A Model for Diagnosing Breast Cancerous Tissue from Thermal Images Using Active Contour and Lyapunov Exponent
,
Abstract
Background: The segmentation of cancerous areas in breast images is important for the early detection of disease. Thermal imaging has advantages, such as being non-invasive, non-radiation, passive, quick, painless, inexpensive, and non-contact. Imaging technique is the focus of this research.
Methods: The proposed model in this paper is a combination of surf and corners that are very resistant. Obtained features are resistant to changes in rotation and revolution then with the help of active contours, this feature has been used for segmenting cancerous areas.
Results: Comparing the obtained results from the proposed method and mammogram show that proposed method is Accurate and appropriate. Benign and malignance of segmented areas are detected by Lyapunov exponent. Values obtained include TP=91.31%, FN=8.69%, FP=7.26%.
Conclusion: The proposed method can classify those abnormally segmented areas of the breast, to the Benign and malignant cancer.
National Cancer Institute (2012). Seer stat fact sheets: female Breast cancer. Available from: http://www.seer.can-cer.gov/statfacts/html/breast.html.
Ng EYK, Sudarshan NM (2001). Numerical com¬putation as a tool to aid thermo graphic Inter¬pretation. J Med Eng Technol, 25(2):53–60.
Leung TK, Lee CM, Chen CH et al (2009). Far in¬frared ray irradiation induces intra-cellular gener¬ation of nitric oxide in breast cancer cells. J Med Boil Eng, 29(1):15-18.
Kerr J (2004). Review of the effectiveness of infra¬red thermal imaging (thermography) for popu¬lation screening and diagnostic testing of breast cancer. NZHTA Tech Brief Series, 2004; 3(3).
Huang CL, Wu YW, Hwang CL, et al (2011). The application of infrared thermography in evalua¬tion of patients at high risk for lower extremity peripheral arterial disease. J Vasc Surg, 54(4):1074-1080.
Ring EFJ, Ammer K (2012). Infrared thermal im¬aging in medicine. Physiol meas, 33(3):R33-46.
Ng EYK (2008). A reviews of thermography as promising non-invasive detection mo-dality for breast tumor. Int J Therm Sci, 48:849-855.
Tan JH, Ng EYK, AcharyaU R, Chee C (2009).In¬frared Thermography on ocular surface tem¬perature: a review. Infrared Phys Techn, 52:97-108.
Ng EYK, Kee EC (2007). Advanced integrat-ed technique in breast cancer Thermogra-phy. J Med Eng Technol, 32(2):103-114.
Ng WK, Ng EYK, Tan YK (2009). Qualita-tive study of sexual functioning in couple with ED: prospective evaluation of the Thermography diagnostic system. J Reprod Med, 54(11-12): 698-705.
Ng EYK, Kaw GJL, Chang WM (2004). Analysis of IR thermal imager for mass blind fever screening. Microvasc Res, 68(2): 104-109.
Francis SV, Sasikala, M, Bharathi GB, Jaipur-kar SD (2014). Breast cancer detection in rotational thermography images using tex-ture features. In¬frared Phys Techn, 67:490-496.
Arora N, Martins D, Ruggerio D, Tousimis E, Simmons M at al (2008). Effectiveness of a noninvasive digital infrared thermal imaging system in the detection of breast cancer. Am J Surg, 196(4): 523–526.
Arabia P, Muttan S (2012). Multiple Irradia-tions by Hybrid Source for Early Breast Carcinoma de¬tection. Procedia Eng, 38: 2398–2412.
Wang S (2003). An Observation on Infrared Ther¬mograph of Lower Back Pain Pa-tients. Ind Health Occ Dis, 29(1).
Cheng KS, Yang SJ, Wang MS, Pan SC (2002). The application of thermal image analysis to diabetic foot diagnosis. J Med Biol Eng, 22(2):75–82.
Duarte A, Carrão L, Espanha M, Viana T, Freitas D, Bártolo P, Almeida H.A (2014). Segmenta¬tion algorithms for thermal im-ages. Procedia Technol, 16: 1560-1569.
Mabuchi K, Chinzei T at al (1998). Evaluating asymmetrical thermal distributions through im¬age processing. IEEE Eng Med Biol Mag, 17(4): 47–55.
Fujimasa I (1998). Path physiological expres-sion and analysis of far infrared thermal Images-A standard thermo graphic image diagnosis pro¬cedure using computed im-age processing. IEEE Eng Med Biol: 34–42.
RajendraAcharya U, Ng EYK, Tan JH, Vin-ithaSree S (2012). Thermography Based Breast Cancer Detection Using Texture Features and Support Vector Machine. J Med Syst, 36(3):1503-1510.
Hairong Qi, Kuruganti PT (2002). Detecting Breast Cancer from Thermal Infrared Images by Asymmetry Analysis. Eds, Medical Devices and Systems.1st ed, Joseph Bronzino. New York, pp.1155-1186.
Eng H, Thida M, Chew B, Leman K, Ang-grelly S (2008). Model -based detection and segmenta¬tion of vehicles for intelli-gent transportation system. IEEE Conf Ind Elec Appl, 2127-2132.
Huang K, Tan T (2010). Vs-star: a visual in-terpre¬tation system for visual surveillance. Pattern Recogn Lett, 31(14):2265-2285.
Harandi N, Sadri S, Moghaddam N, Fattahi R (2010). An automated method for seg-menta¬tion of epithelial cervical cells in im-ages of thin Prep. J Med Syst, 34(6):1043-1058.
Chen Q, Sun Q, Heng P (2010). Two - stage object tracking method based on kernel and active contour. IEEE T Circ Syst Vid, 20(4): 605-609.
Jumaat A, Rahman We, Ibrahim A, Mahmud R (2010). Segmentation of Masses from Breast Ultrasound Images using Paramet-ric Active Contour Algorithm. Procedia So-cial Behav Sci, 8:640–647.
Lee J, Muralidhar GS, Reece GP, Markey MK (2012). A shape constrained parametric ac-tive contour model for breast contour de-tection. Conf Proc IEEE Eng Med Biol Soc, 2012;2012:4450-4453.
EtehadTavakol M, Ng EYK, Lucas C, Sadri S, Ataei M (2012). Nonlinear analysis using Lya¬punov exponents in breast thermo-grams to identify abnormal lesions. Infrared Phys Techn, 55(4):345–352 •
Sahoo P, Wilkins C, Yeager J (1997). Thresh-old se¬lection using Renyi's entropy. Pattern recog¬nit, 30(1):71-84.
Lesser VR, Nawab SH, Klassner FI (1995). IPUS: architecture for the integrated pro-cessing and understanding of signals. Artif Int, 77(1):129-171.
Mokhtarian F, Mohanna F (2006). Perfor-mance evaluation of corner detectors us-ing con¬sistency and accuracy measures. Comput Vis Im¬age Und, 102(1):81-94.
Shen F, Wang H (2000). Real time gray level corner detector. Conf Rob Vision, 6:1-4.
GoutamMajumder G, Bhowmik MK, Bhatacharjee D (2013). Automatic Eye De-tection Using Fast Corner Detector of North East Indian (NEI) Face Images. Procedia Technol, 10: 646–653.
Olson C.F (2000). Adaptive-scale is filtering and feature detection using range data. IEEE T Pat¬tern Anal, 22(9):983-991.
Zhang X,Lei M, Yang D, Wang Y,Ma L (2007). Multi-scale curvature product for robust image corner detection in curvature scale space. Pattern Recogn Lett, 28(5):545-554.
Junli H (2004). Research for Target Recogni-tion of Infrared Bridge Based on Mor-phological Oper¬ator and Bridge Template. IEEE Comput Sci, 58-62.
Jinle Z, Yirong Z, Dong D, Baohua C, Jiluan P (2015). Research on a visual weld detec-tion method based on invariant moment fea¬tures. Ind Rob Int J, 42(2):117-128.
Bing X (2007). Research of image’s scale and rota¬tion invariant recognition based on in-variant moment. Shanxi, 1:19-26.
Wong Y.R (1978). Scene Matching With In-variant Moment. Comput Graphics Image Pro-cess, 8(1):16-24.
Dong CH, Yongjie H, Zhenkang SH (2001). Re¬search of feature extraction method of infrared image based on scale singular val-ue transforms. Infrared Laser Eng, 6:157-159.
Zhongcheng ZH, Qinghua M, Zhen Kang SH (1999). Feature analysis of infrared tar-get. Laser Infrared, 6:166-169.
Chao-jian X, San-xue G (2011). Image target iden¬tification of UAV based on SIFT. Pro-cedia Eng, 15: 3205-3209.
Bradski G, Kaehler A (2008). Learning OpenCV: Computer vision with the Open CV li-brary. 3rd ed. Reilly Media, Canasa, pp.100-110.
Herbert B, Ess A, Tuytelaars T, Gool LV (2008). SURF: Speeded Up Robust Fea-tures. Comput Vis Image Und, 110(3): 346-359.
Wikipedia (2011). Blob detection. Available from: https://en.wikipedia.org/wiki/Blob_detection.
Mikolajczyk K, Schmid C (2005). A perfor-mance evaluation of local descriptors. IEEE Conf Com¬put Vision, 27(10):1615-1630.
Baumberg A (2000). Reliable feature matching across widely separated views. IEEE Conf Com¬put Vision, 1:774–781.
Sroba L, Ravas R, Grman J (2015). The In-fluence of Sub pixel Corner Detection to Determine the Camera Displacement. Pro-cedia Eng, 100:834-840.
Alexandre A, Raphael O, Vandergheynst P (2012). FREAK: Fast Retina Key point. IEEE Conf Comput Vision, 1:16-21.
Charoensa kC (2004). Face contour tracking in video using active contour model. In Image Processing. IEEE Image Process, 2:1021-1024.
Fu Y, Erdem T, TekalpA M (2000). Tracking visi¬ble boundary of objects using occlu-sion adap¬tive motion snake. IEEE Trans Image Process, 9(12):2051–2060.
Kass M, Witkin A, Terzopoulos D (1988). Snakes: active contour models. Int Conf Comput Vis, 321-331.
Prince JL, Xu C (1996).A new external force model for snakes. In Image Multidimension Signal Process Workshop, 30–31.
Kim W, Lee J (2005). Object tracking based on the modular active shape model. Mecha-tronics, 15(3):371-402.
Ivins J, Porrill J (1994). Active region models for segmenting medical images. IEEE Int Conf Im¬age Process, 2: 227-231.
Hamarneh G, Chodorowski A, Gustavsson T (2000). Active Contour Models: Applica-tion to Oral Lesion Detection in Color Images. IEEE Int Conf Syst, 4: 2458 -2463.
Schaub H, Smith C (2003). Color snakes for dy¬namic lighting conditions on mobile manipula¬tion platforms. IEEE Int Conf In-tel Rob Syst, 2:1272-1277.
Mabuchi K, Chinzei T, Fujimasa I, Yonezawa T at al(1997). An image-processing pro-gram for the evaluation of asymmetrical thermal distribu¬tions. IEEE Eng Med Biol Soc, 2:725-728.
Perner P (2000). Mining knowledge in medi-cal image da¬tabases, in: Belur V. Dasarathy (Ed.), Qerner Proceedings of SPIE - Data Mining and Knowledge Discovery: Theo-ry. Tools Technol, 4057: 359–369.
Madabhushi A, Metaxas DN (2003). Com-bining low-, high-level and empirical do-main knowledge for automated segmenta-tion of ul¬trasonic breast lesions. IEEE Trans Med Imaging, 22(2):155–169.
| Files | ||
| Issue | Vol 45 No 5 (2016) | |
| Section | Original Article(s) | |
| Keywords | ||
| Breast cancer Surf and sift algorithm Active contour Thermography | ||
| Rights and permissions | |
|
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
