Machine learning-based analysis of [18F]DCFPyL PET radiomics for risk stratification in primary prostate cancer.
Matthijs C F CysouwBernard H E JansenTim van de BrugDaniela E Oprea-LagerElisabeth PfaehlerBart M de VriesReindert J A van MoorselaarOtto S HoekstraAndré N VisRonald BoellaardPublished in: European journal of nuclear medicine and molecular imaging (2020)
Machine learning-based analysis of quantitative [18F]DCFPyL PET metrics can predict LNI and high-risk pathological tumor features in primary PCa patients. These findings indicate that PSMA expression detected on PET is related to both primary tumor histopathology and metastatic tendency. Multicenter external validation is needed to determine the benefits of using radiomics versus standard PET metrics in clinical practice.
Keyphrases
- pet ct
- machine learning
- prostate cancer
- positron emission tomography
- pet imaging
- computed tomography
- clinical practice
- end stage renal disease
- small cell lung cancer
- ejection fraction
- artificial intelligence
- chronic kidney disease
- lymph node metastasis
- poor prognosis
- radical prostatectomy
- clinical trial
- prognostic factors
- magnetic resonance imaging
- high resolution
- deep learning
- magnetic resonance
- patient reported