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

Recruiting

• Conditions: Healthy People; Benign Prostatic Hyperplasia; Prostate Cancer
• Interventions: Diagnostic Test: Prostatic or Pelvic MR; Diagnostic Test: Prostatic Biopsy

• Registration Number: NCT06589154
• Lead Sponsor: Shanghai Changzheng Hospital

Brief Summary

The application of multimodal data fusion in prostate cancer will bring new opportunities to improve diagnostic accuracy and treatment outcomes. By integrating imaging, genomics, pathology, and clinical data, we expect to realize precision medicine for prostate cancer and significantly improve the survival prognosis of patients.

Detailed Description

Prostate cancer stands as one of the most prevalent malignancies among men across the globe. Global cancer statistics reveal that the number of new prostate cancer diagnoses rises annually.

In recent years, the advent of multimodal data fusion technology has paved the way for innovative diagnostic and prognostic approaches in prostate cancer. For instance, the synergy of MRI imaging with clinical indicators such as PSA levels and Gleason scores not only refines the staging of prostate cancer but also sheds light on a patient's likely response to treatment and survival outlook.

The exponential growth of artificial intelligence, particularly the broad adoption of deep learning and machine learning algorithms, has emerged as a formidable asset in the realm of multimodal data analysis. By developing an AI-driven multimodal data fusion system, vast medical datasets can be efficiently processed, laying the groundwork for a more nuanced auxiliary diagnostic and therapeutic decision-making framework.

Study Timeline

• Study First Submitted: 2024-09-06
• Study First Submitted QC: 2024-09-06
• Study First Posted: 2024-09-19
• Study Start: 2024-10-10
• Status Verified: 2024-12
• Last Update Submitted: 2024-12-20
• Last Update Posted: 2024-12-27
• Primary Completion: 2025-09
• Study Completion: 2025-09

Recruitment & Eligibility

• Status: RECRUITING
• Sex: Male
• Target Recruitment: 1000

Inclusion Criteria

1. Male, 18-80 years of age;
2. Patients with normal prostate, prostatic hyperplasia, or prostate cancer who have undergone a prostate or pelvic magnetic resonance (MR) examination;
3. First visit on January 1, 2014 or later.

Exclusion Criteria

1. Patients with a diagnosis of any other malignancy within the previous 5 years;
2. Patients who have undergone transurethral resection or enucleation of the prostate prior to undergoing imaging;
3. Patients who are not suitable for participation in this clinical trial in the judgment of the investigator;

Patients who meet any of the above criteria may not be enrolled as subjects.

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Arm && Interventions

Group	Intervention	Description
Participants who are required to undergo prostatic or pelvic MR according to the investigators	Prostatic or Pelvic MR	-
Participants who are required to undergo prostatic or pelvic MR according to the investigators	Prostatic Biopsy	-

Primary Outcome Measures

Name	Time	Method
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

Name	Time	Method
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.

Trial Locations

Locations (1)

Shanghai Changzheng Hospital; 🇨🇳 Shanghai, Shanghai, China