Articles

Thermogram-based estimation of foot arterial blood flow using neural networks

Expand
  • 1. School of Energy and Power Engineering, Dalian University of Technology, Dalian 116023, Liaoning Province, China;
    2. State Power Investment Corporation Northeast Electric Power Co., Ltd., Shenyang 110181, China

Received date: 2022-07-03

  Revised date: 2022-11-22

  Online published: 2023-02-04

Supported by

the National Natural Science Foundation of China (No. 51976026) and the Fundamental Research Funds of Central Universities of China (No. DUT22YG206)

Abstract

The altered blood flow in the foot is an important indicator of early diabetic foot complications. However, it is challenging to measure the blood flow at the whole foot scale. This study presents an approach for estimating the foot arterial blood flow using the temperature distribution and an artificial neural network. To quantify the relationship between the blood flow and the temperature distribution, a bioheat transfer model of a voxel-meshed foot tissue with discrete blood vessels is established based on the computed tomography (CT) sequential images and the anatomical information of the vascular structure. In our model, the heat transfer from blood vessels and tissue and the inter-domain heat exchange between them are considered thoroughly, and the computed temperatures are consistent with the experimental results. Analytical data are then used to train a neural network to determine the foot arterial blood flow. The trained network is able to estimate the objective blood flow for various degrees of stenosis in multiple blood vessels with an accuracy rate of more than 90%. Compared with the Pennes bioheat transfer equation, this model fully describes intra- and inter-domain heat transfer in blood vessels and tissue, closely approximating physiological conditions. By introducing a vascular component to an inverse model, the blood flow itself, rather than blood perfusion, can be estimated, directly informing vascular health.

Cite this article

Yueping WANG, Lizhong MU, Ying HE . Thermogram-based estimation of foot arterial blood flow using neural networks[J]. Applied Mathematics and Mechanics, 2023 , 44(2) : 325 -344 . DOI: 10.1007/s10483-023-2959-9

References

[1] HU, F. B. Globalization of diabetes. Diabetes Care, 34(6), 1249–1257(2011)
[2] ASTASHEV, M. E., SEROV, D. A., and TANKANAG, A. V. A study of the oscillatory components of the skin microhemodynamics in mice by laser Doppler flowmetry. Biophysics, 63(1), 122–125(2018)
[3] FORSYTHE, R. O. and HINCHLIFFE, R. J. Assessment of foot perfusion in patients with a diabetic foot ulcer. Diabetes/Metabolism Research and Reviews, 32, 232–238(2016)
[4] ZHANG, Y. and ZHU, K. Relationship between tongue temperature and lingual circulation system in blood stasis syndrome and blood deficiency syndrome. Space Medicine & Medical Engineering, 23(4), 267–273(2010)
[5] SIVANANDAM, S., ANBURAJAN, M., VENKATRAMAN, B., MENAKA, M., and SHARATH, D. Medical thermography: a diagnostic approach for type 2 diabetes based on non-contact infrared thermal imaging. Endocrinology, 42(2), 343–351(2012)
[6] BAGAVATHIAPPAN, S., SARAVANAN, T., PHILIP, J., JAYAKUMAR, T., and JAGADEESAN, K. Investigation of peripheral vascular disorders using thermal imaging. The British Journal of Diabetes & Vascular Disease, 8(2), 102–104(2008)
[7] VAN NETTEN, J. J., VAN BAAL, J. G., LIU, C., VAN DER HEIJDEN, F., and BUS, S. A. Infrared thermal imaging for automated detection of diabetic foot complications. Journal of Diabetes Science and Technology, 7(5), 1122–1129(2013)
[8] NIEUWENHOFF, M. D., WU, Y., HUYGEN, F. J., SCHOUTEN, A. C., VAN DER HELM, F. C., and NIEHOF, S. P. Reproducibility of axon reflex-related vasodilation assessed by dynamic thermal imaging in healthy subjects. Microvascular Research, 106, 1–7(2016)
[9] NAGATA, K., HATTORI, H., SATO, N., ICHIGE, Y., and KIGUCHI, M. Heat transfer analysis for peripheral blood flow measurement system. Review of Scientific Instruments, 80(6), 064902(2009)
[10] SAGAIDACHNYI, A., FOMIN, A. V., USANOV, D. A., and SKRIPAL, A. V. Thermographybased blood flow imaging in human skin of the hands and feet: a spectral filtering approach. Physiological Measurement, 38(2), 272–288(2017)
[11] SAGAIDACHNYI, A., FOMIN, A. V., USANOV, D. A., and SKRIPAL, A. V. Real-time technique for conversion of skin temperature into skin blood flow: human skin as a low-pass filter for thermal waves. Computer Methods in Biomechanics and Biomedical Engineering, 22(12), 1009–1019(2019)
[12] WANG, Y. P., MU, L. Z., HE, Y., TANG, Y. L., LIU, C., LU, Y. X., and XU, L. S. Heat transfer analysis of blood perfusion in diabetic rats using a genetic algorithm. Microvascular Research, 131, 104013(2020)
[13] BAZÀN, F. S. V., BEDIN, L., and BORGES, L. S. Space-dependent perfusion coefficient estimation in a 2D bioheat transfer problem. Computer Physics Communications, 214, 18–30(2017)
[14] RICKETTS, P. L., MUDALIAR, A. V., ELLIS, B. E., PULLINS, C. A., MEYERS, L. A., LANZ, O. I., SCOTT, E. P., and DILLER, T. E. Non-invasive blood perfusion measurements using a combined temperature and heat flux surface probe. International Journal of Heat & Mass Transfer, 51(23-24), 5740–5748(2008)
[15] MA, W., LIU, W., and LI, M. Modeling heat transfer from warm water to foot: analytical solution and experimental validation. International Journal of Thermal Sciences, 98, 364–373(2015)
[16] COPETTI, M., DURÀNY, J., FERNANDEZ, J., and POCEIRO, L. Numerical analysis and simulation of a bio-thermal model for the human foot. Applied Mathematics and Computation, 305, 103–116(2017)
[17] BAYAREH, R., VERA, A., LEIJA, L., and GUTIERREZ, M. Simulation of the temperature distribution on a diabetic foot model: a first approximation. 13th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE), IEEE, New York, 1–5(2016)
[18] PENNES, H. H. Analysis of tissue and arterial blood temperature in the resting human forearm. Journal of Applied Physiology, 1, 93–122(1948)
[19] XUAN, Y. and ROETZEL, W. Bioheat equation of the human thermal system. Chemical Engineering Technology, 20(4), 268–276(1997)
[20] BLOWERS, S., MARSHAL, I., THRIPPLETON, M., ANDREWS, P., HARRIS, B., BETHUNE, I., and VALLURI, P. How does blood regulate cerebral temperatures during hypothermia? Scientific Reports, 8(1), 7877(2018)
[21] HE, Z. and LIU, J. A coupled continuum-discrete bioheat transfer model for vascularized tissue. International Journal of Heat & Mass Transfer, 107, 544–556(2017)
[22] HATWAR, R. and HERMAN, C. Inverse method for quantitative characterisation of breast tumours from surface temperature data. International Journal of Hyperthermia, 33(7), 741–757(2017)
[23] VIE, A., KLEINNIJENHUIS, A. M., and FARMER, D. J. Qualities, challenges and future of genetic algorithms: a literature review. arXiv preprint, arXiv: 2011.05277v3(2021)
[24] MELO, A., LOUREIRO, M., and LOUREIRO, F. Blood perfusion parameter estimation in tumors by means of a genetic algorithm. Procedia Computer Science, 108, 1384–1393(2017)
[25] YUE, K., ZHANG, Y., and ZHANG, X. X. Application of improved genetic algorithm to the noninvasive measurement of thermal parameters for living tissues. Journal of University of Science & Technology Beijing, 30(11), 1317–1321(2008)
[26] KATOCH, S., CHAUHAN, S. S., and KUMAR, V. A review on genetic algorithm: past, present, and future. Multimedia Tools and Applications, 80(5), 8091–8126(2021)
[27] GRIEU, S., OLIVIER, F., TRAORE, A., BERNARD, C., and JEANLUC, B. Artificial intelligence tools and inverse methods for estimating the thermal diffusivity of building materials. Energy & Buildings, 43(2-3), 543–554(2011)
[28] DENG, S. and HWANG, Y. Applying neural networks to the solution of forward and inverse heat conduction problems. International Journal of Heat & Mass Transfer, 49(25-26), 4732–4750(2006)
[29] MITRA, S. and BALAJI, C. A neural network based estimation of tumour parameters from a breast thermogram. International Journal of Heat & Mass Transfer, 53(21-22), 4714–4727(2010)
[30] BLOWERS, S. J. Modelling Brain Temperatures in Healthy Patients and Those with Induced Hypothermia, Ph. D. dissertation, The University of Edinburgh (2018)
[31] KOTTE, A., LEEUWEN, G. V., BREE, J. D., KOIJK, J. V. D., and LAGENFIJK, J. A description of discrete vessel segments in thermal modelling of tissues. Physics in Medicine & Biology, 41(5), 865–884(1996)
[32] BERGMAN, T. L., INCROPERA, F. P., DEWITT, D. P., and LAVINE, A. S. Fundamentals of Heat and Mass Transfer, John Wiley & Sons, New York (2011)
[33] RUMELHART, D. E., HINTON, G. E., and WILLIAMS, R. J. Learning representations by backpropagating errors. nature, 323(99), 533–536(1986)
[34] PENG, W. Y. Research on optimization and implementation of BP neural network algorithm. Proceedings of 7th International Conference on Intelligent Computation Technology and Automation (ICICTA), IEEE, New Yok, 104–107(2014)
[35] BAISH, J. W., AYYASWAMY, P. S., and FOSTER, K. R. Heat transport mechanisms in vascular tissues: a model comparison. Journal of Biomechanical Engineering, 108(4), 324–331(1986)
[36] GATT, A., FORMOSA, C., CASSAR, K., CAMILLERI, K. P., DE RAFFAELE, C., MIZZI, A., AZZOPARDI, C., MIZZI, S., FALZON, O., CRISTINA, S., and CHOCKALINGAM, N. Thermographic patterns of the upper and lower limbs: baseline data. International Journal of Vascular Medicine, 2015, 831369(2015)
[37] WULFF, W. The energy conservation equation for living tissue. IEEE Transactions on Biomedical Engineering, 6, 494–495(1974)
[38] KLINGER, H. Heat transfer in perfused biological tissue I: general theory. Bulletin of Mathematical Biology, 36, 403–415(1974)
[39] HE, Y., HIMENO, R., LIU, H., and HIDEO, Y. Finite element numerical analysis of blood flow and temperature distribution in three-dimensional image-based finger model. International Journal of Numerical Methods for Heat and Fluid Flow, 18(7-8), 932–953(2008)
[40] SHAO, H. W., HE, Y., and MU, L. Z. Numerical analysis of dynamic temperature in response to different levels of reactive hyperaemia in a three-dimensional image-based hand model. Computer Methods in Biomechanics & Biomedical Engineering, 17(5-8), 865–874(2014)
[41] ASTASIO-PICADO, A., MARTINEZ, E. E., and GOMEZ-MARTIN, B. Comparison of thermal foot maps between diabetic patients with neuropathic, vascular, neurovascular, and no complications. Current Diabetes Reviews, 15, 503–509(2019)
[42] CARBONELL, L., QUESADA, J. I. P., RETORTA, P., BENIMELI, M., DE ANDA, R. M. C. O., PALMER, R. S., PENA, R. J. G., GALINDO, C., ALMERO, L. P., BLASCO, M. C., MINGUEZ, M. F., and MACIÀN-ROMERO, C. Thermographic quantitative variables for diabetic foot assessment: preliminary results. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 7(5-6), 660–666(2019)
[43] ZHOU, Q., QIAN, Z. H., WU, J. N., LIU, J., REN, L., and REN, L. Q. Early diagnosis of diabetic peripheral neuropathy based on infrared thermal imaging technology. Diabetes/Metabolism Research and Reviews, 37, e3429(2021)
Outlines

/

APS Journals | CSTAM Journals | AMS Journals | EMS Journals | ASME Journals