WEST LAFAYETTE, Ind. — Your smartphone may already be used for medical appointments and virtual meetings but researchers say its technology capabilities could be used for much more.
The idea behind AI-driven technology developed at Purdue University could use the onboard sensors in a smartphone’s camera to detect and diagnose medical conditions like anemia faster and more accurately than highly specialized medical equipment being developed for the task.
“There are at least 15 different sensors in your smartphone, and our goal is to take advantage of those sensors so people can access health care outside of a doctor’s office,” said lead researcher Young Kim, professor and associate head for research in Purdue’s Weldon School of Biomedical Engineering. “To the best of our knowledge, we believe that we demonstrated the fastest hemodynamic imaging in existence, using a commercially available smartphone.”
While a smartphone camera is convenient it captures measurements of only red, green and blue wavelengths of light in each pixel which limits its medical utility. Hyperspectral imaging can capture all wavelengths of visible light and can be used to detect a variety of skin and retinal conditions and some cancers. Most researchers’ work is now focused on improving specialized equipment which is relatively bulky, slow and expensive.
By pairing deep and statistical techniques with their knowledge of light-tissue interactions Purdue researchers are able to reconstruct the full spectrum of light in each pixel of an ordinary smartphone camera image. The patent-pending approach could help improve access to health care.
The tests were reported in PNAS Naxus when the team tested its method against commercially available imaging equipment when gathering information about the movement of blood oxygen in volunteers’ eyelids, in models meant to mimic human tissue and in a chick embryo. The results show the smartphone camera produced hyperspectral information more quickly, cheaply and just as accurately as those captured using specialized equipment. The smartphone takes a single millisecond to produce images compared to about three minutes for conventional imaging.
Kim disclosed his innovation to the Purdue Research Foundation Office of Technology Commercialization which has applied for a patent to protect the intellectual property.