imaginary-coherence, and we investigated how they were modulated by the MI task. We characterized the resulting FC networks by extracting the strength of connectivity of each EEG sensor and we compared the discriminant power with respect to standard power spectrum features. At the group level, results showed that while spectral-coherence based network features were increasing in the sensorimotor areas, those based on imaginary-coherence were significantly decreasing. We demonstrated that this opposite, but complementary, behavior was respectively determined by the increase in amplitude and phase synchronization between the brain signals. At the individual level, we eventually assessed the potential of these network connectivity features in a simple off-line classification scenario. Taken together, our results provide fresh insights into the oscillatory mechanisms subserving brain network changes during MI and offer new perspectives to improve BCI performance.

More details in 42.

7.18 Improving J-Divergence of Brain Connectivity States by Graph Laplacian Denoising

Participants: Tiziana Cattai [Correspondant], MarieConstance Corsi [Correspondant], Dani Bassett [Correspondant], Fabrizio De Vico Fallani [Correspondant], Stefania Colonnese [Correspondant].

Functional connectivity (FC) can be represented as a network, and is frequently used to better understand the neural underpinnings of complex tasks such as motor imagery (MI) detection in brain-computer interfaces (BCIs). However, errors in the estimation of connectivity can affect the detection performances. In this work, we address the problem of denoising common connectivity estimates to improve the detectability of different connectivity states. Specifically, we propose a graph signal processing based denoising algorithm that acts on the network graph Laplacian. Further, we derive a novel formulation of the Jensen divergence for the denoised Laplacian under different states. Numerical simulations on synthetic data show that denoising improves the Jensen divergence of connectivity patterns corresponding to different task conditions. Furthermore, we apply the Laplacian denoising technique to brain networks estimated from real EEG data recorded during MI-BCI experiments. A novel formulation of the J-divergence allows to quantify the distance between the FC networks in the motor imagery and resting states, as well as to understand the contribution of each Laplacian variable to the total J-divergence between two states. Experimental results on real MI-BCI EEG data demonstrate that the Laplacian denoising improves the separation of motor imagery and resting mental states, and it shortens the time interval required for connectivity estimation. We conclude that the approach shows promise for robust detection of connectivity states while being appealing for implementation in real-time BCI applications.

More details in 43.

7.19 BCI learning induces core-periphery reorganization in M/EEG multiplex brain networks

Participants: MarieConstance Corsi [Correspondant], Mario Chavez [Correspondant], Dani Bassett [Correspondant], Fabrizio De Vico Fallani [Correspondant].

Brain-computer interfaces (BCIs) constitute a promising tool for communication and control. However, mastering non-invasive closed-loop systems remains a learned skill that is difficult to develop for a non-negligible proportion of users. The involved learning process induces neural changes associated with a brain network reorganization that remains poorly understood. Approach: To address this inter-subject variability, we adopted a multilayer approach to integrate brain network properties from electroencephalographic (EEG) and magnetoencephalographic (MEG) data resulting from a four-session BCI training program followed by a group of healthy subjects. Our method gives access to the contribution of each layer to multilayer network that tends to be equal with time. Main results: We show that regardless the chosen modality, a progressive increase in the integration of somatosensory areas in the α band was paralleled by a decrease of the integration of visual processing and working memory areas in the β band. Notably, only brain network properties in multilayer network correlated with future BCI scores in the α 2 band: positively in somatosensory and decision-making related areas and negatively in associative areas. Significance: Our findings cast new light on neural processes underlying BCI training. Integrating multimodal brain network properties provides new information that correlates with behavioral performance and could be considered as a potential marker of BCI learning.

Mores details in 45.

7.20 Learning Riemannian metric for disease progression modeling

Participants: Samuel Gruffaz [Correspondant], Pierre-Emmanuel Poulet [Correspondant], Etienne Maheux [Correspondant], Bruno Jedynak [Correspondant], Stanley Durrleman [Correspondant].

Linear mixed-effect models provide a natural baseline for estimating disease progression using longitudinal data. They provide interpretable models at the cost of modeling assumptions on the progression profiles and their variability across subjects. A significant improvement is to embed the data in a Riemannian manifold and learn patient-specific trajectories distributed around a central geodesic. A few interpretable parameters characterize subject trajectories at the cost of a prior choice of the metric, which determines the shape of the trajectories. We extend this approach by learning the metric from the data allowing more flexibility while keeping the interpretability. Specifically, we learn the metric as the push-forward of the Euclidean metric by a diffeomorphism. This diffeomorphism is estimated iteratively as the composition of radial basis functions belonging to a reproducible kernel Hilbert space. The metric update allows us to improve the forecasting of imaging and clinical biomarkers in the Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort. Our results compare favorably to the 56 methods benchmarked in the TADPOLE challenge.

More details in 71

7.21 Mixture of Conditional Gaussian Graphical Models for unlabelled heterogeneous populations in the presence of co-factors

Participants: Thomas Lartigue, Stanley Durrleman, Stéphanie Allassonnière.

Conditional correlation networks, within Gaussian Graphical Models (GGM), are widely used to describe the direct interactions between the components of a random vector. In the case of an unlabelled Heterogeneous population, Expectation Maximisation (EM) algorithms for Mixtures of GGM have been proposed to estimate both each sub-population's graph and the class labels. However, we argue that, with most real data, class affiliation cannot be described with a Mixture of Gaussian, which mostly groups data points according to their geometrical proximity. In particular, there often exists external co-features whose values affect the features' average value, scattering across the feature space data points belonging to the same sub-population. Additionally, if the co-features' effect on the features is Heterogeneous, then the estimation of this effect cannot be separated from the sub-population identification. In this article, we propose a Mixture of Conditional GGM (CGGM) that subtracts the heterogeneous effects of the co-features to regroup the data points into sub-population corresponding clusters. We develop a penalised EM algorithm to estimate graph-sparse model parameters. We demonstrate on synthetic and real data how this method fulfils its goal and succeeds in identifying the sub-populations where the Mixtures of GGM are disrupted by the effect of the co-features.

More details in 58

7.22 Longitudinal self-supervision to disentangle inter-patient variability from disease progression

Participants: Raphaël Couronné, Paul Vernhet, Stanley Durrleman.

The problem of building disease progression models with longitudinal data has long been addressed with parametric mixed-effect models. They provide interpretable models at the cost of modeling assumptions on the progression profiles and their variability across subjects. Their deep learning counterparts, on the other hand, strive on flexible data-driven modeling, and additional interpretability-or, as far as generative models are involved, disentanglement of latent variables with respect to generative factors-comes from additional constraints. In this work, we propose a deep longitudinal model designed to disentangle inter-patient variability from an estimated disease progression timeline. We do not seek for an explicit mapping between age and disease stage, but to learn the latter solely from the ordering between visits using a differentiable ranking loss. Furthermore, we encourage inter-patient variability to be encoded in a separate latent space, where for each patient a single representation is learned from its set of visits, with a constraint of invariance under permutation of the visits. The modularity of the network architecture allows us to apply our model on various data types: a synthetic image dataset with known generative factors, cognitive assessments and neuroimaging data. We show that, combined with our patient encoder, the ranking loss for visits helps to exceed models with supervision, in particular in terms of disease staging.

More details in 79

7.23 Changes in the use of psychotropic drugs during the course of Alzheimer's disease: A large‐scale longitudinal study of French medical records

Participants: Manon Ansart [Correspondant], Stéphane Epelbaum [Correspondant], Marion Houot [Correspondant], Thomas Nedelec [Correspondant], Béranger Lekens [Correspondant], Laurène Gantzer [Correspondant], Didier Dormont [Correspondant], Stanley Durrleman​ [Correspondant].

Introduction: We aim to understand how patients with Alzheimer's disease (AD) are treated by identifying in a longitudinal fashion the late-life changes in patients' medical history that precede and follow AD diagnosis. Methods: We use prescription history of 34,782 patients followed between 1996 and 2019 by French general practitioners. We compare patients with an AD diagnosis, patients with mild cognitive impairment (MCI), and patients free of mental disorders. We use a generalized mixed-effects model to study the longitudinal changes in the prescription of eight drug types for a period 15 years before diagnosis and 10 years after. Results: In the decades preceding diagnosis, we find that future AD patients are treated significantly more than MCI patients with most psychotropic drugs and that most studied drugs are increasingly prescribed with age. At the time of diagnosis, all psychotropic drugs except benzodiazepines show a significant increase in prescription, while other drugs are significantly less prescribed. In the 10 years after diagnosis, nearly all categories of drugs are less and less prescribed including antidementia drugs. Discussion: Pre-diagnosis differences between future AD patients and MCI patients may indicate that subtle cognitive changes are recognized and treated as psychiatric symptoms. The disclosure of AD diagnosis drastically changes patients' care, priority being given to the management of psychiatric symptoms. The decrease of all prescriptions in the late stages may reflect treatment discontinuation and simplification of therapeutic procedures. This study therefore provides new insights into the medical practices for management of AD. More details in 34

7.24 A machine learning approach to screen for preclinical Alzheimer's disease

Participants: Sinead Gaubert [Correspondant], Marion Houot [Correspondant], Manon Ansart [Correspondant], Marie-Constance Corsi [Correspondant], Marie-Odile Habert [Correspondant], Bruno Dubois [Correspondant], Fabrizio de Vico Fallani [Correspondant], Stanley Durrleman​ [Correspondant], Stéphane Epelbaum [Correspondant].

Combining multimodal biomarkers could help in the early diagnosis of Alzheimer's disease (AD). We included 304 cognitively normal individuals from the INSIGHT-preAD cohort. Amyloid and neurodegeneration were assessed on 18F-florbetapir and 18F-fluorodeoxyglucose PET, respectively. We used a nested cross-validation approach with non-invasive features (electroencephalography [EEG], APOE4 genotype, demographic, neuropsychological and MRI data) to predict: 1/ amyloid status; 2/ neurodegeneration status; 3/ decline to prodromal AD at 5-year follow-up. Importantly, EEG was most strongly predictive of neurodegeneration, even when reducing the number of channels from 224 down to 4, as 4-channel EEG best predicted neurodegeneration (negative predictive value [NPV] = 82%, positive predictive value [PPV] = 38%, 77% specificity, 45% sensitivity). The combination of demographic, neuropsychological data, APOE4 and hippocampal volumetry most strongly predicted amyloid (80% NPV, 41% PPV, 70% specificity, 58% sensitivity) and most strongly predicted decline to prodromal AD at 5 years (97% NPV, 14% PPV, 83% specificity, 50% sensitivity). Thus, machine learning can help to screen patients at high risk of preclinical AD using non-invasive and affordable biomarkers.

More details in 52

7.25 Gaussian Graphical Model exploration and selection in high dimension low sample size setting

Participants: Thomas Lartigue, Simona Bottani, Olivier Colliot, Stanley Durrleman, Stéphanie Allassonnière.

Gaussian graphical models (GGM) are often used to describe the conditional correlations between the components of a random vector. In this article, we compare two families of GGM inference methods: the nodewise approach and the penalised likelihood maximisation. We demonstrate on synthetic data that, when the sample size is small, the two methods produce graphs with either too few or too many edges when compared to the real one. As a result, we propose a composite procedure that explores a family of graphs with a nodewise numerical scheme and selects a candidate among them with an overall likelihood criterion. We demonstrate that, when the number of observations is small, this selection method yields graphs closer to the truth and corresponding to distributions with better KL divergence with regards to the real distribution than the other two. Finally, we show the interest of our algorithm on two concrete cases: first on brain imaging data, then on biological nephrology data. In both cases our results are more in line with current knowledge in each field.

More details in 57

7.26 Mixture modeling for identifying subtypes in disease course mapping

Participants: Pierre-Emmanuel Poulet, Stanley Durrleman.

Disease modeling techniques summarize the possible trajectories of progression from multimodal and longitudinal data. These techniques often assume that individuals form a homogeneous cluster, thus ignoring possible disease subtypes within the population. We extend a non-linear mixed-effect model used for disease course mapping with a mixture framework. We jointly estimate model parameters and subtypes with a tempered version of a stochastic approximation of the Expectation Maximisation algorithm. We show that our model recovers the ground truth parameters from synthetic data, in contrast to the naive solution consisting in post hoc clustering of individual parameters from a one-class model. Applications to Alzheimer’s disease data allows the unsupervised identification of disease subtypes associated with distinct relationship between cognitive decline and progression of imaging and biological biomarkers.

More details in 73

7.27 AD Course Map charts Alzheimer’s disease progression

Participants: Igor Koval [Correspondant], Alexandre Bône [Correspondant], Maxime Louis [Correspondant], Thomas Lartigue [Correspondant], Simona Bottani [Correspondant], Arnaud Marcoux [Correspondant], Jorge Samper-Gonzalez [Correspondant], Ninon Burgos [Correspondant], Benjamin Charlier [Correspondant], Anne Bertrand [Correspondant], Stéphane Epelbaum [Correspondant], Olivier Colliot [Correspondant], Stéphanie Allassonnière [Correspondant], Stanley Durrleman [Correspondant].

Alzheimer's disease (AD) is characterized by the progressive alterations seen in brain images which give rise to the onset of various sets of symptoms. The variability in the dynamics of changes in both brain images and cognitive impairments remains poorly understood. This paper introduces AD Course Map a spatiotemporal atlas of Alzheimer's disease progression. It summarizes the variability in the progression of a series of neuropsychological assessments, the propagation of hypometabolism and cortical thinning across brain regions and the deformation of the shape of the hippocampus. The analysis of these variations highlights strong genetic determinants for the progression, like possible compensatory mechanisms at play during disease progression. AD Course Map also predicts the progression of patient data in the future with a better accuracy than the 56 methods benchmarked in the open challenge TADPOLE. Finally, AD Course Map is used to simulate cohorts of virtual patients developing Alzheimer's disease. AD Course Map offers therefore new tools for exploring the progression of AD and personalizing patients care.

More details in 56

7.28 Understanding the Variability in Graph Data Sets through Statistical Modeling on the Stiefel Manifold

Participants: Clément Mantoux, Baptiste Couvy-Duchesne, Federica Cacciamani, Stéphane Epelbaum, Stanley Durrleman, Stéphanie Allassonnière.

Network analysis provides a rich framework to model complex phenomena, such as human brain connectivity. It has proven efficient to understand their natural properties and design predictive models. In this paper, we study the variability within groups of networks, i.e., the structure of connection similarities and differences across a set of networks. We propose a statistical framework to model these variations based on manifold-valued latent factors. Each network adjacency matrix is decomposed as a weighted sum of matrix patterns with rank one. Each pattern is described as a random perturbation of a dictionary element. As a hierarchical statistical model, it enables the analysis of heterogeneous populations of adjacency matrices using mixtures. Our framework can also be used to infer the weight of missing edges. We estimate the parameters of the model using an Expectation-Maximization-based algorithm. Experimenting on synthetic data, we show that the algorithm is able to accurately estimate the latent structure in both low and high dimensions. We apply our model on a large data set of functional brain connectivity matrices from the UK Biobank. Our results suggest that the proposed model accurately describes the complex variability in the data set with a small number of degrees of freedom.

More details in 61

8.1 Bilateral grants with industry

9.1 International initiatives

9.2 European initiatives

9.3 National initiatives

10.1 Promoting scientific activities

10.2 Teaching - Supervision - Juries

10.3 Popularization

11.1 Major publications

• 1 articleM.Manon Ansart, S.Stéphane Epelbaum, G.Giulia Bassignana, A.Alexandre Bône, S.Simona Bottani, T.Tiziana Cattai, R.Raphäel Couronné, J.Johann Faouzi, I.Igor Koval, M.Maxime Louis, E.Elina Thibeau-Sutre, J.Junhao Wen, A.Adam Wild, N.Ninon Burgos, D.Didier Dormont, O.Olivier Colliot and S.Stanley Durrleman. Predicting the Progression of Mild Cognitive Impairment Using Machine Learning: A Systematic, Quantitative and Critical Review.Medical Image Analysis67January 2021, 101848
  HALDOI
• 2 articleM.Manon Ansart, S.Stéphane Epelbaum, G.Geoffroy Gagliardi, O.Olivier Colliot, D.Didier Dormont, B.Bruno Dubois, H.Harald Hampel and S.Stanley Durrleman. Reduction of recruitment costs in preclinical AD trials. Validation of automatic pre-screening algorithm for brain amyloidosis.Statistical Methods in Medical ResearchJanuary 2019, 096228021882303
  HALDOI
• 3 articleF.Federico Battiston, J.Jérémy Guillon, M.Mario Chavez, V.Vito Latora and F.Fabrizio De Vico Fallani. Multiplex core--periphery organization of the human connectome.Journal of the Royal Society Interface15146September 2018
  HALDOI
• 4 articleA.Anne Bertrand, J.Junhao Wen, D.Daisy Rinaldi, M.Marion Houot, S.Sabrina Sayah, A.Agnès Camuzat, C.Clémence Fournier, S.Sabrina Fontanella, A.Alexandre Routier, P.Philippe Couratier, F.Florence Pasquier, M.-O.Marie-Odile Habert, D.Didier Hannequin, O.Olivier Martinaud, P.Paola Caroppo, R.Richard Levy, B.Bruno Dubois, A.Alexis Brice, S.Stanley Durrleman, O.Olivier Colliot, I.Isabelle Le Ber and P.Prevdemals Study. Early cognitive, structural and microstructural changes in c9orf72 presymptomatic carriers before 40 years of age.JAMA neurology752February 2018, 236-245
  HALDOI
• 5 articleA.Alexandre Bône, O.Olivier Colliot and S.Stanley Durrleman. Learning the spatiotemporal variability in longitudinal shape data sets.International Journal of Computer VisionJuly 2020
  HALDOI
• 6 articleS.Simona Bottani, N.Ninon Burgos, A.Aurélien Maire, A.Adam Wild, S.Sébastian Ströer, D.Didier Dormont and O.Olivier Colliot. Automatic quality control of brain T1-weighted magnetic resonance images for a clinical data warehouse.Medical Image AnalysisVolume 752021
  HALDOIback to textback to text
• 7 articleN.Ninon Burgos, S.Simona Bottani, J.Johann Faouzi, E.Elina Thibeau-Sutre and O.Olivier Colliot. Deep learning for brain disorders: from data processing to disease treatment.Briefings in BioinformaticsDecember 2020
  HALDOI
• 8 articleN.Ninon Burgos, J. M.Jorge M. Cardoso, J.Jorge Samper-González, M.-O.Marie-Odile Habert, S.Stanley Durrleman, S.Sébastien Ourselin and O.Olivier Colliot. Anomaly detection for the individual analysis of brain PET images.Journal of Medical Imaging802April 2021, 024003
  HALDOIback to text
• 9 articleN.Ninon Burgos and O.Olivier Colliot. Machine learning for classification and prediction of brain diseases: recent advances and upcoming challenges.Current Opinion in Neurology3342020, 439-450
  HALDOI
• 10 articleM.-C.Marie-Constance Corsi, M.Mario Chavez, D.Denis Schwartz, N.Nathalie George, L.Laurent Hugueville, A. E.Ari E. Kahn, S.Sophie Dupont, D.Danielle Bassett and F.Fabrizio De Vico Fallani. Functional disconnection of associative cortical areas predicts performance during BCI training.NeuroImageJanuary 2020, 116500
  HALDOI
• 11 articleF.Fabrizio De Vico Fallani and D.Danielle Bassett. Network neuroscience for optimizing brain--computer interfaces.Physics of Life Reviews31December 2019, 304-309
  HALDOI
• 12 articleF.Fabrizio De Vico Fallani, V.Vito Latora and M.Mario Chavez. A Topological Criterion for Filtering Information in Complex Brain Networks.PLoS Computational Biology131January 2017, 1-18
  HALDOI
• 13 articleB.Bruno Dubois, M.Marie Chupin, H.Harald Hampel, S.Simone Lista, E.Enrica Cavedo, B.Bernard Croisile, G.Guy Louis Tisserand, J.Jacques Touchon, A.Alain Bonafe, P. J.Pierre Jean Ousset, A.Amir Ait Ameur, O.Olivier Rouaud, F.Fréderic Ricolfi, A.Alain Vighetto, F.Florence Pasquier, C.Christine Delmaire, M.Mathieu Ceccaldi, N.Nadine Girard, C.Carole Dufouil, S.Stéphane Lehericy, I.Isabelle Tonelli, F.Françoise Duveau, O.Olivier Colliot, L.Line Garnero, M.Marie Sarazin and D.Didier Dormont. Donepezil decreases annual rate of hippocampal atrophy in suspected prodromal Alzheimer's disease.Alzheimer's and Dementia119September 2015, 1041--1049
  HALDOI
• 14 articleF.Filippo Fraggetta, V.Vincenzo L’Imperio, D.David Ameisen, R.Rita Carvalho, S.Sabine Leh, T.-R.Tim-Rasmus Kiehl, M.Mircea Serbanescu, D.Daniel Racoceanu, V.Vincenzo Della Mea, A.Antonio Polonia, N.Norman Zerbe and C.Catarina Eloy. Best Practice Recommendations for the Implementation of a Digital Pathology Workflow in the Anatomic Pathology Laboratory by the European Society of Digital and Integrative Pathology (ESDIP).Diagnostics1111November 2021, 2167
  HALDOI
• 15 articleA.Alexis Guyot, A. B.Ana B Graciano Fouquier, E.Emilie Gerardin, M.Marie Chupin, J.Joan Glaunès, L.Linda Marrakchi-Kacem, J.Johanne Germain, C.Claire Boutet, C.Claire Cury, L.Lucie Hertz-Pannier, A.Alexandre Vignaud, S.Stanley Durrleman, T.Thomas Henry, P.-F.Pierre-François Van De Moortele, A.Alain Trouvé and O.Olivier Colliot. A Diffeomorphic Vector Field Approach to Analyze the Thickness of the Hippocampus from 7T MRI.IEEE Transactions on Biomedical Engineering682February 2021, 393-403
  HALDOI
• 16 inproceedingsC.-H.Chao-Hui Huang and D.Daniel Racoceanu. Enhanced Methods for Lymphocyte Detection and Segmentation on H&E Stained Images using eXclusive Autoencoders.International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC'20)Montreal, CanadaJuly 2020
  HALback to text
• 17 articleG.Gabriel Jiménez and D.Daniel Racoceanu. Deep Learning for Semantic Segmentation vs. Classification in Computational Pathology: Application to Mitosis Analysis in Breast Cancer Grading.Frontiers in Bioengineering and Biotechnology72019, 145
  HALDOIback to text
• 18 inproceedingsK.K Maňoušková, V.V Abadie, M.M Ounissi, G.G Jimenez, L.L Stimmer, B.B Delatour, S.S Durrleman and D.Daniel Racoceanu. Tau Protein Discrete Aggregates in Alzheimer's Disease: Neuritic Plaques and Tangles Detection and Segmentation using Computational Histopathology.SPIE Medical Imaging 2022San Diego, United StatesFebruary 2022
  HALback to text
• 19 proceedingsA. L.Anne L MartelP.Purang AbolmaesumiD.Danail StoyanovD.Diana MateusM. A.Maria A ZuluagaS. K.S. Kevin ZhouL.Leo JoskowiczD.Daniel RacoceanuMedical Image Computing and Computer Assisted Intervention – MICCAI 2020, 23rd International Conference, Lima, Peru, October 4–8, 2020, Proceedings, Part I (machine learning methodologies).October 2020
  HAL
• 20 proceedingsA. L.Anne L MartelP.Purang AbolmaesumiD.Danail StoyanovD.Diana MateusM. A.Maria A ZuluagaS. K.S. Kevin ZhouL.Leo JoskowiczD.Daniel RacoceanuMedical Image Computing and Computer Assisted Intervention – MICCAI 2020, 23rd International Conference, Lima, Peru, October 4–8, 2020, Proceedings, Part II (image reconstruction; prediction and diagnosis; cross-domain methods and reconstruction; domain adaptation; machine learning applications; generative adversarial networks).October 2020
  HAL
• 21 proceedingsA. L.Anne L MartelP.Purang AbolmaesumiD.Danail StoyanovD.Diana MateusM. A.Maria A ZuluagaS. K.S. Kevin ZhouL.Leo JoskowiczD.Daniel RacoceanuMedical Image Computing and Computer Assisted Intervention – MICCAI 2020, 23rd International Conference, Lima, Peru, October 4–8, 2020, Proceedings, Part III (CAI applications; image registration; instrumentation and surgical phase detection; navigation and visualization; ultrasound imaging; video image analysis).October 2020
  HAL
• 22 proceedingsA. L.Anne L MartelP.Purang AbolmaesumiD.Danail StoyanovD.Diana MateusM. A.Maria A ZuluagaS. K.S. Kevin ZhouL.Leo JoskowiczD.Daniel RacoceanuMedical Image Computing and Computer Assisted Intervention – MICCAI 2020, 23rd International Conference, Lima, Peru, October 4–8, 2020, Proceedings, Part IV (segmentation; shape models and landmark detection).October 2020
  HAL
• 23 proceedingsA. L.Anne L MartelP.Purang AbolmaesumiD.Danail StoyanovD.Diana MateusM. A.Maria A ZuluagaS. K.S. Kevin ZhouL.Leo JoskowiczD.Daniel RacoceanuMedical Image Computing and Computer Assisted Intervention – MICCAI 2020, 23rd International Conference, Lima, Peru, October 4–8, 2020, Proceedings, Part V (biological, optical, microscopic imaging; cell segmentation and stain normalization; histopathology image analysis; opthalmology).October 2020
  HAL
• 24 proceedingsA. L.Anne L MartelP.Purang AbolmaesumiD.Danail StoyanovD.Diana MateusM. A.Maria A ZuluagaS. K.S. Kevin ZhouL.Leo JoskowiczD.Daniel RacoceanuMedical Image Computing and Computer Assisted Intervention – MICCAI 2020, 23rd International Conference, Lima, Peru, October 4–8, 2020, Proceedings, Part VI (angiography and vessel analysis; breast imaging; colonoscopy; dermatology; fetal imaging; heart and lung imaging; musculoskeletal imaging).October 2020
  HAL
• 25 proceedingsA. L.Anne L MartelP.Purang AbolmaesumiD.Danail StoyanovD.Diana MateusM. A.Maria A ZuluagaS. K.S. Kevin ZhouL.Leo JoskowiczD.Daniel RacoceanuMedical Image Computing and Computer Assisted Intervention – MICCAI 2020, 23rd International Conference, Lima, Peru, October 4–8, 2020, Proceedings, Part VII (brain development and atlases; DWI and tractography; functional brain networks; neuroimaging; positron emission tomography).October 2020
  HAL
• 26 articleA.Alexandre Routier, N.Ninon Burgos, M.Mauricio Díaz, M.Michael Bacci, S.Simona Bottani, O.Omar El-Rifai, S.Sabrina Fontanella, P.Pietro Gori, J.Jérémy Guillon, A.Alexis Guyot, R.Ravi Hassanaly, T.Thomas Jacquemont, P.Pascal Lu, A.Arnaud Marcoux, T.Tristan Moreau, J.Jorge Samper-González, M.Marc Teichmann, E.Elina Thibeau--Sutre, G.Ghislain Vaillant, J.Junhao Wen, A.Adam Wild, M.-O.Marie-Odile Habert, S.Stanley Durrleman and O.Olivier Colliot. Clinica: an open source software platform for reproducible clinical neuroscience studies.Frontiers in Neuroinformatics15August 2021, 689675
  HALDOIback to text
• 27 articleJ.Jorge Samper-Gonzalez, N.Ninon Burgos, S.Simona Bottani, S.Sabrina Fontanella, P.Pascal Lu, A.Arnaud Marcoux, A.Alexandre Routier, J.Jérémy Guillon, M.Michael Bacci, J.Junhao Wen, A.Anne Bertrand, H.Hugo Bertin, M.-O.Marie-Odile Habert, S.Stanley Durrleman, T.Theodoros Evgeniou and O.Olivier Colliot. Reproducible evaluation of classification methods in Alzheimer's disease: Framework and application to MRI and PET data.NeuroImage183December 2018, 504-521
  HALDOI
• 28 articleJ.-B.Jean-Baptiste Schiratti, S.Stéphanie Allassonniere, O.Olivier Colliot and S.Stanley Durrleman. A Bayesian mixed-effects model to learn trajectories of changes from repeated manifold-valued observations.Journal of Machine Learning Research18December 2017, 1-33
  HAL
• 29 articleQ.Quentin Vanderbecq, E.Eric Xu, S.Sebastian Stroër, B.Baptiste Couvy-Duchesne, M.Mauricio Diaz Melo, D.Didier Dormont and O.Olivier Colliot. Comparison and validation of seven white matter hyperintensities segmentation software in elderly patients.Neuroimage-Clinical272020, 102357
  HALDOI
• 30 articleW.Wen Wei, E.Emilie Poirion, B.Benedetta Bodini, S.Stanley Durrleman, N.Nicholas Ayache, B.Bruno Stankoff and O.Olivier Colliot. Predicting PET-derived Demyelination from Multimodal MRI using Sketcher-Refiner Adversarial Training for Multiple Sclerosis.Medical Image Analysis58101546December 2019
  HALDOI
• 31 articleJ.Junhao Wen, E.Elina Thibeau-Sutre, M.Mauricio Diaz-Melo, J.Jorge Samper-Gonzalez, A.Alexandre Routier, S.Simona Bottani, D.Didier Dormont, S.Stanley Durrleman, N.Ninon Burgos and O.Olivier Colliot. Convolutional Neural Networks for Classification of Alzheimer's Disease: Overview and Reproducible Evaluation.Medical Image Analysis63July 2020, 101694
  HALDOI
• 32 articleR.Ryad Zemouri, N.Noureddine Zerhouni and D.Daniel Racoceanu. Deep Learning in the Biomedical Applications: Recent and Future Status.Applied Sciences98April 2019, 1526
  HALDOIback to text

11.2 Publications of the year