2023Activity reportProject-TeamARAMIS

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 800 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.

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 Neuroimaging-based biomarkers and decision support systems

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 developed: 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.

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 mathematical frameworks to analyze and model brain networks, or graphs, estimated from experimental data via network-science approaches. More specifically, we proposed analytical tools to infer brain networks, characterize their structure and dynamics, over multiple spatial and temporal scales.

3.3 Disease progression modeling with longitudinal data

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 aim here to 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.

3.4 High-dimensional and multimodal data

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. Our aim is to better understand brain disorders by characterizing alterations and their progression, and to validate new tools to assist clinical decisions. While a large part of these clinical studies were in the field of dementia (Alzheimer's disease, fronto-temporal dementia), we have developed successful collaborations in other fields including multiple sclerosis, Parkinson's disease and related disorders, Huntington's disease or spino-cerebellar ataxia.

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. We design new approaches for extracting biomarkers from different types of data. Our tools have the potential to help clinicians in their diagnosis 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.

5.1 Awards

• Ravi Hassanaly received the best poster runner-up award at SPIE Medical Imaging 2023: Image processing for his paper `Simulation-based evaluation framework for deep learning unsupervised anomaly detection on brain FDG PET' 68.

6.1 New software

6.2 New platforms

Platform Brain-computer interface

Participants: Marie-Constance Corsi, Arthur Desbois, 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 extended the contract of our Inria ADT engineer, who is significantly contributing to the extension of the Inria software OpenVibe allowing for new functionalities based on our methodological development on brain connectivity and develop new sofwtare for the individual calibration (A. Desbois)

7.1 Book: Machine Learning for Brain Disorders

Participants: Ninon Burgos, Baptiste Couvy-Duchesne, Marie-Constance Corsi, Johann Faouzi, Federica Cacciamani, Gabriel Jimenez, Daniel Racoceanu, Olivier Colliot [Correspondant].

This book provides readers with an up-to-date and comprehensive guide to both methodological and applicative aspects of machine learning (ML) for brain disorders. The chapters in this book are organized into five parts. Part One presents the fundamentals of ML. Part Two looks at the main types of data used to characterize brain disorders, including clinical assessments, neuroimaging, electro- and magnetoencephalography, genetics and omics data, electronic health records, mobile devices, connected objects and sensors. Part Three covers the core methodologies of ML in brain disorders and the latest techniques used to study them. Part Four is dedicated to validation and datasets, and Part Five discusses applications of ML to various neurological and psychiatric disorders.

More details in 83.

7.2 Evaluation of MRI-based machine learning approaches for computer-aided diagnosis of dementia in a clinical data warehouse

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

A variety of algorithms have been proposed for computer-aided diagnosis of dementia from anatomical brain MRI. These approaches achieve high accuracy when applied to research data sets but their performance on real-life clinical routine data has not been evaluated yet. The aim of this work was to study the performance of such approaches on clinical routine data, based on a hospital data warehouse, and to compare the results to those obtained on a research data set. The clinical data set was extracted from the hospital data warehouse of the Greater Paris area, which includes 39 different hospitals. The research set was composed of data from the Alzheimer's Disease Neuroimaging Initiative data set. In the clinical set, the population of interest was identified by exploiting the diagnostic codes from the 10th revision of the International Classification of Diseases that are assigned to each patient. We studied how the imbalance of the training sets, in terms of contrast agent injection and image quality, may bias the results. We demonstrated that computer-aided diagnosis performance was strongly biased upwards (over 17 percent points of balanced accuracy) by the confounders of image quality and contrast agent injection, a phenomenon known as the Clever Hans effect or shortcut learning. When these biases were removed, the performance was very poor. In any case, the performance was considerably lower than on the research data set. Our study highlights that there are still considerable challenges for translating dementia computer-aided diagnosis systems to clinical routine.

More details in 39.

7.3 Automatic segmentation of the choroid plexuses: Method and validation in controls and patients with multiple sclerosis

Participants: Arya Yazdan-Panah, Olivier Colliot [Correspondant].

Choroid Plexuses (ChP) are structures located in the ventricles that produce the cerebrospinal fluid (CSF) in the central nervous system. They are also a key component of the blood-CSF barrier. Recent studies have described clinically relevant ChP volumetric changes in several neurological diseases including Alzheimer's, Parkinson's disease, and multiple sclerosis (MS). Therefore, a reliable and automated tool for ChP segmentation on images derived from magnetic resonance imaging (MRI) is a crucial need for large studies attempting to elucidate their role in neurological disorders. Here, we propose a novel automatic method for ChP segmentation in large imaging datasets. The approach is based on a 2-step 3D U-Net to keep preprocessing steps to a minimum for ease of use and to lower memory requirements. The models are trained and validated on a first research cohort including people with MS and healthy subjects. A second validation is also performed on a cohort of pre-symptomatic MS patients having acquired MRIs in routine clinical practice. Our method reaches an average Dice coefficient of 0.72 with the ground truth and a volume correlation of 0.86 on the first cohort while outperforming FreeSurfer and FastSurfer-based ChP segmentations. On the dataset originating from clinical practice, the method reaches a Dice coefficient of 0.67 (being close to the inter-rater agreement of 0.64) and a volume correlation of 0.84. These results demonstrate that this is a suitable and robust method for the segmentation of the ChP both on research and clinical datasets.

More details in 61.

7.4 How precise are performance estimates for typical medical image segmentation tasks?

Participants: Rosana El Jurdi, Olivier Colliot [Correspondant].

An important issue in medical image processing is to be able to estimate not only the performances of algorithms but also the precision of the estimation of these performances. Reporting precision typically amounts to reporting standard-error of the mean (SEM) or equivalently confidence intervals. However, this is rarely done in medical image segmentation studies. In this paper, we aim to estimate what is the typical confidence that can be expected in such studies. To that end, we first perform experiments for Dice metric estimation using a standard deep learning model (U-net) and a classical task from the Medical Segmentation Decathlon. We extensively study precision estimation using both Gaussian assumption and bootstrapping (which does not require any assumption on the distribution). We then perform simulations for other test set sizes and performance spreads. Overall, our work shows that small test sets lead to wide confidence intervals (e.g. 8 points of Dice for 20 samples with $\sigma \approx 10$).

More details in 71.

7.5 Introducing Soft Topology Constraints in Deep Learning-based Segmentation using Projected Pooling Loss

Participants: Guanghui Fu, Rosana El Jurdi, Lydia Chougar, Didier Dormont, Olivier Colliot [Correspondant].

Deep learning methods have achieved impressive results for 3D medical image segmentation. However, when the network is only guided by voxel-level information, it may provide anatomically aberrant segmentations. When performing manual segmentations, experts heavily rely on prior anatomical knowledge. Topology is an important prior information due to its stability across patients. Recently, several losses based on persistent homology were proposed to constrain topology. Persistent homology offers a principled way to control topology. However, it is computationally expensive and complex to implement, in particular in 3D. In this paper, we propose a novel loss function to introduce topological priors in deep learning-based segmentation, which is fast to compute and easy to implement. The loss performs a projected pooling within two steps. We first focus on errors from a global perspective by using 3D MaxPooling to obtain projections of 3D data onto three planes: axial, coronal and sagittal. Then, 2D MaxPooling layers with different kernel sizes are used to extract topological features from the multi-view projections. These two steps are combined using only MaxPooling, thus ensuring the efficiency of the loss function. Our approach was evaluated in several medical image datasets (spleen, heart, hippocampus, red nucleus). It allowed reducing topological errors and, in some cases, improving voxel-level accuracy.

More details in 66.

7.6 Interpretable automatic detection of incomplete hippocampal inversions using anatomical criteria

Participants: Lisa Hemforth, Claire Cury, Baptiste Couvy-Duchesne, Olivier Colliot [Correspondant].

Incomplete Hippocampal Inversion (IHI) is an atypical anatomical pattern of the hippocampus that has been associated with several brain disorders (epilepsy, schizophrenia). IHI can be visually detected on coronal T1 weighted MRI images. IHI can be absent, partial or complete (no IHI, partial IHI, IHI). However, visual evaluation can be long and tedious, justifying the need for an automatic method. In this paper, we propose, to the best of our knowledge, the first automatic IHI detection method from T1-weighted MRI. The originality of our approach is that, instead of directly detecting IHI, we propose to predict several anatomical criteria, which each characterize a particular anatomical feature of IHI, and that can ultimately be combined for IHI detection. Such individual criteria have the advantage of providing interpretable anatomical information regarding the morphological aspect of a given hippocampus. We relied on a large population of 2,008 participants from the IMAGEN study. The approach is general and can be used with different machine learning models. In this paper, we explored two different backbone models for the prediction: a linear method (ridge regression) and a deep convolutional neural network. We demonstrated that the interpretable, anatomical based prediction was at least as good as when predicting directly the presence of IHI, while providing interpretable information to the clinician or neuroscientist. This approach may be applied to other diagnostic tasks which can be characterized radiologically by several anatomical features.

More details in 69.

7.7 Interpretability of Machine Learning Methods Applied to Neuroimaging

Participants: Elina Thibeau-Sutre, Ninon Burgos, Olivier Colliot [Correspondant].

Deep learning methods have become very popular for the processing of natural images, and were then successfully adapted to the neuroimaging field. As these methods are non-transparent, interpretability methods are needed to validate them and ensure their reliability. Indeed, it has been shown that deep learning models may obtain high performance even when using irrelevant features, by exploiting biases in the training set. Such undesirable situations can potentially be detected by using interpretability methods. Recently, many methods have been proposed to interpret neural networks. However, this domain is not mature yet. Machine learning users face two major issues when aiming to interpret their models: which method to choose, and how to assess its reliability? Here, we aim at providing answers to these questions by presenting the most common interpretability methods and metrics developed to assess their reliability, as well as their applications and benchmarks in the neuroimaging context. Note that this is not an exhaustive survey: we aimed to focus on the studies which we found to be the most representative and relevant.

More details in 91.

7.8 Evaluating machine learning models and their diagnostic value

Participants: Gaël Varoquaux, Olivier Colliot [Correspondant].

This chapter describes model validation, a crucial part of machine learning whether it is to select the best model or to assess risk of a given model. We start by detailing the main performance metrics for different tasks (classification, regression), and how they may be interpreted, including in the face of class imbalance, varying prevalence, or asymmetric cost-benefit trade-offs. We then explain how to estimate these metrics in a unbiased manner using training, validation, and test sets. We describe cross-validation procedures –to use a larger part of the data for both training and testing– and the dangers of data leakage –optimism bias due to training data contaminating the test set. Finally, we discuss how to obtain confidence intervals of performance metrics, distinguishing two situations: internal validation or evaluation of learning algorithms, and external validation or evaluation of resulting prediction models.

More details in 93.

7.9 Reproducibility in machine learning for medical imaging

Participants: Olivier Colliot, Elina Thibeau-Sutre, Ninon Burgos [Correspondant].

Reproducibility is a cornerstone of science, as the replication of findings is the process through which they become knowledge. It is widely considered that many fields of science are undergoing a reproducibility crisis. This has led to the publications of various guidelines in order to improve research reproducibility. This didactic chapter intends at being an introduction to reproducibility for researchers in the field of machine learning for medical imaging. We first distinguish between different types of reproducibility. For each of them, we aim at defining it, at describing the requirements to achieve it and at discussing its utility. The chapter ends with a discussion on the benefits of reproducibility and with a plea for a non-dogmatic approach to this concept and its implementation in research practice.

More details in 85.

7.10 Association Between Diseases and Symptoms Diagnosed in Primary Care and the Subsequent Specific Risk of Multiple Sclerosis

Participants: Octave Guinebretiere, Thomas Nédelec, Laurène Gantzer, Béranger Lekens, Stanley Durrleman, Céline Louapre [Correspondant].

Previous studies have reported a possible prodrome in multiple sclerosis (MS) defined by non-specific symptoms including mood disorder or genito-urinary symptoms and increased health care use detected several years before diagnosis. This study aimed to evaluate agnostically the associations between diseases and symptoms diagnosed in primary care and the risk of multiple sclerosis (MS) relative to controls and two other autoimmune inflammatory diseases with similar population characteristics, namely lupus and Crohn's disease.

A case-control study was conducted using electronic health records from the Health Improvement Network database in the UK and France. We agnostically assessed the associations between 113 diseases and symptoms in the five years before and after diagnosis in patients with subsequent diagnosis of MS. Individuals with a diagnosis of MS were compared to individuals without MS, and individuals with two other auto-immune diseases, Crohn's disease and lupus

The study population consisted of patients with MS (n= 20,174), patients without MS (n=54,790), patients with Crohn's disease (n=30,477) or patients with lupus (n=7,337). Twelve ICD-10 codes were significantly positively associated with the risk of MS compared to controls without MS. After considering ICD-10 codes suggestive of neurological symptoms as the first diagnosis of MS, five ICD-10 codes remained significantly associated with MS: depression (UK OR 1.22 [95%CI 1.11-1.34]), sexual dysfunction (1.47 [1.11-1.95]), constipation (1.5 [1.27-1.78]), cystitis (1.21 [1.05-1.39]), and urinary tract infections of unspecified site (1.38 [1.18-1.61]). However, none of these conditions was selectively associated with MS in comparisons with both lupus and Crohn's disease. All five ICD-10 codes identified were still associated with MS during the five years after diagnosis.

This study identified 5 health conditions associated with subsequent MS diagnosis, which may be considered not only prodromal but also early-stage symptoms. However, these health conditions overlap with prodrome of two other autoimmune diseases, hence lacking specificity to MS.

More details in 46.

7.11 Charting Disease Trajectories from Isolated REM Sleep Behavior Disorder to Parkinson's Disease

Participants: Cécile di Folco, Raphael Couronné, Isabelle Arnulf, Graziella Mangone, Smaranda Leu-Semenescu, Pauline Dodet, Marie Vidailhet, Jean-Christophe Corvol, Stéphane Lehéricy, Stanley Durrleman [Correspondant].

Clinical presentation and progression dynamics are variable in patients with Parkinson's disease (PD). Disease course mapping is an innovative disease modelling technique that summarizes the range of possible disease trajectories and estimates dimensions related to onset, sequence, and speed of progression of disease markers. Objective To propose a disease course map for PD and investigate progression profiles in patients with or without rapid eye movement sleep behavioral disorders (RBD).

Data of 919 PD patients and 88 isolated RBD patients from three independent longitudinal cohorts were analyzed (follow-up duration: 5.1; 95% confidence interval, 1.1-8.1] years). Disease course map was estimated by using eight clinical markers (motor and non-motor symptoms) and four imaging markers (dopaminergic denervation).

PD course map showed that the first changes occurred in the contralateral putamen 13 years before diagnosis, followed by changes in motor symptoms, dysautonomia, sleep—all before diagnosis—and finally cognitive decline at the time of diagnosis. The model showed earlier disease onset, earlier non-motor and later motor symptoms, more rapid progression of cognitive decline in PD patients with RBD than PD patients without RBD. This pattern was even more pronounced in patients with isolated RBD with early changes in sleep, followed by cognition and non-motor symptoms and later changes in motor symptoms.

These findings are consistent with the presence of distinct patterns of progression between patients with and without RBD. Understanding heterogeneity of PD progression is key to decipher the underlying pathophysiology and select homogeneous subgroups of patients for precision medicine.

More details in 43.

7.12 A Multimodal Disease Progression Model for Genetic Associations with Disease Dynamics

Participants: Némo Fournier [Correspondant], Stanley Durrleman.

This article introduced a disease progression model suited for neurodegenerative pathologies that allows to model associations between covariates and dynamic features of the disease course. It established a statistical framework and implemented an algorithm for its estimation. It showed that the model is reliable and can provide uncertainty estimates of the discovered associations thanks to its Bayesian formulation. The model's interest was showcased by shining a new light on genetic associations.

More details in 65.

7.13 Interaction of sex and onset site on the disease trajectory of amyotrophic lateral sclerosis

Participants: Juliette Ortholand [Correspondant], Pierre-François Pradat, Sophie Tezenas du Montcel, Stanley Durrleman.

Studies showed the impact of sex and onset site (spinal or bulbar) on disease onset and survival in ALS. However, they mainly result from cross-sectional or survival analysis, and the interaction of sex and onset site on the different proxies of disease trajectory has not been fully investigated.

We selected all patients with repeated observations in the PRO-ACT database. We divided them into four groups depending on their sex and onset site. We estimated a multivariate disease progression model, named ALS Course Map, to investigate the combined temporal changes of the four sub-scores of the revised ALS Functional Rating Scale (ALSFRSr), the forced vital capacity (FVC), and the body mass index (BMI). We then compared the progression rate, the estimated age at onset, and the relative progression of the outcomes across each group.

We included 1,438 patients from the PRO-ACT database. They were 51% men with spinal onset, 12% men with bulbar onset, 26% women with spinal onset, and 11% women with bulbar onset. We showed a significant influence of both sex and onset site on the ALSFRSr progression. The BMI decreased 8.9 months earlier (95% CI = [3.9, 13.8]) in women than men, after correction for the onset site. Among patients with bulbar onset, FVC was impaired 2.6 months earlier (95% CI = [0.6, 4.6]) in women. Conclusion: Using a multivariable disease modelling approach, we showed that sex and onset site are important drivers of the progression of motor function, BMI, and FVC decline.

More details in 52.

7.14 Impact of sex and APOE-e4 genotype on regional brain metabolism in Alzheimer's Disease

Participants: Benoît Sauty [Correspondant], Stanley Durrleman.

Age, sex and APOE-e4 genotype have been identified as the strongest predictors of the risk of developing Alzheimer's Disease (AD). This work models the pathological progression of regional brain hypometabolism, using mixed-effect models with latent time variable and longitudinal FDG-PET data. Statistical comparisons then disentangle the effects of sex and APOE-e4 genotype on the onset age and pace of progression of hympometabolism in each brain region, while correcting for education level. They provide a brain map of the regions with earlier and/or faster alterations of the metabolism. We show that females are associated with faster hypometabolism in the caudate nuclei, the thalamus and right temporal and medial-occipital lobes, while APOE-e4 is associated with earlier hypometabolism in the limbic system (hippocampus, parahippocampus and amygdala) and temporal lobe.

More details in 74.

7.15 Forecasting individual progression trajectories in Alzheimer's disease

The anticipation of progression of Alzheimer's disease (AD) is crucial for evaluations of secondary prevention measures thought to modify the disease trajectory. However, it is difficult to forecast the natural progression of AD, notably because several functions decline at different ages and different rates in different patients. We evaluate here AD Course Map, a statistical model predicting the progression of neuropsychological assessments and imaging biomarkers for a patient from current medical and radiological data at early disease stages. We tested the method on more than 96,000 cases, with a pool of more than 4,600 patients from four continents. We measured the accuracy of the method for selecting participants displaying a progression of clinical endpoints during a hypothetical trial. We show that enriching the population with the predicted progressors decreases the required sample size by 38% to 50%, depending on trial duration, outcome, and targeted disease stage, from asymptomatic individuals at risk of AD to subjects with early and mild AD. We show that the method introduces no biases regarding sex or geographic locations and is robust to missing data. It performs best at the earliest stages of disease and is therefore highly suitable for use in prevention trials.

Participants: Etienne Maheux [Correspondant], Igor Koval, Juliette Ortholand, Colin Birkenbihl, Damanio Archetti, Vincent Bouteloup, Stéphane Epelbaum, Carole Dufouil, Martin Hofmann-Apitius, Stanley Durrleman.

More details in 48.

7.16 Measuring Neuronal Avalanches to inform Brain-Computer Interfaces

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

Large-scale interactions among multiple brain regions manifest as bursts of activations called neuronal avalanches, which reconfigure according to the task at hand and, hence, might constitute natural candidates to design brain-computer interfaces (BCI). To test this hypothesis, we used source-reconstructed magneto/electroencephalography, during resting state and a motor imagery task performed within a BCI protocol. To track the probability that an avalanche would spread across any two regions we built an avalanche transition matrix (ATM) and demonstrated that the edges whose transition probabilities significantly differed between conditions hinged selectively on premotor regions in all subjects. Furthermore, we showed that the topology of the ATMs allows task-decoding above the current gold standard. Hence, our results suggest that Neuronal Avalanches might capture interpretable differences between tasks that can be used to inform brain-computer interfaces.

More details in 41.

7.17 Automatic motion artefact detection in brain T1-weighted magnetic resonance images from a clinical data warehouse using synthetic data

Participants: Sophie Loizillon, Simona Bottani, Didier Dormont, Olivier Colliot, Ninon Burgos [Correspondant].

Containing the medical data of millions of patients, clinical data warehouses (CDWs) represent a great opportunity to develop computational tools. Magnetic resonance images (MRIs) are particularly sensitive to patient movements during image acquisition, which will result in artefacts (blurring, ghosting and ringing) in the reconstructed image. As a result, a significant number of MRIs in CDWs are corrupted by these artefacts and may be unusable. Since their manual detection is impossible due to the large number of scans, it is necessary to develop tools to automatically exclude (or at least identify) images with motion in order to fully exploit CDWs. In this paper, we propose a novel transfer learning method for the automatic detection of motion in 3D T1-weighted brain MRI. The method consists of two steps: a pre-training on research data using synthetic motion, followed by a fine-tuning step to generalise our pre-trained model to clinical data, relying on the labelling of 4045 images. The objectives were both (1) to be able to exclude images with severe motion, (2) to detect mild motion artefacts. Our approach achieved excellent accuracy for the first objective with a balanced accuracy nearly similar to that of the annotators (balanced accuracy>80%). However, for the second objective, the performance was weaker and substantially lower than that of human raters. Overall, our framework will be useful to take advantage of CDWs in medical imaging and highlight the importance of a clinical validation of models trained on research data.

More details in 47.

7.18 How can data augmentation improve attribution maps for disease subtype explainability?

Participants: Elina Thibeau-Sutre, Olivier Colliot, Ninon Burgos [Correspondant].

As deep learning has been widely used for computer aided-diagnosis, we wished to know whether attribution maps obtained using gradient back-propagation could correctly highlight the patterns of disease subtypes discovered by a deep learning classifier. As the correctness of attribution maps is difficult to evaluate directly on medical images, we used synthetic data mimicking the difference between brain MRI of controls and demented patients to design more reliable evaluation criteria of attribution maps. We demonstrated that attribution maps may mix the regions associated with different subtypes for small data sets while they could accurately characterize both subtypes using a large data set. We then proposed simple data augmentation techniques and showed that they could improve the coherence of the explanations for a small data set.

More details in 77.

7.19 Transfer learning from synthetic to routine clinical data for motion artefact detection in brain T1-weighted MRI

Participants: Sophie Loizillon, Simona Bottani, Didier Dormont, Olivier Colliot, Ninon Burgos [Correspondant].

Clinical data warehouses (CDWs) contain the medical data of millions of patients and represent a great opportunity to develop computational tools. MRIs are particularly sensitive to patient movements during image acquisition, which will result in artefacts (blurring, ghosting and ringing) in the reconstructed image. As a result, a significant number of MRIs in CDWs are unusable because corrupted by these artefacts. Since their manual detection is impossible due to the number of scans, it is necessary to develop a tool to automatically exclude images with motion in order to fully exploit CDWs. In this paper, we propose a CNN for the automatic detection of motion in 3D T1-weighted brain MRI. Our transfer learning approach, based on synthetic motion generation, consists of two steps: a pre-training on research data using synthetic motion, followed by a fine-tuning step to generalise our pre-trained model to clinical data, relying on the manual labelling of 5500 images. The objectives were both (1) to be able to exclude images with severe motion, (2) to detect mild motion artefacts. Our approach achieved excellent accuracy for the first objective with a balanced accuracy nearly similar to that of the annotators (balanced accuracy>80%). However, for the second objective, the performance was weaker and substantially lower than that of human raters. Overall, our framework will be useful to take advantage of CDWs in medical imaging and to highlight the importance of a clinical validation of models trained on research data.

More details in 72.

7.20 Simulation-based evaluation framework for deep learning unsupervised anomaly detection on brain FDG PET

Participants: Ravi Hassanaly, Simona Bottani, Benoît Sauty, Olivier Colliot, Ninon Burgos [Correspondant].

Unsupervised anomaly detection using deep learning models is a popular computer-aided diagnosis approach because it does not need annotated data and is not restricted to the diagnosis of a disease seen during training. Such approach consists in first learning the distribution of anomaly free images. Images presenting anomalies are then detected as outliers of this distribution. These approaches have been widely applied in neuroimaging to detect sharp and localized anomalies such as tumors or white matter hyper-intensities from structural MRI. In this work, we aim to detect anomalies from FDG PET images of patients with Alzheimer's disease. In this context, the anomalies can be subtle and difficult to delineate, making the task more difficult and meaning that no ground truth exists to evaluate the approaches. We thus propose a framework to evaluate unsupervised anomaly detection approaches that consists in simulating realistic anomalies from images of healthy subjects. We demonstrate the use of this framework by evaluating an approach based on a 3D variational autoencoder.

More details in 68.

7.21 Unsupervised anomaly detection in 3D brain FDG PET: A benchmark of 17 VAE-based approaches

Participants: Ravi Hassanaly, Camille Brianceau, Olivier Colliot, Ninon Burgos [Correspondant].

The use of deep generative models for unsupervised anomaly detection is an area of research that has gained interest in recent years in the field of medical imaging. Among all the existing models, the variational autoencoder (VAE) has proven to be efficient while remaining simple to use. Much research to improve the original method has been achieved in the computer vision literature, but rarely translated to medical imaging applications. To fill this gap, we propose a benchmark of fifteen variants of VAE that we compare with a vanilla autoencoder and VAE for a neuroimaging use case relying on a simulation-based evaluation framework. The use case is the detection of anomalies related to Alzheimer's disease and other dementias in 3D FDG PET. We show that among the fifteen VAE variants tested, nine lead to a good reconstruction accuracy and are able to generate healthy-looking images. This indicates that many approaches developed for computer vision applications can generalize to the unsupervised detection of anomalies of various shapes, intensities and locations in 3D FDG PET. However, these models do not outperform the vanilla autoencoder and VAE. More details in 81.

7.22 Semi-supervised domain adaptation for automatic quality control of FLAIR MRIs in a clinical data warehouse

Participants: Sophie Loizillon, Olivier Colliot, Lydia Chougar, Didier Dormont, Ninon Burgos [Correspondant].

Domain adaptation is a very useful approach to exploit the potential of clinical data warehouses, which gather a vast amount of medical imaging encompassing various modalities, sequences, manufacturers and machines. In this study, we propose a semi-supervised domain adaptation (SSDA) framework for automatically detecting poor quality FLAIR MRIs within a clinical data warehouse. Leveraging a limited number of labelled FLAIR and a large number of labelled T1-weighted MRIs, we introduce a novel architecture based on the well known Domain Adversarial Neural Network (DANN) that incorporates a specific classifier for the target domain. Our method effectively addresses the covariate shift and class distribution shift between T1-weighted and FLAIR MRIs, surpassing existing SSDA approaches by more than 10 percent points.

More details in 73.

7.23 A2V: A Semi-Supervised Domain Adaptation Framework for Brain Vessel Segmentation via Two-Phase Training Angiography-to-Venography Translation

Participants: Francesco Galati, Ninon Burgos, Maria A. Zualuaga [Correspondant].

We present a semi-supervised domain adaptation framework for brain vessel segmentation from different image modalities. Existing state-of-the-art methods focus on a single modality, despite the wide range of available cerebrovascular imaging techniques. This can lead to significant distribution shifts that negatively impact the generalization across modalities. By relying on annotated angiographies and a limited number of annotated venographies, our framework accomplishes image-to-image translation and semantic segmentation, leveraging a disentangled and semantically rich latent space to represent heterogeneous data and perform image-level adaptation from source to target domains. Moreover, we reduce the typical complexity of cycle-based architectures and minimize the use of adversarial training, which allows us to build an efficient and intuitive model with stable training. We evaluate our method on magnetic resonance angiographies and venographies. While achieving state-of-the-art performance in the source domain, our method attains a Dice score coefficient in the target domain that is only 8.9% lower, highlighting its promising potential for robust cerebrovascular image segmentation across different modalities.

More details in 67.

7.24 Temporal dynamics of the Scale for the Assessment and Rating of Ataxia in Spinocerebellar ataxias

Participants: Paul Moulaire, Pierre Emmanuel Poulet, Emilien Petit, Thomas Klockgether, Alexandra Durr, Tetsuo Ashisawa, Sophie Tezenas Du Montcel [Correspondant].

Background The Scale for the Assessment and Rating of Ataxia (SARA) is the reference clinical scale to assess the severity of cerebellar ataxia. In the context of upcoming therapeutic trials, a reliable clinical outcome is needed to assess the efficiency of treatments. Objective The aim is to precisely assess and compare temporal dynamics of SARA and a new f-SARA. Methods We analyzed data from four cohorts (EUROSCA, RISCA, CRC-SCA, and SPATAX) comprising 1210 participants and 4092 visits. The linearity of the progression and the variability were assessed using an ordinal Bayesian mixed-effect model (Leaspy). We performed sample size calculations for therapeutic trials with different scenarios to improve the responsiveness of the scale. Results Seven of the eight different items had a nonlinear progression. The speed of progression was different between most of the items, with an average time for a one-point increase from 3.5 years [3.4; 3.6] (median, 95% credible interval) for the fastest item to 11.4 [10.9; 12.0] years. The total SARA score had a linear progression with an average time for a one-point increase of 0.95 [0.92; 0.98] years. After removing the four last items and rescaling all items from 0 to 4, variability increased and progression was slower and thus would require a larger sample size in a future therapeutic trial. Conclusion Despite a heterogeneous temporal dynamics at the item level, the global progression of SARA was linear. Changing the initial scale deteriorates the responsiveness. This new information about the temporal dynamics of the scale should help design the outcome of future clinical trials.

More details in 50.

7.25 Baseline Clinical and Blood Biomarker in Patients With Preataxic and Early-Stage Disease Spinocerebellar Ataxia 1 and 3

Participants: Sophie Tezenas Du Montcel [Correspondant], Emilien Petit, Titilayo Olubajo, Jennifer Faber, Pauline Lallemant-Dudek, Khalaf Bushara, Susan Perlman, Sub Subramony, David Morgan, Brianna Jackman, Henry Lauris Paulson, Gülin Öz, Thomas Klockgether, Alexandra Durr, Tetsuo Ashisawa.

Background and Objective: In spinocerebellar ataxia, ataxia onset can be preceded by mild clinical manifestation, cerebellar and/or brainstem alterations or biomarkers modifications. READISCA is a prospective, longitudinal observational study of patients with spinocerebellar ataxias type 1 and 3 to provide essential markers for therapeutic interventions. We looked for clinical, imaging or biological markers that are present at an early-stage of the disease. Methods: We enrolled carriers of a pathological ATXN1 or ATXN3 expansion and controls from 18 US and two European ataxia referral centers. Clinical, cognitive, quantitative motor, neuropsychological measures and plasma neurofilament light chain (NfL) measurements were compared between mutation carriers with and without ataxia and controls. Results: We enrolled 200 participants: 45 carriers of a pathological ATXN1 expansion (31 patients with ataxia (median SARA: 9 [7;10]), 14 mutation carriers without ataxia (1 [0;2])) and 116 carriers of a pathological ATXN3 expansion (80 patients with ataxia (7 [6;9]), 36 mutation carriers without ataxia (1 [0;2])). In addition, we enrolled 39 controls who did not carry a pathological expansion in ATXN1 or ATXN3 . Plasma NfL levels were significantly higher in mutation carriers without ataxia than controls, despite similar mean age (controls: 5.7 pg/mL, SCA1: 18.0 pg/mL (P <0.0001), SCA3: 19.8 pg/mL (P<0.0001). Mutation carriers without ataxia differed from controls by significantly more upper motor signs (SCA1 P=0.0003, SCA3 P=0.003) and by the presence of sensor impairment and diplopia in SCA3 (P=0.0448, and 0.0445 respectively). Functional scales, fatigue and depression scores, swallowing difficulties, and cognitive impairment were worse in mutation carriers with ataxia than those without ataxia. Ataxic SCA3 subjects showed extrapyramidal signs, urinary dysfunction and lower motor neuron signs significantly more often than mutation carriers without ataxia. Discussion: READISCA showed the feasibility of harmonized data acquisition in a multi-national network. NfL alterations, early sensory ataxia and corticospinal signs were quantifiable between preataxic participants and controls. Patients with ataxia differed in many parameters from controls and mutation carriers without ataxia, with a graded increase of abnormal measures from control to preataxic to ataxic cohorts.

More details in 59.

7.26 A meta-graph approach for analyzing whole slide histopathological images of human brain tissue with Alzheimer's disease biomarkers

Participants: Gabriel Jimenez, Pablo Mas, Anuradha Kar, Lea Ingrassia, Suzana Boluda, Benoit Delatour, Lev Stimmer, Daniel Racoceanu [Correspondant].

Recently, high performance deep learning models have allowed automatic and precise analysis of high-content medical images. In digital histopathology, a typical challenge lies in analyzing whole slide images (WSI) due to their large dimensions which most often requires splitting them into small patches for feeding deep learning models. This leads to loss in global tissue level information and is particularly limiting to classification or clustering of patients based on tissue characteristics. In this study, a meta-graph approach is developed for a semantic spatial analysis of histopathological WSIs of human brain tissue containing biomarkers of Alzheimer’s disease (AD) such as tau protein aggregates in brain gray matter. We propose a pipeline that extracts morphological features of tau aggregates like neuritic plaques or neurofibrillary tangles using a pre-trained U-Net model and uses these to build a graph based on Delaunay triangulation at the WSI level in order to extract topological features from them. This pipeline is generating morphological and topological tabular data from WSI for classification and clustering patients using boosted trees, SVM or K-means algorithms. Further, combining locally extracted morphological features - at the neuritic plaques or neurofibrillary tangle level - with the constructed Delaunay graph, allows constructing a meta-graph that can be efficiently fed to graph neural network models, instead of the voluminous WSIs. This pipeline is developed and tested on a dataset of 60 WSIs from various cohorts of patients having normal and rapidly advancing AD. The purpose of this pipeline is to identify novel insights into AD evolution, as well as to provide a generic framework for creating knowledge-rich graphs for WSI characterization and analysis.

More details in 70.

7.27 Efficient 3D reconstruction of Whole Slide Images in Melanoma

Participants: Janan Arslan, Mehdi Ounissi, Haocheng Luo, Matthieu Lacroix, Pierrick Dupré, Pawan Kumar, Arran Hodgkinson, Sarah Dandou, Romain Larive, Christine Pignodel, Laurent Le Cam, Ovidiu Radulescu, Daniel Racoceanu [Correspondant].

Cutaneous melanoma is an invasive cancer with a worldwide annual death toll of 57,000 (Arnold et al., JAMA Dermatol 2022). In a metastatic state, surgical interventions are not curative and must be coupled with targeted therapy, or immunotherapy. However, resistance appears almost systematically and late-stage prognosis can remain poor. The complexity to eradicate melanoma stems from its plasticity; these cancer cells continually adapt to the tumor microenvironment, which leads to treatment resistance. Our primary assumption is that therapeutic resistance relies in part on a series of non-genetic transitions including changes in the metabolic states of these cancer cells. The 3D spatial distribution of blood vessels that are sources of nutrition and oxygen that drive this metabolic status is an important variable for understanding zoning aspects of this adaptation process. Using Whole Slide Images (WSI) of melanoma tumors from Patient-Derived Xenograft (PDX) mouse models, we build 3D vascular models to help predict and understand the metabolic states of cancer cells within the tumor. Our 3D reconstruction pipeline was based on PDX tumor samples sectioned over 2mm depth and stained with Hematoxylin and Eosin (H&E). The pipeline involves three primary steps, including 2D vessel segmentation using Deep Learning, intensity- and affine-based image registration, and 3D reconstruction using interpolation and 3D rendering (allowing for better interaction with biologists, pathologists, and clinicians). The originality of our computer-assisted pipeline is its capability to (a) deal with sparse data (i.e., not all tissue sections were readily available), and (b) adapt to a multitude of WSI-related challenges (e.g., epistemic uncertainty, extended processing times due to WSI scale, etc.). We posit both our 3D reconstruction pipeline, quantitative results of the major stages of the process, and a detailed illustration of the challenges faced, presenting resolutions to improve the pipeline’s efficiency.

More details in 63.

7.28 Computational Pathology for Brain Disorders

Participants: Gabriel Jimenez, Daniel Racoceanu [Correspondant].

Non-invasive brain imaging techniques allow understanding the behavior and macro changes in the brain to determine the progress of a disease. However, computational pathology provides a deeper understanding of brain disorders at cellular level, able to consolidate a diagnosis and make the bridge between the medical image and the omics analysis. In traditional histopathology, histology slides are visually inspected, under the microscope, by trained pathologists. This process is time-consuming and labor-intensive; therefore, the emergence of Computational Pathology has triggered great hope to ease this tedious task and make it more robust. This chapter focuses on understanding the state-of-the-art machine learning techniques used to analyze whole slide images within the context of brain disorders. We present a selective set of remarkable machine learning algorithms providing discriminative approaches and quality results on brain disorders. These methodologies are applied to different tasks, such as monitoring mechanisms contributing to disease progression and patient survival rates, analyzing morphological phenotypes for classification and quantitative assessment of disease, improving clinical care, diagnosing tumor specimens, and intraoperative interpretation. Thanks to the recent progress in machine learning algorithms for high-content image processing, computational pathology marks the rise of a new generation of medical discoveries and clinical protocols, including in brain disorders.

More details in 90.

7.29 Phagocytosis Unveiled: A Scalable and Interpretable Deep learning Framework for Neurodegenerative Disease Analysis

Participants: Mehdi Ounissi, Daniel Racoceanu [Correspondant].

Quantifying the phagocytosis of dynamic, unstained cells is essential for evaluating neurodegenerative diseases. However, measuring rapid cell interactions and distinguishing cells from backgrounds make this task challenging when processing time-lapse phase-contrast video microscopy. In this study, we introduce a fully automated, scalable, and versatile realtime framework for quantifying and analyzing phagocytic activity. Our proposed pipeline can process large data-sets and includes a data quality verification module to counteract potential perturbations such as microscope movements and frame blurring. We also propose an explainable cell segmentation module to improve the interpretability of deep learning methods compared to black-box algorithms. This includes two interpretable deep learning capabilities: visual explanation and model simplification. We demonstrate that interpretability in deep learning is not the opposite of high performance, but rather provides essential deep learning algorithm optimization insights and solutions. Incorporating interpretable modules results in an efficient architecture design and optimized execution time. We apply this pipeline to quantify and analyze microglial cell phagocytosis in frontotemporal dementia (FTD) and obtain statistically reliable results showing that FTD mutant cells are larger and more aggressive than control cells. To stimulate translational approaches and future research, we release an open-source pipeline and a unique microglial cells phagocytosis dataset for immune system characterization in neurodegenerative diseases research. This pipeline and dataset will consistently crystallize future advances in this field, promoting the development of efficient and effective interpretable algorithms dedicated to this critical domain.

More details in 99.

7.30 HappyFeat—An interactive and efficient BCI framework for clinical applications

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

Brain–Computer Interface (BCI) systems allow to perform actions by translating brain activity into commands. Such systems require training a classification algorithm to discriminate between mental states, using specific features from the brain signals. This step is crucial and presents specific constraints in clinical contexts. HappyFeat is an open-source software making BCI experiments easier in such contexts: effortlessly extracting and selecting adequate features for training, in a single GUI. Novel features based on Functional Connectivity can be used, allowing graph-oriented approaches. We describe HappyFeat’s mechanisms, showing its performances in typical use cases, and showcasing how to compare different types of features.

More details in 42.

7.31 Vizaj—A free online interactive software for visualizing spatial networks

Participants: Thibault Rolland [Correspondant], Fabrizio De Vico Fallani [Correspondant].

In many fields of science and technology we are confronted with complex networks. Making sense of these networks often require the ability to visualize and explore their intermingled structure consisting of nodes and links. To facilitate the identification of significant connectivity patterns, many methods have been developed based on the rearrangement of the nodes so as to avoid link criss-cross. However, real networks are often embedded in a geometrical space and the nodes code for an intrinsic physical feature of the system that one might want to preserve. For these spatial networks, it is therefore crucial to find alternative strategies operating on the links and not on the nodes. Here, we introduce Vizaj a javascript web application to render spatial networks based on optimized geometrical criteria that reshape the link profiles. While optimized for 3D networks, Vizaj can also be used for 2D networks and offers the possibility to interactively customize the visualization via several controlling parameters, including network filtering and the effect of internode distance on the link trajectories. Vizaj is further equipped with additional options allowing to improve the final aesthetics, such as the color/size of both nodes and links, zooming/rotating/translating, and superimposing external objects. Vizaj is an open-source software which can be freely downloaded and updated via a github repository. Here, we provide a detailed description of its main features and algorithms together with a guide on how to use it. Finally, we validate its potential on several synthetic and real spatial networks from infrastructural to biological systems. We hope that Vizaj will help scientists and practitioners to make sense of complex networks and provide aesthetic while informative visualizations.

More details in 55.

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, 101848HALDOI
• 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, 096228021882303HALDOI
• 3 inproceedingsJ.Janan Arslan, H.Haocheng Luo, M.Matthieu Lacroix, P.Pierrick Dupré, P.Pawan Kumar, A.Arran Hodgkinson, S.Sarah Dandou, R. M.Romain M Larive, C.Christine Pignodel, L.Laurent Le cam, O.Ovidiu Radulescu and D.Daniel Racoceanu. 3D Reconstruction of H&E Whole Slide Images in Melanoma.SPIE Medical ImagingSPIE Medical Imaging 2023San Diego, California, United StatesFebruary 2023HAL
• 4 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 2018HALDOI
• 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 2020HALDOI
• 6 articleS.Simona Bottani, N.Ninon Burgos, A.Aurélien Maire, D.Dario Saracino, S.Sebastian Stroer, D.Didier Dormont and O.Olivier Colliot. Evaluation of MRI-based machine learning approaches for computer-aided diagnosis of dementia in a clinical data warehouse.Medical Image Analysis89October 2023, 102903HAL
• 7 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 752021HALDOI
• 8 articleS.Sandrine Brice, S.Sonia Reyes, A.Aude Jabouley, C.Carla Machado, C.Christina Rogan, N.Nathalie Gastellier, N.Nassira Alili, S.Stephanie Guey, E.Eric Jouvent, D.Dominique Hervé, S.Sophie Tezenas Du Montcel and H.Hugues Chabriat. Trajectory Pattern of Cognitive Decline in Cerebral Autosomal Dominant Arteriopathy With Subcortical Infarcts and Leukoencephalopathy.Neurology9910September 2022, e1019-e1031HALDOI
• 9 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 2020HALDOI
• 10 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, 024003HALDOI
• 11 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, 439-450HALDOI
• 12 articleG.Giulia Coarelli, A.Anna Heinzmann, C.Claire Ewenczyk, C.Clara Fischer, M.Marie Chupin, M.-L.Marie-Lorraine Monin, H.Hortense Hurmic, F.Fabienne Calvas, P.Patrick Calvas, C.Cyril Goizet, S.Stéphane Thobois, M.Mathieu Anheim, K.Karine Nguyen, D.David Devos, C.Christophe Verny, V. a.Vito a G Ricigliano, J.-F.Jean-François Mangin, A.Alexis Brice, S.Sophie Tezenas Du Montcel and A.Alexandra Durr. Safety and efficacy of riluzole in spinocerebellar ataxia type 2 in France (ATRIL): a multicentre, randomised, double-blind, placebo-controlled trial.The Lancet Neurology21January 2022, 225 - 233HALDOI
• 13 bookO.Olivier Colliot. Machine Learning for Brain Disorders.197NeuromethodsSpringer2023HALDOI
• 14 inbookO.Olivier Colliot, E.Elina Thibeau-Sutre and N.Ninon Burgos. Reproducibility in machine learning for medical imaging.Machine Learning for Brain DisordersSpringer2023HAL
• 15 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, 116500HALDOI
• 16 articleB.Baptiste Couvy-Duchesne, F.Futao Zhang, K.Kathryn Kemper, J.Julia Sidorenko, N.Naomi Wray, P.Peter Visscher, O.Olivier Colliot and J.Jian Yang. Parsimonious model for mass-univariate vertexwise analysis.Journal of Medical Imaging905September 2022HALDOI
• 17 articleB.Baptiste Couvy‐duchesne, L. T.Lachlan T Strike, F.Futao Zhang, Y.Yan Holtz, Z.Zhili Zheng, K. E.Kathryn E Kemper, L.Loïc Yengo, O.Olivier Colliot, M.Margaret Wright, N.Naomi Wray, J.Jian Yang and P. M.Peter M. Visscher. A unified framework for association and prediction from vertex-wise grey-matter structure.Human Brain MappingJuly 2020HALDOI
• 18 articleF.Fabrizio De Vico Fallani and D.Danielle Bassett. Network neuroscience for optimizing brain--computer interfaces.Physics of Life Reviews31December 2019, 304-309HALDOI
• 19 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, 1-18HALDOI
• 20 articleS.Songhui Diao, Y.Yinli Tian, W.Wanming Hu, J.Jiaxin Hou, R.Ricardo Lambo, Z.Zhicheng Zhang, Y.Yaoqin Xie, X.Xiu Nie, F.Fa Zhang, D.Daniel Racoceanu and W.Wenjian Qin. Weakly Supervised Framework for Cancer Region Detection of Hepatocellular Carcinoma in Whole-Slide Pathologic Images Based on Multiscale Attention Convolutional Neural Network.American Journal of Pathology1923March 2022, 553-563HALDOI
• 21 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, 393-403HALDOI
• 22 inproceedingsG.Gabriel Jiménez, A.Anuradha Kar, M.Mehdi Ounissi, L.Léa Ingrassia, S.Susana Boluda, B.Benoît Delatour, L.Lev Stimmer and D.Daniel Racoceanu. Visual deep learning-based explanation for neuritic plaques segmentation in Alzheimer's Disease using weakly annotated whole slide histopathological images.Lecture Notes in Computer ScienceMICCAI 2022 - 25th International Conference on Medical Image Computing and Computer Assisted InterventionLNCS-13432Medical Image Computing and Computer Assisted InterventionPart VIIISingapore, SingaporeSpringer Nature SwitzerlandSeptember 2022, 336-344HALDOI
• 23 inbookG.Gabriel Jimenez and D.Daniel Racoceanu. Computational Pathology for Brain Disorders.197Machine Learning for Brain DisordersPart of the Neuromethods book series (NM,volume 197)Springer; Humana, New York, NYJuly 2023, 533–572HALDOI
• 24 articleI.Igor Koval, A.Alexandre Bône, M.Maxime Louis, T.Thomas Lartigue, S.Simona Bottani, A.Arnaud Marcoux, J.Jorge Samper-Gonzalez, N.Ninon Burgos, B.Benjamin Charlier, A.Anne Bertrand, S.Stéphane Epelbaum, O.Olivier Colliot, S.Stéphanie Allassonnière and S.Stanley Durrleman. AD Course Map charts Alzheimer’s disease progression.Scientific Reports111April 2021HALDOI
• 25 articleI.Igor Koval, T.Thomas Dighiero-Brecht, A. J.Allan J Tobin, S. J.Sarah J Tabrizi, R. I.Rachael I Scahill, S.Sophie Tezenas Du Montcel, S.Stanley Durrleman and A.Alexandra Durr. Forecasting individual progression trajectories in Huntington disease enables more powered clinical trials.Scientific Reports121December 2022, 18928HALDOI
• 26 articleK.Kevin de Matos, C.Claire Cury, L.Lydia Chougar, L. T.Lachlan T Strike, T.Thibault Rolland, M.Maximilien Riche, L.Lisa Hemforth, A.Alexandre Martin, T.Tobias Banaschewski, A. L.Arun L W Bokde, S.Sylvane Desrivières, H.Herta Flor, A.Antoine Grigis, H.Hugh Garavan, P.Penny Gowland, A.Andreas Heinz, R.Rüdiger Brühl, J.-L.Jean-Luc Martinot, M.-L.Marie-Laure Paillère Martinot, E.Eric Artiges, F.Frauke Nees, J. H.Juliane H Fröhner, H.Herve Lemaitre, D.Dimitri Papadopoulos Orfanos, T.Tomáš Paus, L.Luise Poustka, S.Sarah Hohmann, S.Sabina Millenet, J. H.Juliane H Fröhner, M. N.Michael N Smolka, N.Nilakshi Vaidya, H.Henrik Walter, R.Robert Whelan, G.Gunter Schumann, V.Vincent Frouin, M.Meritxell Bach Cuadra, O.Olivier Colliot and B.Baptiste Couvy-Duchesne. Temporo-basal sulcal connections: a manual annotation protocol and an investigation of sexual dimorphism and heritability.Brain Structure and Function2286June 2023, 1459-1478HALDOI
• 27 articleP.Paul Moulaire, P.-E.Pierre-Emmanuel Poulet, E.Emilien Petit, T.Thomas Klockgether, A.Alexandra Durr, T.Tetsuo Ashizawa and S.Sophie Tezenas Du Montcel. Temporal Dynamics of the Scale for the Assessment and Rating of Ataxia in Spinocerebellar Ataxias.Movement DisordersOctober 2022HALDOI
• 28 articleT.Thomas Nedelec, B.Baptiste Couvy-Duchesne, F.Fleur Monnet, T.Timothy Daly, M.Manon Ansart, L.Laurène Gantzer, B.Béranger Lekens, S.Stéphane Epelbaum, C.Carole Dufouil and S.Stanley Durrleman. Identifying health conditions associated with Alzheimer's disease up to 15 years before diagnosis: an agnostic study of French and British health records.The Lancet Digital HealthMarch 2022HALDOI
• 29 miscM.Mehdi Ounissi, M.Morwena Latouche and D.Daniel Racoceanu. Phagocytosis Unveiled: A Scalable and Interpretable Deep learning Framework for Neurodegenerative Disease Analysis.April 2023HAL
• 30 articleD.Daniel Racoceanu, M.Mehdi Ounissi and Y. L.Yannick L. Kergosien. Explainability in Artificial Intelligence; towards Responsible AI: Instanciation dans le domaine de la santé.Techniques de l'IngenieurDecember 2022HALDOI
• 31 articleA.Alexandre Routier, N.Ninon Burgos, M.Mauricio Diaz, 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, 689675HALDOI
• 32 articleJ.Jorge Samper-González, 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, 504-521HALDOI
• 33 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, 1-33HAL
• 34 articleS.Sophie Tezenas Du Montcel, E.Emilien Petit, T.Titilayo Olubajo, J.Jennifer Faber, P.Pauline Lallemant-Dudek, K.Khalaf Bushara, S.Susan Perlman, S.Sub Subramony, D.David Morgan, B.Brianna Jackman, H. L.Henry Lauris Paulson, G.Gülin Öz, T.Thomas Klockgether, A.Alexandra Durr and T.Tetsuo Ashizawa. Baseline Clinical and Blood Biomarker in Patients With Preataxic and Early-Stage Disease Spinocerebellar Ataxia 1 and 3.NeurologyFebruary 2023, 10.1212/WNL.0000000000207088HALDOI
• 35 articleE.Elina Thibeau-Sutre, M.Mauricio Diaz, R.Ravi Hassanaly, A. M.Alexandre M Routier, D.Didier Dormont, O.Olivier Colliot and N.Ninon Burgos. ClinicaDL: an open-source deep learning software for reproducible neuroimaging processing.Computer Methods and Programs in Biomedicine220June 2022, 106818HALDOI
• 36 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, 102357HALDOI
• 37 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 2019HALDOI
• 38 articleJ.Junhao Wen, E.Elina Thibeau-Sutre, M.Mauricio Diaz-Melo, J.Jorge Samper-González, 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, 101694HALDOI

11.2 Publications of the year