Using decision curve analysis to benchmark performance of a magnetic resonance imaging-based deep learning model for prostate cancer risk assessment.
Dominik DeniffelNabila AbrahamKhashayar NamdarXin DongEmmanuel SalinasLaurent MilotFarzad KhalvatiMasoom A HaiderPublished in: European radiology (2020)
• A 3D deep learning model applied to multiparametric MRI may help to prevent unnecessary prostate biopsies in patients eligible for MRI-targeted biopsy. • Owing to miscalibration, original risk estimates by the deep learning model require prior calibration to enable clinical utility. • Decision curve analysis confirmed a net benefit of using our calibrated deep learning model for biopsy decisions compared with alternative strategies, including PI-RADSv2 alone and in combination with prostate-specific antigen density.
Keyphrases
- deep learning
- prostate cancer
- magnetic resonance imaging
- risk assessment
- contrast enhanced
- artificial intelligence
- convolutional neural network
- machine learning
- end stage renal disease
- computed tomography
- ultrasound guided
- chronic kidney disease
- radical prostatectomy
- newly diagnosed
- magnetic resonance
- heavy metals
- fine needle aspiration
- drug delivery
- diffusion weighted imaging