Skip to main content
Premium Trial:

Request an Annual Quote

Indica Labs, iCAIRD to Develop Digital Pathology Algorithm for Colon Cancer

NEW YORK – Digital pathology firm Indica Labs announced on Tuesday that it is partnering with the UK's Industrial Centre for Artificial Intelligence Research in Digital Diagnostics (iCAIRD) to jointly develop a digital pathology algorithm to detect colon cancer.

The artificial intelligence-based solution will be used to detect cancer within lymph nodes from colorectal surgery cases and is intended to improve the efficiency of pathology teams reporting colorectal cancer cases and the detection of metastatic cancer in lymph nodes, Albuquerque, New Mexico-based Indica Labs said in a statement.

Anonymized hematoxylin and eosin-stained slides from the National Health Service Greater Glasgow and Clyde's (NHSGGC) digital pathology archive will be used to train, validate, and test the algorithm, which will report negative and positive lymph node status and be compared to pathologist reports. Positive lymph nodes will be categorized into metastases, micro-metastases, and individual tumor cells, Indica Labs added.

Indica's Halo AI and Halo AP products will be used to develop the solution. Halo AI uses deep learning neural networks to classify and quantify clinically significant tissue patterns and cell populations, while Halo AP is a software platform that can be used as a standalone case and image management system or integrated within a laboratory information system, Indica said. The colorectal cancer algorithm will be delivered on Halo AP, and Halo AP will be evaluated by the pathology department at NHSGGC. Halo AP received CE marking in January.

"Our belief is that AI-powered decision support tools, such as the one we are working on, may help to support pathologists by improving the process' efficiency, while simultaneously increasing sensitivity in detecting small metastasis — which will direct patient therapy," Gareth Bryson, consultant pathologist at NHSGGC and clinical director for laboratory medicine at iCAIRD, said in a statement. "Colorectal cancer resections are one of the most common cancer resection specimens, and a disproportionate amount of pathologist’s time is utilized in screening lymph nodes."

Scotland-based iCAIRD is a collaboration of 30 partners from NHS, industry, academia, and technology working on AI-based projects across radiology and pathology.