A5026355368- Medical Imaging and Analysis
- Brain Tumor Detection and Classification
- Radiomics and Machine Learning in Medical Imaging
- Advanced Neuroimaging Techniques and Applications
- AI in cancer detection
- Botulinum Toxin and Related Neurological Disorders
- Bone and Joint Diseases
- Spine and Intervertebral Disc Pathology
- Advanced MRI Techniques and Applications
- Cervical and Thoracic Myelopathy
- Multiple Sclerosis Research Studies
- Neurological disorders and treatments
- Coral and Marine Ecosystems Studies
- Digital Imaging for Blood Diseases
- COVID-19 diagnosis using AI
- Spinal Fractures and Fixation Techniques
- Advanced Neural Network Applications
- Peripheral Nerve Disorders
- Spinal Dysraphism and Malformations
- Nerve Injury and Rehabilitation
- Marine Biology and Ecology Research
- Shoulder Injury and Treatment
- Traumatic Brain Injury Research
- Pain Management and Opioid Use
- Pituitary Gland Disorders and Treatments
Polytechnique Montréal
2017-2023
Mila - Quebec Artificial Intelligence Institute
2020-2023
University of Tasmania
2022-2023
National Imaging Facility
2021
The University of Queensland
2021
ARC Centre of Excellence in Advanced Molecular Imaging
2021
Université de Montréal
2017-2018
Hôpital Saint Eloi
1984
Hôpital Gui de Chauliac
1976-1984
Centre Hospitalier Universitaire de Montpellier
1979
Spinal cord lesions detected on MRI hold important diagnostic and prognostic value for multiple sclerosis. Previous attempts to correlate lesion burden with clinical status have had limited success, however, suggesting that location may be a contributor. Our aim was explore the spatial distribution of sclerosis in cervical spinal cord, respect status. We included 642 suspected or confirmed patients (31 clinically isolated syndrome, 416 relapsing-remitting, 84 secondary progressive, 73...
<h3>BACKGROUND AND PURPOSE:</h3> Our aim was to use 2D convolutional neural networks for automatic segmentation of the spinal cord and traumatic contusion injury from axial T2-weighted MR imaging in a cohort patients with acute injury. <h3>MATERIALS METHODS:</h3> Forty-seven who underwent 3T within 24 hours were included. We developed an image-analysis pipeline integrating whole intramedullary lesion segmentation. Linear mixed modeling used compare test results between our network (Brain...
Abstract In a companion paper by Cohen-Adad et al . we introduce the spine generic quantitative MRI protocol that provides valuable metrics for assessing spinal cord macrostructural and microstructural integrity. This was used to acquire single subject dataset across 19 centers multi-subject 42 (for total of 260 participants), spanning three main manufacturers: GE, Philips Siemens. Both datasets are publicly available via git-annex. Data were analysed using Spinal Cord Toolbox produce...
Despite important efforts to solve the clinico-radiological paradox, correlation between lesion load and physical disability in patients with multiple sclerosis remains modest. One hypothesis could be that location corticospinal tracts plays a key role explaining motor impairment. In this study, we describe distribution of lesions along from cortex cervical spinal cord various disease phenotypes status. We also assess link within tracts, at baseline 2-year follow-up. retrospectively included...
Spinal cord tumors lead to neurological morbidity and mortality. Being able obtain morphometric quantification (size, location, growth rate) of the tumor, edema, cavity can result in improved monitoring treatment planning. Such requires segmentation these structures into three separate classes. However, manual three-dimensional is time consuming, tedious prone intra- inter-rater variability, motivating development automated methods. Here, we tailor a model adapted spinal tumor task. Data...
There is an emerging need for biomarkers to better categorize clinical phenotypes and predict progression in amyotrophic lateral sclerosis. This study aimed quantify cervical spinal gray matter atrophy sclerosis investigate its association with disability at baseline after 1 year.Twenty-nine patients 22 healthy controls were scanned 3T MR imaging. Standard functional scale was recorded the time of imaging year. data processed automatically measure cord, matter, white cross-sectional areas. A...
Abstract A significant proportion of Southern Ocean seafloor biodiversity is thought to be associated with fragile, slow growing, long-lived, and habitat-forming taxa. Minimizing adverse impact these so-called vulnerable marine ecosystems (VMEs) a conservation priority that often managed by relying on fisheries bycatch data, combined threshold-based rules in which all “indicator” taxa are considered equal. However, VME indicator have different vulnerabilities fishing disturbance more...
Our experience is based on a series of 25 patients suffering from infantile dyskinesias and dystonias who underwent stereotaxic surgery basal ganglia.
Medical tasks are prone to inter-rater variability due multiple factors such as image quality, professional experience and training, or guideline clarity. Training deep learning networks with annotations from raters is a common practice that mitigates the model’s bias towards single expert. Reliable models generating calibrated outputs reflecting disagreement key integration of artificial intelligence in clinical practice. Various methods exist take into account different expert labels. We...
Human activity puts our oceans under multiple stresses, whose impacts are already significantly affecting biodiversity and physicochemical properties. Consequently, there is an increased international focus on the conservation sustainable use of oceans, including protection fragile benthic hotspots in deep sea, identified as vulnerable marine ecosystems (VMEs). International VME risk assessment efforts hampered because we largely do not know where VMEs located. distribution modelling has...
Background: Vascular risk factors such as arterial stiffness play an important role in the etiology of Alzheimer’s disease (AD), presumably due to emergence white matter lesions. However, impact structure involved AD, including corpus callosum remains poorly understood. Objective: The aims study are better understand relationship between stiffness, microstructure, and perfusion older adults. Methods: Arterial was estimated using gold standard measure carotid-femoral pulse wave velocity...
ivadomed is an open-source Python package for designing, end-to-end training, and evaluating deep learning models applied to medical imaging data.The includes APIs, commandline tools, documentation, tutorials.ivadomed also pre-trained such as spinal tumor segmentation vertebral labeling.Original features of include a data loader that can parse image subject metadata custom splitting or extra information during training evaluation.Any dataset following the Brain Imaging Data Structure (BIDS)...
Abstract Marine imagery is a comparatively cost-effective way to collect data on seafloor organisms, biodiversity and habitat morphology. However, annotating these images extract detailed biological information time-consuming expensive, reference libraries of consistently annotated are rarely publicly available. Here, we present the Antarctic Seafloor Annotated Imagery Database (AS-AID), result multinational collaboration collate annotate regional datasets from 19 research cruises between...