AI Algorithm-Informed Biopsy for Prostate Cancer

AH
Overseen ByAaron Holley
Age: 18+
Sex: Male
Trial Phase: Academic
Sponsor: University of Arkansas
No Placebo GroupAll trial participants will receive the active study treatment (no placebo)

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial tests a new application of artificial intelligence (AI) to improve prostate cancer detection. The AI, a bi-parametric MRI-based cascaded deep-learning algorithm, analyzes MRI scans to identify potentially cancerous areas. It aims to enhance detection in patients with unclear or low-risk MRI results but who exhibit other high-risk signs, such as elevated PSA levels (a protein in the blood that can indicate prostate cancer). This trial targets men who recently had an MRI showing uncertain areas and have high PSA levels or other risk factors, like a family history of prostate cancer. As an unphased trial, it offers participants the chance to contribute to groundbreaking research that could enhance prostate cancer detection for future patients.

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications. It's best to discuss this with the trial team or your doctor.

What prior data suggests that this AI algorithm is safe for prostate cancer detection?

Research has shown that deep learning AI, like the one used in this trial, has been tested with promising results. In one study, these AI systems effectively identified cancerous areas on prostate MRI scans. Another study found that the AI's ability to detect prostate cancer matched that of experienced radiologists.

The AI model used in this trial has been tested for its ability to find prostate cancer using MRI scans. It performed well, particularly in identifying cancer in patients with larger prostate glands. While these studies focused on the AI's effectiveness rather than its safety, they suggest that the AI process is safe since it only involves analyzing images, not interacting with the body directly.

Overall, the AI has successfully detected prostate issues without any reported side effects, as it doesn't involve physical contact or invasive procedures. This suggests that participating in a trial using this AI method should be safe regarding the AI component itself.12345

Why are researchers excited about this trial?

Researchers are excited about this trial because it explores a cutting-edge AI algorithm designed to enhance prostate cancer detection. Unlike the standard of care, which involves systematic and MRI-targeted biopsies, this AI-driven method uses advanced bi-parametric MRI scans to provide precise segmentations of prostate tissues and lesions. This could potentially improve the accuracy of diagnosing prostate cancer, especially in cases where existing methods may yield ambiguous results. By leveraging deep learning, this approach aims to identify cancerous lesions earlier and with greater accuracy, which could lead to better treatment outcomes for patients with equivocal or negative MRI findings but high clinical risk.

What evidence suggests that the AI algorithm is effective for prostate cancer detection?

This trial will compare a deep learning AI program with standard perilesional prostate biopsy. Studies have shown that the AI program effectively identifies cancerous spots in prostate MRI scans. It uses special MRI images to detect suspicious areas with high accuracy. Research indicates that the AI's results match those of doctors in detecting prostate cancer. This suggests that AI-assisted detection could reliably identify significant prostate cancer cases, especially when MRI results are unclear.16789

Who Is on the Research Team?

AM

Ahmet M Aydin, MD

Principal Investigator

University of Arkansas

Are You a Good Fit for This Trial?

This trial is for men aged 40 or older who have had a recent prostate MRI showing uncertain or low-risk lesions, along with high PSA levels or other risk factors like suspicious exam results, certain genetic risks, family history, or being of Black/African American ancestry. Participants must be in good physical health.

Inclusion Criteria

I am 40 years old or older.
I had an MRI of my brain in the last 12 weeks.
I have a significant medical history.
See 7 more

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Phase I Feasibility

Assess the acceptance rate of randomization and biopsy recommendations based on study protocol and AI algorithm results by the patients

4 months
Initial visit for randomization and biopsy procedure

Phase II Efficacy

Evaluate the per-patient and per-lesion csPCa detection rates of AI algorithm-informed biopsy versus contemporary biopsy

4 months
Multiple visits for biopsy procedures and assessments

Follow-up

Participants are monitored for safety, adverse events, and quality of life measures after biopsy procedures

4 weeks
2 visits (in-person)

What Are the Treatments Tested in This Trial?

Interventions

  • Bi-parametric MRI-based cascaded deep-learning AI algorithm

Trial Overview

The study tests whether using an AI algorithm to guide prostate biopsies can better detect significant prostate cancer compared to standard methods in patients with unclear or low-risk MRI findings but higher clinical risk.

How Is the Trial Designed?

2

Treatment groups

Experimental Treatment

Active Control

Group I: Bi-parametric MRI-based cascaded deep-learning AI algorithmExperimental Treatment1 Intervention
Group II: Perilesional prostate biopsyActive Control1 Intervention

Find a Clinic Near You

Who Is Running the Clinical Trial?

University of Arkansas

Lead Sponsor

Trials
500
Recruited
153,000+

Citations

Evaluation of a Cascaded Deep Learning–based Algorithm for ...

A deep learning–based algorithm automatically detected cancerous lesions on prostate biparametric MRI scans with reasonable performance and ...

A Cascaded Deep Learning–Based Artificial Intelligence ...

We aimed to develop and test a cascaded deep learning detection and classification system trained on biparametric prostate MRI using PI-RADS for assisting ...

3.

pubmed.ncbi.nlm.nih.gov

pubmed.ncbi.nlm.nih.gov/34598869/

A Cascaded Deep Learning-Based Artificial ... - PubMed

Our cascaded U-Net, residual network architecture can detect, classify cancer suspicious lesions at prostate MRI with good detection, reasonable classification ...

Evaluation of a Cascaded Deep Learning–based Algorithm ...

A deep learning–based algorithm automatically detected cancerous lesions on prostate biparametric MRI scans with reasonable performance and reliably ...

Evaluating a deep learning AI algorithm for detecting residual ...

Our study investigates the efficacy of a biparametric MRI (bpMRI)-based deep learning algorithm for post-FT PCa identification. This ...

Evaluating Artificial Intelligence–Assisted Prostate ...

We used a cascaded, deep learning–based AI algorithm for PCa detection, developed within the Molecular Imaging Branch of the National Cancer ...

MRI-based Deep Learning Algorithm for Assisting ...

A commercial MRI-based deep learning algorithm for prostate cancer detection showed greater positive predictive value, despite its lower sensitivity.

Evaluation of a Deep Learning-based Algorithm for Post ...

A bpMRI-based AI model detected most locally radiorecurrent cancers. The AI model performance was comparably better in patients with larger glands.

Evaluation of a Cascaded Deep Learning-based Algorithm ...

Prostate Cancer. Evaluation of a Cascaded Deep Learning-based Algorithm for Prostate Lesion Detection at Biparametric MRI. May 8, 2024.