The Development and Validation of MRI-AI-based Predictive Models for csPCa

NCT ID: NCT06842264

Last Updated: 2026-01-29

Basic Information

• Recruitment Status: RECRUITING
• Total Enrollment: 3000 participants
• Study Classification: OBSERVATIONAL
• Study Start Date: 2024-01-01
• Study Completion Date: 2029-12-31

Brief Summary

This study retrospectively included patients who underwent prostate magnetic resonance imaging (MRI) and subsequent ultrasound-guided prostate biopsy at Peking University First Hospital from January 2019 to December 2023, and prospectively enrolls patients from January 2024 to December 2029. Clinical information such as age, PSA levels, PI-RADS scores, and digital rectal examination findings are collected. A well-performing artificial intelligence model is employed to measure prostate volume, transitional zone volume, and lesion volume using MRI images. Furthermore, prostate-specific antigen density (PSAD), transitional zone-based prostate-specific antigen density (TZ-PSAD) and lesion-based prostate-specific antigen density (lesion-PSAD) are calculated using prostate volume, transitional zone volume and lesion volume. Utilizing the aforementioned data, machine learning predictive models for clinically-significant prostate cancer (csPCa) are developed and validated.

Detailed Description

This study retrospectively included patients who underwent prostate magnetic resonance imaging (MRI) and subsequent ultrasound-guided prostate biopsy at Peking University First Hospital from January 2019 to December 2023, and prospectively enrolls patients from January 2024 to December 2029. Clinical information such as age, PSA levels, PI-RADS scores, and digital rectal examination findings are collected. A well-performing artificial intelligence model is employed to measure prostate volume, transitional zone volume, and lesion volume using MRI images. Furthermore, prostate-specific antigen density (PSAD), transitional zone-based prostate-specific antigen density (TZ-PSAD) and lesion-based prostate-specific antigen density (lesion-PSAD) are calculated using prostate volume, transitional zone volume and lesion volume. Utilizing the aforementioned data, machine learning predictive models for clinically-significant prostate cancer (csPCa) are developed and validated

Conditions

Prostate Cancer

Study Design

• Observational Model Type: COHORT
• Study Time Perspective: PROSPECTIVE

Study Groups

cohort 1

Cohort 1 comprises patients who underwent prostate magnetic resonance imaging (MRI) at Peking University First Hospital between January 2024 and December 2029, followed by an ultrasound-guided prostate biopsy.

No interventions assigned to this group

Eligibility Criteria

Inclusion Criteria

• The interval between prostate MRI and biopsy within 3 months
• Integrity of related data

Exclusion Criteria

• PSA less than 50ng/ml
• Any treatment for PCa prior to either MRI or biopsy, including radical prostatectomy, radiotherapy, chemotherapy, and endocrine therapy
• Previous history of surgical treatment or 5α-reductase inhibitor therapy for benign prostatic hyperplasia
• Subjects undergoing MRI with an indwelling urinary catheter or suprapubic catheter
• Inadequate quality of MRI images

• Eligible Sex: MALE
• Accepts Healthy Volunteers: No

Sponsors

Peking University First Hospital

OTHER

Sponsor Role: lead

Responsible Party

Responsibility Role: SPONSOR

Principal Investigators

Yi LIU

Role: PRINCIPAL_INVESTIGATOR

Dept. of Urology, Peking University First Hospital

Locations

Peking University First Hospital

Beijing, , China

Site Status: RECRUITING

Countries

China

Central Contacts

Yi LIU

Role: CONTACT

liuyipkuhsc@163.com

+8613611035261

Yi LIU

Role: CONTACT

liuyipkuhsc@163.com

Other Identifiers

prostatemodel19-29

Identifier Type: -

Identifier Source: org_study_id