An integrated nomogram combining deep learning, Prostate Imaging–Reporting and Data System (PI-RADS) scoring, and clinical variables for identification of clinically significant prostate cancer on biparametric MRI: a retrospective multicentre study

EN BREF ...

"Biparametric MRI, which comprises T2-weighted MRI and apparent diffusion coefficient maps derived from diffusion-weighted imaging, is increasingly being used for the detection and characterisation of prostate cancer. The Prostate Imaging–Reporting and Data System (PI-RADS) has standardised the diagnosis of prostate cancer using MRI and is effective for characterisation of prostate cancer. However, MRI is still restricted by benign confounding appearances and substantial intra-reader and inter-reader variability. Therefore, Gleason grade grouping (GGG), which assigns a prostate cancer lesion to one of five categories based on invasive biopsies, remains the standard of care in determining the aggressiveness of prostate cancer. According to the 2017 European Association of Urology prostate cancer guidelines, patients with intermediate- risk and high-risk prostate cancer with clinically signifi- cant disease (defined as GGG ≥2 on pathology) are recommended a definitive treatment, such as radical prostatectomy, whereas those with very low-risk or low-risk disease (clinically insignificant prostate cancer, defined as GGG 1) and some with intermediate favourable risk (GGG 2) are recommended to follow an active surveillance strategy wherein patients are closely monitored without being provided any definitive treatment." En bref issu de l'étude.