Mehrdad MOGHBEL, Syamsiah MASHOHOR, Rozi MAHMUD, Saiful NIZAM, HAMID Suzana Abd, Suraini SANI MOHAMAD, M. Iqbal Bin SARIPAN

Breast boundary segmentation in thermography images based on random walkers

Breast and areola boundary detection and segmentation present the biggest challenge in breast segmentation from thermography images, as breast boundaries, especially in the upper quadrants of the breast, are nonexistent. Many segmentation approaches have been proposed for breast segmentation, such as active contours and snakes, circular Hough transforms, and live wires, but these methods often fail to achieve satisfactory results. With recent advances in image processing techniques, new segmentation concepts are being developed, such as random walkers, which have received high interest from the medical imaging community. In this study, 91 images acquired utilizing a FLIR A320 thermal camera are used for developing an automatic breast segmentation from thermography images based on the random walker algorithm. A series of enhancement filters are applied to the image to make areola detection more accurate. Afterwards, the areola is detected using a series of circular Hough transforms. The detected areola region is then utilized for automatic seed placement for the random walker algorithm. Based on expert radiologist evaluation, the proposed segmentation algorithm was able to achieve 81.3% success rate in breast segmentation, while there was a 37.5% increase in the detection of breast cancer-related abnormalities by radiologists utilizing the segmented images, compared to utilizing original images.

PDF

___

[1] Ohsumi S, Takashima S, Aogi K, Usuki H. Prognostic value of thermographical findings in patients with primary breast cancer. Breast Cancer Res Tr 2002; 3: 213-220.
[2] Head J, Wang F, Elliott R. Breast thermography is a noninvasive prognostic procedure that predicts tumor growth rate in breast cancer patients. Ann NY Acad Sci 1993; 1: 153-158.
[3] Head J, Wang F, Lipari C, Elliott R. The important role of infrared imaging in breast cancer. IEEE Eng Med Biol Mag 2000; 3: 52-57.
[4] Diakides NA, Bronzino JD, Peterson R. Medical Infrared Imaging: Principles and Practices. Boca Raton, FL, USA: CRC Press, 2012.
[5] Bronzino JD. Medical Devices and Systems. Boca Raton, FL, USA: CRC Press, 2006.
[6] Bronzino JD, Diakides NA. Medical Infrared Imaging. Boca Raton, FL, USA: CRC Press, 2008.
[7] Qi H, Diakides NA. Thermal infrared imaging in early breast cancer detection. In: Hammoud R. Augmented Vision Perception in Infrared. London, UK: Springer Press, 2009. pp. 139-152.
[8] Keyserlingk J, Ahlgren P, Yassa M, Belliveau N. Overview of functional infrared imaging as part of a multi-imaging strategy for breast cancer detection and therapeutic monitoring. In: IEEE 2002 Engineering in Medicine and Biology Conference; 2326 October 2002; Houston, TX, USA. New York, NY, USA: IEEE. pp. 1126-1128.
[9] Keyserlingk J, Yassa M, Ahlgren P, Belliveau N. Preliminary evaluation of preoperative chemohormonotherapyinduced reduction of the functional infrared imaging score in patients with locally advanced breast cancer. In: IEEE 2001 Engineering in Medicine and Biology Conference; 2528 October 2001; ˙Istanbul, Turkey. New York, NY, USA: IEEE. pp. 2861-2863.
[10] Head J, Lipari C, Elliott R. Comparison of mammography and breast infrared imaging: sensitivity, specificity, false negatives, false positives, positive predictive value and negative predictive value. In: IEEE 1999 Engineering in Medicine and Biology Conference; 1316 October 1999; Atlanta, GA, USA. New York, NY, USA: IEEE. pp. 1116.
[11] Moghbel M, Mashohor S. A review of computer assisted detection/diagnosis (CAD) in breast thermography for breast cancer detection. Artif Intell Rev 2013; 4: 305-313.
[12] Ng E, Chen Y. Segmentation of breast thermogram: improved boundary detection with modified snake algorithm. J Mech Med Biol 2006; 6: 123-136.
[13] Qi H, Head J. Asymmetry analysis using automatic segmentation and classification for breast cancer detection in thermograms. In: IEEE 2001 Engineering in Medicine and Biology Conference; 2528 October 2001; Istanbul, Turkey. New York, NY, USA: IEEE. pp. 2866-2869.
[14] Baoping C, Zengqiang M. Automated image segmentation and asymmetry analysis for breast using infrared images. In: IEEE 2008 International Workshop on Geoscience and Remote Sensing; 2122 December 2008; Shanghai, China. New York, NY, USA: IEEE. pp. 410-413.
[15] Scales N, Kerry C. Automated image segmentation for breast analysis using infrared images. In: IEEE 2004 Engineering in Medicine and Biology Conference; 15 September 2004; San Francisco, CA, USA. New York, NY, USA: IEEE. pp. 1737-1740.
[16] Borgstein P, Pijpers R, Comans F, Diest J, Boom P, Meijer S. Sentinel lymph node biopsy in breast cancer: guidelines and pitfalls of lymphoscintigraphy and gamma probe detection. J Am Coll Surgeons 1998; 186: 275-283.
[17] Vaidya S, Vyas J, Chinoy F, Merchant N, Sharma P, Mittra I. Multicentricity of breast cancer: whole-organ analysis and clinical implications. Brit J Cancer 1996; 74: 820-824.
[18] Moghbel M, Mahmud R, Mashohor S, Iqbal M. Random walkers based segmentation method for breast thermography. In: IEEE 2012 Biomedical Engineering and Sciences Conference; 1719 December 2012; Langkawi, Malaysia. New York, NY, USA: IEEE. pp. 627-630.
[19] Gonzalez R, Woods R. Digital Image Processing. 2nd ed. Upper Saddle River, NJ, USA: Prentice Hall, 2002. [20] Otsu N. A threshold selection method from gray-level histograms. Automatica 1975; 1: 285-296.
[21] Peng T, Balijepalli A, Gupta S, LeBrun T. Algorithms for on-line monitoring of components in an optical tweezersbased assembly cell. In: ASME 2006 International Design Engineering Technical Conference; 1013 September 2006; Philadelphia, PA, USA. New York, NY, USA: ASME. pp. 297-309.
[22] Grady L. Multilabel random walker image segmentation using prior models. In: IEEE 2005 Computer Vision and Pattern Conference; 2025 June 2005; San Diego, CA, USA. New York, NY, USA: IEEE. pp. 763-770.
[23] Cui Z, Li W, Pan G, Gao L. An improved random walker using spatial feature for image segmentation. In: IEEE 2013 Chinese Control and Decision Conference; 2527 May 2013; Guiyang, China. New York, NY, USA: IEEE. pp. 1479-1482.
[24] Andrews S, Hamarneh G, Saad A. Fast random walker with priors using precomputation for interactive medical image segmentation. In: Tianzi J, Nassir N, Josien P, Pluim W, Viergever M , editors. Medical Image Computing and Computer-Assisted Intervention MICCAI 2010. Berlin, Germany: Springer Heidelberg, 2010. pp. 9-16.
[25] Grady L, Schiwietz T, Aharon S, Westermann R. Random walks for interactive organ segmentation in two and three dimensions: implementation and validation. In: Duncan J, Gerig G, editors. Medical Image Computing and Computer-Assisted Intervention MICCAI 2005, Berlin, Germany: Springer Heidelberg, 2005. pp. 773-780.
[26] Grady L. Random walks for image segmentation. IEEE T Pattern Anal Mach Intell 2006; 28: 1768-1783.
[27] Ba˘gc U, Yao J, Caban J, Turkbey E, Aras O, Mollura J. A graph-theoretic approach for segmentation of PET images. In: IEEE 2011 Engineering in Medicine and Biology Conference; 30 August3 September 2011; Boston, MA, USA. New York, NY, USA: IEEE. pp. 8479-8482.
[28] Chen M, Helm E, Joshi N, Brady S. Random walk-based automated segmentation for the prognosis of malignant pleural mesothelioma. In: IEEE 2011 International Symposium on Biomedical Imaging: From Nano to Macro Conference; 30 March2 April 2011; Chicago, IL, USA. New York, NY, USA: IEEE. pp. 1978-1981.
[29] Choubey M, Agrawal S. An implementation of random walk algorithm to detect brain cancer in 2-d MRI. Magn Reson Imag 2012; 2: 998-1001.
[30] Ng E, Chen Y, Ung L. Computerized breast thermography: study of image segmentation and temperature cyclic variations. J Med Eng Technol 2001; 25: 12-16.
[31] Kapoor P, Prasad S. Image processing for early diagnosis of breast cancer using infrared images. In: IEEE 2010 International Computer and Automation Engineering Conference; 2628 February 2010; Singapore. New York, NY, USA: IEEE. pp. 564-566.
[32] Golestani N, Tavakol M, Ng E. Level set method for segmentation of infrared breast thermograms. EXCLI J 2014; 13: 241-251.
[33] Ali A, Sayed I, Gaber T, Hassanien A, Snasel V, Silva L. Detection of breast abnormalities of thermograms based on a new segmentation method. In: IEEE 2015 Computer Science and Information Systems Conference; 1316 September 2015; Lodz, Poland. New York, NY, USA: IEEE. pp. 255-261.