Lung, Computer applications, Oncology, PET-CT, Nuclear medicine conventional, Staging, Computer Applications-Detection, diagnosis, Decision analysis, Cancer
A. W. Sauter, G. Sommer, T. J. Weikert, K. S. Mader, J. Cyriac, A. Wallnoefer, B. Stieltjes; Basel/CH
Methods and materials
98 PET and CT image datasets from patients who underwent FDG-PET/CT for staging of NSCLC were extracted from the PACS and transferred to a 3D Slicer-based annotation software that allows for a manual tumor segmentation.
Tumor segmentation was performed by an experienced radiology and nuclear medicine physician.
For each patient a status of ‘diameter-based staging’ (n=50; DBS) or ‘morphological upstaging’ (n=48; MU) were assigned.
radiomics were compiled for each patient covering shape,
and PET textures (see bar plot for excerpt).
An ensemble of decision trees were then trained using these features to classify the cases and the most significant variables were taken as decision criteria (see bar plot).