University of Oulu

V. Dremin et al., "Skin Complications of Diabetes Mellitus Revealed by Polarized Hyperspectral Imaging and Machine Learning," in IEEE Transactions on Medical Imaging, vol. 40, no. 4, pp. 1207-1216, April 2021, doi: 10.1109/TMI.2021.3049591

Skin complications of diabetes mellitus revealed by polarized hyperspectral imaging and machine learning

Saved in:
Author: Dremin, Viktor1,2; Marcinkevics, Zbignevs3; Zherebtsov, Evgeny2;
Organizations: 1College of Engineering and Physical Sciences, Aston University, Birmingham B4 7ET, U.K.
2Opto-Electronics and Measurement Techniques Unit, University of Oulu, 90570 Oulu, Finland
3Department of Human and Animal Physiology, University of Latvia, LV-1004 Riga, Latvia
4VTT Technical Research Centre of Finland, 90571 Oulu, Finland
5Biophotonics Laboratory, Institute of Atomic Physics and Spectroscopy, University of Latvia, LV-1004 Riga, Latvia
6Medical Center Plavnieki, LV-1021 Riga, Latvia
7Pauls Stradins Clinical University Hospital, LV-1002 Riga, Latvi
8Computer Graphics Group, School of Engineering and Computer Science, Victoria University of Wellington, Wellington 6140, New Zealand
9Opto- Electronics and Measurement Techniques Unit, University of Oulu, 90570 Oulu, Finland
10Institute of Engineering Physics for Biomedicine (PhysBio), National Research Nuclear University MEPhI (Moscow Engineering Physics Institute), 115409 Moscow, Russia
11Interdisciplinary Laboratory of Biophotonics, National Research Tomsk State University, 634050 Tomsk, Russia
12Institute of Clinical Medicine N.V. Sklifosovsky, I.M. Sechenov First Moscow State Medical University, 129090 Moscow, Russia
Format: article
Version: published version
Access: open
Online Access: PDF Full Text (PDF, 3.5 MB)
Persistent link:
Language: English
Published: Institute of Electrical and Electronics Engineers, 2021
Publish Date: 2021-05-04


Aging and diabetes lead to protein glycation and cause dysfunction of collagen-containing tissues. The accompanying structural and functional changes of collagen significantly contribute to the development of various pathological malformations affecting the skin, blood vessels, and nerves, causing a number of complications, increasing disability risks and threat to life. In fact, no methods of non-invasive assessment of glycation and associated metabolic processes in biotissues or prediction of possible skin complications, e.g., ulcers, currently exist for endocrinologists and clinical diagnosis. In this publication, utilizing emerging photonics-based technology, innovative solutions in machine learning, and definitive physiological characteristics, we introduce a diagnostic approach capable of evaluating the skin complications of diabetes mellitus at the very earlier stage. The results of the feasibility studies, as well as the actual tests on patients with diabetes and healthy volunteers, clearly show the ability of the approach to differentiate diabetic and control groups. Furthermore, the developed in-house polarization-based hyperspectral imaging technique accomplished with the implementation of the artificial neural network provides new horizons in the study and diagnosis of age-related diseases.

see all

Series: IEEE transactions on medical imaging
ISSN: 0278-0062
ISSN-E: 1558-254X
ISSN-L: 0278-0062
Volume: 40
Issue: 4
Pages: 1207 - 1216
Article number: 9316275
DOI: 10.1109/TMI.2021.3049591
Type of Publication: A1 Journal article – refereed
Field of Science: 213 Electronic, automation and communications engineering, electronics
Funding: The authors would like to acknowledge the patients and volunteers. They are very grateful to Timo Hyvarinen and Katja Lefevre (SPECIM, Spectral Imaging Ltd., Finland) for the constructive comments and critical remarks in the frame of the current study.
Copyright information: © The Authors 2021. This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see