A5021794500- Radiomics and Machine Learning in Medical Imaging
- Mathematical Biology Tumor Growth
- Medical Imaging Techniques and Applications
- Advanced Neuroimaging Techniques and Applications
- Glioma Diagnosis and Treatment
- Machine Learning in Materials Science
- MRI in cancer diagnosis
- RNA Research and Splicing
- Cancer Research and Treatments
- Lung Cancer Diagnosis and Treatment
- Prostate Cancer Treatment and Research
- Radiopharmaceutical Chemistry and Applications
- Advanced MRI Techniques and Applications
- Peptidase Inhibition and Analysis
Université Libre de Bruxelles
2021-2022
Erasmus Hospital
2019-2022
Recent works have demonstrated the added value of dynamic amino acid positron emission tomography (PET) for glioma grading and genotyping, biopsy targeting, recurrence diagnosis. However, most these studies are exclusively based on hand-crafted qualitative or semi-quantitative features extracted from mean time activity curve (TAC) within predefined volumes. Voxelwise PET data analysis could instead provide a better insight into intra-tumour heterogeneity gliomas. In this work, we investigate...
Reaction-diffusion models have been proposed for decades to capture the growth of gliomas, most common primary brain tumors. However, ill-posedness initialization at diagnosis time and parameter estimation such restrained their clinical use as a personalized predictive tool. In this work, we investigate ability deep convolutional neural networks (DCNNs) address commonly encountered pitfalls in field. Based on 1200 synthetic tumors grown over real geometries derived from magnetic resonance...
Diffuse gliomas are highly infiltrative tumors whose early diagnosis and follow-up usually rely on magnetic resonance imaging (MRI). However, the limited sensitivity of this technique makes it impossible to directly assess extent glioma cell invasion, leading sub-optimal treatment planing. Reaction-diffusion growth models have been proposed for decades extrapolate infiltration beyond margins visible MRI predict its spatial-temporal evolution. These nevertheless require an initial condition,...
Abstract BACKGROUND The survival of the patients with high-grade gliomas may be improved through a multidisciplinary approach including stereotactic re-irradiation such as Gamma-Knife at recurrence in selected population. We report our experience targeting hypermetabolic areas using 11C-Methionine PET/CT patients. MATERIAL AND METHODS retrospectively evaluated local response treated by for recurrent Institution between 2000 and 2018, area Methionine PET/CT. RESULTS included 25 bearing (14...
Purpose: The current study investigates the usefulness of metabolic positron emission tomography (PET) imaging (in particular with 11C-methionine (MET)), for target definition during gamma knife radiosurgery (GKRS) locally multirecurrent malignant glioma at inoperable stage. Patients and Methods: We retrospectively evaluated results GKRS MET-PET targeting 24 adult focally recurrent gliomas treated Erasme Gamma Knife Center between 2007 2018. type tumour progression (local vs remote),...
Reaction-diffusion models have been proposed for decades to capture the growth of gliomas, most common primary brain tumours. However, severe limitations regarding estimation initial conditions and parameter values such restrained their clinical use as a personalised tool. In this work, we investigate ability deep convolutional neural networks (DCNNs) address pitfalls commonly encountered in field. Based on 1,200 synthetic tumours grown over real geometries derived from magnetic resonance...