A5024282327- Radiomics and Machine Learning in Medical Imaging
- Advanced X-ray and CT Imaging
- Medical Imaging Techniques and Applications
- MRI in cancer diagnosis
- Lung Cancer Diagnosis and Treatment
- Glioma Diagnosis and Treatment
- Radiopharmaceutical Chemistry and Applications
- Sarcoma Diagnosis and Treatment
- Pancreatic and Hepatic Oncology Research
- AI in cancer detection
- Ferroptosis and cancer prognosis
- Colorectal Cancer Treatments and Studies
Institut d'Imagerie Biomédicale
2018-2023
Laboratoire d'imagerie translationnelle en oncologie
2023
Institut Curie
2020-2023
Université Paris-Saclay
2018-2022
Inserm
2018-2022
Commissariat à l'Énergie Atomique et aux Énergies Alternatives
2018-2021
CEA Paris-Saclay
2018
Centre National de la Recherche Scientifique
2018
Textural and shape analysis is gaining considerable interest in medical imaging, particularly to identify parameters characterizing tumor heterogeneity feed radiomic models. Here, we present a free, multiplatform, easy-to-use freeware called LIFEx, which enables the calculation of conventional, histogram-based, textural, features from PET, SPECT, MR, CT, US images, or any combination imaging modalities. The application does not require programming skills was developed for professionals. goal...
Few methodological studies regarding widely used textural indices robustness in MRI have been reported. In this context, study aims to propose some rules compute reliable from multimodal 3D brain MRI. Diagnosis and post-biopsy MR scans including T1, post-contrast T2 FLAIR images thirty children with diffuse intrinsic pontine glioma (DIPG) were considered. The hybrid white stripe method was adapted standardize intensities. Sixty then computed for each modality different regions of interest...
Predicting H3.1, TP53, and ACVR1 mutations in DIPG could aid the selection of therapeutic options. The contribution clinical data multi-modal MRI were studied for these three predictive tasks. To keep maximum number subjects, which is essential a rare disease, missing considered. A model was proposed, collecting all available each patient, without performing any imputation. retrospective cohort 80 patients with confirmed at least one four MR modalities (T1w, T1c, T2w, FLAIR), acquired two...
Radiomics was proposed to identify tumor phenotypes noninvasively from quantitative imaging features. The present study aimed at investigating if radiomic features measured diagnosis time structural MRI can predict histone H3 mutations and overall survival of patients with diffuse intrinsic pontine glioma. To this end, 316 multimodal diagnostic 38 were extracted, three clinical parameters added. Two approaches for computing proposed: a global estimation spherical region interest defined...
<div>Abstract<p>Textural and shape analysis is gaining considerable interest in medical imaging, particularly to identify parameters characterizing tumor heterogeneity feed radiomic models. Here, we present a free, multiplatform, easy-to-use freeware called LIFEx, which enables the calculation of conventional, histogram-based, textural, features from PET, SPECT, MR, CT, US images, or any combination imaging modalities. The application does not require programming skills was...
Radiomics was proposed to identify tumor phenotypes non-invasively from quantitative imaging features. Calculating a large amount of information on images, allows the development reliable classification models. In multi-modal protocols, question arises adding an modality improve model performance. addition, in implementation clinical some modalities are not acquired or insufficient quality and cannot be reliably taken into account. Furthermore, multi-scanner studies generate variability...
<p>Well-known software programs that enable the calculation of radiomic features and associated characteristics.</p>
<p>A real-time complete example of radiomic feature calculation from a PET/MR scan, where the same volumes interest are used to extract PET and MR features.</p>
<p>Distribution of SUVpeak, Entropy, HGZE, and SRE in healthy tissues tumors as a function the voxel size: blue for 4x4x4 mm3, green 2x2x2 mm3 pink 1x1x1 mm3.</p>
<p>Examples of published articles that used LIFEx to produce results with biological or clinical impact.</p>
<p>Examples of published articles that used LIFEx to produce results with biological or clinical impact.</p>
<p>Well-known software programs that enable the calculation of radiomic features and associated characteristics.</p>
<p>A real-time complete example of radiomic feature calculation from a PET/MR scan, where the same volumes interest are used to extract PET and MR features.</p>
<p>Distribution of SUVpeak, Entropy, HGZE, and SRE in healthy tissues tumors as a function the voxel size: blue for 4x4x4 mm3, green 2x2x2 mm3 pink 1x1x1 mm3.</p>
<div>Abstract<p>Textural and shape analysis is gaining considerable interest in medical imaging, particularly to identify parameters characterizing tumor heterogeneity feed radiomic models. Here, we present a free, multiplatform, easy-to-use freeware called LIFEx, which enables the calculation of conventional, histogram-based, textural, features from PET, SPECT, MR, CT, US images, or any combination imaging modalities. The application does not require programming skills was...
Lung cancer, and more precisely, non-small cell lung cancer (NSCLC) is the leading cause of cancer-related mortality due to its high prevalence. Likewise, brain metastases from are most frequent type secondary tumors. Different prognostic scores have been proposed better stratify treatment metastases. More recently, GPA has updated considering two molecular characteristics in adenocarcinoma: EGFR ALK alterations. However, best our knowledge, crosstalk between imaging features currently used...
Abstract INTRODUCTION: ACVR1 mutations are found in about 25% of patients with diffuse intrinsic pontine glioma (DIPG). Recent work has identified the combination vandetanib and everolimus as a promising therapeutic approach for these patients. We investigate predictive power an AI model integrating clinical radiomic information to predict mutation. METHODS: This retrospective monocentric study includes 65 known status. Patients were scanned at diagnosis time least one four structural MRI...