Comparison of MRI Artificial Intelligence-guided cTB Versus Routine cTB in Prostate Cancer Diagnosis

Cognitive fusion MRI-guided targeted biopsy (cTB) has been widely used in the diagnosis of prostate cancer (PCa). However, cTB relies heavily on the operator's experience and confidence in MRI readings. Our previously single-center RCT has demonstrated the effectiveness of accurately detecting clinically significant PCa (csPCa). The goal of this clinical trial is to compare the cancer detection rates of MRI artificial intelligence-guided cTB (AI-cTB) and routine cTB, and explore the added value of using AI for the guidance of cTB. This multicenter RCT aims to further validate the ability of MRI artificial intelligence in different institutions and investigate the generalizability of the MRI artificial intelligence assistant diagnosis system.

The main questions it aims to answer are:

Does AI-cTB promote the accurate diagnosis and treatment of prostate cancer? What's the value of prostate MRI artificial intelligence assistant diagnosis system in developing the best scheme of prostate biopsy? What's the value of prostate MRI artificial intelligence assistant diagnosis system in predicting the pathological results of prostate targeted biopsy? What's the generalizability of the MRI artificial intelligence assistant diagnosis system? This multicenter RCT compared the csPCa detection rates of the AI-cTB and routine cTB. Participants were prospectively enrolled at Peking University First Hospital (Beijing, China), Beijing Miyun District Hospital (Beijing, China), and Shanghai East Hospital (Shanghai, China) from May 2024 to April 2025.

Participants were randomly allocated to AI-cTB group and routine cTB group. Researchers will compare the cancer detection rates of AI-cTB and routine cTB to explore the added value of using AI for the guidance of cTB.

Participants will:

Receive AI-cTB or routine cTB.

Inclusion criteria

• The age of the patient is between 45 and 85.
• Patients with complete multiparametric magnetic resonance imaging (mpMRI) data, qualified image quality control, suspicious lesions, and Prostate Imaging Reporting and Data System version 2.1 (PI-RADS V2.1) of ≥ 3.
• Patients were in accordance with the indication of prostate biopsy, including patients with suspicious prostate nodes found by digital rectal examination (DRE), the suspicious lesions found by transrectal ultrasound (TRUS) or MRI, total prostate-specific antigen (tPSA) >10ng/mL, tPSA 4-10ng/mL with free-to-total PSA ratio (f/tPSA) <0.16 or PSA density (PSAD) >0.15.
• Patients were in accordance with the indication of repeated prostate biopsy (patients with atypical acinar hyperplasia or high-grade intraepithelial neoplasia, especially when the pathological results of multi-needle puncture were as above; re-examination of PSA > 10 ng/ml; re-examination of PSA 4~10ng/ml, abnormal f/tPSA, abnormal PSAD, abnormal DRE, or imaging abnormalities; for patients with the results of re-examination of PSA 4~10ng/ml and with close follow-up, PSA for 2 consecutive years > 10ng/ml or PSA volume > 0.75/ml/years). The time interval between the two prostate biopsies should be longer than three months.
• The targeted prostate biopsy pathological results of above lesions were complete. The time interval between targeted prostate biopsy and prostate mpMRI examination should not exceed one month.
• Patients with complete clinical information.

Exclusion criteria

• The mpMRI data was unqualified or incomplete.
• Patients had received radiotherapy, chemotherapy, androgen deprivation therapy, or surgery treatment before prostate mpMRI examination or prostate biopsy.
• The mpMRI did not find suspicious prostate lesions.
• Patients were not in accordance with the indication of prostate biopsy or were not received systematic biopsy combined with targeted biopsy.
• The patients could not cooperate to complete the systematic biopsy combined with targeted biopsy. The patients or their family members refused to participate in this study.
• Patients with incomplete clinical information.