Detection of breast cancer mass using MSER detector and features matching

Detection of breast cancer masses in mammogram images is an essential step in any computer-aided system for breast cancer diagnosis. In this paper, we propose a novel technique for breast cancer masses detection in mammograms based on the feature matching of different regions using Maximally Stable Extremal Regions (MSER). Firstly, a pre-processing step is applied to the original mammogram image to produce an enhanced version of this image. Then, MSER regions are extracted from both the original image and its enhanced version using MSER detector. Finally, feature matching process is applied between these regions to detect the mass area. The proposed algorithm has been tested on a collected set of 300 mammogram images containing abnormalities (i.e. benign and malignant masses) from four different databases. The proposed algorithm is able to accurately detect locations of masses with an accuracy of 95%. There aren’t any processing steps for pectoral muscle removal, this results in reducing the processing time. The average time taken by the proposed method to process one mammogram image is 0.14 s. The proposed method is fully automated and there is no need for user intervention or any readjustment. The proposed algorithm is robust against noise and it is not affected by the image quality, breast density category, or mass nature. The results show that the proposed algorithm has higher accuracy than the state of the art approaches.

[1]  J. Anitha,et al.  A dual stage adaptive thresholding (DuSAT) for automatic mass detection in mammograms , 2017, Comput. Methods Programs Biomed..

[2]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[3]  Jacey-Lynn Minoi,et al.  Keypoint Descriptors in SIFT and SURF for Face Feature Extractions , 2017 .

[4]  Aziz Makandar,et al.  Threshold Based Segmentation Technique for Mass Detection in Mammography , 2016, J. Comput..

[5]  Ghassan Hamarneh,et al.  Mammography Segmentation with Maximum Likelihood Active Contours , 2022 .

[6]  Marcelo Zanchetta do Nascimento,et al.  Segmentation and detection of breast cancer in mammograms combining wavelet analysis and genetic algorithm , 2014, Comput. Methods Programs Biomed..

[7]  Shabana Urooj,et al.  An Improved CAD System for Breast Cancer Diagnosis Based on Generalized Pseudo-Zernike Moment and Ada-DEWNN Classifier , 2016, Journal of Medical Systems.

[8]  Ahmed Tamtaoui,et al.  Detection of breast abnormalities in digital mammograms using the electromagnetism-like algorithm , 2018, Multimedia Tools and Applications.

[9]  Shohreh Kasaei,et al.  Benign and malignant breast tumors classification based on region growing and CNN segmentation , 2015, Expert Syst. Appl..

[10]  Mohammed S. Sayed,et al.  Selective energy-based histogram equalization for mammograms , 2017, 2017 Japan-Africa Conference on Electronics, Communications and Computers (JAC-ECC).

[11]  G. Raju,et al.  Automated Mammogram Segmentation Using Seed Point Identification and Modified Region Growing Algorithm , 2015 .

[12]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[13]  Min Zhang,et al.  Breast Mass Detection in Digital Mammogram Based on Gestalt Psychology , 2018, Journal of healthcare engineering.

[14]  Pritee Khanna,et al.  Computer-Aided Diagnosis of Malignant Mammograms using Zernike Moments and SVM , 2015, Journal of Digital Imaging.

[15]  Yasser M. Kadah,et al.  An Automatic Computer-Aided Diagnosis System for Breast Cancer in Digital Mammograms via Deep Belief Network , 2018 .

[16]  Mohammed S. Sayed,et al.  Segmentation of breast cancer lesion in digitized mammogram images , 2014, 2014 Cairo International Biomedical Engineering Conference (CIBEC).

[17]  Udhav Bhosle,et al.  SURF features based classifiers for mammogram classification , 2017, 2017 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET).

[18]  V. R. Thool,et al.  Mass Detection in Mammographic Images Using Wavelet Processing and Adaptive Threshold Technique , 2016, Journal of Medical Systems.

[19]  Abel G. Silva-Filho,et al.  An adaptive semi-supervised Fuzzy GrowCut algorithm to segment masses of regions of interest of mammographic images , 2016, Appl. Soft Comput..

[20]  Anselmo Cardoso de Paiva,et al.  Automatic mass detection in mammography images using particle swarm optimization and functional diversity indexes , 2017, Multimedia Tools and Applications.

[21]  P Soorya,et al.  Cancer Mass Detection from Mammogram Based on Enhanced Feature Extraction Method , 2018 .

[22]  Dwi Pebrianti,et al.  Mammography Image Segmentation: Chan-Vese Active Contour and Localised Active Contour Approach , 2017 .

[23]  David Nistér,et al.  Linear Time Maximally Stable Extremal Regions , 2008, ECCV.

[24]  Anselmo Cardoso de Paiva,et al.  Diagnosis of breast tissue in mammography images based local feature descriptors , 2018, Multimedia Tools and Applications.

[25]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[26]  Richard H. Moore,et al.  THE DIGITAL DATABASE FOR SCREENING MAMMOGRAPHY , 2007 .

[27]  Jaime S. Cardoso,et al.  INbreast: toward a full-field digital mammographic database. , 2012, Academic radiology.

[28]  Hong Liu,et al.  Marker-Controlled Watershed for Lesion Segmentation in Mammograms , 2011, Journal of Digital Imaging.