18F-FDG PET/CT Uptake Classification in Lymphoma and Lung Cancer by Using Deep Convolutional Neural Networks
L Sibille, R Seifert, N Avramovic, T Vehren… - Radiology, 2020 - pubs.rsna.org
Background Fluorine 18 ( 18 F)−fluorodeoxyglucose (FDG) PET/CT is a routine tool for
staging patients with lymphoma and lung cancer. Purpose To evaluate configurations of deep …
staging patients with lymphoma and lung cancer. Purpose To evaluate configurations of deep …
Deep-learning 18F-FDG uptake classification enables total metabolic tumor volume estimation in diffuse large B-cell lymphoma
…, AS Cottereau, L Vercellino, L Sibille… - Journal of Nuclear …, 2021 - Soc Nuclear Med
Total metabolic tumor volume (TMTV), calculated from 18 F-FDG PET/CT baseline studies, is
a prognostic factor in diffuse large B-cell lymphoma (DLBCL) whose measurement requires …
a prognostic factor in diffuse large B-cell lymphoma (DLBCL) whose measurement requires …
[HTML][HTML] Whole-body uptake classification and prostate cancer staging in 68Ga-PSMA-11 PET/CT using dual-tracer learning
N Capobianco, L Sibille, M Chantadisai… - European journal of …, 2022 - Springer
Purpose In PSMA-ligand PET/CT imaging, standardized evaluation frameworks and image-derived
parameters are increasingly used to support prostate cancer staging. Clinical …
parameters are increasingly used to support prostate cancer staging. Clinical …
The autopet challenge: towards fully automated lesion segmentation in oncologic pet/ct imaging
We describe the results of the autoPET challenge, a biomedical image analysis challenge
aimed to motivate and focus research in the field of automated whole-body PET/CT image …
aimed to motivate and focus research in the field of automated whole-body PET/CT image …
[HTML][HTML] Evaluation of an automatic classification algorithm using convolutional neural networks in oncological positron emission tomography
P Pinochet, F Eude, S Becker, V Shah, L Sibille… - Frontiers in …, 2021 - frontiersin.org
Introduction: Our aim was to evaluate the performance in clinical research and in clinical
routine of a research prototype, called positron emission tomography (PET) Assisted Reporting …
routine of a research prototype, called positron emission tomography (PET) Assisted Reporting …
Whole-body tumor segmentation of 18f-fdg pet/ct using a cascaded and ensembled convolutional neural networks
Background: A crucial initial processing step for quantitative PET/CT analysis is the
segmentation of tumor lesions enabling accurate feature ex-traction, tumor characterization, …
segmentation of tumor lesions enabling accurate feature ex-traction, tumor characterization, …
PET uptake classification in lymphoma and lung cancer using deep learning
L Sibille, N Avramovic, B Spottiswoode, M Schaefers… - 2018 - Soc Nuclear Med
325 Objectives: The interpretation of 18 F-Fluorodeoxyglucose (FDG) PET/CT images is
challenging given the sources of variability such as data acquisition, reconstruction methods …
challenging given the sources of variability such as data acquisition, reconstruction methods …
Transfer learning of AI-based uptake classification from 18F-FDG PET/CT to 68Ga-PSMA-11 PET/CT for whole-body tumor burden assessment
N Capobianco, A Gafita, G Platsch, L Sibille… - 2020 - Soc Nuclear Med
1411 Objectives: PET-derived tumor burden biomarkers have shown promising results for risk
stratification and response assessment 1 2 3 . Their measurement requires detection of all …
stratification and response assessment 1 2 3 . Their measurement requires detection of all …
An AI system to determine reconstruction parameters and improve PET image quality
F Gao, V Shah, L Sibille, S Zuehlsdorff - 2018 - Soc Nuclear Med
31 Objectives: PET/CT scans typically involve complex, configurable workflows and scan
protocols to image different tracers in patients with different conditions. Artificial Intelligence (AI) …
protocols to image different tracers in patients with different conditions. Artificial Intelligence (AI) …
Multitask learning-to-rank neural network for predicting survival of diffuse large B-cell lymphoma patients from their unsegmented baseline [18F] FDG-PET/CT scans.
3250 Introduction: A common way to train a neural network on censored follow-up data is to
combine a neural network with a Cox proportional hazards model (eg DeepSurv). In this …
combine a neural network with a Cox proportional hazards model (eg DeepSurv). In this …