UDC

616-092.11

Authors

Irina S. Kozhevnikova*, Mikhail N. Pankov*, Nadezhda A. Ermoshina**
*Northern (Arctic) Federal University named after M.V. Lomonosov (Arkhangelsk, Russian Federation)
**Baltic State Technical University “VOENMEH” named after D.F. Ustinov (St. Petersburg, Russian Federation)

Abstract

This article provides an analytical review of recent achievements in the development of automated thermogram interpretation systems for diagnosing breast cancer. Effective use of thermography in diagnosing breast cancer requires a computer-aided diagnosis system (CADx) capable of performing instant image analysis and providing an interpretation of the data. The purpose of CADx is to determine the nature of the phenomena presented in the thermogram. Computer algorithms involved in the CADx scheme include four steps: image pre-processing, segmentation, feature extraction and selection, and classification. Over the past few years, significant results have been achieved in automating the diagnosis based on thermogram analysis in terms of accuracy, specificity and sensitivity. These results were possible mainly due to improved performance of thermal imagers, as well as successful development of algorithms for image processing and data analysis. The accuracy with which algorithms determine the presence or absence of a tumour is close to 100 %; there are models that are able to reliably identify the anatomical areas of interest. Nevertheless, the problem of a significant number of false positive and false negative results is still far from being solved. The most promising research areas address such problems as thermal image sequence analysis and interpretation which makes it possible not only to record the spatial distribution of body temperature but also to analyse the temporal changes in temperature or stress test responses. Another important research area focuses on the development of methods for a detailed analysis of detected tumours in order to separate cancerous tissue from the normal one, classify benign and malignant cancers and identify the stage of the disease. The quality of the existing models of computer-aided diagnosis systems based on thermogram analysis is not sufficient for their implementation and application in clinical practice. However, the dynamics of the development and improvement of new methods allows us to suggest that it will be possible in the nearest future.

Keywords

computer-aided diagnosis systems, infrared thermography, medical image processing, breast tumour detection

References

1. Makarova M.V., Yunitsyna A.V. Teplovizionnoe issledovanie molochnykh zhelez v otsenke ob”emnykh obrazovaniy [Thermal Imaging of Breast for Tumour Evaluation]. Vestnik Severnogo (Arkticheskogo) federal’nogo universiteta. Ser.: Mediko-biologicheskie nauki, 2013, no. 3, pp. 44–50.
   
2. Etehadtavakol M., Ng E.Y.K. Breast Thermography as a Potential Non-Contact Method in the Early Detection of Cancer: A Review. J. Mech. Med. Biol., 2013, vol. 13, no. 2. Art. no. 1330001.
   
3. Isard H.J., Becker W., Shilo R., Ostrum B.J. Breast Thermography After Four Years and 10,000 Studies. Am. J. Roentgenol., 1972, vol. 115, no. 4, pp. 811–821.
   
4. Jones C.H. Thermography of the Female Breast. Diagnosis of Breast Disease. Baltimore, 1983, pp. 214–234.
   
5. Gautherie M., Gros C. Breast Thermography and Cancer Risk Prediction. Cancer, 1980, vol. 45, no. 1, pp. 51–56.
   
6. Silva L.F., Sequeiros G.O., Santos M.L., Fontes C.A., Muchaluat-Saade D.C., Conci A. Signal Analysis for Breast Cancer Risk Verification. Stud. Health Technol. Inform., 2015, vol. 216, pp. 746–750.
   
7. Gerasimova E., Audit B., Roux S.G., Khalil A., Argoul F., Naimark O., Arneodo A. Multifractal Analysis of Dynamic Infrared Imaging of Breast Cancer. Europhys. Lett., 2014, vol. 104, no. 6. Art. no. 68001.
   
8. Antonini S., Kolarić D., Nola I.A., Herceg Ž., Ramljak V., Kuliš T., Holjevac J.K., Ferenčić Ž. Thermography Surveillance After Breast Conserving Surgery – Three Cases. ELMAR: Proc. 53rd Int. Symp. Zadar, 14–16 September 2011. IEEE, 2011, pp. 317–319.
   
9. Agostini V., Knaflitz M., Molinari F. Motion Artifact Reduction in Breast Dynamic Infrared Imaging. IEEE Trans. Biomed. Eng., 2009, vol. 56, no. 3, pp. 903–906.
   
10. Negin M., Ziskin M.C., Piner C., Lapayowker M.S. A Computerized Breast Thermographic Interpreter. IEEE Trans. Biomed. Eng., 1977, vol. 24, no. 4, pp. 347–352.
    
11. Perona P., Malik J. Scale Space and Edge Detection Using Anisotropic Diffusion. IEEE Trans. Pattern Anal. Mach. Intell., 1990, vol. 12, no. 7, pp. 629–639.
    
12. Suganthi S.S., Ramakrishnan S. Anisotropic Diffusion Filter Based Edge Enhancement for Segmentation of Breast Thermogram Using Level Sets. Biomed. Signal Process. Control, 2014, vol. 10, no. 1, pp. 128–136.
    
13. Chao S.-M., Tsai D.-M. An Improved Anisotropic Diffusion Model for Detail- and Edge-Preserving Smoothing. Pattern Recognit. Lett., 2010, vol. 31, no. 13, pp. 2012–2023.
    
14. Kafieh R., Rabbani H. Wavelet-Based Medical Infrared Image Noise Reduction Using Local Model for Signal and Noise. IEEE Stat. Signal Process. Workshop, 2011, pp. 549–552.
    
15. Dinsha D., Manikandaprabu N. Breast Tumor Segmentation and Classification Using SVM and Bayesian from Thermogram Images. Unique J. Eng. Adv. Sci., 2014, vol. 2, no. 2, pp. 147–151.
    
16. Kamath D., Kamath S., Prasad K., Rajagopal K.V. Segmentation of Breast Thermogram Images for the Detection of Breast Cancer – A Projection Profile Approach. J. Image Graph., 2015, vol. 3, no. 1, pp. 213–217.
    
17. Nader A.E.-R.M. Breast Cancer Risk Detection Using Digital Infrared Thermal Images. Int. J. Bioinform. Biomed. Eng., 2015, vol. 1, no. 2, pp. 185–194.
    
18. Kapoor P., Prasad S.V.A.V., Patni S. Image Segmentation and Asymmetry Analysis of Breast Thermograms for Tumor Detection. Int. J. Comput. Appl., 2012, vol. 50, no. 9, pp. 40–45.
    
19. Pramanik S., Bhattacharjee D., Nasipuri M. Wavelet Based Thermogram Analysis for Breast Cancer Detection. Int. Symp. Adv. Comput. Commun. Silchar, 14–15 September 2015. IEEE, 2015, pp. 67–72.
    
20. Rajaa N.S.M., Sukanya S.A., Nikita Y. Improved PSO Based Multi-Level Thresholding for Cancer Infected Breast Thermal Images Using Otsu. Procedia Comput. Sci., 2015, vol. 48, pp. 524–529.
    
21. Zadeh H.G., Kazerouni I.A., Haddadnia J. Distinguish Breast Cancer Based on Thermal Features in Infrared Images. Can. J. Image Process. Comput. Vis., 2011, vol. 2, no. 6, pp. 116–121.
    
22. Golestani N., Etehadtavakol M., Ng E.Y.K. Level Set Method for Segmentation of Infrared Breast Thermograms. EXCLI J., 2014, vol. 13, pp. 241–251.
    
23. Fisenko V.T., Fisenko T.Yu. Wavelet Segmentation of Color Texture Images. J. Opt. Technol., 2012, vol. 79, no. 11, pp. 693–697.
    
24. Nurhayati O.D., Widodo T.S., Susanto A., Tjokronagoro M. First Order Statistical Features for Breast Cancer Detection Using Thermal Images. WASET, 2010, vol. 46, pp. 382–384.
    
25. Milosevic M., Jankovic D., Peulic A. Thermography Based Breast Cancer Detection Using Texture Features and Minimum Variance Quantization. EXCLI J., 2014, no. 13, pp. 1204–1215.
    
26. Lashkari A., Pak F., Firouzmand M. Full Intelligent Cancer Classification of Thermal Breast Images to Assist Physician in Clinical Diagnostic Applications. J. Med. Signals Sens., 2016, vol. 6, no. 1, pp. 12–24.
    
27. Suganthi S.S., Ramakrishnan S. Analysis of Breast Thermograms Using Gabor Wavelet Anisotropy Index. J. Med. Syst., 2014, vol. 38, no. 9, pp. 101–106.
    
28. Francis S.V., Sasikala M., Saranya S. Detection of Breast Abnormality from Thermograms Using Curvelet Transform Based Feature Extraction. J. Med. Syst., 2014, vol. 38, no. 4. Art. no. 23.
    
29. Etehadtavakol M., Lucas C., Sadri S., Ng E.Y.K. Analysis of Breast Thermography Using Fractal Dimension to Establish Possible Difference Between Malignant and Benign Patterns. J. Healthc. Eng., 2010, vol. 1, no. 1, pp. 27–43.
    
30. Etehadtavakol M., Ng E.Y.K., Chandran V., Rabbani H. Separable and Non-Separable Discrete Wavelet Transform Based Texture Features and Image Classification of Breast Thermograms. Infrared Phys. Technol., 2013, vol. 61, pp. 274–286.
    
31. Lakshmi N.V.S.S.R., Jaipurkar S., Neelakanta K. Study on Mammary Rotational Infrared Thermographic System (MAMRIT). Proc. 2015 Glob. Conf. Commun. Technol. Thuckalay, 23–24 April 2015. IEEE, 2015, pp. 576–578.
    
32. Francis S.V., Sasikala M., Bharathi G.B., Jaipurkar S.D. Breast Cancer Detection in Rotational Thermography Images Using Texture Features. Infrared Phys. Technol., 2014, vol. 67, pp. 490–496.
    
33. Popova N.V., Popov V.A., Gudkov A.B. Diagnosticheskoe znachenie termografii ruk, ul’trazvukovogo issledovaniya sonnykh arteriy i arterial’nogo davleniya u bol’nykh ishemicheskoy bolezn’yu serdtsa [Diagnostic Significance of Hand Thermography, Ultrasonic Research of Carotid and Arterial Pressure in Patients with Ischemic Heart Disease]. Ekologiya cheloveka, 2013, no. 10, pp. 32–36.
    
34. Kozhevnikova I.S., Pankov M.N., Gribanov A.V., Startseva L.F., Ermoshina N.A. Primenenie infrakrasnoy termografii v sovremennoy meditsine (obzor literatury) [The Use of Infrared Thermography in Modern Medicine (Literature Review)]. Ekologiya cheloveka, 2017, no. 2, pp. 39–46.