LabPON publishes clinical validation of Ibex’s AI showing improved quality of prostate cancer diagnoses

Share this article:

Laboratorium Pathologie Oost-Nederland (LabPON) is one of the largest laboratories in the Netherlands, processing more than 90,000 samples each year. They are committed to using the latest technology, and under the leadership of Dr. Alexi Baidoshvili, LabPON became the first laboratory in the world to reach 100% digital pathology diagnosis in June 2015.

Now, with the rising number of cancer cases and increases in case complexity, LabPON identified the need for AI-powered digital pathology tools to support their pathologists in providing accurate and timely diagnoses. LabPON assessed Ibex Prostate and recently published results in the Journal of Clinical and Medical Images[1] showing that Ibex’s AI improves the quality of prostate cancer diagnoses.

“Accurate and timely diagnoses are crucial for patient management, and AI algorithms like Ibex Prostate enhance cancer detection and grading, reducing diagnostic errors and treatment delays,” the authors state in the publication’s conclusion.

Method: In their retrospective study, LabPON validated Ibex’s algorithms for prostate adenocarcinoma detection and Gleason grading. They digitized 168 prostate cases using a Philips Ultrafast Scanner and then analyzed by Ibex Prostate’s AI embedded within Proscia’s Concentriq IMS. Three expert uropathologists reviewed discrepancies between the original diagnosis and the AI results.

Study Figure 2: Showing the tumor length measure by AI algorithm (0.8mm)
Study Figure 3: Showing the Gleason grading of the tumor (G3+3)
LabPON study figures
Results: LabPON found that Ibex Prostate had a positive predictive value (PPV) of 99.6% for cancer cases and a negative predictive value (NPV) of 99.7% for benign cases. The authors shared that two cases originally diagnosed as benign were flagged by the AI for a high likelihood of cancer; following expert review, one case was then diagnosed as nonmalignant high-grade PIN and the other required IHC for further analysis.

Study Figure 3: Case 153, part I: Original report was diagnosed as benign. Ibex highlighted small focus highly suspicious of cancer. Review and ground truth adjudication: High-grade PIN

LabPON study figure 3

The researchers also noted that Ibex Prostate’s Gleason score was within one grade of the pathologist’s diagnosis for 96.7% of the cases. “The intricate Gleason grading system, requiring detailed evaluation, can lead to bottlenecks and human errors that negatively impact patient care. AI technologies, such as the Ibex Prostate system, offer significant benefits, including high diagnostic accuracy and the ability to serve as a reliable second-read method, thus alleviating the burden of labor-intensive manual readings.”

Following the impressive results, Dr. Baidoshvili and team are now continuing to lead the way in advanced technology adoption and implementing these AI algorithms into their routine clinical diagnostics.

Review LabPON’s complete validation study: VIEW HERE

The Ibex platform includes solutions that are CE-IVD certified and registered with the UK MHRA, TGA in Australia and ANVISA in Brazil. It includes a solution that is FDA cleared and others that are Research Use Only (RUO) in the United States.

[1] Khacheishvili et al. J Clin Med Img. 2024; V8 (7): 1-6

Share this article:

Subscribe to our newsletter:

By providing my details I agree that my data will be handled in accordance with IBEX Privacy Policy.

About IBEX

IBEX is the leader in AI-powered cancer diagnostics in pathology. We empower physicians to provide every patient with an accurate, timely and personalized cancer diagnosis. Our AI platform is deployed worldwide, supporting pathologists and providers with AI-insights that help improve the quality and accuracy of diagnosis, reduce turnaround times and boost productivity.

Subscribe to our newsletter:

By providing my details I agree that my data will be handled in accordance with IBEX Privacy Policy.

Scroll to Top
IBEX
Privacy Overview

This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.