Integrating Quantitative MRI and Artificial Intelligence to Improve Prostate Cancer Classification

This study evaluates how new magnetic resonance imaging (MRI) and artificial intelligence techniques improve the image quality and quantitative information for future prostate MRI exams in patients with suspicious of confirmed prostate cancer. The MRI and artificial intelligence techniques developed in this study may improve the accuracy in diagnosing prostate cancer in the future using less invasive techniques than what is currently used.

Study Overview

• Status: Recruiting
• Conditions: Prostate Carcinoma
• Intervention / Treatment: Other: Electronic Health Record Review; Procedure: 3 Tesla Magnetic Resonance Imaging

Detailed Description

PRIMARY OBJECTIVES:

I. To develop and evaluate quantitative dynamic contrast-enhanced (DCE)-MRI analysis techniques that minimize patient- and scanner-specific variabilities in the calculation of quantitative parameters.

II. To develop and evaluate diffusion weighted imaging (DWI) methods that reduce prostate geometric distortion due to patient- and scanner-specific susceptibility and eddy current effects.

III. To develop and evaluate multi-class deep learning models that systematically integrate quantitative multi-parametric (mp)-MRI features for accurate detection and classification of clinically significant prostate cancer (csPCa).

OUTLINE:

RETROSPECTIVE: Patients' medical records are reviewed.

PROSPECTIVE: Patients undergo additional 3 Tesla (T) MRI imaging over 30 minutes before, during, or after their standard of care 3T MRI for a total of 1.5 hours.

• Study Type: Observational
• Enrollment (Estimated): 275

Contacts and Locations

• Study Contact: Name: Nashla Barroso; Phone Number: (310) 794-7952; Email: nbarroso@mednet.ucla.edu

Study Locations

• United States
  • California
    • Los Angeles, California, United States, 90095
      • Recruiting
      • UCLA / Jonsson Comprehensive Cancer Center
      • Contact: Nashla Barroso; Phone Number: 310-794-7952; Email: nbarroso@mednet.ucla.edu
      • Principal Investigator: Kyung H. Sung, PhD

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (Adult, Older Adult)
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Patients at the University of California, Los Angeles (UCLA) who may have already undergone 3 T prostate multi-parametric MRI or were referred for 3 T multi-parametric prostate MRI prior to biopsy or radical prostatectomy.

Description

Inclusion Criteria:

• Male patients 18 years of age and older
• Clinical suspicion of prostate cancer or biopsy-confirmed prostate cancer
• Undergone or undergoing multi-parametric 3 T prostate MRI at the University of California at Los Angeles (UCLA)
• Ability to provide consent

Exclusion Criteria:

• Contraindications to MRI (e.g., cardiac devices, prosthetic valves, severe claustrophobia)
• Contraindications to gadolinium contrast-based agents other than the possibility of an allergic reaction to the gadolinium contrast-based agent
• Prior radiotherapy

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Observational (electronic health record review, 3 T MRI); RETROSPECTIVE: Patients' medical records are reviewed. PROSPECTIVE: Patients undergo additional 3T MRI imaging over 30 minutes before, during, or after their standard of care 3T MRI for a total of 1.5 hours.	Other: Electronic Health Record Review; Medical charts are reviewed; Procedure: 3 Tesla Magnetic Resonance Imaging; Undergo 3T MRI; Other Names: 3T MRI; 3 Tesla MRI

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Development of quantitative dynamic contrast (DCE)-enhanced-magnetic resonance imaging (MRI) analysis techniques	Both transfer constant (Ktrans) and rate constant (Kep) from normal prostate tissue will be evaluated for the inter-scanner variability. Pairwise dissimilarities between distributions will be estimated by computing the Kolmogorov-Smirnov statistic, defined as the maximum difference between the empirical distribution functions over the range of the parameter, using 200 cases for each of three MRI scanners. The mean of these pairwise dissimilarities between scanners will be computed to quantify the overall discrepancy of each DCE-MRI model. Construction of a 95% confidence interval for the difference in the mean discrepancies using the nonparametric bootstrap will be done to compare this mean discrepancy between DCE-MRI models. 10,000 bootstrap samples will be generated by sampling patients with replacement, stratifying by the scanner. Will conclude that the proposed DCE-MRI model has a reduced inter-scanner variability if the 95% confidence interval is entirely less than zero.	Up to 5 years
Development of diffusion weighted imaging (DWI) methods that reduce prostate geometric distortion	Differences between rectangular field of view-ENCODE and standard DWI in terms of the prostate Dice's similarity coefficient (primary outcome) and apparent diffusion coefficient consistency will be compared.	Up to 5 years
Development of multi-class deep learning models	The overall performance of FocalNet and Prostate Imaging Reporting & Data System version 2 will be compared in terms of area under the curve. Comparison between area under the curves will be performed using DeLong's test. Will also include the comparison between FocalNet and baseline deep learning methods (U-Net and Deeplab without focal loss [FL] and mutual finding loss [MFL]) to characterize the advantages of using FL and MFL with the same study cohort. For each of these approaches, an optimal cut-point for classification of clinically significant prostate cancer will be identified by maximizing Youden's J (= sensitivity + specificity - 1) and will report sensitivity, specificity and 95% confidence intervals based on the selected cut-point.	Up to 5 years

Collaborators and Investigators

• Sponsor: Jonsson Comprehensive Cancer Center
• Collaborators: National Cancer Institute (NCI); National Institutes of Health (NIH)
• Investigators: Principal Investigator: Kyung H Sung, PhD, UCLA / Jonsson Comprehensive Cancer Center

Study record dates

Study Major Dates

• Study Start (Actual): April 1, 2021
• Primary Completion (Estimated): June 1, 2026
• Study Completion (Estimated): June 1, 2027

Study Registration Dates

• First Submitted: February 18, 2021
• First Submitted That Met QC Criteria: February 18, 2021
• First Posted (Actual): February 21, 2021

Study Record Updates

• Last Update Posted (Actual): April 16, 2024
• Last Update Submitted That Met QC Criteria: April 12, 2024
• Last Verified: April 1, 2024

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Neoplasms; Urogenital Neoplasms; Neoplasms by Site; Genital Neoplasms, Male; Prostatic Diseases; Urogenital Diseases; Male Urogenital Diseases; Genital Diseases, Male; Genital Diseases; Prostatic Neoplasms
• Other Study ID Numbers: 19-002202 (Other Identifier: UCLA / Jonsson Comprehensive Cancer Center); NCI-2021-00373 (Registry Identifier: CTRP (Clinical Trial Reporting Program)); R01CA248506 (U.S. NIH Grant/Contract); 441480-KS-29447 (Other Grant/Funding Number: NCI)

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No