A Novel Framework for Automated Segmentation and Labeling of Homogeneous Versus Heterogeneous Lung Tumors in [18F]FDG-PET Imaging.

Motahare SoufiAlireza Kamali-AslParham GeramifarXinchi Hou

Published in: Molecular imaging and biology (2018)

We proposed and demonstrated an automatic framework for significantly improved segmentation and labeling of homogeneous vs. heterogeneous tumors in lung [18F]FDG-PET images.

Keyphrases

pet imaging
deep learning
convolutional neural network
positron emission tomography
machine learning
computed tomography
pet ct
high throughput