İdil ISIKLI ESENER, Şükriye KARA, Semih ERGİN, Cüneyt ÇALIŞIR

A HYBRID TEXTURAL AND GEOMETRICAL FEATURE EXTRACTION TO REVEAL HIDDEN INFORMATION FROM SUSPICIOUS REGIONS ON MAMMOGRAMS

Anahtar Kelimeler:

Digital Mammography, Computer-Aided Diagnosis, Feature Extraction, Geometric Descriptor, Textural Descriptor

A HYBRID TEXTURAL AND GEOMETRICAL FEATURE EXTRACTION TO REVEAL HIDDEN INFORMATION FROM SUSPICIOUS REGIONS ON MAMMOGRAMS

A mammographic feature extraction scheme through textural and geometrical descriptors is examined to implement in a computer-aided diagnosis system for breast cancer diagnosis in this paper. This scheme is verified on a selected subset of suspicious regions (Region of Interest – ROIs) detected on a publicly available mammogram image database constructed by the Mammographic Image Analysis Society. The ROI detection is succeeded using the Chan-Vese active contour modelling after some pre-processing operations which are median filtering, morphological operations, and a region growing method performed for digitization noise reduction, artifact suppression and background removal, and pectoral muscle removal, respectively, applied on mammogram images. Then, a new adaptive convex hull approach is introduced for extracting geometrical descriptors of the ROIs accompanied by the Haralick features extracted from the gray-level co-occurrence matrices for textural description. In addition to geometrical and textural features, a hybrid mammographic feature vector is constructed by concatenating these features. All the three feature vectors are separately utilized to diagnose the ROIs via Random Forest classifier using 5-fold cross-validation. The experimental studies show that the textural features diagnose benignity more specifically and malignancy more accurately; and they are more effective on discriminating healthy ROIs when concatenated with geometrical features. Hence, a feature combination of these three features is proposed for diagnosis. The proposed feature combination is determined to be more effective for more accurate diagnoses of benignity and malignancy.

Keywords:

Digital Mammography, Computer-Aided Diagnosis, Feature Extraction, Geometric Descriptor, Textural Descriptor,

PDF

___

[1] World Health Organization, available at https://www.who.int/cancer/prevention/diagnosis-screening/breast-cancer/en/ (accessed January 2020).
[2] Wang, L. Early diagnosis of breast cancer. Sensors 2017; 17 (7): 1572-1591.
[3] Meenalochini G, Ramkumar S. Survey of machine learning algorithms for breast cancer detection using mammogram images. Materials Today: Proceedings, 2021; 37 (2): 2738-2743.
[4] Ergin S, Kılınç O. A new feature extraction framework based on wavelets for breast cancer diagnosis. Comput Biol Med, 2014; 51: 171-182.
[5] Heywang-Köbrunner SH, Hacker A, Sedlacek S. Advantages and disadvantages of mammography screening. Breast Care, 2011; 6 (3):199-207.
[6] Jemal A, Bray F, Center MM, Ferlay J, Ward E, Forman D. Global cancer statistics. CA Cancer J Clin, 2011; 61 (2): 69-90.
[7] Üncü YA, Özdoğan H. Mamografi sistemlerinde ilgi alanı, türev ve ince gruplama seçimlerinin modülasyon transfer fonksiyonunun üzerine etkileri. Süleyman Demirel Üniversitesi Fen Edebiyat Fakültesi Fen Dergisi, 2020; 15 (1): 23-35.
[8] Üncü YA, Sevim G, Mercan T, Vural V, Durmaz E, Canpolat M. Differentiation of tumoral and non-tumoral breast lesions using back reflection diffuse optical tomography: A pilot clinical study. Int J Imaging Syst Technol, 2021; 1-9.
[9] Radovic M, Djokovic M, Peulic A, Filipovic N. Application of data mining algorithms for mammogram classification. In: 2013 IEEE 13th International Conference on Bioinformatics and Bioengineering (BIBE); 10-13November 2013; Chania, Greece, 1–4.
[10] Ganesan K, Acharya UR, Chua CK, Min LC, Matthew B, Thomas AK. Decision support system for breast cancer detection using mammograms. Proc Inst Mech Eng H, 2013; 227 (7): 721–732.
[11] Li JB, Wang YH, Chu SC, Roddick JF. Kernel self-optimization learning for kernel-based feature extraction and recognition. Inf Sci, 2014; 257: 70-80.
[12] Ramos RP, Nascimento MZ, Pereira DC. Texture extraction: an evaluation of ridgelet, wavelet and co-occurrence based techniques applied to mammograms. Expert Syst Appl, 2012; 39 (12): 11036-11047.
[13] Shradhananda B, Banshidhar M, Ratnakar D. Mammogram classification using two dimensional discrete wavelet transform and gray-level co-occurrence matrix for detection of breast cancer. Neurocomputing, 2015; 154: 1–14.
[14] Vallez N et al. Breast density classification to reduce false positives in CADe systems. Comput Biol Med, 2013;113 (2): 569–584.
[15] Imran S, Lodhi BA, Alzahrani A. Unsupervised method to localize masses in mammograms," in IEEE Access, 2021; 9: 99327-99338.
[16] Heidari M et al. Applying a random projection algorithm to optimize machine learning model for breast lesion classification. IEEE Trans Biomed Eng, 2021; 68 (9): 2764-2775.
[17] Loizidou K, Skouroumouni G, Nikolaou C, Pitris C. An Automated breast micro-calcification detection and classification technique using temporal subtraction of mammograms. IEEE Access, 2020; 8: 52785-52795.
[18] Heidari M, Mirniaharikandehei S, Liu W, Hollingsworth AB, Liu H, Zheng B. Development and assessment of a new global mammographic image feature analysis scheme to predict likelihood of malignant cases. IEEE Trans Med Imaging, 2020; 39 (4): 1235-1244.
[19] Sampaio WB, Diniz EM, Silva AC, Paiva AC, Gattass M. Detection of masses in mammogram images using CNN, geostatistic functions and SVM. Comput Biol Med, 2011; 41 (8): 653–664.
[20] Keleş A, Keleş, A, Yavuz U. Expert system based on neuro-fuzzy rules for diagnosis breast cancer. Expert Syst Appl, 2011; 38 (5): 5719–5726.
[21] Krishnan MMR, Banerjee S, Chakraborty C, Chakraborty C, Ray AK. Statistical analysis of mammographic features and its classification using support vector machine. Expert Syst Appl, 2010; 37 (1): 470–478.
[22] Verma B, McLeod P, Klevansky A. A novel soft cluster neural network for the classification of suspicious areas in digital mammograms. Pattern Recognit, 2009; 42 (9): 1845–1852.
[23] Papadopoulos A, Fotiadis DI, Costaridou L. Improvement of microcalcification cluster detection in mammography utilizing image enhancement techniques. Comput Biol Med, 2008; 38 (10): 1045–1055.
[24] Işıklı Esener İ, Ergin S, Yüksel T. A genuine GLCM-based feature extraction for breast tissue classification on mammograms. Int J Intell Syst Appl Eng, 2016; 4 (Special Issue): 124-129.
[25] Song R, Li T, Wang Y. Mammographic classification based on xgboost and dcnn with multi features. in IEEE Access, 2020; 8: 75011-75021.
[26] Souza JC, Silva TF, Rocha SV, Paiva AC, Braz G, Almeida JD, Silva AC. Classification of malignant and benign tissues in mammography using dental shape descriptors and shape distribution. In: 2017 7th Latin American Conference on Networked and Electronic Media (LACNEM 2017); 6-7 Nov. 2017; Valparaiso, Chile, 22-27.
[27] Osada R, Funkhouser T, Chazelle B, Dobkin D. Shape distributions. ACM Trans Graph, 2002; 21(4): 807–832.
[28] Yu M, Atmosukarto I, Leow WK, Huang Z, Xu R. 3D model retrieval with morphing based geometric and topologic topological feature maps. In: 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition; 18-20 June 2003; Madison, WI, USA, II-656.
[29] Mahdikhanlou K, Ebrahimnezhad H. Plant leaf classification using centroid distance and axis of least inertia method. In: 2014 22nd Iranian Conference on Electrical Engineering (ICEE); 20-22 May 2014; Tehran, Iran, 1690-1694.
[30] Türkoğlu M, Hanbay D. Plant recognition system based on extreme learning machine by using shearlet transform and new geometric features (article in Turkish with an abstract in English). J Fac Eng Archit Gaz, 2019; 34 (4): 2097-2112.
[31] Azlan NAN, Lu CK, Elamvazuthi I, Tang TB. Automatic detection of masses from mammographic images via artificial intelligence techniques. IEEE Sens J, 2020 (21): 13094-13102.
[32] Mohanty F, Rup S, Dash B, Majhi B, Swamy MNS. An improved scheme for digital mammogram classification using weighted chaotic salp swarm algorithm-based kernel extreme learning machine, Appl Soft Comput, 2020; 91: 1568-4946.
[33] Işıklı Esener İ, Ergin S, Yüksel T. A coping with breast cancer diagnosis using a normalized texture feature set. In: 2017 International Conference on Engineering Technologies (ICENTE17); 7-9 December 2017; Konya, Turkey, 38-43.
[34] Işıklı Esener İ, Ergin S, Yüksel T. A novel multistage system for the detection and removal of pectoral muscles in mammograms. Turk J Elec Eng & Comp Sci, 2018; 26 (1): 35-49.
[35] Işıklı Esener İ, Ergin S, Yüksel T. A practical Region-of-Interest (ROI) detection approach for suspicious region identification in breast cancer diagnosis. In: 2017 International Conference on Engineering Technologies (ICENTE17); 7-9 December 2017; Konya, Turkey, 44-47.
[36] Haralick RM, Shanmugam K, Dinstein I. Textural features of image classification. IEEE Trans Syst, Man, Cybern Syst, 1973; SMC-3 (6): 610-621.
[37] Soh L, Tsatsaulis C. Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices. IEEE Trans Geosci Remote Sens, 1999; 37 (2): 780 – 795.
[38] Clausi DA. An analysis of co-occurrence texture statistics as a function of grey level quantization. Can J Remote Sens, 2002; 28 (1): 45-62.
[39] Suckling J, et al. The Mammographic Image Analysis Society Digital Mammogram Database. Exerpta Medica Int Congr Ser, 1994; 1069: 375-378.
[40] Chan TF, Vese LA. Active contours without edges. IEEE Trans Image Process 2001; 10: 266-277.