Tumor Detection in Digital Mammogram Based on Support Vector Machine Using Co-occurrence Matrix

Majlesi Journal of Electrical Engineering

مقاله 2، دوره 3، شماره 2، خرداد 2009، صفحه 7-17   

نوع مقاله: Review Article

شناسه دیجیتال (DOI): 10.1234/mjee.v3i2.72

نویسندگان

SayedMasoud Hashemi Amroabadi^{* 1}؛ MohammadReza Ahmadzadeh¹؛ Ali Hekmatnia²

¹IUT

²Medicine University of Isfahan

چکیده

 Breast cancer is one of the leading causes of deaths among women. Mammography is currently the best method for early detection. Due to the breast tissue type and different kinds of lesions, by using low dose x-ray in mammography, the detection of lesions in mammograms becomes very ambiguous and a tedious work .  Early detection is the most effective ways to reduce the mortality rate. Our main aim in this paper is detection and recognition of tumors in digital mammograms. Mammograms usually have a large size so the processing of the entire mammogram takes a lot of time. To reduce the size and therefore the processing time and also to decrease the False Positive Rate, a two-step algorithm is used. At the first step some unimportant regions such as background and pectoral muscle are eliminated and at the second step an ROI detection algorithm is proposed which extracts the most likely regions to tumors. To recognize the tumors in the detected regions, some features are extracted from each region. To find the most effective features for tumor detection, several data mining feature extraction and feature selection methods are used and then compared. To increase the performance and reduce the number of features a GA based algorithm is proposed. Finally, SVM is used as our classifier, because it has the best results in comparison with other tools in our application. Experimental results show that the performance of proposed methods is better than other previous methods. The True Positive Rate using SVM is 94.59% and the False Positive Rate is 22.95%.

کلیدواژه‌ها

Mammogram؛ fa؛ Tumor Detection؛ image processing؛ Support vector machine

مراجع

1] Fauchi F, Raso G, Magro Rl, "A massive lesion detection algorithm in mammo-graphy", Physica Medica, Vol. 21, No. 1, pp. 21-28, 2005.

[2] Qi H, and Snyder W.E, "Lesion detection and characterization in digital mammo-graphy by Bezier histograms", The 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, vol. 2, No. 29, pp. 1021-1024, 1998.

[3] Image Processing Fundamentals, Morphology-based Operations: www.ph.tn.tudelft.nl/Courses/FIP/noframes/fip-morpholo.html#Heading104

[4] Magoulas G.D, Karkanis S.A, Karras D.A, and Vrahatis M.N, "Comparison Study of Descriptors for Training Neural Network classifier", The 19th Annual International Conference of the IEEE Engineering in Medicine and Biology society, vol. 3, No. 30, pp. 1359, 1362, 1997.

[5] Kurani A.S, Xu D.H, Frust J, "Co-Occurrence matrices for volumetric data", Computer Graphics and Imaging CGIM 2004, vol. 12, No. 3, pp. 426-430, 2004.

[6] Martin, Hagan, Howard, Demuth, and Mark H. Beale. Neural Network Design. Oklahoma State University, 2002.

[7] Haralick R.M, Shanmugam K, and Dinstein I, “Textural Features for Image Classification,” IEEE Trans. on Systems, Man., and Cybernetics, Vol. SMC-3, No.6, pp. 610-621, 1973.

[8] سید مسعود هاشمی عمروآبادی، طراحی سیستم بازشناسی اتوماتیک تومورهای سرطانی از روی تصاویر ماموگرام ، پایان نامه کارشناسی ارشد، دانشکده برق و کامپیوتر، دانشگاه صنعتی اصفهان، 138٧.

[9] سید مسعود هاشمی عمروآبادی، محمدرضا احمدزاده، علی حکمت نیا، " آشکار سازی مرز سینه در تصاویر ماموگرام با استفاده از روشهای مبتنی بر بخشبندی بافت و آستانه گذاری"، پنجمین کنفرانس ماشین بینایی و پردازش تصویر ایران، دانشگاه تبریز، ص ٣٢٩-٣٣٥، ١٤-١٦ آبان ١٣٨٧.

[10] سید مسعود هاشمی عمروآبادی، محمدرضا احمدزاده، علی حکمت نیا، "تشخیص خودکار مرز ماهیچه پکتورال در تصاویر ماموگرام با استفاده از مدل ترکیب گوسی و مدل مارکوف"، پنجمین کنفرانس ماشین بینایی و پردازش تصویر ایران، دانشگاه تبریز، ص ٣٣٦-٣٤٢، ١٤-١٦ آبان ١٣٨٧.