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 in brain disorders, with an emphasis on imaging data. The core methodological domains of our team are: machine learning, data science, and medical image computing. These new approaches are applied to clinical research in brain disorders in collaboration with other teams of the ICM, clinical departments of the Pitié-Salpêtrière hospital and external partners. The main objectives of the team are thus two-fold: i) advance the state-of-the-art in the fields of machine learning and data science for healthcare, ii) build useful digital tools to better understand, diagnose and predict brain disorders and create the next generation of clinical trials.

We develop various clinical applications of our research, in particular in neurodegenerative disorders (Alzheimer's disease and other dementias, Parkinson's disease...), multiple sclerosis, and developmental disorders.

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 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.

3.3 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.

3.4 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.

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.

5.1 Chairing of major international conferences in medical image computing

• Olivier Colliot was Conference Chair at SPIE Medical Imaging (San Diego, USA)
• Ninon Burgos was General Chair of MIDL - Medical Imaging with Deep Learning 2024 (Paris, France)

5.2 Awards

• Ayse Gungor received the Best Poster award at the Congress of the European Neuro-ophthalmology Society - EUNOS 2024, Rotterdam, Netherlands.
• Olivier Colliot received the Outstanding Area Chair award at MICCAI - Medical Image Computing and Computer-Assisted Intervention (Marrakech, Morocco)

6.1 New software

7.1 Reproducibility in medical image computing: what is it and how is it assessed?

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

Medical image computing (MIC) is devoted to computational methods for analysis of medical imaging data and their assessment through experiments. It is thus an experimental science. Reproducibility is a cornerstone of progress in all experimental sciences. As in many other fields, there are major concerns that reproducibility is unsatisfactory in MIC. However, reproducibility is not a single concept but a spectrum, which is often misunderstood by researchers. Moreover, even though some measures have been put in place to promote reproducibility in the MIC community, it is unclear if they have been effective so far. The objectives of the present chapter are three-fold: i) to provide readers with the necessary concepts underlying reproducibility in MIC; ii) to describe the measures which have been put in place and assess some of them; iii) to sketch some possible new actions that could be taken. First, we present a conceptual framework which distinguishes between different types of reproducibility as well as the main building blocks of reproducible research. We then describe how reproducibility is currently assessed at the MICCAI (Medical Image Computing and Computer Assisted Interventions) conference. In particular, we perform a quantitative analysis of MICCAI reviews. It reveals that, on the matter of reproducibility, reviews are unreliable and uninformative. Furthermore, we unveil some bad practices of some of the authors. Finally, we summarize the current state of affairs and suggest some potential actions that could be discussed within the community to progress towards more reproducible research. We insist that reproducibility is a spectrum, that there will never be a "one-size-fits-all" model but that there is plenty of room for improvement across all types of reproducibility. The code and data to reproduce the results of this paper are available at: https://github.com/reproducibility-reviews/reproducibility-reviews.

More details in 82.

7.2 Automatic rating of incomplete hippocampal inversions evaluated across multiple cohorts

Participants: Lisa Hemforth, Baptiste Couvy-Duchesne, Kevin De Matos, Camille Brianceau, Claire Cury, Olivier Colliot [Correspondant].

Incomplete Hippocampal Inversion (IHI), sometimes called hippocampal malrotation, is an atypical anatomical pattern of the hippocampus found in about 20% of the general population. IHI can be visually assessed on coronal slices of T1 weighted MR images, using a composite score that combines four anatomical criteria. IHI has been associated with several brain disorders (epilepsy, schizophrenia). However, these studies were based on small samples. Furthermore, the factors (genetic or environmental) that contribute to the genesis of IHI are largely unknown. Large-scale studies are thus needed to further understand IHI and their potential relationships to neurological and psychiatric disorders. However, visual evaluation is long and tedious, justifying the need for an automatic method. In this paper, we propose, for the first time, to automatically rate IHI. We proceed by predicting four anatomical criteria, which are then summed up to form the IHI score, providing the advantage of an interpretable score. We provided an extensive experimental investigation of different machine learning methods and training strategies. We performed automatic rating using a variety of deep learning models (”conv5-FC3”, ResNet and ”SECNN”) as well as a ridge regression. We studied the generalization of our models using different cohorts and performed multi-cohort learning. We relied on a large population of 2,008 participants from the IMAGEN study, 993 and 403 participants from the QTIM and QTAB studies as well as 985 subjects from the UKBiobank. We showed that deep learning models outperformed a ridge regression. We demonstrated that the performances of the ”conv5-FC3” network were at least as good as more complex networks while maintaining a low complexity and computation time. We showed that training on a single cohort may lack in variability while training on several cohorts improves generalization (acceptable performances on all tested cohorts including some that are not included in training). The trained models will be made publicly available should the manuscript be accepted.

More details in 51.

7.3 Confidence intervals uncovered: Are we ready for real-world medical imaging AI?

Participants: Evangelia Christodoulou, Annika Reinke, Ninon Burgos, Sofiène Boutaj, Sophie Loizillon, Maëlys Solal, Gaël Varoquaux [Correspondant], Olivier Colliot [Correspondant], Lena Maier-Hein [Correspondant].

Medical imaging is spearheading the AI transformation of healthcare. Performance reporting is key to determine which methods should be translated into clinical practice. Frequently, broad conclusions are simply derived from mean performance values. In this paper, we argue that this common practice is often a misleading simplification as it ignores performance variability. Our contribution is threefold. (1) Analyzing all MICCAI segmentation papers (n = 221) published in 2023, we first observe that more than 50% of papers do not assess performance variability at all. Moreover, only one (0.5%) paper reported confidence intervals (CIs) for model performance. (2) To address the reporting bottleneck, we show that the unreported standard deviation (SD) in segmentation papers can be approximated by a second-order polynomial function of the mean Dice similarity coefficient (DSC). Based on external validation data from 56 previous MICCAI challenges, we demonstrate that this approximation can accurately reconstruct the CI of a method using information provided in publications. (3) Finally, we reconstructed 95% CIs around the mean DSC of MICCAI 2023 segmentation papers. The median CI width was 0.03 which is three times larger than the median performance gap between the first and second ranked method. For more than 60% of papers, the mean performance of the second-ranked method was within the CI of the first-ranked method. We conclude that current publications typically do not provide sufficient evidence to support which models could potentially be translated into clinical practice.

More details in 68.

7.4 Projected pooling loss for red nucleus segmentation with soft topology constraints

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

Deep learning is the standard for medical image segmentation. However, it may encounter difficulties when the training set is small. Also, it may generate anatomically aberrant segmentations. Anatomical knowledge can be potentially useful as a constraint in deep learning segmentation methods. In this paper, we propose a novel loss function based on projected pooling to introduce soft topological contraints. Our main application is the segmentation of the red nucleus from quantitative susceptibility mapping (QSM) which is of interest in parkinsonian syndromes. This new loss function introduces soft constraints on the topology by magnifying small parts of the structure to segment to avoid that they are discarded in the segmentation process. To that purpose, we use projection of the structure onto the three planes and then use a series of MaxPooling operations with increasing kernel sizes. These operations are performed both for the ground-truth and the prediction and the difference is computed to obtain the loss function. As a result, it can reduce topological errors as well as defects in the structure boundary. The approach is easy to implement and computationally efficient. When applied to the segmentation of the red nucleus from QSM data, the approach led to a very high accuracy (Dice 89.9%) and no topological errors. Moreover, the proposed loss function improved the Dice accuracy over the baseline when the training set was small. We also studied three tasks from the medical segmentation decathlon challenge (MSD) (heart, spleen, and hippocampus). For the MSD tasks, the Dice accuracies were similar for both approaches but the topological errors were reduced. We proposed an effective method to automatically segment the red nucleus which is based on a new loss for introducing topology constraints in deep learning segmentation.

More details in 48.

7.5 Automatic quality control of segmentation results using early epochs as data augmentation: application to choroid plexuses

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

The establishment of automated image segmentation methods in medical imaging allows the analysis of very large datasets. However, visual quality control (QC) of segmentation results is impractical in large datasets, hence the need for automatic QC. In this paper, we introduce a novel automatic approach for QC of segmentation results. We developed a QC deep learning model (referred to as QC model) that, for a given patient, predicts the accuracy of the corresponding automatic segmentation (in our work the Dice score) provided by a deep learning segmentation model (referred to as segmentation model) in the absence of a ground truth annotation. To train the QC model, we introduce data augmentation by using the early epochs of the segmentation model. These early epochs allow us to feed the training of the QC model with examples of poor segmentation. We applied our approach to the QC of automatic segmentation of the choroid plexuses of the brain from MRI in controls and patients with multiple sclerosis. However, the method is generic and could be used with any segmentation model. The experiments showed that the proposed approach is very effective for predicting the segmentation accuracy with a correlation coefficient of 0.92, an R2 of 0.763, a mean absolute error (MAE) of 0.078, and a mean squared error (MSE) of 0.009. Overall, this work shall provide a valuable tool for the automatic QC of segmentation results.

More details in 78.

7.6 The intriguing effect of frequency disentangled learning on medical image segmentation

Participants: Guanghui Fu, Olivier Colliot [Correspondant].

Deep models have been shown to tend to fit the target function from low to high frequencies (a phenomenon called the frequency principle of deep learning). One may hypothesize that such property can be leveraged for better training of deep learning models, in particular for segmentation tasks where annotated datasets are often small. In this paper, we exploit this property to propose a new training method based on frequency-domain disentanglement. It consists of three main stages. First, it disentangles the image into high- and low-frequency components. Then, the segmentation network model learns them separately (the approach is general and can use any segmentation network as backbone). Finally, feature fusion is performed to complete the downstream task. The method was applied to the segmentation of the red and dentate nuclei in Quantitative Susceptibility Mapping (QSM) data and to three tasks of the Medical Segmentation Decathlon (MSD) challenge under different training sample sizes. For segmenting the red and dentate nuclei and the heart, the proposed approach resulted in considerable improvements over the baseline (respectively between 8 and 16 points of Dice and between 5 and 8 points). On the other hand, there was no improvement for the spleen and the hippocampus. We believe that these intriguing results, which echo theoretical work on the frequency principle of deep learning, are of interest for the community.

More details in 70.

7.7 Border irregularity loss for automated segmentation of primary brain lymphomas on post-contrast MRI

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

Unlike for other brain tumors, there has been little work on the automatic segmentation of primary central nervous system (CNS) lymphomas. This is a challenging task due the highly variable pattern of the tumor and its boundaries. In this work, we propose a new loss function that controls border irregularity for deep learning-based automatic segmentation of primary CNS lymphomas. We introduce a border irregularity loss which is based on the comparison of the segmentation and it smoothed version. The border irregularity loss is combined with a previously proposed topological loss to better control the different connected components. The approach is general and can be used with any segmentation network. We studied a population of 99 patients with primary CNS lymphoma. 40 patients were isolated from the very beginning and formed the independent test set. The segmentations were performed on post-contrast T1-weighted MRI. The MRI were acquired in clinical routine and were highly heterogeneous. The proposed approach substantially outperformed the baseline across the various evaluation metrics (by 6 percent points of Dice, 40mm of Hausdorff distance and 6mm of mean average surface distance). However, the overall performance was moderate, highlighting that automatic segmentation of primary CNS lymphomas is a difficult task, especially when dealing with clinical routine MRI.

More details in 69.

7.8 Anosognosia is associated with increased prevalence and faster development of neuropsychiatric symptoms in mild cognitive impairment

Participants: Federica Cacciamani.

Both the loss of awareness for cognitive decline (a. k.a anosognosia) and neuropsychiatric symptoms (NPS) are common in patients with Alzheimer's disease (AD) dementia, even in prodromal stages, and may exacerbate functional impairment and negatively impact caregiver burden. Despite the high impact of these symptoms on patients and their caregivers, our knowledge of how they develop across the AD spectrum is limited. Here, we explored the cross-sectional and longitudinal associations between anosognosia and NPS in individuals with mild cognitive impairment (MCI). We included 237 participants from the Alzheimer's Disease Neuroimaging Initiative (ADNI) with a baseline clinical diagnosis of MCI. Everyday Cognition (ECog) questionnaire scores were used to measure complaints from participants and study-partners at baseline and annually over a mean of 4.29 years (standard deviation (SD) = 2.72). Anosognosia was defined as the study-partner having an ECog score greater or equal than 2.5/4 and the participant having an ECog score smaller technological 2.5/4 on their baseline measure and their last observation without more than two consecutive deviating observations during the follow-up period. The 12-item study-partner-rated Neuropsychiatric Inventory determined the presence or absence of specific NPS. Survival analyses were performed to analyze the frequency and temporal onset of NPS over time in individuals with and without anosognosia. Thirty-eight out of 237 participants displayed anosognosia. Groups had similar lengths of follow-up at baseline ( p > 0.9), though participants with anosognosia had lower MMSE scores ( p = 0.049) and a higher proportion of amyloid-positivity using PET ( p < 0.001. At baseline, the frequencies of agitation ( p = 0.029 ) and disinhibition ( p < 0.001 ) were higher in the anosognosia group compared to the non-anosognosia group. Survival analyses showed earlier onset of seven of the 12 NPS in the anosognosia group (p's < 0.001). Loss of awareness for cognitive decline is associated with greater frequency and earlier onset of NPS over time in participants with MCI. These results support the hypothesis of a potential common underlying neurophysiological process for anosognosia and NPS, a finding that needs to be addressed in future studies.

More details in 65

7.9 Contrast-enhanced to non-contrast-enhanced image translation to exploit a clinical data warehouse of T1-weighted brain MRI

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

Clinical data warehouses provide access to massive amounts of medical images, but these images are often heterogeneous. They can for instance include images acquired both with or without the injection of a gadolinium-based contrast agent. Harmonizing such data sets is thus fundamental to guarantee unbiased results, for example when performing differential diagnosis. Furthermore, classical neuroimaging software tools for feature extraction are typically applied only to images without gadolinium. The objective of this work is to evaluate how image translation can be useful to exploit a highly heterogeneous data set containing both contrast-enhanced and non-contrast-enhanced images from a clinical data warehouse. We propose and compare different 3D U-Net and conditional GAN models to convert contrast-enhanced T1-weighted (T1ce) into non-contrast-enhanced (T1nce) brain MRI. These models were trained using 230 image pairs and tested on 77 image pairs from the clinical data warehouse of the Greater Paris area. Validation using standard image similarity measures demonstrated that the similarity between real and synthetic T1nce images was higher than between real T1nce and T1ce images for all the models compared. The best performing models were further validated on a segmentation task. We showed that tissue volumes extracted from synthetic T1nce images were closer to those of real T1nce images than volumes extracted from T1ce images. We showed that deep learning models initially developed with research quality data could synthesize T1nce from T1ce images of clinical quality and that reliable features could be extracted from the synthetic images, thus demonstrating the ability of such methods to help exploit a data set coming from a clinical data warehouse.

More details in 41.

7.10 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 from research to clinical data 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 57.

7.11 Automated MRI quality assessment of brain T1-weighted MRI in clinical data warehouses: A transfer learning approach relying on artefact simulation

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

The emergence of clinical data warehouses (CDWs), which contain the medical data of millions of patients, has paved the way for vast data sharing for research. The quality of MRIs gathered in CDWs differs greatly from what is observed in research settings and reflects a certain clinical reality. Consequently, a significant proportion of these images turns out to be unusable due to their poor quality. Given the massive volume of MRIs contained in CDWs, the manual rating of image quality is impossible. Thus, it is necessary to develop an automated solution capable of effectively identifying corrupted images in CDWs. This study presents an innovative transfer learning method for automated quality con- trol of 3D gradient echo T1-weighted brain MRIs within a CDW, leveraging artefact sim- ulation. We first intentionally corrupt images from research datasets by inducing poorer contrast, adding noise and introducing motion artefacts. Subsequently, three artefact- specific models are pre-trained using these corrupted images to detect distinct types of artefacts. Finally, the models are generalised to routine clinical data through a transfer learning technique, utilising 3660 manually annotated images. The overall image quality is inferred from the results of the three models, each designed to detect a specific type of artefact. Our method was validated on an independent test set of 385 3D gradient echo T1-weighted MRIs. Our proposed approach achieved excellent results for the detection of bad quality MRIs, with a balanced accuracy of over 87%, surpassing our previous approach by 3.5 percent points. Additionally, we achieved a satisfactory balanced accuracy of 79% for the detection of moderate quality MRIs, outperforming our previous performance by 5 percent points. Our framework provides a valuable tool for exploiting the potential of MRIs in CDWs.

More details in 56.

7.12 Detecting brain anomalies in clinical routine with the $\beta$-VAE: Feasibility study on age-related white matter hyperintensities

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

This experimental study assesses the ability of variational autoencoders (VAEs) to perform anomaly detection in clinical routine, in particular the detection of age-related white matter lesions in brain MRIs acquired at different hospitals and gathered in a clinical data warehouse (CDW). We pre-trained a state-of-the-art -VAE on a healthy cohort of over 10,000 FLAIR MR images from the UK Biobank to learn the distribution of healthy brains. The model was then fine-tuned on a cohort of nearly 700 healthy FLAIR images coming from a CDW. We first ensured the good performance of our pre-trained model compared with the state-of-the-art using a widely used public dataset (MSSEG). We then validated it on our target task, age-related WMH detection, on ADNI3 and on a curated clinical dataset from a single-site neuroradiology department, for which we had manually delineated lesion masks. Next, we applied the fine-tuned VAE for anomaly detection in a CDW characterised by an exceptional heterogeneity in terms of hospitals, scanners and image quality. We found a correlation between the Fazekas scores extracted from the radiology reports and the volumes of the lesions detected by our model, providing a first insight into the performance of VAEs in a clinical setting. We also observed that our model was robust to image quality, which strongly varies in the CDW. However, despite these encouraging results, such approach is not ready for an application in clinical routine yet due to occasional failures in detecting certain lesions, primarily attributed to the poor quality of the images reconstructed by the VAE.

More details in 73.

7.13 Evaluation of pseudo-healthy image reconstruction for anomaly detection with deep generative models: Application to brain FDG PET

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

Over the past years, pseudo-healthy reconstruction for unsupervised anomaly detection has gained in popularity. This approach has the great advantage of not requiring tedious pixel-wise data annotation and offers possibility to generalize to any kind of anomalies, including that corresponding to rare diseases. By training a deep generative model with only images from healthy subjects, the model will learn to reconstruct pseudo-healthy images. This pseudo-healthy reconstruction is then compared to the input to detect and localize anomalies. The evaluation of such methods often relies on a ground truth lesion mask that is available for test data, which may not exist depending on the application. We propose an evaluation procedure based on the simulation of realistic abnormal images to validate pseudo-healthy reconstruction methods when no ground truth is available. This allows us to extensively test generative models on different kinds of anomalies and measuring their performance using the pair of normal and abnormal images corresponding to the same subject. It can be used as a preliminary automatic step to validate the capacity of a generative model to reconstruct pseudo-healthy images, before a more advanced validation step that would require clinician's expertise. We apply this framework to the reconstruction of 3D brain FDG PET using a convolutional variational autoencoder with the aim to detect as early as possible the neurodegeneration markers that are specific to dementia such as Alzheimer's disease.

More details in 50.

7.14 Recent advances in the open-source ClinicaDL software for reproducible neuroimaging with deep learning

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

We present ClinicaDL, an open-source software platform that aims at enhancing the reproducibility and rigor of research for deep learning in neuroimaging. We first provide an overview of the software platform and then focus on recent advances. Features of the software aim at addressing three key issues in the field: the lack of reproducibility, the methodological flaws that plague many published studies and the difficulties using neuroimaging datasets for people with little expertise in this application area. Key existing functionalities include automatic data splitting, checking for data leakage, standards for data organization and results storing, continuous integration and integration with Clinica for preprocessing, amongst others. The most prominent recent features are as follows. We now provide various data augmentation and synthetic data generation functions (both standard and advanced ones including motion and hypometabolism simulation). Continuous integration test data are now versioned using DVC (data version control). Tools for generating validation splits have been made more generic. We made major improvements regarding usability and performance. We now support multi-GPU training and automatic mixed precision (to exploit tensor cores). We created a graphical interface to easily generate training specifications. We allow tracking of experiments through standard tools (MLflow, Weights&Biases). We believe that ClinicaDL can contribute to enhance the trustworthiness of research in deep learning for neuroimaging. Moreover, its functionalities and coding practices may serve as inspiration for the whole medical imaging community, beyond neuroimaging.

More details in 72.

7.15 Leveraging healthy population variability in deep learning unsupervised anomaly detection in brain FDG PET

Participants: Maelys Solal, Ravi Hassanaly, Ninon Burgos [Correspondant].

Unsupervised anomaly detection is a popular approach for the analysis of neuroimaging data as it allows to identify a wide variety of anomalies from unlabelled data. It relies on building a subject-specific model of healthy appearance to which a subject's image can be compared to detect anomalies. In the literature, it is common for anomaly detection to rely on analysing the residual image between the subject's image and its pseudo-healthy reconstruction. This approach however has limitations partly due to the pseudo-healthy reconstructions being imperfect and to the lack of natural thresholding mechanism. Our proposed method, inspired by Z-scores, leverages the healthy population variability to overcome these limitations. Our experiments conducted on FDG PET scans from the ADNI database demonstrate the effectiveness of our approach in accurately identifying Alzheimer's disease related anomalies.

More details in 75.

7.16 SARA captures disparate progression and responsiveness in spinocerebellar ataxias

Participants: Emilien Petit [Correspondant], Sophie Tezenas du Montcel.

The Scale for Assessment and Rating of Ataxia (SARA) is a widely used clinical scale to assess cerebellar ataxia but faces some criticisms about the relevancy of all its items. To prepare for future clinical trials, we analyzed the progression of SARA and its items in several polyQ spinocerebellar ataxias (SCA) from various cohorts. Methods: We included data from patients with SCA1, SCA2, SCA3, and SCA6 from four cohorts (EUROSCA, RISCA, CRC-SCA, and SPATAX) for a total of 850 carriers and 3431 observations. Longitudinal progression of the SARA and its items was measured. Cohort, stage and genetic effects were tested. We looked at the respective contribution of each item to the total scale. Sensitivity to change of the scale and the impact of item removal was evaluated by calculating sample sizes needed in various scenarios. Longitudinal progression was significantly different between cohorts in SCA1, SCA2 and SCA3, the EUROSCA cohort having the fastest progression. Advanced stage patient were progressing slower in SCA2 and SCA6. Items were not contributing equally to the full scale through ataxia severity: gait, stance, hand-movement, and heel-shin contributed the most in early stage, and finger-chase, nose-finger, and sitting in later stages. Few items drove the sensitivity to change of SARA, but changes in the scale structure could not improve its sensitivity in all populations. SARA and its items progression pace showed high heterogeneity across cohorts and SCAs. However, no combinations of items improved the responsiveness in all SCAs or populations taken separately.

More details in 60.

7.17 Development and validation of CADA-PRO, a patient questionnaire measuring key cognitive, motor, emotional and behavioral Outcomes in CADASIL.

Participants: Cécile di Folco, Sophie Tezenas du Montcel [Correspondant].

Cerebral Small Vessel Disease (cSVD) of ischemic type, either sporadic or genetic, as Cerebral Autosomal Dominant Arteriopathy with Subcortical Infarcts and Leukoencephalopathy (CADASIL), can impact the quality of daily life on various cognitive, motor, emotional or behavioral aspects. No instrument has been developed to measure these outcomes from the patient's perspective. We thus aimed to develop and validate a patient-reported questionnaire. Methods In a development study, 79 items were generated by consensus between patients, family representatives and cSVD experts. A first sample of patients allowed assessing the feasibility (missing data, floor and ceiling effect, acceptability), internal consistency, and dimensionality of a first set of items. Thereafter, in a validation study, we tested a reduced version of the item set in a larger sample to assess the feasibility, internal consistency, dimensionality, test-retest reliability, concurrent validity, and sensitivity to change. The scale was developed in 44 cSVD patients and validated in a second sample of 89 individuals (including 43 patients with CADASIL and 46 with another cSVD). The final CADASIL Patient-Reported Outcome (CADA-PRO) scale comprised 18 items covering four categories of consequences (depression/anxiety, attention/executive functions, motor, daily activities) of the disease. The proportion of missing data was low, no item displayed major floor or ceiling effect. Both the internal consistency and test-retest reliability were good (Cronbach alpha=0.95, intraclass correlation coefficient=0.88). In patients with CADASIL, CADA-PRO scores correlated with the modified Rankin scale, Starkstein Apathy Scale (SAS), Hospital Anxiety and Depression scale (HAD), Working Memory Index, and Trail Making Test times. In patients with other cSVDs, CADA-PRO correlated only with HAD and SAS. The CADA-PRO may be an innovative instrument for measuring patient-reported outcomes in future cSVD trials. Full validation was obtained for its use in CADASIL patients, but further improvement is needed for its application in other cSVDs.

More details in 46.

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

Participants: Mehdi Ounissi, Morwena Latouche, 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 background make this task very challenging when processing time-lapse phase-contrast video microscopy. In this study, we introduce an end-to-end, scalable, and versatile real-time framework for quantifying and analyzing phagocytic activity. Our proposed pipeline is able to 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, by additionally providing essential deep learning algorithm optimization insights and solutions. Besides, 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. The method has been tested and validated on several public benchmarks by generating state-of-the art performances. To stimulate translational approaches and future studies, we release an open-source end-to-end pipeline and a unique microglial cells phagocytosis dataset for immune system characterization in neurodegenerative diseases research. This pipeline and the associated dataset will consistently crystallize future advances in this field, promoting the development of efficient and effective interpretable algorithms dedicated to the critical domain of neurodegenerative diseases' characterization.

More details in 59.

7.19 Virtual staining in paired setings

Participants: Mehdi Ounissi, Dominique Berrebi, Daniel Racoceanu [Correspondant].

Filled patent - EP 24 305 221.4, Europe, February 9, 2024, applicant: ICM (Institut du Cerveau et de la Moelle Épinière), "Device and method for generating n virtual immunohistochemical (IHC) stain images from one hematoxylin and eosin (H&E) stain image (virtual staining - paired images)".

7.20 Virtual staining in unpaired setings

Participants: Mehdi Ounissi, Dominique Berrebi, Daniel Racoceanu [Correspondent].

Filled patent - EP 24 305 224.8, region: Europe, filed on: February 9, 2024, applicant: ICM (Institut du Cerveau et de la Moelle Épinière), "Device and method for generating n virtual immunohistochemical (IHC) stain images from one hematoxylin and eosin (H&E) stain image (virtual staining - unpaired images)".

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 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
• 5 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
• 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 752021HALDOI
• 7 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
• 8 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
• 9 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
• 10 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
• 11 inproceedingsE.Evangelia Christodoulou, A.Annika Reinke, R.Rola Houhou, P.Piotr Kalinowski, S.Selen Erkan, C. H.Carole H Sudre, N.Ninon Burgos, S.Sofiène Boutaj, S.Sophie Loizillon, M.Maëlys Solal, N.Nicola Rieke, V.Veronika Cheplygina, M.Michela Antonelli, L. D.Leon D Mayer, M. D.Minu D Tizabi, M. J.M. Jorge Cardoso, A.Amber Simpson, P. F.Paul F Jäger, A.Annette Kopp-Schneider, G.Gaël Varoquaux, O.Olivier Colliot and L.Lena Maier-Hein. Confidence intervals uncovered: Are we ready for real-world medical imaging AI?MICCAI 2024 - Medical Image Computing and Computer-Assisted Intervention15010Lecture Notes in Computer ScienceMarrakech, MoroccoSpringer Nature SwitzerlandOctober 2024, 124-132HALDOI
• 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 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
• 16 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
• 17 articleC.Cécile Di Folco, A.Aude Jabouley, S.Sonia Reyes, C.Carla Machado, S.Stéphanie Guey, D.Dominique Hervé, F.Fanny Fernandes, J.Joseph Agossa, H.Hugues Chabriat and S.Sophie Tezenas Du Montcel. CADA-PRO, a patient questionnaire measuring key cognitive, motor, emotional and behavioral Outcomes in CADASIL.StrokeSeptember 2024, Online ahead of printHALDOI
• 18 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
• 19 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
• 20 articleR.Ravi Hassanaly, C.Camille Brianceau, M.Maëlys Solal, O.Olivier Colliot and N.Ninon Burgos. Evaluation of pseudo-healthy image reconstruction for anomaly detection with deep generative models: Application to brain FDG PET.Journal of Machine Learning for Biomedical Imaging2January 2024, 611HALDOI
• 21 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
• 22 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
• 23 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
• 24 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
• 25 articleS.Sophie Loizillon, S.Simona Bottani, S.Stéphane Mabille, Y.Yannick Jacob, A.Aurélien Maire, S.Sebastian Ströer, D.Didier Dormont, O.Olivier Colliot and N.Ninon Burgos. Automated MRI Quality Assessment of Brain T1-weighted MRI in Clinical Data Warehouses: A Transfer Learning Approach Relying on Artefact Simulation.Journal of Machine Learning for Biomedical Imaging2June 2024June 2024, 888-915HALDOI
• 26 articleS.Sophie Loizillon, S.Simona Bottani, A.Aurélien Maire, S.Sebastian Ströer, D.Didier Dormont, O.Olivier Colliot and N.Ninon Burgos. Automatic motion artefact detection in brain T1-weighted magnetic resonance images from a clinical data warehouse using synthetic data.Medical Image Analysis93April 2024, 103073HALDOI
• 27 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
• 28 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
• 29 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
• 30 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
• 31 articleE.Emilien Petit, T.Tanja Schmitz-Hübsch, G.Giulia Coarelli, H.Heike Jacobi, A.Anna Heinzmann, K.Karla Figueroa, S.Susan Perlman, C.Christopher Gomez, G.George Wilmot, J.Jeremy Schmahmann, S.Sarah Ying, T.Theresa Zesiewicz, H.Henry Paulson, V.Vikram Shakkottai, K.Khalaf Bushara, S.-H.Sheng-Han Kuo, M.Michael Geschwind, G.Guangbin Xia, S.Stefan Pulst, S.S. Subramony, C.Claire Ewenczyk, A.Alexis Brice, A.Alexandra Durr, T.Thomas Klockgether, T.Tetsuo Ashizawa and S.Sophie Tezenas Du Montcel. SARA captures disparate progression and responsiveness in spinocerebellar ataxias.Journal of NeurologyJune 2024HALDOI
• 32 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
• 33 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
• 34 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
• 35 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
• 36 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
• 37 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
• 38 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
• 39 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
• 40 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