A5054657918- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- Functional Brain Connectivity Studies
- COVID-19 diagnosis using AI
- Statistical Methods and Inference
- Bayesian Modeling and Causal Inference
- Bayesian Methods and Mixture Models
- Advanced Neuroimaging Techniques and Applications
- Statistical Methods and Bayesian Inference
- Morphological variations and asymmetry
- Osteoarthritis Treatment and Mechanisms
- Dementia and Cognitive Impairment Research
- COVID-19 Clinical Research Studies
- Traditional Chinese Medicine Studies
- Advanced X-ray and CT Imaging
- Digital Imaging for Blood Diseases
- Body Composition Measurement Techniques
- Artificial Intelligence in Healthcare and Education
- Blind Source Separation Techniques
- Frailty in Older Adults
- Explainable Artificial Intelligence (XAI)
- Data Mining Algorithms and Applications
- Biomedical Text Mining and Ontologies
- Pancreatic and Hepatic Oncology Research
- Nutrition and Health in Aging
Université Paris Cité
2018
Délégation Paris 5
2018
Centre de Recherche des Cordeliers
2018
Laboratoire Traitement et Communication de l’Information
2018
Institut du Cerveau
2015-2017
Centre National de la Recherche Scientifique
2015-2017
Sorbonne Université
2015-2017
Centre de Mathématiques Appliquées
2015-2017
École Polytechnique
2015-2017
Inserm
2015-2017
The SARS-COV-2 pandemic has put pressure on intensive care units, so that identifying predictors of disease severity is a priority. We collect 58 clinical and biological variables, chest CT scan data, from 1003 coronavirus-infected patients two French hospitals. train deep learning model based scans to predict severity. then construct the multimodal AI-severity score includes 5 variables (age, sex, oxygenation, urea, platelet) in addition model. show neural network analysis CT-scans brings...
Computational pathology is revolutionizing the field of by integrating advanced computer vision and machine learning technologies into diagnostic workflows. It offers unprecedented opportunities for improved efficiency in treatment decisions allowing pathologists to achieve higher precision objectivity disease classification, tumor microenvironment description identification new biomarkers. However, potential computational personalized medicine comes with significant challenges, particularly...
Abstract Background The identification of patients with knee osteoarthritis (OA) likely to progress rapidly in terms structure is critical facilitate the development disease-modifying drugs. Methods Using 9280 magnetic resonance (MR) images (3268 patients) from Osteoarthritis Initiative (OAI) database , we implemented a deep learning method predict, MR and clinical variables including body mass index (BMI), further cartilage degradation measured by joint space narrowing at 12 months. Results...
This paper proposes a patient-specific supervised classification algorithm to detect seizures in long offline intracranial electroencephalographic (iEEG) recordings. The main idea of the proposed is combine set probabilistic classifiers, trained on dataset 1 s epochs, into weighted ensemble classifier which can be used analyze longer 5 data segments. method and evaluated 24 patients, all suffering from focal medically intractable epilepsy, Epilepsiae database. evaluation method, conducted...
As AI-based medical devices are becoming more common in imaging fields like radiology and histology, interpretability of the underlying predictive models is crucial to expand their use clinical practice. Existing heatmap-based methods such as GradCAM only highlight location features but do not explain how they contribute prediction. In this paper, we propose a new method that can be used understand predictions any black-box model on images, by showing input image would modified order produce...
Repeated failures in clinical trials for Alzheimer's Disease (AD) have raised a strong interest the prodromal phase of disease. A better understanding brain alterations during this early is crucial to diagnose patients sooner, estimate an accurate disease stage and give reliable prognosis. According recent evidence, structural are likely be sensitive markers progression. Neuronal loss translates specific spatiotemporal patterns cortical atrophy, starting enthorinal cortex spreading over...
Spatial Transcriptomics (spTx) offers unprecedented insights into the spatial arrangement of tumor microenvironment, initiation/progression and identification new therapeutic target candidates. However, spTx remains complex unlikely to be routinely used in near future. Hematoxylin eosin (H&E) stained histological slides, on other hand, are generated for a large fraction cancer patients. Here, we present novel deep learning-based approach multiscale integration with morphology (MISO). We...
The SARS-COV-2 pandemic has put pressure on Intensive Care Units, and made the identification of early predictors disease severity a priority. We collected clinical, biological, chest CT scan data, radiology reports from 1,003 coronavirus-infected patients two French hospitals. Among 58 variables measured at admission, 11 clinical 3 radiological were associated with severity. Next, using 506,341 images, we trained evaluated deep learning models to segment scans reproduce radiologists’...
Abstract The need for developing new biomarkers is increasing with the emergence of many targeted therapies. In this study, we used artificial intelligence (AI) to develop a multimodal model (PULS-AI) predicting survival solid tumor patients treated antiangiogenic treatments. Our retrospective, multicentric study included 616 7 different cancer types: renal cell carcinoma, colorectal hepatocellular gastrointestinal melanoma, breast cancer, and sarcoma. A set 196 was left out validation....
Abstract -- Background --The identification of patients with knee osteoarthritis (OA) likely to progress rapidly in terms structure is critical facilitate the development disease-modifying drugs. Methods --Using data from Osteoarthritis Initiative database (OAI), we implemented a Deep Learning method predict, baseline magnetic resonance images, further cartilage degradation, latter being measured by Joint Space Narrowing at 12 months. Results COR IW TSE our classification model achieved ROC...