Examine Diabetes with Skin Scanner and AI

Changes in small blood vessels are a common consequence of developing diabetes. Researchers from the Technical University of Munich (TUM) and Helmholtz Munich have developed a method that can be used to measure these microvascular changes in the skin and thus assess the severity of the disease. To achieve this, they combine artificial intelligence (AI) and innovative high-resolution optoacoustic imaging technology. The work is published in the journal Natural biomedical engineering.

Optoacoustic imaging methods use pulses of light to generate ultrasound inside tissues. The generated ultrasound waves are then recorded by sensors and converted into images. The signals are caused by tiny expansions and contractions of the tissues surrounding molecules that strongly absorb light. One of these molecules is hemoglobin. Since hemoglobin is concentrated in blood vessels, optoacoustic imaging can produce unique and detailed images of the vessels, which is not possible with other non-invasive techniques.

The basic principles of optoacoustics, or photoacoustics, have been known for more than a century, but practical applications in medicine are quite recent. Vasilis Ntziachristos is Professor of Biological Imaging at TUM and Director of the Institute for Biological and Medical Imaging and the Center for Bioengineering at Helmholtz Munich. With his team, he developed a range of optoacoustic imaging methods, including RSOM, short for raster-scan optoacoustic mesoscopy.

32 particularly notable changes

Researchers have now successfully used RSOM to study the effects of diabetes on human skin. Using RSOM images of blood vessels in the legs of 75 diabetics and a control group, researchers identified the characteristics of diabetes using an AI algorithm.

They created a list of 32 particularly significant changes based on alterations in the appearance of skin microvasculature. These included characteristics such as the number of vessel branches or their diameter.

RSOM allows rapid measurement of vascular changes

The fact that the small blood vessels in the skin of diabetics are altered is well established thanks to biopsies, that is to say the examination of small excised parts of the skin. However, biopsies do not accurately represent living conditions because they can distort blood vessels. They are also invasive and not suitable for observations over a prolonged period.

RSOM measurements, on the other hand, are non-invasive, last less than a minute, and do not use radiation or contrast agents. “Other optical methods do not achieve the depth or detail achieved by RSOM,” says Angelos Karlas, lead clinician on the study.

With a single RSOM measurement, data on different skin depths can be obtained simultaneously. This allowed researchers to determine for the first time that diabetes affects the vessels of different layers of the skin differently. For example, while the number of vessels and branches in the so-called dermal layer was reduced in diabetics, they increased closer to the surface of the skin, in the so-called epidermal layer.

Assess diabetes stage by combining skin characteristics

The 32 characteristics mentioned above are all affected by disease progression and severity. Yet only when they are combined and a score is calculated can a link be established in time between the condition of the small blood vessels in the skin and the severity of diabetes. This is done for the first time in the present study.

“Thanks to RSOM, we can now quantitatively describe the effects of diabetes,” explains Vasilis Ntziachristos. “With the emerging ability to make RSOM portable and cost-effective, these results open a new avenue for continuous monitoring of the condition of affected individuals, more than 400 million people worldwide. In the future, through “Quick and painless exams would take only a few minutes to determine whether the therapies are having an effect, even at home.”