The Application of Multimodal Artificial Intelligence Systems in Prostate Cancer Diagnosis and Prognosis Analysis

Prostate-specific antigen (PSA) testing has limited specificity for prostate cancer diagnosis, leading to a high rate of unnecessary biopsies. This multi-center study aims to develop and validate a non-invasive, multi-modal artificial intelligence model that combines cell-free DNA (cfDNA) profiles with multi-parametric MRI (mpMRI). The primary goal is to improve the accuracy of prostate cancer detection and risk stratification, particularly for men with PSA levels in the 4-10 ng/mL "gray zone," thereby providing a robust tool to guide clinical decision-making and reduce avoidable invasive procedures.

Study Overview

• Status: Completed
• Conditions: Benign Prostatic Hyperplasia; Prostate Cancer; Healthy People
• Intervention / Treatment: Diagnostic test: Multi-modal artificial intelligence model (BEAM)

Detailed Description

Prostate cancer is a leading cause of cancer morbidity in men globally. The current diagnostic pathway, heavily reliant on PSA levels, is particularly challenging in the 4-10 ng/mL "gray zone," where its inability to reliably distinguish benign conditions from cancer results in a substantial number of unnecessary biopsies and the overtreatment of indolent disease.

While advanced non-invasive methods like cfDNA analysis and mpMRI have shown individual promise, each possesses inherent limitations when used as a standalone tool. cfDNA assays can lack sensitivity due to low tumor fraction, and mpMRI interpretation is subject to variability and has suboptimal accuracy. This study hypothesizes that a synergistic fusion of these complementary data modalities-integrating the systemic molecular information from cfDNA with the localized anatomical and functional data from mpMRI-can overcome these limitations.

To test this hypothesis, we developed a multimodal Model, an end-to-end deep learning framework. This study was designed to rigorously develop and validate the BEAM model across a large, multi-center population, including a retrospective discovery cohort and two prospective validation cohorts. The ultimate goal is to establish a powerful, non-invasive tool that can accurately detect prostate cancer and, critically, stratify patients by risk of clinically significant disease, thereby personalizing patient management.

• Study Type: Observational
• Enrollment (Actual): 1651

Contacts and Locations

Study Locations

• China
  • Beijing Municipality
    • Beijing, Beijing Municipality, China, 100021
      • Cancer hospital, Chinese Academy of Medical Sciences
  • Guangdong
    • Guangzhou, Guangdong, China, 510120
      • The First Affiliated Hospital of Guangzhou Medical University
  • Jiangsu
    • Nanjing, Jiangsu, China
      • Zhongda Hospital, Southeast University
    • Nanjing, Jiangsu, China, 210029
      • Jiangsu Provincial People's Hospita
    • Suzhou, Jiangsu, China, 215006
      • the First Affiliated Hospital of Soochow University
    • Yangzhou, Jiangsu, China, 225001
      • Northern Jiangsu People's Hospita
  • Shanghai Municipality
    • Shanghai, Shanghai Municipality, China, 200433
      • Changhai Hospital
    • Shanghai, Shanghai Municipality, China, 201209
      • Shanghai Changzheng Hospital
  • Sichuan
    • Chengdu, Sichuan, China, 610041
      • West China Hospital, Sichuan University
  • Zhejiang
    • Ningbo, Zhejiang, China, 315010
      • Ningbo No. 1 Hospita

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

• Sampling Method: Probability Sample

Study Population

People who are required to undergo prostatic or pelvic magnetic resonance (MR) examination

Description

Inclusion Criteria:

• Men aged 18-80 years with a clinical indication for prostate or pelvic magnetic resonance (MR) examination.
• Patients with normal prostate, benign prostatic hyperplasia, or prostate cancer.
• First visit on January 1, 2014, or later.

Exclusion Criteria:

• Diagnosis of any other malignancy within the previous 5 years.
• Prior transurethral resection or enucleation of the prostate before imaging.
• Any condition deemed by the investigator to make the patient unsuitable for study participation.

Study Plan

How is the study designed?

Number of groups / cohorts

3

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Discovery cohort; Participants with PSA levels >4 ng/mL and had undergone prostatic biopsy and mpMR according to the investigators retrospectively.	Diagnostic test: Multi-modal artificial intelligence model (BEAM); Data from mpMRI and cfDNA analysis will be integrated and processed by deep learning. The model's output will be compared against the final pathological diagnosis from the prostate biopsy to evaluate its performance.
Prospective internal validation cohort; Patients who are scheduled for prostate biopsy and mpMR, with PSA levels in the 4-10 ng/mL gray zone, will be consented and enrolled in this group prospectively.	Diagnostic test: Multi-modal artificial intelligence model (BEAM); Data from mpMRI and cfDNA analysis will be integrated and processed by deep learning. The model's output will be compared against the final pathological diagnosis from the prostate biopsy to evaluate its performance.
Prospective external validation cohort; Patients who are scheduled for prostate biopsy and mpMR, with PSA levels in the 4-10 ng/mL gray zone, will be consented and enrolled in this group prospectively.	Diagnostic test: Multi-modal artificial intelligence model (BEAM); Data from mpMRI and cfDNA analysis will be integrated and processed by deep learning. The model's output will be compared against the final pathological diagnosis from the prostate biopsy to evaluate its performance.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Time Frame
Sensitivity of Prostate Cancer Multimodal Model in Predicting Prostate Biopsy Pathology Outcomes (Benign or Malignant)	Through completion of study and all data analysis which may take up to one year.
Specificity of Prostate Cancer Multimodal Model in Predicting Prostate Biopsy Pathology Outcomes (Benign or Malignant)	Through completion of study and all data analysis which may take up to one year.
ROC value of Prostate Cancer Multimodal Model in Predicting Prostate Biopsy Pathology Outcomes (Benign or Malignant)	Through completion of study and all data analysis which may take up to one year.

Secondary Outcome Measures

Outcome Measure	Time Frame
ROC value of a Prostate Cancer Multimodal Model in Predicting the Pathological Outcomes of Gleason Score Categories (≤6, 7, ≥8) in Men Underwent for Prostate Biopsy	Through completion of study and all data analysis which may take up to one year.
Sensitivity of a Prostate Cancer Multimodal Model in Predicting the Pathological Outcomes of Gleason Score Categories (≤6, 7, ≥8) in Men Underwent for Prostate Biopsy	Through completion of study and all data analysis which may take up to one year.
Specificity of a Prostate Cancer Multimodal Model in Predicting the Pathological Outcomes of Gleason Score Categories (≤6, 7, ≥8) in Men Underwent for Prostate Biopsy	Through completion of study and all data analysis which may take up to one year.
ROC value of a Prostate Cancer Multimodal Model in Predicting Clinically Significant Prostate Cancer (csPCa) in Men Underwent Prostate Biopsy	Through completion of study and all data analysis which may take up to one year.
Sensitivity of a Prostate Cancer Multimodal Model in Predicting Clinically Significant Prostate Cancer (csPCa) in Men Underwent Prostate Biopsy	Through completion of study and all data analysis which may take up to one year.
Specificity of a Prostate Cancer Multimodal Model in Predicting Clinically Significant Prostate Cancer (csPCa) in Men Underwent Prostate Biopsy	Through completion of study and all data analysis which may take up to one year.

Collaborators and Investigators

• Sponsor: Shanghai Changzheng Hospital
• Collaborators: Changhai Hospital; Cancer Institute and Hospital, Chinese Academy of Medical Sciences; West China Hospital; The First Affiliated Hospital of Soochow University; The First Affiliated Hospital of Guangzhou Medical University; Zhongda Hospital; Ningbo No. 1 Hospital; Jiangsu Provincial People's Hospital; Northern Jiangsu People's Hospital

Study record dates

Study Major Dates

• Study Start (Actual): October 10, 2024
• Primary Completion (Actual): July 30, 2025
• Study Completion (Actual): July 30, 2025

Study Registration Dates

• First Submitted: September 6, 2024
• First Submitted That Met QC Criteria: September 6, 2024
• First Posted (Actual): September 19, 2024

Study Record Updates

• Last Update Posted (Estimated): September 2, 2025
• Last Update Submitted That Met QC Criteria: August 25, 2025
• Last Verified: August 1, 2025

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Urogenital Diseases; Genital Diseases; Genital Neoplasms, Male; Urogenital Neoplasms; Neoplasms by Site; Neoplasms; Genital Diseases, Male; Prostatic Diseases; Male Urogenital Diseases; Prostatic Neoplasms; Prostatic Hyperplasia
• Other Study ID Numbers: M_PCa

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No