Abstract
Almost 50% of individuals around the globe are unaware of diabetes and its complications. So, an early screening of diabetes is very important at this current situation. To overcome the difficulties such as pain and discomfort to the subjects obtained from the biochemical diagnostic procedures; an infrared thermography is the diagnostic technique which measures the skin surface temperature noninvasively. Thus, the aim of our proposed study was to evaluate the type II diabetes in facial thermograms and to develop a computer aided diagnosis (CAD) system to classify the normal and diabetes. The facial thermograms (n = 160) including male (n = 79) and female (n = 81) were captured using FLIR A 305sc infrared thermal camera. The Haralick textural features were extracted from the facial thermograms based on gray level co-occurrence matrix algorithm. The TROI, TMAX, and TTOT are the statistical temperature parameters exhibited a significant negative correlation with HbA1c (r = − 0.421, − 0.411, − 0.242, p < 0.01 (TROI); r = − 0.259, p < 0.01(TMAX) and − 0.173, p < 0.05 (TTOT)). An optimal regression equation has been constructed by using the significant facial variables and standard HbA1c values. The model has achieved sensitivity, specificity, and accuracy rate as 91.42%, 88.57%, and 90% respectively. The anthropometrical variables, extracted textural features and temperature parameters were fed into the classifiers and their performances were compared. The Support Vector Machine outperformed the Linear Discriminant Analysis (84.37%) and k-Nearest Neighbor (81.25%) classifiers with the maximum accuracy rate of 89.37%. The developed CAD system has achieved 89.37% of accuracy rate for the classification of diabetes. Thus, the facial thermography could be used as the basic non-invasive prognostic tool for the evaluation of type II diabetes mellitus.
Similar content being viewed by others
References
World Health Organization (2019) Classification of diabetes mellitus. WHO, Geneva
American Diabetes Association (2019) Classification and diagnosis of diabetes mellitus: standards of medical care in diabetes. Diabetes Care 42:S13–S28
Swinburn BA, Caterson I, Seidell JC, James WP (2004) Diet, nutrition and the prevention of excess weight gain and obesity. Public Health Nutr 7:123–146
Kaveeshwar SA, Cornwall J (2014) The current state of diabetes mellitus in India. Australas Med J 7:45–48
Roglic G (2016) WHO global report on diabetes: a summary. Int J Noncommun Dis 1:5
Mohan V, Sandeep S, Deepa R, Shah B, Varghese C (2007) Epidemiology of type 2 diabetes: Indian scenario. Indian J Med Res 125:217–230
Ciudin A, Hernandez C, Simo R (2012) Noninvasive methods of glucose measurement: current status and future perspectives. Curr Diabetes Rev 8:48–54
Cox ME, Edelman D (2009) Tests for screening and diagnosis of type 2 diabetes. Clin Diabetes 27:132–138
Solnica B, Naskalski JW, Sieradzi J (2003) Analytical performance of glucometers used for routine glucose self-monitoring of diabetic patients. Clin Chim Acta 331:29–35
Ng EYK (2009) A review of thermography as promising non-invasive detection modality for breast tumor. Int J Therm Sci 48:849–859
Hardy JD (1934) The radiation of heat from the human body: I. An instrument for measuring the radiation and surface temperature of the skin. J Clin Invest 13:593–604
Flesch U (1983) The application of infrared-sensors in medicine. Adv Infrared Sens Technol 0395:210–219
Faust O, Acharya UR, Ng EYK, Hong TJ, Yu W (2014) Application of infrared thermography in computer aided diagnosis. Infrared Phys Technol 66:160–175
Ring F (2010) Thermal imaging today and its relevance to diabetes. J Diabetes Sci Technol 4:857–862
Ring EFJ, Ammer K (2000) The technique of infrared imaging in medicine. Thermol Int 10:7–14
Formenti D, Ludwig N, Gargano M, Gondola M, Dellerma N, Caumo A, Alberti G (2013) Thermal imaging of exercise-associated skin temperature changes in trained and untrained female subjects. Ann Biomed Eng 41:863–871
Hernandez-Contreras D, Peregrina-Barreto H, Rangel-Magdaleno J, Gonzalez-Bernal J (2016) Narrative review: diabetic foot and infrared thermography. Infrared Phys Technol 78:105–117
Pontes SMM, Melo LHP, Maia NPS, Nogueira ANC, Vasconcelos TB, Pereira EDB, Bastos VPD, Holanda MA (2017) Influence of the ventilator mode on acute adverse effects and facial thermography after noninvasive ventilation. J Bras Pneumol 43:87–94
Alan Weinstein S, Weinstein G, Weinstein EL, Gelb M (1991) Facial thermography, basis, protocol, and clinical value. J Craniomandib Sleep Pract 9:201–211
Sivanandam S, Anburajan M, Venkataraman B, Menaka M, Sharath D (2012) Medical thermography: a diagnostic approach for type 2 diabetes mellitus based on non-contact infrared thermal imaging. Endocrine 42:343–351
Schulte BP, Bomhof MA, Aarts NJ (1975) Facial thermography in the diagnosis of cerebrovascular disease and in evaluation of carotid endarterectomy. Clin Neurol Neurosurg 78:118–130
Thiruvengadam J, Anburajan M, Menaka M, Venkataraman B (2014) Potential of thermal imaging as a tool for prediction of cardiovascular disease. J Med Phys 39:98–105
Ludwig N, Formenti D, Rossi A (2016) Assessing facial skin temperature asymmetry in different methods. Proceedings of QIRT
Haddad DS, Brioschi ML, Baladi MG, Arita ES (2016) A new evaluation of heat distribution on facial skin surface by infrared thermography. Dentomaxillofac Radiol 45:20150264
Nathan DM (2009) International expert committee report on the role of the A1C assay in the diagnosis of diabetes. Diabetes Care 32:1327–1334
American Diabetes Association (2018) Standards of medical care in diabetes-2018. Diabetes Care 41:S1–S118
Amalu W, Block J, Chaudhry A (2002) Standards and protocols in clinical thermographic imaging. Int Acad Clin Thermol 1–35
Ludwig N, Formenti D, Gargano M, Alberti G (2014) Skin temperature evaluation by infrared thermography: comparison of image analysis methods. Infrared Phys Technol 62:1–6
Gomez W, Pereira WCA, Infantosi AFC (2012) Analysis of co-occurrence texture statistics as a function of gray-level quantization for classifying breast ultrasound. IEEE Trans Med Imaging 31:1889–1899
Haralick RM, Shanmugam K, Its'Hak D (1973) Textural features for image classification. IEEE Trans Syst Man Cybern 3:610–621
Lo CS, Wang CM (2012) Support vector machine for breast MR image classification. Comput Math Appl 64:1153–1162
Etemad K, Chellappa R (1997) Discriminant analysis for recognition of human face images. J Opt Soc Am A 14:1724–1733
Ramteke RJ, Yashawant KM (2012) Automatic medical image classification and abnormality detection using k-nearest neighbour. Int J Adv Comput Res 4:190–196
Zweig MH, Campbell G (1993) Receiver-operating characteristic (ROC) plots: a fundamental evaluation tool in clinical medicine. Clin Chem 39:561–577
Bowers AJ, Zhou X (2019) Receiver operating characteristic (ROC) area under the curve (AUC): a diagnostic measure for evaluating the accuracy of predictors of education outcomes. J Educ Stud Placed Risk 24:20–46
Mungreiphy NK, Kapoor S, Sinha R (2011) Association between BMI, blood pressure, and age: study among Tangkhul Naga Tribal Males of Northeast India. J Anthropol. https://doi.org/10.1155/2011/748147
Torchinsky MY, Gomez R, Rao J, Vargas A, Mercante DE, Chalew SA (2004) Poor glycemic control is associated with increased diastolic blood pressure and heart rate in children with Type 1 diabetes. J Diabetes Complicat 18:220–223
Wang J, Liu L, Zhou Y, Wang C, Hu H, Hoff K, Guo Y, Gao X, Wang A, Wu S, Zhao X (2014) Increased fasting glucose and the prevalence of arterial stiffness: a cross-sectional study in Chinese adults. Neurol Res 36:427–433
Jonasson H, Bergstrand S, Nystrom FH, Lanne T, Ostgren CJ, Bjarnegard NJ, Fredriksson I, Larsson M, Stromberg T (2017) Skin microvascular endothelial dysfunction is associated with type 2 diabetes independently of microalbuminuria and arterial stiffness. Diabetes Vasc Dis Res 1:1–9
Charkoudian N (2003) Skin blood flow in adult human thermoregulation: how it works, when it does not, and why. Mayo Clin Proc 78:603–612
Irace C, Carallo C, Scavelli F, De MS, Esposito FT, Gnasso A (2014) Blood viscosity in subjects with normoglycemia and prediabetes. Diabet Care 37:488–492
Sivanandam S, Anburajan M, Venkataraman B, Menaka M, Sharath D (2013) Estimation of blood glucose by noninvasive infrared thermography for diagnosis of type 2 diabetes: an alternative for blood sample extraction. Mol Cell Endocrinol 367:57–63
Kabeya Y, Kato K, Tomita M, Katsuki T, Oikawa Y, Shimada A (2015) Association between diabetes and increased prevalence of paranasal sinus disease: A cross sectional study in Japanese Adults. J Epidemio 25:297–302
Zhang M, Lin L, Xu X, Wu X, Jin Q, Liu H (2019) Noninvasive screening tool to detect undiagnosed diabetes among young and middle-aged people in Chinese community. Int J Diab Dev Count 39:458–462
Arora AS, Singh J (2015) Paranasal sinusitis detection using thermal imaging. Proceedings of the science and information conference, London, UK, July 28–30; pp 184–188
Jonsson A, Wales JK (1976) Blood glycoprotein levels in diabetes. Diabetologia 12:245–250
Adama M, Ng EYK, Oh SH, Heng ML, Hagiwara Y, Tan JH, Tong JWK, Acharya UR (2018) Automated characterization of diabetic foot using nonlinear features extracted from thermograms. Infrared Phys Technol 89:325–337
Mahendran G, Dhanasekaran R (2015) Investigation of the severity level of diabetic retinopathy using supervised classifier algorithms. Comput Electr Eng 45:312–323
Murugeswari S, Sukanesh R (2017) Investigations of severity level measurements for diabetic macular oedema using machine learning algorithms. Ir J Med Sci 4:929–938
Gopinath MP, Murali S (2017) Comparative study on classification algorithm foe diabetes dataset. International Journal of Pure and Applied Mathematics 117:47–52
Janardhanan P, Heena L, Sabika F (2015) Effectiveness of support vector machines in medical data mining. J Commun Softw Syst 11:25–30
Vardasca R, Vaz L, Mendes J (2018) Classification and decision making of medical infrared thermal images. Classification in BioApps. Springer, Cham, pp 79–104
Vardasca R, Magalhaes C, Mendes J (2019) Biomedical applications of infrared thermal imaging: current state of machine learning classification. In: The 15th international workshop on advanced infrared technology and applications (AITA2019), Florence, Italy, 17–19 September 2019, 27:46
Bandalakunta Gururajarao S, Venkatappa U, Shivaram JM, Sikkandar MY, Al Amoudi A (2019) Infrared Thermography and Soft Computing for Diabetic Foot Assessment. Machine Learning in Bio-Signal Analysis and Diagnostic Imaging. 73–97
Nowakowski A, Kaczmarek M (2011) Active dynamic thermography-problems of implementation in medical diagnostics. Quant InfraRed Thermogr J 8:89–106
Kaczmarek M, Nowakowski A (2016) Active IR-thermal imaging in medicine. J Non destruct Eval 35:19
Acknowledgements
The authors would like to express their sincere gratefulness to SRM Hospital and Research Centre, Kattankulathur, Tamilnadu, India for the facility provided in the hospital to acquire the data. And, also wish to thank Dr. Anburajan Mariamichael, Director at Directorate of Radiation Safety, AMTZ, Vishakhapatnam, Andhra Pradesh, India for his technical support and advice.
Funding
This article does not receive funding from any agencies. All expenses have been managed by the first author.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
Ethical Approval
All procedures performed in studies involving human participants by the ethical standards of the institutional research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.
Informed Consent
Informed consent was obtained from all individual participants included in the study.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Thirunavukkarasu, U., Umapathy, S., Janardhanan, K. et al. A computer aided diagnostic method for the evaluation of type II diabetes mellitus in facial thermograms. Phys Eng Sci Med 43, 871–888 (2020). https://doi.org/10.1007/s13246-020-00886-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13246-020-00886-z