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

Peking University

Status: Enrolling

Conditions: Prostate Cancer

Treatments: Procedure: MRI-AI guided cognitive prostate targeted biopsy; Procedure: Routine cognitive prostate targeted biopsy

Study type: Interventional

Funder types: Other

Identifiers

NCT06392737

AITB-002

Details and patient eligibility

About

The goal of this multicenter 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. 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?

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.

Full description

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.

Enrollment: 360 estimated patients

Sex: Male

Ages: 45 to 85 years old

Volunteers: No Healthy Volunteers

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.

Trial design

Primary purpose: Diagnostic

Allocation: Randomized

Interventional model: Parallel Assignment

Masking: Single Blind

---

360 participants in 2 patient groups

MRI-AI-guided cTB (AI-cTB) group

Experimental group

Description:

The trained AI algorithms were embedded into proprietary structured reporting software. Before prostate biopsy, the MR images of patients in the AI-cTB group were uploaded to the AI software. The prostate gland and suspicious lesions were annotated and highlighted by AI software. The urologists who were blinded to the picture archiving and communication system (PACS) and MRI reports read the AI findings at their discretion and then conducted 3-5 core TB at each suspicious lesion, followed by 12 core SB. If there was no suspicious lesion detected by the AI, only SB would be performed.

Treatment:

Procedure: MRI-AI guided cognitive prostate targeted biopsy

Routine cTB group

Experimental group

Description:

For patients in the cTB group, the MR images and reports were viewed by urologists preceding the biopsy. Then 3-5 core cTB were performed, followed by 12 core SB. In patients with negative MRI findings, only SB was performed. When urologists performed biopsies, ultrasound technicians and radiologists were present to provide necessary assistance.

Treatment:

Procedure: Routine cognitive prostate targeted biopsy