Artificial Intelligence could help medical experts detect tuberculosis (TB) in patients if Cleveland-based Diascopic LLC can successfully bring their diagnostic technology to market.
Aiding them in this endeavor is a federal business innovation grant — the National Institute of Health Small Business Innovation Research (SBIR) grant. With the funds this has provided, the medical research company hopes to develop and apply new AI and digital pathology tools to fighting one of the world’s most deadly diseases. Preliminary studies have already been conducted and their promising results prompted the federal attention.
An estimated 1.8 billion people are infected with the bacterium that causes TB, and health care specialists are hunting for a quicker, more flexible method of detection. Diascopic proposes to achieve this through its iON platform, which can detect TB bacterium digitally in less than 60 seconds, using only a single sample.
“By digitizing the process, we’re able to reuse the image in perpetuity, which makes the test highly repeatable,” Cary Serif, CEO of Diascopic, said. “Just as importantly, the digitization allows us to build a massive reference library to which we can apply artificial intelligence and data analytics to continue improving the test’s accuracy.”
The iON platform mixes low-magnification, high-resolution imaging with digital analysis software. In this way, it pursues instant inspection of microscopic specimen in a way that can be portable, low cost, and highly flexible. To test it, Diascopic is working with the Uganda Case Research Collaboration to collect 400 specimens. From these, Diascopic hopes to push forward with the development of around 60,000 digital images.