Leeds Teaching Hospitals NHS Trust (LTHT) is piloting a new artificial intelligence (AI) tool designed to improve prostate cancer diagnosis. In collaboration with Lucida Medical, LTHT is testing the effectiveness of the Prostate Intelligence (Pi) tool, an advanced AI and machine learning software system, in detecting prostate cancer lesions from MRI scans.
Prostate cancer is the most common cancer among men, with one in eight men in the UK diagnosed during their lifetime. The risk is even higher for black men, with one in four facing a prostate cancer diagnosis. Patients with prostate cancer face a complex diagnostic pathway, and by using this AI software, the Trust says it aims to help speed up the process and prioritise those with cancer.
The software could also free up radiologists to report on additional patients every day and may, in the future, allow patients to be booked for a biopsy more quickly. Currently, MRI imaging plays a critical role in diagnosing prostate cancer and guiding targeted biopsies.
Dr Oliver Hulson, Consultant Radiologist at LTHT said: “Our goal is to determine if this AI tool can accurately identify prostate cancer without underestimating or overestimating the likelihood based on MRI scans. If successful, this could enable us to streamline our prostate cancer pathway and reduce the waiting time for a biopsy from the current two to three weeks to less than one week. Ultimately, faster diagnosis means faster treatment and better outcomes for our patients.”
“The aim would be to provide our patients with a rapid diagnostic approach, or ‘one stop shop’ where they could potentially have their MRI scan in the morning, reviewed by the radiologist with the benefit of the AI tool, and if needed, plan for their biopsy that afternoon, performing all their investigations in a single day, rather than over weeks as is the case currently. This would of course reduce their anxiety whilst waiting for tests and would provide their results as quickly as possible.”
The ongoing study will compare the AI-generated results from the Pi software against real-world outcomes for 100 patients who have recently completed the prostate cancer pathway. The Pi software assists radiologists by highlighting potential areas of concern on MRI scans and assessing risk scores and prostate size, which can impact biopsy and treatment decisions.
Pi does this by using AI algorithms to analyse prostate MRI images. It has been trained to spot the signatures of cancer using MRI and biopsy data from patients in the Netherlands and UK. In clinical use, Pi would be set up to run automatically as soon as a patient’s MRI scan is completed, so that the AI outputs are available when the clinical team reviews it.
Lucida Medical has been a key partner in introducing this innovative software to the Trust. The trial has also benefitted from the expertise of LTHT’s medical physics team and academic partners at the university, who have supported the image transfer and analysis processes. Initial retrospective data collection is underway, and a prospective pilot study is planned for the autumn.
As the project progresses, the team says it hopes that the AI software will prove both sensitive and specific in identifying prostate cancer, potentially revolutionising the diagnostic pathway and expediting patient care.
