Despite lymph node involvement (LNI) being one of the main prognostic factors in patients with prostate cancer (PCa), pelvic lymph node irradiation remains debated, possibly due to an insufficient selection of patients. Significant advances in LNI risk modelling have been achieved with the addition of visual interpretation of magnetic resonance imaging (MRI) data, but it is likely that quantitative analysis could further improve prediction models. In this study, the investigators aimed to develop and internally validate a novel LNI risk prediction model based on radiomic features extracted from pre-operative multimodal MRI.

Inclusion Criteria:

• Histologically proven adenocarcinoma of the prostate treated by prostatectomy with extensive lymph node dissection
• Available pre-operative +/- PET choline

Exclusion Criteria:

• Unanalyzable pre-operative MRI

The population consists of patients operated on for an adenocarcinoma of the prostate by radical prostatectomy with extensive lymph node dissection and for whom pre-operative MRI is available and analyzable.

All collected data that underlie results in a publication

Data will be available beginning three month and ending five years following the publication

Data access requests will be reviewed by the internal committee of Brest UH. Requestors will be required to sign and complete a data access agreement.