Diagnostic Value of an AI-Based Software Solution for the Automated Classification of Lesions in Prostate MRI

Status

Recruiting

Phases

Unknown

Study type

Observational

Source

DRKS

Registry ID

DRKS00035299

Enrollment

500

Registered

2025-04-10

Start date

2024-12-21

Completion date

Unknown

Last updated

2026-06-01

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

C61

Interventions

Group 1: The study includes patients aged 18 and older who have undergone a prostate MRI (either mpMRI with contrast agent or bpMRI without contrast agent) with a diagnostic image quality of PI-QUAL 4

Eligibility

Sex/Gender

All

Age

18 Years to No maximum

Inclusion criteria

Inclusion criteria: - Prostate MRI in-house (with contrast agent/mpMRI and without contrast agent/biparametric) - MRI (bpMRI), period starting from 2021 - Diagnostic image quality (PI-QUAL 4/5)

Exclusion criteria

Exclusion criteria: - Low image quality (PI-QUAL 3 or lower) - Status post focal therapies of the prostate such as high-intensity focused ultrasound (HIFU), vascular photodynamic therapy (VPT), radiation therapy, transurethral resection of the prostate (TUR-P), holmium laser enucleation of the prostate (HoLEP), prostate artery embolization (PAE)

Design outcomes

Primary

Measure	Time frame
Correct classification of prostate lesions (PI-RADS 1–5) with and without AI compared to the reference standard – overall PI-RADS / index lesion.	—

Countries

Germany

Contacts

Public ContactHüdanur Bayraktaroglu

Klinikum der Universität München, Klinik und Poliklinik für Radiologie

Huedanur.Bayraktaroglu@med.uni-muenchen.de089 4400 73620

Outcome results

None listed

Source: DRKS (via WHO ICTRP) · Data processed: Jun 11, 2026