A team of researchers has utilized a high-resolution, non-invasive technique to obtain images of the small blood vessels located beneath the skin of diabetic patients, employing an artificial intelligence algorithm to formulate a "score" that can be used to determine the severity of the disease. Once this technology becomes portable, it could be used to monitor treatment effectiveness, according to a report by New Atlas, citing the journal Nature Biomedical Engineering.
**Microvascular Complications**
Microvascular complications, where the walls of capillaries thicken and weaken to the point of bleeding and protein leakage, as well as slow blood flow, are one of the main complications of diabetes, which can affect various body organs, including the skin. Researchers from the Technical University of Munich (TUM) developed a method for obtaining detailed images of blood vessels beneath the skin of diabetic patients, using artificial intelligence to quantify the severity of the condition.
**Photoacoustic Imaging**
Photoacoustic imaging utilizes light pulses to generate ultrasound waves within tissues. Small expansions and contractions in the surrounding tissues that strongly absorb light create signals recorded by sensors and converted into high-resolution images. Hemoglobin, a protein that carries oxygen, is one of these light-absorbing molecules. Since it is concentrated in blood vessels, photoacoustic imaging yields detailed images of blood vessels that other non-invasive techniques cannot produce, and it is a rapid procedure that does not use radiation.
**Increased Depth and Detail**
In the new study, the researchers developed a specific method for photoacoustic imaging called RSOM, which stands for Raster-Scanning Optical Microcopy. This method can retrieve data from varying skin depths simultaneously, up to a depth of 1 mm, which Angelos Karlas, the lead researcher in the study, stated achieves "greater depth and detail than other optical methods."
**RSOM Technique**
The researchers used RSOM to capture images of the skin on the legs of 75 diabetic patients and a control group of 40 individuals. They employed an artificial intelligence algorithm to determine clinically relevant features associated with diabetic complications. The researchers compiled a list of 32 particularly significant changes in microvascular structures in the skin, including the diameter of blood vessels and the number of branches within them.
**Vessel Count**
The researchers observed that the number of vessels and branches in the skin layer decreases in diabetic patients, while it increases in the epidermis closest to the skin surface. All 32 characteristics identified by the researchers were affected by the progression and severity of the disease. By aggregating these 32 features, the research team calculated a "microvascular score," linking the condition of small blood vessels in the skin to the severity of diabetes.
**Lower Costs and Rapid Assessments**
Vassilis Ntziachristos, a researcher in the study, stated that the "RSOM technique can quantitatively describe the effects of diabetes," explaining that "with the emerging ability to make RSOM portable and cost-effective, these findings will open a new way for continuous monitoring of the condition for over 400 million people worldwide. In the future, with quick and painless testing, it will take only a few minutes to determine whether treatments have an effect, even while the patient is at home."
