Overview
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.
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.
Eligibility
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