skip to main content
survey

Empirical Review of Various Thermography-based Computer-aided Diagnostic Systems for Multiple Diseases

Published: 08 May 2023 Publication History

Abstract

The lifestyle led by today’s generation and its negligence towards health is highly susceptible to various diseases. Developing countries are at a higher risk of mortality due to late-stage presentation, inaccessible diagnosis, and high-cost treatment. Thermography-based technology, aided with machine learning, for screening inflammation in the human body is non-invasive and cost-wise appropriate. It requires very little equipment, especially in rural areas with limited facilities. Recently, Thermography-based monitoring has been deployed worldwide at various organizations and public gathering points as a first measure of screening COVID-19 patients. In this article, we systematically compare the state-of-the-art feature extraction approaches for analyzing thermal patterns in the human body, individually and in combination, on a platform using three publicly available Datasets of medical thermal imaging, four Feature Selection methods, and four well-known Classifiers, and analyze the results. We developed and used a two-level sampling method for training and testing the classification model. Among all the combinations considered, the classification model with Unified Feature-Sets gave the best performance for all the datasets. Also, the experimental results show that the classification accuracy improves considerably with the use of feature selection methods. We obtained the best performance with a features subset of 45, 57, and 39 features (from Unified Feature Set) with a combination of mRMR and SVM for DB-DMR-IR and DB-FOOT-IR and a combination of ReF and RF for DB-THY-IR. Also, we found that for all the feature subsets, the features obtained are relevant, non-redundant, and distinguish normal and abnormal thermal patterns with the accuracy of 94.75% on the DB-DMR-IR dataset, 93.14% on the DB-FOOT-IR dataset, and 92.06% on the DB-THY-IR dataset.

References

[1]
U. Rajendra Acharya, Eddie Yin-Kwee Ng, Jen-Hong Tan, and S. Vinitha Sree. 2012. Thermography-based breast cancer detection using texture features and support vector machine. J. Med. Syst. 36, 3 (2012), 1503–1510.
[2]
Muhammad Adam, Eddie Y. K. Ng, Shu Lih Oh, Marabelle L. Heng, Yuki Hagiwara, Jen Hong Tan, Jasper W. K. Tong, and U. Rajendra Acharya. 2018. Automated detection of diabetic foot with and without neuropathy using double density-dual tree-complex wavelet transform on foot thermograms. Infrared Phys. Technol. 92 (2018), 270–279.
[3]
M. A. Aweda, A. O. Adeyomoye, and G. A. Abe. 2012. Thermographic analysis of thyroid diseases. Adv. Appl. Sci. Res 3, 4 (2012), 2027–2032.
[4]
S. Bagavathiappan, J. Philip, T. Jayakumar, B. Raj, P. N. S. R. Rao, M. Varalakshmi, and V. V. Mohan. 2010. Correlation between plantar foot temperature and diabetic neuropathy: A case study by using an infrared thermal imaging technique. J. Diabetes Sci. Technol. 1, 4 (2010), 1386–1392.
[5]
Shawli Bardhan and Mrinal Kanti Bhowmik. 2019. 2-stage classification of knee joint thermograms for rheumatoid arthritis prediction in subclinical inflammation. Australas. Phys. Eng. Sci. Med. 42, 1 (2019), 259–277.
[6]
Shawli Bardhan, Mrinal Kanti Bhowmik, Satyabrata Nath, and Debotosh Bhattacharjee. 2015. A review on inflammatory pain detection in human body through infrared image analysis. In International Symposium on Advanced Computing and Communication (ISACC). 251–257. DOI:
[7]
O. H. Beahrs. 1979. Report to the working group to review the National Cancer Institute-American Cancer Society breast cancer demonstration projects. J. Natl. Cancer Inst. 62 (1979), 639–709.
[8]
Christopher M. Bishop. 2006. Pattern Recognition and Machine Learning. Springer. Retrieved from https://www.microsoft.com/en-us/research/people/cmbishop/#!prml-book.
[9]
Tiago B. Borchartt, Aura Conci, Rita C. F. Lima, Roger Resmini, and Angel Sanchez. 2013. Breast thermography from an image processing viewpoint: A survey. Sig. Process. 93, 10 (2013), 2785–2803. DOI:
[10]
Leo Breiman, J. H. Friedman, R. A. Olshen, and C. J. Stone. 1984. Classification and Regression Trees. Wadsworth Publishing Company, Belmont, CA.
[11]
Busra Can, Ozgur Kara, Muhammet Cemal Kizilarslanoglu, Gunes Arik, Gozde Sengul Aycicek, Fatih Sumer, Ramazan Civelek, Canan Demirtas, and Zekeriya Ulger. 2017. Serum markers of inflammation and oxidative stress in sarcopenia. Aging Clin. Experim. Res. 29, 4 (2017), 745–752.
[12]
Martha Rebeca Canales-Fiscal, Rocío Ortiz López, Regina Barzilay, Víctor Treviño, Servando Cardona-Huerta, Luis Javier Ramírez-Treviño, Adam Yala, and José Tamez-Peña. 2021. COVID-19 classification using thermal images: Thermal images capability for identifying COVID-19 using traditional machine learning classifiers. In 12th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics. 1–5.
[13]
C. Cortes and V. Vapnik. 1995. Support-vector networks. Mach. Learn. 20 (1995), 273–297.
[14]
T. Cover and P. Hart. 1967. Nearest neighbor pattern classification. IEEE Trans. Inf. Theor. 13, 1 (1967), 21–27. DOI:
[15]
Israel Cruz-Vega, Hayde Peregrina-Barreto, Jose de Jesus Rangel-Magdaleno, and Juan Manuel Ramirez-Cortes. 2019. A comparison of intelligent classifiers of thermal patterns in diabetic foot. In IEEE International Instrumentation and Measurement Technology Conference (I2MTC). IEEE, 1–6.
[16]
Nicholas A. Diakides and Joseph D. Bronzino. 2007. Medical Infrared Imaging. CRC Press.
[17]
Mahnaz Etehadtavakol, Zahra Emrani, and Eddie Yin Kwee Ng. 2019. Rapid extraction of the hottest or coldest regions of medical thermographic images. Med. Biolog. Eng. Comput. 57, 2 (2019), 379–388.
[18]
Mahnaz Etehadtavakol and Eddie Y. K. Ng. 2017. Potential of thermography in pain diagnosing and treatment monitoring. In Application of Infrared to Biomedical Sciences. Springer, 19–32.
[19]
Mahnaz Etehadtavakol, Eddie Y. K. Ng, and Mohammad Hassan Emami. 2017. Potential of infrared imaging in assessing digestive disorders. In Application of Infrared to Biomedical Sciences. Springer, 1–18.
[20]
Oliver Faust, U. Rajendra Acharya, E. Y. K. Ng, Tan Jen Hong, and Wenwei Yu. 2014. Application of infrared thermography in computer aided diagnosis. Infrared Phys. Technol. 66 (2014), 160–175.
[21]
Sheeja V. Francis, M. Sasikala, and S. Saranya. 2014. Detection of breast abnormality from thermograms using curvelet transform-based feature extraction. J. Med. Syst. 38, 4 (2014), 23.
[22]
Michel Gautherie. 1983. Thermobiological assessment of benign and malignant breast diseases. Amer. J. Obstet. Gynecol. 147, 8 (1983), 861–869.
[23]
Usha Rani Gogoi, Mrinal Kanti Bhowmik, Anjan Kumar Ghosh, Debotosh Bhattacharjee, and Gautam Majumdar. 2017. Discriminative feature selection for breast abnormality detection and accurate classification of thermograms. In International Conference on Innovations in Electronics, Signal Processing and Communication (IESC). IEEE, 39–44.
[24]
José R. González, Charbel Damião, and Aura Conci. 2017. An infrared thermal images database and a new technique for thyroid nodules analysis. Stud. Health Technol. Inform. 245 (2017), 384–387. Retrieved from http://europepmc.org/abstract/MED/29295121.
[25]
Trasha Gupta, Rajni Jindal, and S. Indu. 2020. Empirical analysis of thermography effectiveness for health diagnosis. In International Conference on Computational Science and Computational Intelligence (CSCI). IEEE, 830–835.
[26]
Peter E. Hart, David G. Stork, and Richard O. Duda. 2000. Pattern Classification. Wiley Hoboken.
[27]
Daniel Hernández-Contreras, Hayde Peregrina-Barreto, Jose Rangel-Magdaleno, and Francisco Renero-Carrillo. 2019. Plantar thermogram database for the study of diabetic foot complications. IEEE Access 7 (2019), 161296–161307. DOI:
[28]
H. Usuki, T. Ikeda, Y. Igarashi, I. Takahashi, A. Fukami, T. Yokoe, H. Sonoo, and K. Asaishi. 1998. What kinds of non-palpable breast cancer can be detected by thermography? Biomed. Thermol. 4, 18 (1998), 8–12.
[29]
Erik Ingelsson, Johan Årnlöv, Johan Sundström, and Lars Lind. 2005. Inflammation, as measured by the erythrocyte sedimentation rate, is an independent predictor for the development of heart failure. J. Amer. Coll. Cardiol. 45, 11 (2005), 1802–1806.
[30]
R. Karthiga and K. Narasimhan. 2021. Medical imaging technique using curvelet transform and machine learning for the automated diagnosis of breast cancer from thermal image. Pattern Anal. Applic. 24, 3 (2021), 1–11.
[31]
Kosar Khaksari, Thien Nguyen, Brian Y. Hill, Timothy Quang, John Perrault, Viswanath Gorti, Ravi Malpani, Emily Blick, Tomas Gonzalez Cano, Babak Shadgan et al. 2021. Review of the efficacy of infrared thermography for screening infectious diseases with applications to COVID-19. J. Med. Imag. 8, S1 (2021), 010901.
[32]
Kenji Kira, Larry A. Rendell et al. 1992. The feature selection problem: Traditional methods and a new algorithm. In AAAI Conference on Artificial Intelligence. 129–134.
[33]
Lauren N. Ko, Adam B. Raff, Anna C. Garza-Mayers, Allison S. Dobry, Antonio Ortega-Martinez, R. Rox Anderson, and Daniela Kroshinsky. 2018. Skin surface temperatures measured by thermal imaging aid in the diagnosis of cellulitis. J. Investig. Dermatol. 138, 3 (2018), 520–526.
[34]
Igor Kononenko. 1994. Estimating attributes: Analysis and extensions of RELIEF. In European Conference on Machine Learning. Springer, 171–182.
[35]
R. Lawson. 1956. Implications of surface temperatures in the diagnosis of breast cancer. Canadian Medical Association Journal 75, 4 (1956), 309–311.
[36]
Huan Liu and Rudy Setiono. 1995. Chi2: Feature selection and discretization of numeric attributes. In 7th IEEE International Conference on Tools with Artificial Intelligence. IEEE, 388–391.
[37]
Haochen Liu, Yiqi Wang, Wenqi Fan, Xiaorui Liu, Yaxin Li, Shaili Jain, Yunhao Liu, Anil Jain, and Jiliang Tang. 2022. Trustworthy AI: A computational perspective. ACM Trans. Intell. Syst. Technol. 14, 1 (Nov.2022). DOI:
[38]
Scott M. Lundberg, Gabriel Erion, Hugh Chen, Alex DeGrave, Jordan M. Prutkin, Bala Nair, Ronit Katz, Jonathan Himmelfarb, Nisha Bansal, and Su-In Lee. 2020. From local explanations to global understanding with explainable AI for trees. Nature Mach. Intell. 2, 1 (2020), 2522–5839.
[39]
Scott M. Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems 30. Curran Associates, Inc., 4765–4774. Retrieved from http://papers.nips.cc/paper/7062-a-unified-approach-to-interpreting-model-predictions.pdf.
[40]
G. Machin, A. Whittam, S. Ainarkar, J. Allen, J. Bevans, M. Edmonds, B. Kluwe, A. Macdonald, N. Petrova, P. Plassmann et al. 2017. A medical thermal imaging device for the prevention of diabetic foot ulceration. Physiol. Measur. 38, 3 (2017), 420.
[41]
Eddie Y. K. Ng and Mahnaz Etehadtavakol. 2017. Application of Infrared to Biomedical Sciences. Springer.
[42]
Kalliopi Pafili and Nikolaos Papanas. 2015. Thermography in the follow up of the diabetic foot: best to weigh the enemy more mighty than he seems. Expert Rev Med Devices. 12, 2 (2015), 131–3. DOI:
[43]
Karl Pearson. 1920. Notes on the history of correlation. Biometrika 13, 1 (101920), 25–45. DOI:
[44]
Hanchuan Peng, Fuhui Long, and Chris Ding. 2005. Feature selection based on mutual information: Criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans. Pattern Anal. Mach. Intell. 27, 8 (Aug.2005), 1226–1238. DOI:
[45]
Stephen P. Power, Fiachra Moloney, Maria Twomey, Karl James, Owen J. O’Connor, and Michael M. Maher. 2016. Computed tomography and patient risk: Facts, perceptions and uncertainties. World J. Radiol. 8, 12 (2016).
[46]
Jose Ignacio Priego Quesada, Marcos Roberto Kunzler, and Felipe P. Carpes. 2017. Methodological aspects of infrared thermography in human assessment. In Application of Infrared Thermography in Sports Science. Springer, 49–79.
[47]
Hairong Qi, Phani Teja Kuruganti, and Wesley E. Snyder. 2012. Detecting breast cancer from thermal infrared images by asymmetry analysis. Med. Medic. Res. 38 (2012).
[48]
Rozita Rastghalam and Hossein Pourghassem. 2016. Breast cancer detection using MRF-based probable texture feature and decision-level fusion-based classification using HMM on thermography images. Pattern Recog. 51 (2016), 176–186.
[49]
J. Saminathan, M. Sasikala, V. B. Narayanamurthy, K. Rajesh, and R. Arvind. 2020. Computer aided detection of diabetic foot ulcer using asymmetry analysis of texture and temperature features. Infrared Phys. Technol. 105 (2020), 103219.
[50]
Dayakshini Sathish, Surekha Kamath, Keerthana Prasad, and Rajagopal Kadavigere. 2019. Role of normalization of breast thermogram images and automatic classification of breast cancer. Visual Comput. 35, 1 (2019), 57–70.
[51]
Gerald Schaefer, Michal Závišek, and Tomoharu Nakashima. 2009. Thermography-based breast cancer analysis using statistical features and fuzzy classification. Pattern Recog. 42, 6 (2009), 1133–1137.
[52]
G. Serbu. 2009. Infrared imaging of the diabetic foot. In Proceedings on InfraMation. Vol. 86, Citeseer, 5–20.
[53]
L. F. Silva, D. C. M. Saade, G. O. Sequeiros, A. C. Silva, A. C. Paiva, R. S. Bravo, and Aura Conci. 2014. A new database for breast research with infrared image. J. Med. Imag. Health Inform. 4, 1 (2014), 92–100.
[54]
Valmir Oliveira Silvino, Regis Bernardo Brandim Gomes, Sérgio Luiz Galan Ribeiro, Davyson de Lima Moreira, and Marcos Antonio Pereira dos Santos. 2020. Identifying febrile humans using infrared thermography screening: Possible applications during COVID-19 outbreak. Revista Contexto Saúde 20, 38 (2020), 5–9.
[55]
Vera A. van Atteveld, Jeanine M. Van Ancum, Esmee M. Reijnierse, Marijke C. Trappenburg, Carel G. M. Meskers, and Andrea B. Maier. 2019. Erythrocyte sedimentation rate and albumin as markers of inflammation are associated with measures of sarcopenia: A cross-sectional study. BMC Geriat. 19, 1 (2019), 1–8.
[56]
Ricardo Vardasca, Carolina Magalhaes, and Joaquim Mendes. 2019. Biomedical applications of infrared thermal imaging: Current state of machine learning classification. Proceedings 27 (2019), 46. DOI:
[57]
Valanarasi Antony Santiagu Vaz. 2014. Diagnosis of hypo and hyperthyroid using MLPN network. Int. J. Innov. Res. Sci. Eng. Technol. 3, 7 (2014), 14314–14323.

Cited By

View all
  • (2024)Self-derived Knowledge Graph Contrastive Learning for RecommendationProceedings of the 32nd ACM International Conference on Multimedia10.1145/3664647.3681693(7571-7580)Online publication date: 28-Oct-2024
  • (2024) Segmenting hotspots from medical thermal images using Density-based modified FC- P c FS with spatial information Quantitative InfraRed Thermography Journal10.1080/17686733.2024.2408714(1-37)Online publication date: 10-Oct-2024

Index Terms

  1. Empirical Review of Various Thermography-based Computer-aided Diagnostic Systems for Multiple Diseases

      Recommendations

      Comments

      Information & Contributors

      Information

      Published In

      cover image ACM Transactions on Intelligent Systems and Technology
      ACM Transactions on Intelligent Systems and Technology  Volume 14, Issue 3
      June 2023
      451 pages
      ISSN:2157-6904
      EISSN:2157-6912
      DOI:10.1145/3587032
      • Editor:
      • Huan Liu
      Issue’s Table of Contents

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      Published: 08 May 2023
      Online AM: 16 February 2023
      Accepted: 29 December 2022
      Revised: 15 December 2022
      Received: 25 July 2022
      Published in TIST Volume 14, Issue 3

      Permissions

      Request permissions for this article.

      Check for updates

      Author Tags

      1. Breast cancer
      2. medical thermography
      3. diabetes
      4. thyroid cancer
      5. feature extraction
      6. classification
      7. feature selection

      Qualifiers

      • Survey

      Contributors

      Other Metrics

      Bibliometrics & Citations

      Bibliometrics

      Article Metrics

      • Downloads (Last 12 months)89
      • Downloads (Last 6 weeks)5
      Reflects downloads up to 02 Mar 2025

      Other Metrics

      Citations

      Cited By

      View all
      • (2024)Self-derived Knowledge Graph Contrastive Learning for RecommendationProceedings of the 32nd ACM International Conference on Multimedia10.1145/3664647.3681693(7571-7580)Online publication date: 28-Oct-2024
      • (2024) Segmenting hotspots from medical thermal images using Density-based modified FC- P c FS with spatial information Quantitative InfraRed Thermography Journal10.1080/17686733.2024.2408714(1-37)Online publication date: 10-Oct-2024

      View Options

      Login options

      Full Access

      View options

      PDF

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      Full Text

      View this article in Full Text.

      Full Text

      HTML Format

      View this article in HTML Format.

      HTML Format

      Figures

      Tables

      Media

      Share

      Share

      Share this Publication link

      Share on social media