Ibex deploys AI system for digital pathology cancer diagnosis

Charlotte Edwards 16 April 2018 (Last Updated April 16th, 2018 17:13)

AI-powered cancer diagnostics developer Ibex Medical Analytics has deployed the first ever artificial intelligence based digital pathology system in a live clinical setting.

Ibex deploys AI system for digital pathology cancer diagnosis
Ibex Medical Analytics has developed AI-driven clinical decision support tools that help pathologists deliver accurate diagnosis. Credit: Ibex Medical Analytics.

AI-powered cancer diagnostics developer Ibex Medical Analytics has deployed the first ever artificial intelligence based digital pathology system in a live clinical setting.

The Israel-based company aims to eliminate errors in diagnosing prostate cancer with its new technology.

The Ibex Second Read (SR) system was deployed in the pathology institute of Maccabi Healthcare Services, one of the largest healthcare providers in Israel and Ibex’s strategic partner. The institute is a centralised pathology unit which deals with 160,000 histology accessions annually, around 700 of which are prostate core needle biopsies (PCNBs).

The full-scale deployment of the system comes after a pilot period, which saw the technology identify isolated major errors in previously assessed PCNBs that were originally diagnosed as benign.

Following the deployment, the system immediately identified a suspicious PCNB that was reported as benign by a pathologist a few hours earlier. The PCNB was subsequently re-examined and diagnosed as low-grade prostate cancer, also referred to as adenocarcinoma. This new diagnosis had a clinical significance for the patient’s treatment pathway.

Ibex Medical Analytics co-founder and CEO Joseph Mossel said: “We are excited to be the first company to ever deploy an AI-based system in a clinically-active pathology lab, leveraging the enormous potential of artificial intelligence to make a real impact on human lives.

“It is extremely pleasing that our system has already positively affected a patient. We are now putting our full focus on making this system commercially available.”

Ibex developed the software to identify various cell types and features within whole slide images of PCNBs. It also has the ability to grade cancerous glands and other clinically significant features.

The company says its algorithm is designed to use AI and machine learning techniques and was trained on thousands of image samples taken from hundreds of PCNBs from multiple institutes. The digital images were produced by the Philips Intellisite Pathology Solution, which was installed at the institute last year.

Maccabi pathology institute head and Ibex Medical Analytics chief medical officer Dr Judith Sandbank said: “The complexity of prostate cancer diagnosis, together with the considerable shortage of pathologists, makes a second read system like this extremely useful for diagnostic accuracy and safety.”