Hyperspectral Imaging

Hyperspectral imaging is a technique that unites conventional imaging and spectroscopy. Using this technology, both the spatial and spectral information of an object can be acquired. The obtained 3D image (two spatial and one spectral dimension) consists of about a hundred or more spectral bands for every measured point of an object. Initially developed as a complex satellite or aircraft-based system, the technology has finally evolved into a compact imaging tool that can be used for medical, industrial, and other relevant applications. Application of the machine learning (ML) algorithms allows close to real-time image processing based on the advanced numerical models such as seven-layer skin model we use in our study.

Selected results

Hyperspectral imaging assisted with the ML technique has been applied for functional skin imaging

Reconstructed values of the epidermal thickness (b) and melanin content (c) for the Caucasian skin type (a). Retrieved maps of skin blood volume fraction before (d), during (e) and 1 min after (f) the ring finger occlusion. Increase of skin blood volume fraction after the release of the occlusion ring (f) clearly indicated the reactive hyperemia. Corresponding maps of skin blood oxygenation before (g), during (h) and 1 min after (i) the occlusion.

Monitorig of skin complications of Diabetes Mellitus with Polarized Hyperspectral imaging.

The developed system has been used to reveal early changes in skin blood microcirculation and skin structure of patients with diabetes. The dorsal surface of the patients’ feet has been imaged.

It was observed that the diabetic patients had increased skin blood content and, at the same time, the reduced oxygen level in comparison to the control group of healthy volunteers. In addition, the diabetic group has an increased polarization index that is attributed to the changes in skin collagen structure.

The values of blood volume fraction, skin blood oxygenation, and polarization index were found to have statistically significant difference between the control and the diabetic groups.

Media appearance

(FI) https://www.kaleva.fi/oulun-yliopistossa-kehitetty-uusi-menetelma-palja…

(FI) https://www.oulu.fi/fi/uutiset/uusi-menetelma-paljastaa-diabeteksen-aih…

(ENG) https://www.oulu.fi/en/news/new-method-reveals-skin-complications-diabe…

Selected publications

1. V. Dremin, Z. Marcinkevics, E. Zherebtsov, A. Popov, A. Grabovskis, H. Kronberga, K. Geldnere, A. Doronin, I. Meglinski, A. Bykov, "Skin complications of diabetes mellitus revealed by polarized hyperspectral imaging and machine learning", IEEE Trans. Med. Imaging, 40(4), 1207-1216 (2021).

2. V. Dremin, E. Zherebtsov, A. Bykov, A. Popov, A. Doronin, and I. Meglinski, "Influence of blood pulsation on diagnostic volume in pulse oximetry and photoplethysmography measurements," Appl. Opt. 58, 9398-9405 (2019).

3. E. Zherebtsov, V. Dremin, A. Popov, A. Doronin, D. Kurakina, M. Kirillin, I. Meglinski, A. Bykov, “Hyperspectral imaging of human skin aided by artificial neural networks”, Biomed. Opt. Express, 10(7), 3545-3559 (2019). (top downloads Jul 2019, noteworthy research highlight 2021).

4. A. Popov, A. Bykov, I. Meglinski, “Influence of probe pressure on diffuse reflectance spectra of human skin measured in vivo” J. Biomed. Opt., 22(11), 110504 (2017). (cover page article).

5. J. Spigulis, I. Oshina, A. Berzina, A. Bykov, “Smartphone snapshot mapping of skin chromophores under triple-wavelength laser illumination”, J. Biomed. Opt., 22(9), 091508 (2017).