Neural Networks for Nodal Staging of Non–Small Cell Lung Cancer with FDG PET and CT: Importance of Combining Uptake Values and Sizes of Nodes and Primary Tumor

摘要

We have demonstrated that an artificial neural network can be used to synthesize multiple parameters from fluorine 18 fluorodeoxyglucose positron emission tomography (PET)/computed tomography to predict non–small cell lung cancer nodal status with consistently high accuracy (mean, 99.2% ± 0.8) surpassing that of an expert PET reader.