DPP sponsors:                            

How Aira Matrix supports digital pathology with deep learning on demand w/ Chaith Kondragunta

Today’s guest, Chaith Kondragunta, started working on neural network applications as an engineer back in the days when the computing power to fully utilize them was not available yet. This research field had to wait for the technology to catch up with the theoretical concepts. When this was achieved, Chaith harnessed deep learning for data analytics in the financial sector, but always knew, that to make a real difference it should be implemented in health care and medical sciences. This opportunity came in 2018 when he became the CEO of Aira Matrix – an image analysis company applying deep learning to pathology images.

Aira Matrix is based in Mumbai, India, and was definitely a pioneer in the tissue image analysis space in that region. They started when digitization in pathology was still far off in India and were serving mostly international clients. Currently more and more organizations in India are investing in digital pathology infrastructure, and Aira Matrix is standing strong in the local market as well.

The company started with image analysis software as a product, but to better address the needs of the medical and scientific community, gradually added services for building customized solutions to their portfolio.

Starting in the non-clinical toxicologic pathology area with solutions aiming to streamline the tox path study such as:

  • Vacuole Segmentation and Quantification in Liver Images of Wistar Rat
  • and Deep Learning-Based Spermatogenic Staging Assessment for Hematoxylin and Eosin-Stained Sections of Rat Testes

the team expanded their services into the clinical area focusing on prostate cancer.

Currently the standard grading system for this disease relies on the Gleason score – a system grading the difference in appearance of the prostate glands when compared to normal. This is done visually on a two-dimensional glass slide or a whole slide image. Thanks to deep learning pathologists can expand the diagnostic process by multiple parameters and modalities including volumetric prostate gland construction.

Aira Matrix was founded to solve complex toxicopathologic problems and is wired to think in terms of complex problems. In addition to that, with more than 50% of Aira’s employees having an advanced degree, the culture of research and innovation is embedded in the company. To stay on top of the game the team regularly takes part in different computer vision challenges.

To learn more about Aira Matrix visit:  https://www.airamatrix.com/

Related Projects