Enlitic Secures $15M for Chest X-Ray Interpretation AI Solution

The AI platform identifies and analyzes suspicious findings in chest X-rays.

Photo has been modified. Courtesy of Stillwaterising [CC0] via Wikimedia Commons.

Enlitic today announced the close of a $15 million Series B funding round for its artificial intelligence (AI) solution used to streamline medical imaging workflows for radiologists.

The funding was led by Marubeni, with additional investments from Capitol Health and investors in Australia.

Enlitic uses deep learning and other forms of AI to develop algorithms that identify and analyze suspicious findings in medical images.

The company’s first platform is meant to enable the development, validations and seamless integration of clinical AI at scale. The platform interprets chest X-rays and triages normal from abnormal scans to detect and can characterize more than 40 distinct abnormalities, such as cardiomegaly, lung nodules and pneumothorax.

“(Radiologists) need to be able to identify thousands of different abnormalities in hundreds of different types of images,” said Kevin Lyman, CEO of Enlitic. “Even a single mistake can mean life or death, and yet they’re asked to read under tremendous time pressure in an environment full of distractions.”

Lyman believes that the funding round could be a big step toward helping radiologists be relieved of pressure and improve patient outcomes.

Enlitic claims its technology has sped up radiologist’s interpretation of chest X-rays by over 20 percent, while improving true positives and reducing false positive rates by over 10 percent.

The funding will be used to enhance Enlitic’s AI product portfolio, expand its engineering and data scientist teams and focus on regulatory approval for clinical use in the U.S., Japan, Europe, Canada, Brazil and Australia.

Close to 10 percent of the funding was set aside for radiologists and physicians who have trained or used the company’s medical AI solutions.

The company is rapidly training models to assist in more areas of radiology and expects to be able to interpret 95 percent of all types of X-rays by the end of 2019.

Get the best insights in healthcare analytics directly to your inbox.

Related

How AI Can Make Clinicians Better

Machine Learning Algorithms Predict Opioid Overdose Risk

New Deep Neural Network Model Can Predict Adverse Drug Reactions