Indica Labs has received a CE-IVD mark for its deep learning-based screening tool, HALO Prostate AI, to aid pathologists to identify and grade prostate cancer from core needle biopsy samples.

Indica Labs, a provider of computational pathology software and services, created the HALO Prostate AI to work with pathologists to increase productivity and provide a layer of quality control to assure diagnosis accuracy.

HALO Prostate AI tool is installed using Indica Labs’ CE-IVD marked HALO AP platform to deliver a completely verified and automated end-to-end process.

The firm said that the HALO AP can be used as a stand-alone case management system or can be integrated with LIS systems to allow outputs from HALO Prostate AI or other AI diagnostics to be accessed directly from the LIS.

HALO Prostate AI was trained using digital scans from many scanning systems and clinically verified against the Hamamatsu NanoZoomer S360 and Leica GT450 platforms.

The firm developed the tool in close collaboration with Dr Yuri Tolkach and colleagues from the University of Cologne.

HALO Prostate AI was trained using more than 870,000 digital scans of prostate cancer subtypes, leason grades, as well as benign tissue.

According to Indica Labs, the algorithm demonstrated high sensitivity of 95-100%, specificity of 88-98%, and a negative predictive value of 98-100% in a validation trial on 4,973 core needle biopsies.

The screening tool showed its diagnostic accuracy and patient care by discovering a tumour in 26 cores in the validation trial that had previously been reported as tumour negative.

Dr Tolkach said: “I am very excited about the digital future of pathology. With tools such as HALO Prostate AI, our work can be substantially optimized while controlling for high-quality, reliable, and objective diagnostics.

“HALO Prostate AI showed very high accuracy in the large multi-institutional study for tumour detection and Gleason Grading in prostate biopsies.

“It’s really enjoyable to work back-to-back with such a powerful AI assistant.”