No . 1 January 2018 PP . 12 – 32 AUTOMATIC IMAGE SEGMENTATION METHOD FOR BREAST CANCER ANALYSIS USING THERMOGRAPHY

Breast Cancer (BC) is considered one from various diseases that has got great attention in the last decades. This is because the high mortality rates among young women in the whole world according to this disease. The early detection of this disease is necessary to enhance the opportunity of survival. Thermography is an efficient screening tool that can help in detecting BC by indicating parts of the body where an abnormal temperature variation is found. To realize an effective BC detection system using thermography, it is necessary to locate the region of interest (ROI) in the thermograms prior to analysis. This paper introduces a new automatic segmentation method (SM) for identifying the ROI image from breast thermograms. It depends on the statistics of image in DMR-IR database. After detecting the boundaries of ROI using this new SM, two different approaches for accurate identifying and enhancing the breast boundaries are investigated: the Hough transform (HT) algorithm to locate and define the parabola curves in the breast image, and a second approach introducing the enhancement of the contrast of detected boundaries in the breast ROI image. To evaluate the results of this method, statistical features have been extracted from the segmented ROI image. Then, we used the Support Vector Machine (SVM) and the Artificial Neural Network (ANN) classifiers to detect the normal and abnormal breasts based on these features. The experimental results prove that the accuracy of SVM, and ANN classifiers reached to 96.67% and 96.07%, respectively. This denotes that the proposed automatic SM is a favorable technique for extracting the breast ROI image from breast thermograms.

[1]  Allan Hanbury,et al.  Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool , 2015, BMC Medical Imaging.

[2]  Michael Bretthauer,et al.  Benefits and harms of mammography screening , 2015, Breast Cancer Research.

[3]  A. Jemal,et al.  Global cancer statistics, 2012 , 2015, CA: a cancer journal for clinicians.

[4]  Marcus C. Araújo,et al.  Interval symbolic feature extraction for thermography breast cancer detection , 2014, Expert Syst. Appl..

[5]  Irving P. Herman,et al.  Biological and medical physics, biomedical engineering , 2014 .

[6]  S. Saranya,et al.  Detection of Breast Abnormality from Thermograms Using Curvelet Transform Based Feature Extraction , 2014, Journal of Medical Systems.

[7]  Aura Conci,et al.  A New Database for Breast Research with Infrared Image , 2014 .

[8]  Ramakrishnan Swaminathan,et al.  Segmentation of Breast Tissues in Infrared Images Using Modified Phase Based Level Sets , 2013 .

[9]  Vinod Chandran,et al.  Breast cancer detection from thermal images using bispectral invariant features , 2013 .

[10]  U. Rajendra Acharya,et al.  Data mining technique for breast cancer detection in thermograms using hybrid feature extraction strategy , 2012 .

[11]  Pinaki Pratim Acharjya,et al.  Study and Comparison of Different Edge Detectors for Image Segmentation , 2012 .

[12]  U. Rajendra Acharya,et al.  Thermography Based Breast Cancer Detection Using Texture Features and Support Vector Machine , 2012, Journal of Medical Systems.

[13]  V. Umadevi,et al.  Framework for estimating tumour parameters using thermal imaging , 2011, The Indian journal of medical research.

[14]  Ming-Yih Lee,et al.  Entropy-based feature extraction and decision tree induction for breast cancer diagnosis with standardized thermograph images , 2010, Comput. Methods Programs Biomed..

[15]  E. Y.-K. Ng,et al.  A review of thermography as promising non-invasive detection modality for breast tumor , 2009 .

[16]  Jake K. Aggarwal,et al.  Boundary extraction in thermal images by edge map , 2004, SAC '04.

[17]  E Y Ng,et al.  Numerical computation as a tool to aid thermographic interpretation , 2001, Journal of medical engineering & technology.

[18]  C. A. Lipari,et al.  Advanced infrared image processing for breast cancer risk assessment , 1997, Proceedings of the 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 'Magnificent Milestones and Emerging Opportunities in Medical Engineering' (Cat. No.97CH36136).

[19]  Raúl Rojas,et al.  Neural Networks - A Systematic Introduction , 1996 .

[20]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[21]  Andrea Baraldi,et al.  An investigation of the textural characteristics associated with gray level cooccurrence matrix statistical parameters , 1995, IEEE Transactions on Geoscience and Remote Sensing.

[22]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[24]  L. R. Dice.  Measures of the Amount of Ecologic Association Between Species , 1945 .

[25]  S. Ramakrishnan,et al.  Semi Automatic Segmentation of Breast Thermograms Using Variational Level Set Method , 2014 .

[26]  Tanya Lee,et al.  A Comparative Review of Thermography as a Breast Screening Technique , 2008 .

[27]  Moncef Gabbouj,et al.  Rock Texture Retrieval Using Gray Level Co-occurrence Matrix , 2002 .

[28]  Dana H. Ballard,et al.  Generalizing the Hough transform to detect arbitrary shapes , 1981, Pattern Recognit..

[29]  Richard O. Duda,et al.  Use of the Hough transformation to detect lines and curves in pictures , 1972, CACM.

[30]  R. Besar,et al.  Biomedical Imaging and Intervention Journal Identification of Masses in Digital Mammogram Using Gray Level Co-occurrence Matrices , 2022 .