Fully automatic segmentation of diffuse large B cell lymphoma lesions on 3D FDG-PET/CT for total metabolic tumour volume prediction using a convolutional neural network.

Paul Blanc-DurandSimon JégouSalim KanounAlina Berriolo-RiedingerCaroline Bodet-MilinFrançoise Kraeber-BodéréThomas CarlierSteven Le GouillRené-Olivier CasasnovasMichel MeignanEmmanuel Itti

Published in: European journal of nuclear medicine and molecular imaging (2020)

Our CNN is a promising tool for automatic detection and segmentation of lymphoma lesions, despite slight underestimation of TMTV. The fully automatic and open-source features of this CNN will allow to increase both dissemination in routine practice and reproducibility of TMTV assessment in lymphoma patients.

Keyphrases

convolutional neural network
deep learning
diffuse large b cell lymphoma
epstein barr virus
machine learning
end stage renal disease
ejection fraction
newly diagnosed
healthcare
primary care
prognostic factors
quality improvement
clinical practice
neural network
real time pcr