A5030817992- Radiomics and Machine Learning in Medical Imaging
- Morphological variations and asymmetry
- AI in cancer detection
- Advanced MRI Techniques and Applications
- Medical Image Segmentation Techniques
- Medical Imaging Techniques and Applications
- Bayesian Methods and Mixture Models
- Liver Disease Diagnosis and Treatment
- Image Retrieval and Classification Techniques
- Prostate Cancer Diagnosis and Treatment
- Advanced X-ray and CT Imaging
- Brain Tumor Detection and Classification
- Dementia and Cognitive Impairment Research
- 3D Shape Modeling and Analysis
- Domain Adaptation and Few-Shot Learning
- Advanced Neural Network Applications
- Machine Learning in Healthcare
- Medical Imaging and Analysis
- COVID-19 diagnosis using AI
- MRI in cancer diagnosis
- Pancreatic and Hepatic Oncology Research
- Functional Brain Connectivity Studies
- Anatomy and Medical Technology
- Hepatocellular Carcinoma Treatment and Prognosis
- Artificial Intelligence in Healthcare
Guerbet (France)
2021-2025
Sorbonne Université
2017-2022
Centre National de la Recherche Scientifique
2017-2022
Inserm
2017-2022
Institut du Cerveau
2017-2021
Institut national de recherche en informatique et en automatique
2019-2020
Université Paris 1 Panthéon-Sorbonne
2019
Allen Institute for Brain Science
2018
Abstract Alzheimer’s disease (AD) is characterized by the progressive alterations seen in brain images which give rise to onset of various sets symptoms. The variability dynamics changes both and cognitive impairments remains poorly understood. This paper introduces AD Course Map a spatiotemporal atlas progression. It summarizes progression series neuropsychological assessments, propagation hypometabolism cortical thinning across regions deformation shape hippocampus. analysis these...
This monocentric retrospective study leveraged 200 multiparametric brain MRIs acquired between November 2019 and February 2020 at Gustave Roussy Cancer Campus (Villejuif, France). A total of 145 patients were included: 107 formed the training sample (55 ± 14 years, 58 women) 38 separate test (62 12 22 women). Patients had glioma, metastases, meningioma, or no enhancing lesion. T1, T2-FLAIR, diffusion-weighted imaging, low-dose, standard-dose postcontrast T1 sequences acquired. deep network...
Hepatocellular carcinoma is the most spread primary liver cancer across world ($\sim$80\% of tumors). The gold standard for HCC diagnosis biopsy. However, in clinical routine, expert radiologists provide a visual by interpreting hepatic CT-scans according to standardized protocol, LI-RADS, which uses five radiological criteria with an associated decision tree. In this paper, we propose automatic approach predict histology-proven from CT images order reduce radiologists' inter-variability. We...
Objective: The clinical aim of this work is to predict intraoperative LRC from preoperative CT scans only. Summary Background Data: Liver resection (LR) the most prevalent curative treatment for primary liver cancer, yet overall mortality/morbidity rates remain elevated. conventional definition and classification LR complexity (LRC) lack inclusion disease-induced 3D anatomical surgery complexity. Methods: models organ, tumors blood vessels were generated Deep Learning trained on patients...
The aim of this study was to evaluate a deep learning method designed increase the contrast-to-noise ratio in contrast-enhanced gradient echo T1-weighted brain magnetic resonance imaging (MRI) acquisitions. processed images are quantitatively evaluated terms lesion detection performance.A total 250 multiparametric MRIs, acquired between November 2019 and March 2021 at Gustave Roussy Cancer Campus (Villejuif, France), were considered for inclusion retrospective monocentric study. Independent...
Objectives This study proposes and evaluates a deep learning method to detect pancreatic neoplasms identify main duct (MPD) dilatation on portal venous computed tomography scans. Materials Methods A total of 2890 scans from 9 institutions were acquired, among which 2185 had neoplasm 705 healthy controls. Each scan was reviewed by one in group radiologists. Physicians contoured the pancreas, lesions if present, MPD visible. They also assessed tumor type dilatation. Data split into training...
We propose a method to learn distribution of shape trajectories from longitudinal data, i.e. the collection individual objects repeatedly observed at multiple time-points. The allows compute an average spatiotemporal trajectory changes group level, and variations this both in terms geometry time dynamics. First, we formulate non-linear mixed-effects statistical model as combination generic for manifold-valued deformation defining via action finite-dimensional set diffeomorphisms with...
Contrast-enhanced medical images offer vital insights for the accurate diagnosis, characterization and treatment of tumors, are routinely used worldwide. Acquiring such requires to inject patient intravenously with a gadolinium-based contrast agent (GBCA). Although GBCAs considered safe, recent concerns about their accumulation in body tilted consensus towards more parsimonious usage. Focusing on case brain magnetic resonance imaging, this paper proposes deep learning method that synthesizes...
Background and aimsDiagnosis of Hepatocellular Carcinoma (HCC) in cirrhotic patients relies on non-invasive criteria international guidelines. The advent systemic therapies motivates reconsideration the role biopsy. Accordingly, we investigated diagnostic performance Liver Imaging Reporting Data System (LI-RADS) 2018 American Association for Study Diseases (AASLD) 2011 criteria.MethodsConsecutive undergoing biopsy suspected HCC between 2015 2020 were included. available imaging (CT and/or...
Abstract We performed a systematic review of studies focusing on the automatic prediction progression mild cognitive impairment to Alzheimer’s disease (AD) dementia, and quantitative analysis methodological choices impacting performance. This included 172 articles, from which 234 experiments were extracted. For each them, we reported used data set, feature types, algorithm type, performance potential issues. The impact these characteristics was evaluated using multivariate mixed effect...
Antibody drug conjugates (ADCs) have revolutionized the treatment of many solid tumours and hematological diseases. Little is known about influence body composition on efficacy safety ADCs. All patients treated with ADCs in early phase clinical trials between 03/2015 03/2023 at Gustave Roussy were retrospectively included. A deep learning software (Anthropometer3DNet) automatically measured anthropometric parameters 3D pretreatment scans, allowing multi-slice measurements muscle mass (MBM),...
Abstract Background: Antibody drug conjugates (ADCs) have revolutionized the treatment of many solid tumours and hematological diseases. Little is known about influence body composition on efficacy safety ADCs. Methods: All patients treated with ADCs in early phase clinical trials between 03/2015 03/2023 at Drug Development Department Gustave Roussy were retrospectively included analysis. A deep learning software (Anthropometer3DNet) automatically measured anthropometric parameters 3D...