Photograph approach tests cholesterol levels noninvasively

Researchers at the the Sree Sastha Institute of Engineering and Technology (Chennai, India) and colleagues have developed a total cholesterol test that uses a digital camera to take a snapshot of the back of the patient's hand rather than a blood sample. The image obtained is cropped and compared with images in a database for known cholesterol levels.

The noninvasive test looks at cholesterol levels in patients with increased risk of heart disease. Their approach is based on the creation of a large database of cholesterol levels recorded using standard blood tests and linked to a standardized photograph of the hand for each patient; cholesterol is concentrated in the creases of one's fingers. They developed an image-processing computer program that compares the image from a new patient with the thousands of entries in the database and matches it to a specific cholesterol reading.

Measuring the amount and type of cholesterol circulating in the blood is an important risk factor in cardiovascular disease. Excess cholesterol not used by the body in making hormones and building cells is laid down on the inner wall of arteries as a waxy plaque, which can reduce the normal flow of blood potentially causing heart problems and increasing the risk of cerebral stroke. Total cholesterol is a useful early indicator, although more detailed testing to distinguish between high-density lipoprotein (HDL), low-density lipoprotein (LDL), and triglycerides is needed for a more accurate health assessment of patients found to have high total cholesterol. It is LDL, so-called "bad" cholesterol, that contributes to the formation of arterial plaques (known as atherosclerosis). So, image analysis can reveal the presence of different cholesterol levels in the skin.

What's more, a noninvasive and inexpensive method for cholesterol screening would allow this risk factor be determined in much larger patient populations without the need for costly and inconvenient blood tests. The team will also soon publish details of the extension of this work to classifying cholesterol type using their approach.

More details on the existing work have been published in the Journal of Medical Engineering and Informatics; for more information, please visit http://www.inderscience.com/info/inarticle.php?artid=48384.

-----

Follow us on Twitter, 'like' us on Facebook, and join our group on LinkedIn

Laser Focus World has gone mobile: Get all of the mobile-friendly options here.

Subscribe now to BioOptics World magazine; it's free!