Bot Image announced that their ProstatID software received clearance from the US FDA for use in detecting and diagnosing prostate cancer by combining AI with traditional MRI scanning.
Over the past several years, artificial intelligence (AI) tools have been developed by researchers with the goal of making cancer imaging and screening faster and more accurate, though there is still some skepticism around whether they are ready for larger-scale use in doctor’s offices.
Naturally, people may not automatically trust AI — these tools use algorithms to learn from data to make decisions or predictions. To train AI, scientists provide it with data in the form of rules, instructions, images, or other material for it to “learn” from and analyze to make decisions much like a human would.
The aim of AI is to have it display human-like “intelligent behaviour.” In the case of cancer screening or diagnosis, this means recognizing visual images, like MRI scans, of people who have a specific form of cancer and those who do not.
Bot Image is one company that aims to provide AI-driven software to improve the accuracy and speed of prostate cancer detection and diagnosis.
Last week, Bot Image announced in a press release that their ProstatID software received clearance from the US Food and Drug Administration (FDA) for use in detecting and diagnosing prostate cancer by combining AI with traditional MRI scanning.
ProstatID is available in the form of software as a service (SaaS) and is both HIPAA-compliant and secure as its use requires a secure VPN connection between a radiology department’s server or MRI system and the cloud-hosted ProstatID server.
Live and On-Demand: Thursday, September 22, 2022, at 10am EDT (3pm BST/UK)
Register for this free webinar to explore the potential for including in silico modeling and simulation as an integral part of the product development plan.
Training ProstatID to Detect Prostate Cancer
Dr. Randall W. Jones, Bot Image founder and CEO, explains that “Prostate cancer screening and detection methods adoption has changed little over the past 30 years, despite the mountain of evidence pointing to the efficacy of superior technologies and the futility of the old methods.” This has unfortunately resulted in unnecessary premature deaths of numerous men.
The approval of ProstatID is progress in the mission to save lives with early and accurate detection and demonstrates time and cost savings for both patients and medical providers.
The AI was trained with thousands of MRI scans, radiological interpretations, biopsies, and pathology lab results. The software’s algorithm assigns a cancer probability to any suspicious cancer lesions it detects. Subsequently, it provides a diagnostic case score called a PI-RADS score (Prostate Imaging Reporting and Data System).
Two clinical studies with twenty-five US-based radiologists used this AI-based method, and it resulted in significantly improved radiologic interpretation accuracy. The improved accuracy was based on improved detection of cancer and fewer false positives when radiologists used ProstatID.
The software’s ability to detection lesions and assign a probability score to patient MRI scans surpasses the capabilities of existing technologies that may improve on-screen visualization of MRI cases but fall short in the actual detection and diagnosis of prostate cancer.