Overview of Artificial Intelligence Based Biomedical Applications of Infrared Thermal Imag-ing

Year 2021, Volume: 1 Issue: 1, 24 - 34, 15.04.2021

Saim Ervural Murat Ceylan

Abstract

Infrared thermal imaging is a non-invasive, harmless radiation-free non-contact mo-dality that allows monitoring of body temperature distribution and change. Providing physiological information about peripheral blood flow, autonomic nervous system, va-soconstriction / vasodilation, inflammation, sweating or other processes has expanded its use in the medical field. Developments in the field of artificial intelligence have also found response in medical applications, and machine learning methods have become used for many tasks such as decision making, disease monitoring, and surgical plan-ning. Using artificial intelligence methods to interpret thermal data can be an effective solution to provide doctors with a second opinion in a diagnosis, treatment planning or surgical evaluation scenario. The purpose of this research; To evaluate the functioning of artificial intelligence methods in medical applications such as classification and decision making of thermal imaging by examining the literature sources and to provide informa-tion about the literature.

Keywords

Artificial intelligence, Classification, Thermography, Infrared thermal imaging, Biomedical decision making

Kızılötesi Termal Görüntülemenin Yapay Zekâ Tabanlı Biyomedikal Uygulamalarına Bakış

Abstract

Kızılötesi termal görüntüleme, vücut sıcaklığı dağılımının ve değişiminin izlenmesine izin veren invazif olmayan, zararlı radyasyon içermeyen, temassız bir modalitedir. Peri-ferik kan akışı, otonom sinir sistemi, vazokonstrüksiyon / vazodilatasyon, iltihaplanma, terleme veya diğer süreçler hakkında fizyolojik bilgiler sağlaması medikal alanda kul-lanımını yaygınlaştırmıştır. Yapay zekâ alanında yaşanan gelişmeler medikal uygula-malarda da karşılık bulmuş ve makine öğrenimi metotları; karar verme, hastalık takibi, cerrahi planlama gibi birçok görev için kullanılır hâle gelmiştir. Termal verilerin yo-rumlanması için yapay zekâ yöntemlerinin kullanılması, bir tanı, tedavi planlama veya cerrahi değerlendirme senaryosunda doktorlara ikinci bir görüş sağlamak için etkin bir çözüm olabilir. Bu araştırmanın amacı: Literatür kaynaklarının incelenerek termal gö-rüntülemenin medikal uygulamalardaki sınıflandırma, karar verme gibi süreçlerde yapay zekâ yöntemlerinin işleyişlerini değerlendirmek ve literatür hakkında bilgi sunmaktır.

Keywords

Yapay zekâ, Sınıflandırma, Termografi, Kızılötesi termal görüntüleme, Biyomedikal karar verme

References

• 1.Rogalski, A. and Chrzanowski, K. Infrared devices and tech-niques. Optoelectronics Review, 2002. 10(2): p. 111-136.
• 2. Sruthi, S. and Sasikala, M. A. low cost thermal imaging system for medical diagnostic applications. in 2015 International Con-ference on Smart Technologies and Management for Computing, Communication, Controls, Energy and Materials (ICSTM). 2015. IEEE.
• 3. Bouzida, N., Bendada, A. and Maldague, X.P. Visualization of body thermoregulation by infrared imaging. Journal of Thermal Biology, 2009. 34(3): p. 120-126.
• 4.Ring, E. and Bacon, P. Quantitative thermographic assessment of inositol nicotinate therapy in Raynaud’s phenomena. Journal of International Medical Research, 1977. 5(4): p. 217-222.
• 5.Lahiri, B., et al. Medical applications of infrared thermography: a review. Infrared Physics & Technology, 2012. 55(4): p. 221-235.
• 6.Hildebrandt, C., et al. The application of medical infrared ther-mography in sports medicine. An international perspective on topics in sports medicine and sports injury, 2012. 534.
• 7.Knobel, R.B., Guenther, B.D.and Rice, H.E. Thermoregulation and thermography in neonatal physiology and disease. Biologi-cal research for nursing, 2011. 13(3): p. 274-282.
• 8.Jones, B.F. A reappraisal of the use of infrared thermal image analysis in medicine. IEEE transactions on medical imaging, 1998. 17(6): p. 1019-1027.
• 9.Ring, E. and Ammer, K. Infrared thermal imaging in medicine. Physiological measurement, 2012. 33(3): p. R33.
• 10.Technical reference for thermal imagers for human tempera-ture screening. Part 1, Requirements and test methods. 2003: Sin-gapore
• 11. Technical reference for thermal imagers for human tempera-ture screening. Part 2, SPRING Singapore. 2004, Standardisa-tion Dept., SPRING Singapore: Singapore.12. Ammer, K., The Glamorgan Protocol for recording and eval-uation of thermal images of the human body. Thermol Int, 2008. 18(4): p. 125-44.
• 13. Schwartz, R., et al. The american academy of thermology. Guidelines for neuromusculoskeletal thermography. Thermol Int, 2006. 16: p. 5-9.
• 14. Govindarajan, J., A Case for Joint Development of IR Camer-as in India. Journal on Intelligent Electronic Systems, 2007. 1(1).
• 15. Steketee, J., Spectral emissivity of skin and pericardi-um. Physics in Medicine & Biology, 1973. 18(5): p. 686.
• 16. Amalu, W., et al. Infrared imaging of the breast—An overview. The Biomedical Engineering Handbook, 3rd ed., Med-ical Devices and Systems. CRC Press, Baton Rouge, 2006.
• 17. Lawson, R. Implications of surface temperatures in the diagnosis of breast cancer. Canadian Medical Association Jour-nal, 1956. 75(4): p. 309.
• 18. Williams, K.L., Williams, F.L. and Handley, R. Infra-red ther-mometry in the diagnosis of breast disease. The Lancet, 1961. 278(7217): p. 1378-1381.
• 19. Gershon-Cohen, J., Haberman-Brueschke, J. and Brueschke, E. Medical thermography: A summary of current status. Radio-logic Clinics of North America, 1965. 3(3): p. 403-431.
• 20. Haberman, J.D. The present status of mammary thermogra-phy. CA: a cancer journal for clinicians, 1968. 18(6): p. 314-321.
• 21. Winsor, T. and Bendezu, J. Thermography and the peripheral circulation. Annals of the New York Academy of Sciences, 1964. 121(1): p. 135-156.
• 22. Skversky, N.J., Herring, A.B. and Baron, R.C. Thermography in peripheral vascular diseases. Annals of the New York Academy of Sciences, 1964. 121(1): p. 118-134.
• 23. Albert, S., Glickman, M. and Kallish, M. Thermography in orthopedics. Annals of the New York Academy of Sciences, 1964. 121(1): p. 157-170.
• 24. Connell Jr, J.F., Morgan, E. and Rousselot, L.M. Thermog-raphy in trauma. Annals of the New York Academy of Sciences, 1964. 121(1): p. 171-176.
• 25. Boas, N.F. Thermography in rheumatoid arthritis. Annals of the New York Academy of Sciences, 1964. 121(1): p. 223-234.
• 26. Lane, W.Z., Thermography in diseases of the thorax. Annals of the New York Academy of Sciences, 1964. 121(1): p. 190-208.
• 27. Sandrow, R.E., et al. The use of thermography in the early diagnosis of neuropathic arthropathy in the feet of diabetics. Clin-ical Orthopaedics and Related Research®, 1972. 88: p. 31-33.
• 28. Hartmann, M., Kunze, J. and Friedel, S. Telethermography in the diagnostics and management of malignant melanomas. The journal of dermatologic surgery and oncology, 1981. 7(3): p. 213-218.
• 29. Cole, R.P., Jones, S. and Shakespeare, P. Thermographic as-sessment of hand burns. Burns, 1990. 16(1): p. 60-63.
• 30. Soffin, C.B., et al. Thermography and oral inflammato-ry . Oral surgery, oral medicine, oral pathology, 1983. 56(3): p. 256-262.
• 31. Steed, P.A., The utilization of contact liquid crystal thermog-raphy in the evaluation of temporomandibular dysfunction. CRA-NIO®, 1991. 9(2): p. 120-128.
• 32. Herrick, R.T. and Herrick, S.K. Thermography in the detec-tion of carpal tunnel syndrome and other compressive neuropa-thies. The Journal of hand surgery, 1987. 12(5): p. 943-949.
• 33. Shatsova, E. and Popov, V. The possibilities of infrared ther-mography in the diagnosis of thyroid pathology. Problemy en-dokrinologii, 1989. 35(2): p. 34-37.
• 34. Nilsson, N.J. Principles of artificial intelligence. 2014: Mor-gan Kaufmann.
• 35. Deo, R.C. Machine learning in medicine. Circulation, 2015. 132(20): p. 1920-1930. Medikal Termografi ve Yapay Zekâ Tabanlı Uygulamaları32
• 36. Ng, E. and Sudharsan, N. Numerical computation as a tool to aid thermographic interpretation. Journal of medical engineering & technology, 2001. 25: p. 53-60.
• 37. Zuluaga-Gomez, J., et al. A CNN-based methodology for breast cancer diagnosis using thermal images. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visual-ization, 2020: p. 1-15.
• 38. Gogoi, U.R., et al. Singular value based characterization and analysis of thermal patches for early breast abnormality detection. Australasian physical & engineering sciences in medicine, 2018. 41(4): p. 861-879.
• 39. Roslidar, R., et al. A Review on Recent Progress in Thermal Imaging and Deep Learning Approaches for Breast Cancer Detec-tion. IEEE Access, 2020. 8: p. 116176-116194.
• 40. Sathish, D., et al. Asymmetry analysis of breast thermograms using automated segmentation and texture features. Signal, Image and Video Processing, 2017. 11(4): p. 745-752.
• 41. Araujo, A.D.S., et al. Computer aided diagnosis for breast diseases based on infrared images. in 2017 IEEE/ACS 14th In-ternational Conference on Computer Systems and Applications (AICCSA). 2017. IEEE.
• 42. Gogoi, U.R., et al. Evaluating the efficiency of infrared breast thermography for early breast cancer risk prediction in asymp-tomatic population. Infrared Physics & Technology, 2019. 99: p. 201-211.
• 43. Baffa, M.d.F.O. and Lattari, L.G. Convolutional neural net-works for static and dynamic breast infrared imaging classifica-tion. in 2018 31st SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI). 2018. IEEE.
• 44. Fernández-Ovies, F.J., et al. Detection of breast cancer using infrared thermography and deep neural networks. in International Work-Conference on Bioinformatics and Biomedical Engineer-ing. 2019. Springer.
• 45. Roslidar, R., et al. A study of fine-tuning CNN models based on thermal imaging for breast cancer classification. in 2019 IEEE International Conference on Cybernetics and Computational In-telligence (CyberneticsCom). 2019. IEEE.
• 46. Schaefer, G., Závišek, M. and Nakashima, T. Thermography based breast cancer analysis using statistical features and fuzzy classification. Pattern recognition, 2009. 42(6): p. 1133-1137.
• 47. Nicandro, C.-R., et al. Evaluation of the diagnostic power of thermography in breast cancer using bayesian network classifi-ers. Computational and mathematical methods in medicine, 2013. 2013.
• 48. EtehadTavakol, M., et al. Breast cancer detection from ther-mal images using bispectral invariant features. International Jour-nal of Thermal Sciences, 2013. 69: p. 21-36.
• 49. Silva, L.F., et al. Thermal Signal Analysis for Breast Cancer Risk Verification. in MedInfo. 2015.
• 50. Wahab, A.A., et al. Tumor localization in breast thermography with various tissue compositions by using Artificial Neural Net-work. in 2015 IEEE Student Conference on Research and Devel-opment (SCOReD). 2015. IEEE.
• 51. Milosevic, M., Jankovic, D. and Peulic, A. Thermography based breast cancer detection using texture features and minimum variance quantization. EXCLI journal, 2014. 13: p. 1204.
• 52. Francis, S.V., Sasikala, M. and Saranya, S. Detection of breast abnormality from thermograms using curvelet transform based feature extraction. Journal of medical systems, 2014. 38(4): p. 1-9.
• 53. Zadeh, H.G., et al. Segmenting breast cancerous regions in thermal images using fuzzy active contours. EXCLI journal, 2016. 15: p. 532.
• 54. Lashkari, A. Early Breast Cancer Detection in Thermogram Images using Supervised and Unsupervised Algorithms. Middle East Journal of Cancer, 2016. 7(3): p. 113-124.
• 55. Raghavendra, U., et al. An integrated index for breast cancer identification using histogram of oriented gradient and kernel lo-cality preserving projection features extracted from thermograms. Quantitative InfraRed Thermography Journal, 2016. 13(2): p. 195-209.
• 56. Sims Jr, D.S., Cavanagh, P.R. and Ulbrecht, J.S. Risk factors in the diabetic foot: recognition and management. Physical thera-py, 1988. 68(12): p. 1887-1902.
• 57. Purnima, S., et al. Automated Detection of Diabetic Foot Us-ing Thermal Images by Neural Network Classifiers. International Journal of Emerging Trends in Science and Technology, 2017. 4(2348-9480): p. 5183-5188.
• 58. Hernandez-Contreras, D., et al. Automatic classification of thermal patterns in diabetic foot based on morphological pattern spectrum. Infrared Physics & Technology, 2015. 73: p. 149-157.
• 59. Alzubaidi, L., et al. DFU_QUTNet: diabetic foot ulcer classi-fication using novel deep convolutional neural network. Multime-dia Tools and Applications, 2020. 79(21): p. 15655-15677.
• 60. Cruz-Vega, I., et al. A comparison of intelligent classifiers of thermal patterns in diabetic foot. in 2019 IEEE Internation-al Instrumentation and Measurement Technology Conference (I2MTC). 2019. IEEE.
• 61. Adam, M., et al. Automated detection of diabetic foot with and without neuropathy using double density-dual tree-complex wavelet transform on foot thermograms. Infrared Physics & Tech-nology, 2018. 92: p. 270-279.
• 62. Gururajarao, S.B., et al. Infrared thermography and soft computing for diabetic foot assessment, in Machine Learning in Bio-Signal Analysis and Diagnostic Imaging. 2019, Elsevier. p. 73-97.
• 63. Samant, P. and Agarwal, R. Machine learning techniques for medical diagnosis of diabetes using iris images. Computer meth-ods and programs in biomedicine, 2018. 157: p. 121-128.
• 64. Lupi, O., Tyring, S.K. and McGinnis, M.R. Tropical derma-tology: Fungal tropical diseases. Journal of the American Acade-my of Dermatology, 2005. 53(6): p. 931-951.
• 65. Magalhaes, C., et al. Distinguishing melanocytic nevi from melanomas using static and dynamic infrared thermal imaging. Journal of the European Academy of Dermatology and Venereol-ogy, 2019. 33(9): p. 1700-1705.
• 66. Linos, E., et al. Increasing burden of melanoma in the Unit-ed States. Journal of Investigative Dermatology, 2009. 129(7): p. 1666-1674.
• 67. Magalhaes, C., Vardasca, R. and Mendes, J. Recent use of medical infrared thermography in skin neoplasms. Skin Research and Technology, 2018. 24(4): p. 587-591.
• 68. Bauer, J., et al. Non-contact thermal imaging as potential tool for personalized diagnosis and prevention of cellulite. Journal of Thermal Analysis and Calorimetry, 2018. 133(1): p. 571-578.
• 69. Organization, W.H. Newborn death and illness. 2020; Avail-able from: https://www.who.int/pmnch/media/press_materials/fs/fs_newborndealth_illness/en/.
• 70. Hug, L., et al. National, regional, and global levels and trends in neonatal mortality between 1990 and 2017, with scenar-io-based projections to 2030: a systematic analysis. The Lancet Global Health, 2019. 7(6): p. e710-e720.
• 71. Vyas, H.V., Greenberg, S.B. and Krishnamurthy, R. MR imaging and CT evaluation of congenital pulmonary vein abnormali-ties in neonates and infants. Radiographics, 2012. 32(1): p. 87-98.
• 72. Taylor, A.M. Cardiac imaging: MR or CT? Which to use when. Pediatric radiology, 2008. 38: p. 433.
• 73. Topalidou, A., et al. Thermal imaging applications in neona-tal care: a scoping review. BMC pregnancy and childbirth, 2019. 19(1): p. 1-14.
• 74. Ervural, S., Ceylan, M. and Örnek, A.H. Yapay zekânın ter-mal görüntüleme üzerine uygulamaları. Türkiye Klinikleri Rady-oloji, 2020: p. 6-11.
• 75. Herry, C.L., Frize, M. and Bariciak. E. Assessment of abdom-inal skin temperature change in premature newborns with NEC compared to healthy controls. in 5th European Conference of the International Federation for Medical and Biological Engineering. 2011. Springer.
• 76. Frize, M., et al. Infrared Imaging and Classification of Neo-nates with Necrotising Enterocolitis. in World Congress on Med-ical Physics and Biomedical Engineering May 26-31, 2012, Bei-jing, China. 2013. Springer.
• 77. Ornek, A.H., Ervural, S. and Ceylan, M. Determination of Correct Approaches in Evaluation of Thermograms, in IX. UR-SI-TÜRKİYE 2018 BİLİMSEL KONGRESİ. 2018, International Union of Radio Science: KTO Karatay Üniversitesi, Konya.
• 78. Ornek, A.H., Ceylan, M. and Ervural, S. Health status detec-tion of neonates using infrared thermography and deep convo-lutional neural networks. Infrared Physics & Technology, 2019. 103: p. 103044.
• 79. Örnek, A.H. and Ceylan. M. Classification of Medical Ther-mograms using Transfer Learning. in 2020 28th Signal Process-ing and Communications Applications Conference (SIU). 2020. IEEE.
• 80. Örnek, A.H. and Ceylan. M. Explainable Features in Classi-fication of Neonatal Thermograms. in 2020 28th Signal Process-ing and Communications Applications Conference (SIU). 2020. IEEE.
• 81. Savasci, D., et al. Classification of unhealthy and healthy neo-nates in neonatal intensive care units using medical thermography processing and artificial neural network, in Classification Tech-niques for Medical Image Analysis and Computer Aided Diagno-sis. 2019, Elsevier. p. 1-29.
• 82. Ervural, S. and Ceylan, M. Detection of Pulmonary Abnor-malities of Neonates Using Thermal Imaging and Convolutional Neural Network, in Conference on Machine Intelligence in Med-ical Imaging. 2020, Society for Imaging Informatics in Medicine: Online.
• 83. Gulyaev, Y.V., et al. Dynamical infrared thermography in humans. IEEE Engineering in Medicine and Biology Magazine, 1995. 14(6): p. 766-771.
• 84. Ogura, Y., et al. Elevation of body temperature is an essen-tial factor for exercise-increased extracellular heat shock protein 72 level in rat plasma. American Journal of Physiology-Regula-tory, Integrative and Comparative Physiology, 2008. 294(5): p. R1600-R1607.
• 85. Alpar, O. and Krejcar, O. Detection of irregular thermoreg-ulation in hand thermography by fuzzy C-means. in Internation-al Conference on Bioinformatics and Biomedical Engineering. 2018. Springer.
• 86. Papež, B.J., et al. Infrared thermography based on artificial intelligence as a screening method for carpal tunnel syndrome di-agnosis. Journal of International Medical Research, 2009. 37(3): p. 779-790.
• 87. Papež, B.J., Palfy, M. and Turk, Z. Infrared thermography based on artificial intelligence for carpal tunnel syndrome diag-nosis. Journal of International Medical Research, 2008. 36(6): p. 1363-1370.
• 88. Acharya, U.R., et al. Automated diagnosis of dry eye using infrared thermography images. Infrared Physics & Technology, 2015. 71: p. 263-271.
• 89. Acharya, U.R., et al. Diagnosis of response and non-response to dry eye treatment using infrared thermography images. Infra-red Physics & Technology, 2014. 67: p. 497-503.
• 90. Frize, M. and Ogungbemile, A. Estimating rheumatoid arthri-tis activity with infrared image analysis. Studies in health technol-ogy and informatics, 2012. 180: p. 594-598.
• 91. Umapathy, S., Vasu, S. and Gupta, N. Computer aided diag-nosis based hand thermal image analysis: a potential tool for the evaluation of rheumatoid arthritis. Journal of Medical and Bio-logical Engineering, 2018. 38(4): p. 666-677.
• 92. Egbert, D.D., Kaburlasos, V.G. and Goodman, P.H. Neural network discrimination of subtle image patterns. in 1990 IJCNN International Joint Conference on Neural Networks. 1990. IEEE.
• 93. Koprowski, R. Automatic analysis of the trunk thermal imag-es from healthy subjects and patients with faulty posture. Com-puters in biology and medicine, 2015. 62: p. 110-118.
• 94. Gopinath, M. and Prabu, S. Classification of thyroid abnor-malities on thermal image: a study and approach. IIOABJ, May, 2016: p. 41-57.
• 95. Procházka, A., et al. Breathing analysis using thermal and depth imaging camera video records. Sensors, 2017. 17(6): p. 1408.
• 96. Koukiou, G. and Anastassopoulos, V. Fusion of Dissimi-lar Features from Thermal Imaging for Improving Drunk Person Identification. Int. J. Signal Process. Syst, 2017. 5: p. 106-111.
• 97. Lopez, M.B., del-Blanco, C.R. and Garcia, N. Detecting ex-ercise-induced fatigue using thermal imaging and deep learning. in 2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA). 2017. IEEE.
• 98. Thiruvengadam, J. and Mariamichael, A. A preliminary study for the assessment of hypertension using static and dynamic IR thermograms. Biomedical Engineering/Biomedizinische Tech-nik, 2018. 63(2): p. 197-206.
• 99. Jian, B.L., et al. The facial expression of schizophrenic pa-tients applied with infrared thermal facial image sequence. BMC psychiatry, 2017. 17(1): p. 1-7.
• 100. Martínez-Jiménez, M.A., et al. Development and validation of an algorithm to predict the treatment modality of burn wounds using thermographic scans: Prospective cohort study. PloS one, 2018. 13(11): p. e0206477.
• 101. Jayanthi, T. and Anburajan, M. Model-based computer-aided method for diagnosis of cardiovascular disease using IR thermo-gram. 2019.
• 102. Nagori, A., et al. Predicting hemodynamic shock from ther-mal images using machine learning. Scientific reports, 2019. 9(1): p. 1-9.
• 103. Cho, Y., Julier, S.J. and Bianchi-Berthouze, N. Instant stress: detection of perceived mental stress through smartphone pho-toplethysmography and thermal imaging. JMIR mental health, 2019. 6(4): p. e10140.
• 104. Chang, T.C., Hsiao, Y.L. and Liao, S.L. Application of dig-ital infrared thermal imaging in determining inflammatory state and follow-up effect of methylprednisolone pulse therapy in pa-tients with Graves’ ophthalmopathy. Graefe’s Archive for Clinical and Experimental Ophthalmology, 2008. 246(1): p. 45-49.
• 105. Acharya, U.R., et al. Thermography based breast cancer de-tection using texture features and support vector machine. Journal of medical systems, 2012. 36(3): p. 1503-1510.
• 106. Magalhaes, C., Vardasca, R. and Mendes, J. Classifying Skin Neoplasms with Infrared Thermal Images. in presented at the 14th Quantitative InfraRed Thermography Conference (QIRT 2018). 2018.
• 107. Armstrong, D., et al. Infrared Dermal Thermometry for the High-Risk Diabetic Foot. Physical therapy, 1997. 77: p. 169-75; discussion 176.