Predictive method for lung nodules volume doubling time based on a single chest CT examination

Abstract

The invention discloses a predictive method for lung nodule volume doubling time based on a single chest CT scanning, which comprises the following steps: feature data is generated based on samples of a sample set and features are extracted to obtain the first feature set, and a training feature set is determined; according to the training feature set and the calculation multiplication time, the prediction model is obtained; the CT image of the single chest examination of the patient to be predicted is input into the prediction model to obtain the predicted volume doubling time of the lung nodules. The invention can predict the volume doubling time of lung nodules.