Sign up for our newsletter - Navigating the horizon of business technology​
Technology / Emerging Technology

SigTuple Tests AI Microscope to Address Pathologist Shortage

AI is becoming a major part of our lives and with IBM’s Crypto Anchor Verifier being able to spot fakes, as well as testing water quality, there is a lot of movement going around at the moment with new daily concepts and ideas.

Indian deep learning start-up SigTuple, which is part of American technology company NVIDIA’s incubation start-up programme “Inception” is currently testing an AI microscope that could address the global pathologist shortage.

Since the company was founded in Bangalore, India in 2015 by co-founders Rohit Kumar Pandey, Tathagato Rai Dastidar and Apurv Anand, SigTuple has raised $5.8 million (approx. £4.3 million) in funding from American venture capital firm Accel Partners in February 2017 and is continuing to expand with the help of NVIDIA’s Inception Program.

The pathologist shortage is a major problem not only for the poor, but for well-developed countries as well. According to recent figures for the United States, there will be 5.7 pathologists per 100,000 American people although that figure is expected to decrease to 3.7 per 100,000 by 2030.

White papers from our partners

Tathagato Rai Dastidar, co-founder and CSO of Sigtuple highlighted that there was a human cost to the shortage of pathologists available worldwide whilst linking to the fact India has one pathologist per 65,000 people with 20,000 available to the country’s 1.3 billion population.

Dastidar said on NVIDIA’s blog “There is a human cost here. In many places, where there is no pathologist, a half-trained technician will write out a report and cases will go undetected until it’s too late.”

The device, which is not the first automated microscope uses a GPU-powered device to automatically scan and analyse blood smears as well as detecting problems with other biological samples.

SigTuple’s AI microscope works by scanning slides under its lens and uses deep learning to analyse digital images either by its own AI platform in the cloud or on the microscope itself.

Blood smears are able to detect red and white blood cells by using “Shonit” to pinpoint their location and calculate ratios for varying types of white blood cells and can compute 3D information about the cells from 2D images using machine learning.

SigTuple has plans to carry out their next formal trial of Shonit before commercially rolling the microscope out.

Image Credited to SigTuple
This article is from the CBROnline archive: some formatting and images may not be present.