MRI and Radiomics Evaluation for Prostate Cancer

(MRI-PREDICT Trial)

Overseen By Beverly A Lieuwen, BSc

Age: Any Age

Sex: Male

Trial Phase: Academic

Sponsor: Nova Scotia Health Authority

Disqualifiers: Past prostatic interventions, others

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Approved in 3 Jurisdictions This treatment is already approved in other countries

Compensation: Varies

Number of Visits: 2

60 Participants Needed

Trial Summary

What is the purpose of this trial?

Prostate cancer is the most common cancer diagnosed in men in Canada. Magnetic resonance imaging (MRI) may become a valuable tool to non-invasively identify prostate cancer and assess its biological aggressiveness, which in turn will help doctors make better decisions about how to treat an individual patient's prostate cancer. Despite the promise of MRI for detecting and characterizing prostate cancer, there are several recognized limitations and challenges. These include lack of standardized interpretation and reporting of prostate MRI exams. The investigators propose to validate and improve a computer program computerized prediction tool that will use information from MR images to inform us how aggressive a prostate cancer is. The hypothesis is that this computer-aided approach will increase the reproducibility and accuracy of MRI in predicting the tumor biology information about the imaged prostate cancer.

Do I need to stop my current medications for the trial?

The trial information does not specify whether you need to stop taking your current medications.

What data supports the effectiveness of the treatment MRI of the Prostate Combined with Radiomics Evaluation for prostate cancer?

Research shows that using MRI with radiomics (a method that analyzes medical images) can help distinguish between more serious and less serious prostate cancer, predict how long patients might live without the cancer getting worse, and assess the likelihood of cancer spreading beyond the prostate. ^{1 2 3 4 5}

Is MRI and Radiomics Evaluation for Prostate Cancer safe for humans?

Multiparametric MRI (mpMRI) is widely used for prostate cancer detection and is considered safe for humans. It is a non-invasive imaging technique that helps in diagnosing and managing prostate cancer without significant safety concerns. ^{6 7 8 9 10}

How does the MRI and Radiomics Evaluation treatment for prostate cancer differ from other treatments?

This treatment is unique because it uses multiparametric MRI (mpMRI) combined with radiomics, which involves extracting detailed data from medical images to better detect and categorize prostate cancer. This approach aims to improve the accuracy of diagnosis and treatment planning by providing a more comprehensive analysis of the tumor's characteristics, potentially reducing the need for invasive procedures like biopsies. ^{3 4 7 11 12}

Research Team

Dr. Michael Kucharczyk

Principal Investigator

Nova Scotia Health Authority

Eligibility Criteria

This trial is for men in Canada with prostate cancer who have had a specific type of MRI at the Halifax Infirmary and a diagnostic biopsy showing at least one nodule corresponding to cancer. They must not have altered testosterone levels, past interventions affecting prostate structure, or conditions causing significant MRI artifacts.

Inclusion Criteria

- Being performed on 3T MRI at the Halifax Infirmary Building

- Acquired T1+contrast, T2, and attenuated diffusion coefficient (ADC) series axial images of the prostate

- Having a detectable nodule which anatomically localizes to prostate cancer (PCa) identified in diagnostic biopsy specimen

Exclusion Criteria

Alterations to physiological testosterone levels

Inability to position one's self in a reproducible fashion for an MRI-P

Patient factors reported to produce significant artifact on MRI-P 1

Timeline

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Baseline MRI-P

Participants undergo the first MRI-P as part of the standard of care

Baseline

1 visit (in-person)

Follow-up MRI-P

Participants undergo a second MRI-P to assess the stability of MRT classification

8 weeks

1 visit (in-person)

Follow-up

Participants are monitored for the accuracy and stability of MRT classification compared to biopsy results

8 weeks

Treatment Details

Interventions

• MRI of the Prostate Combined with Radiomics Evaluation

Trial Overview The study aims to validate and enhance a computer program that uses MR images to predict the aggressiveness of prostate cancer. It will assess if this tool can improve the standardization and accuracy of MRI evaluations in determining tumor biology.

Participant Groups

Group I: Prospective Cohort Experimental Treatment 2 Interventions

Sixty patients with a new diagnosis of prostate cancer that meet eligibility criteria. The group will have two standard MRI-P's completed. The first MRI-P will be acquired as standard of care and the second will be an additional investigation for the purposes of this study. The efficacy of the MRT will be compared at both time points, evaluating if the MRT demonstrates clinically sufficient stability in its findings (i.e., does the MRT report an accurate and similar result at both time points).

Who Is Running the Clinical Trial?

Nova Scotia Health Authority

Lead Sponsor

Trials

302

Recruited

95,300+

Findings from Research

A multimodal MRI-based radiomics nomogram was developed and validated using data from 141 training cases and 182 external validation cases, showing improved accuracy in predicting clinically significant prostate cancer (CS-PCa) compared to traditional evaluations.

The nomogram, which combines a radiomics signature derived from MRI scans with the PI-RADS scoring system, significantly outperformed subjective assessments in all datasets, indicating its potential for noninvasive and precise cancer prediction.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Prediction of clinically significant prostate cancer with a multimodal MRI-based radiomics nomogram. Jing, G., Xing, P., Li, Z., et al.[2022]

A hybrid model combining MRI radiomics features and clinical data was highly effective in predicting progression-free survival (PFS) in prostate cancer patients, achieving AUCs of 0.926 in the training group and 0.917 in the validation group based on a study of 191 patients.

The developed nomogram serves as a non-invasive tool for risk stratification, indicating that patients in the high-risk group had shorter PFS compared to those in the low-risk group, highlighting its potential clinical application.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

MRI radiomics predicts progression-free survival in prostate cancer. Jia, Y., Quan, S., Ren, J., et al.[2023]

A multi-parametric MRI (mp-MRI)-based radiomics signature was developed using data from 280 prostate cancer patients, showing significant ability to distinguish between clinically significant prostate cancer (csPCa) and insignificant prostate cancer (ciPCa).

The radiomics signature demonstrated strong classification performance with an area under the curve (AUC) of 0.872 in the training cohort and 0.823 in the test cohort, indicating its potential as a noninvasive diagnostic tool for prostate cancer assessment.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Multi-parametric MRI-based radiomics signature for discriminating between clinically significant and insignificant prostate cancer: Cross-validation of a machine learning method. Min, X., Li, M., Dong, D., et al.[2019]

A radiomics approach using multiparametric MRI features can effectively quantify the phenotype of clinically significant prostate cancer, with the best model achieving an area under the curve (AUC) of 0.870 based on T2-weighted and diffusion-weighted imaging.

While dynamic contrast-enhanced imaging (DCE) features were included, their removal did not significantly affect diagnostic performance, indicating that T2-weighted and diffusion-weighted imaging are the key components for effective diagnosis.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Multiparametric MRI and auto-fixed volume of interest-based radiomics signature for clinically significant peripheral zone prostate cancer. Bleker, J., Kwee, TC., Dierckx, RAJO., et al.[2021]

MRI-based radiomics models demonstrated good performance in distinguishing between benign and malignant prostate lesions, with the best model achieving an area under the curve (AUC) of 0.905 when combining T2-weighted imaging and apparent diffusion coefficient features.

The integrated models also showed promise in predicting extracapsular extension (ECE) and positive surgical margins (PSM), with the highest AUC for ECE being 0.728, indicating that these models could enhance clinical diagnosis and treatment strategies.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

MRI-based radiomics models to assess prostate cancer, extracapsular extension and positive surgical margins. He, D., Wang, X., Fu, C., et al.[2021]

Multiparametric magnetic resonance imaging (mpMRI) significantly enhances the detection and risk classification of prostate cancer, especially in patients with previous negative biopsies and elevated PSA levels.

While mpMRI improves diagnostic accuracy, it may still miss smaller tumors, highlighting the need for continued advancements in imaging techniques to support safe treatment options like focal therapy.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Multiparametric magnetic resonance imaging: Overview of the technique, clinical applications in prostate biopsy and future directions. Demirel, HC., Davis, JW.[2020]

Multiparametric MRI (mp-MRI) is highly effective for detecting prostate cancer (PCa) and is essential for tumor localization, cancer staging, and monitoring recurrence, making it a key tool in patient management.

Radiomics enhances the evaluation of PCa by converting MRI images into detailed data, which can help in assessing tumor aggressiveness, reducing unnecessary biopsies, and improving predictions for treatment outcomes.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Multiparametric MRI and Radiomics in Prostate Cancer: A Review of the Current Literature. Midiri, F., Vernuccio, F., Purpura, P., et al.[2021]

Multiparametric prostatic MRI (mpMRI) is currently the best imaging tool for detecting prostate cancer (PCa), aiding in diagnosis, treatment planning, and follow-up, despite some limitations in identifying significant cancers in certain patients.

Inter-reader variability in interpreting mpMRI results is a major limitation, but advancements in radiomics may help improve detection accuracy and reduce costs by identifying imaging biomarkers.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Multiparametric magnetic resonance imaging of the prostate: Lights and shadows. Santoro, AA., Di Gianfrancesco, L., Racioppi, M., et al.[2021]

Multiparametric MRI (mpMRI) combined with radiomics can enhance the identification of different tumor habitats in prostate cancer, allowing for better differentiation between indolent and aggressive disease, which can lead to more personalized treatment decisions.

The use of radiogenomics may improve biopsy targeting and reduce unnecessary procedures by non-invasively identifying areas likely to harbor aggressive cancers, potentially leading to more effective and less toxic treatment strategies.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Prostate cancer radiomics and the promise of radiogenomics. Stoyanova, R., Takhar, M., Tschudi, Y., et al.[2022]

In a study of 78 men with non-suspicious multiparametric MRI results, 92.3% had no cancer detected in subsequent biopsies, indicating a high negative predictive value for mpMRI in ruling out significant prostate cancer.

Among the few cases where prostate cancer was found (7.7%), the majority were classified as indolent, suggesting that non-suspicious mpMRI can effectively identify patients at low risk for aggressive disease.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Relationship between non-suspicious MRI and insignificant prostate cancer: results from a monocentric study. Renard-Penna, R., Roupret, M., Compérat, E., et al.[2018]

Radiomics models using high-resolution T2-weighted MRI were found to be more effective for detecting prostate cancer compared to dynamic contrast-enhanced MRI, based on a study of 32 patients with high prostate-specific antigen levels.

The best-performing model achieved 100% accuracy, specificity, and sensitivity in classifying prostate lesions, demonstrating the potential of machine learning techniques to improve the reliability of prostate cancer diagnosis in MRI images.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Radiomics-based machine-learning method to diagnose prostate cancer using mp-MRI: a comparison between conventional and fused models. Jamshidi, G., Abbasian Ardakani, A., Ghafoori, M., et al.[2023]

Multiparametric prostate MRI (mpMRI) is evolving from just staging prostate cancer to also detecting and categorizing lesions, thanks to the emerging field of radiomics, which analyzes data from medical images.

Radiomics can help predict important factors like Gleason scores and the likelihood of cancer spreading, and future advancements in artificial intelligence may further enhance its effectiveness in prostate cancer diagnosis and management.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Radiomics and Prostate MRI: Current Role and Future Applications. Cutaia, G., La Tona, G., Comelli, A., et al.[2021]

References

1. Switzerland pubmed.ncbi.nlm.nih.gov

Prediction of clinically significant prostate cancer with a multimodal MRI-based radiomics nomogram. [2022]

2. Switzerland pubmed.ncbi.nlm.nih.gov

MRI radiomics predicts progression-free survival in prostate cancer. [2023]

3. Ireland pubmed.ncbi.nlm.nih.gov

Multi-parametric MRI-based radiomics signature for discriminating between clinically significant and insignificant prostate cancer: Cross-validation of a machine learning method. [2019]

4. Germany pubmed.ncbi.nlm.nih.gov

Multiparametric MRI and auto-fixed volume of interest-based radiomics signature for clinically significant peripheral zone prostate cancer. [2021]

5. England pubmed.ncbi.nlm.nih.gov

MRI-based radiomics models to assess prostate cancer, extracapsular extension and positive surgical margins. [2021]

6. Turkey pubmed.ncbi.nlm.nih.gov

Multiparametric magnetic resonance imaging: Overview of the technique, clinical applications in prostate biopsy and future directions. [2020]

7. Switzerland pubmed.ncbi.nlm.nih.gov

Multiparametric MRI and Radiomics in Prostate Cancer: A Review of the Current Literature. [2021]

8. United States pubmed.ncbi.nlm.nih.gov

Multiparametric magnetic resonance imaging of the prostate: Lights and shadows. [2021]

9. China pubmed.ncbi.nlm.nih.gov

Prostate cancer radiomics and the promise of radiogenomics. [2022]

10. Germany pubmed.ncbi.nlm.nih.gov

Relationship between non-suspicious MRI and insignificant prostate cancer: results from a monocentric study. [2018]

11. Germany pubmed.ncbi.nlm.nih.gov

Radiomics-based machine-learning method to diagnose prostate cancer using mp-MRI: a comparison between conventional and fused models. [2023]

12. Switzerland pubmed.ncbi.nlm.nih.gov

Radiomics and Prostate MRI: Current Role and Future Applications. [2021]