Radiomics analysis of 18F-Choline PET/CT in the prediction of disease outcome in high-risk prostate cancer: an explorative study on machine learning feature classification in 94 patients.
Pierpaolo AlongiAlessandro StefanoAlbert ComelliRiccardo LaudicellaSalvatore ScalisiGiuseppe ArnoneStefano BaroneMassimiliano SpadaPierpaolo PurpuraTommaso Vincenzo BartolottaMassimo MidiriRoberto LagallaGiorgio RussoPublished in: European radiology (2021)
• Artificial intelligence applications are feasible and useful to select Cho-PET features. • Our model demonstrated the presence of specific features for T, N, and M with valuable association with high-risk PCa patients' outcomes. • Further prospective studies are necessary to confirm our results and to develop the application of artificial intelligence in PET imaging of PCa.
Keyphrases
- artificial intelligence
- machine learning
- deep learning
- pet ct
- prostate cancer
- end stage renal disease
- big data
- pet imaging
- ejection fraction
- newly diagnosed
- chronic kidney disease
- positron emission tomography
- prognostic factors
- computed tomography
- peritoneal dialysis
- type diabetes
- adipose tissue
- radical prostatectomy
- skeletal muscle
- patient reported