A5029673123- Radiomics and Machine Learning in Medical Imaging
- Lung Cancer Diagnosis and Treatment
- Medical Imaging Techniques and Applications
- Advanced Radiotherapy Techniques
- Fibromyalgia and Chronic Fatigue Syndrome Research
- Heart Rate Variability and Autonomic Control
- MRI in cancer diagnosis
- Advanced X-ray and CT Imaging
- AI in cancer detection
- Musculoskeletal pain and rehabilitation
- Cancer Immunotherapy and Biomarkers
- Advanced MRI Techniques and Applications
- Functional Brain Connectivity Studies
- Colorectal Cancer Surgical Treatments
- Head and Neck Cancer Studies
- Ultrasound and Hyperthermia Applications
- Gastric Cancer Management and Outcomes
- Colorectal Cancer Screening and Detection
- Nuclear Physics and Applications
- Pain Management and Placebo Effect
Laboratoire de Traitement de l'Information Médicale
2019-2025
Inserm
2019-2025
Université de Bretagne Occidentale
2019-2024
McGill University
2022-2023
Edwards (United Kingdom)
2022
Abstract Multicenter studies are needed to demonstrate the clinical potential value of radiomics as a prognostic tool. However, variability in scanner models, acquisition protocols and reconstruction settings unavoidable radiomic features notoriously sensitive these factors, which hinders pooling them statistical analysis. A harmonization method called ComBat was developed deal with “batch effect” gene expression microarray data used “center-effect”. Our goal evaluate modifications allowing...
The aim of this retrospective multicentric study was to develop and evaluate a prognostic <sup>18</sup>F-FDG PET/CT radiomic signature in early-stage non–small cell lung cancer patients treated with stereotactic body radiotherapy (SBRT). <b>Methods:</b> Patients from 3 different centers (<i>n</i> = 27, 29, 8) were pooled constitute the training set, whereas fourth center 23) used as testing set. primary endpoint local control. tumor semiautomatically delineated PET images using fuzzy locally...
Chronic pain is a complex condition influenced by combination of biological, psychological and social factors. Using data from the UK Biobank (n = 493,211), we showed that spreads proximal to distal sites developed biopsychosocial model predicted number coexisting sites. This data-driven was used identify risk score classified various chronic conditions (area under curve (AUC) 0.70-0.88) pain-related medical (AUC 0.67-0.86). In longitudinal analyses, development widespread pain, spreading...
Purpose To facilitate the demonstration of prognostic value radiomics, multicenter radiomics studies are needed. Pooling radiomic features such data in a statistical analysis is however challenging, as they sensitive to variability scanner models, acquisition protocols and reconstruction settings, which often unavoidable multicentre retrospective analysis. A harmonization strategy called ComBat was utilized deal with “center-effect”. The goal present work integrate transfer learning (TL)...
To develop a radiomic model predicting nonresponse to induction chemotherapy in laryngeal cancers, from multicenter pretherapeutic contrast-enhanced computed tomography (CE-CT) and evaluate the benefit of feature harmonization such context.Patients (n = 104) eligible for preservation were included five centers. Primary tumor was manually delineated on CE-CT images. The following features extracted with an in-house software (MIRAS v1.1, LaTIM UMR 1101): intensity, shape, textural derived...
Abstract Chronic pain conditions are complex syndromes characterized by a mosaic of biological, psychological, and social factors. We derived predictive models for the number co- existing sites in UK Biobank identified common risk score that classified different chronic cross-sectional data, predicted development pain-free individuals, determined spreading to multiple or its recovery nine years later. The features with strongest prognosis included sleeplessness, feeling ‘fed-up’, tiredness,...
Programmed death-ligand 1 (PD-L1) expressions play a crucial role in guiding therapeutic interventions such as the use of tyrosine kinase inhibitors (TKIs) and immune checkpoint (ICIs) lung cancer. Conventional determination PD-L1 status includes careful surgical or biopsied tumor specimens. These specimens are gathered through invasive procedures, representing risk difficulties potential challenges getting reliable representative tissue samples. Using single center cohort 189 patients, our...
Introduction: Due to its comorbidities with other symptoms and lack of effective treatments, chronic pain is considered a complex disease. At the same time, advancements in brain imaging, spread machine learning methods, creation new diagnostic tools based on these technologies have demonstrated that may be an option for assisting healthcare professionals making decisions. However, growing body research neuroimaging suggests functional networks show dynamic changes connection strength as...