Abstract
Background: This paper attempts to pinpoint different techniques for Pectoral Muscle (PM) segmentation, Microcalcification (MC) detection and classification in digital mammograms. The segmentation of PM and detection of MC and its classification are mostly based on image processing and data mining techniques.
Discussion: The review centered on major techniques in image processing and data mining that is employed for PM segmentation, MC detection and classification in digital mammograms. Breast cancer is one of the significant causes of death among women aged above 40. Mammography is considered the most successful means for prompt and timely detection of breast cancers. One notable visual indication of the malignant growth is the appearance of Masses, Architectural Distortions, and Microcalcification Clusters (MCCs). There are some disadvantages and hurdles for mankind viewers, and it is hard for radiologists to supply both precise and steady assessment for a large number of mammograms created in extensive screening. Computer Aided Detection has been employed to help radiologists in detecting MC and MCCs. The automatic recognition of malignant MCCs could be very helpful for diagnostic purpose. In this paper, we summarize the methods of automatic detection and classification of MCs in digitized mammograms. Pectoral muscle segmentation techniques are also summarized.
Conclusion: The techniques used for segmentation of PM, MC detection and classification in a digitized mammogram are reviewed.
Keywords: Computer aided detection, classifier, digital mammogram, image processing, microcalcification, microcalcification cluster.
Graphical Abstract
[1]
Thomas N, Heinz OP. Scale-Space Signatures for the detection of clustered microcalcifiations in Digital Mammograms. IEEE Trans Med Imaging 1999; 18(9): 774-86.
[2]
Moti Melloul. Segmentation of microcalcification in X-ray mammogram
using entropy thresholding. PhD dissertation, The Hebrew
University of Jerusalem 2001.
[3]
Naga RM, Rangaraj MR, Leo JE. Detection of breast masses in mammograms by density slicing and texture flow-field analysis. IEEE Trans Med Imaging 2001; 20(12): 1225-7.
[4]
San KL, Pau CC. Chein-I, et al. Classification of clustered microcalcifications using a shape cognitron neural network. Neu Net 2003; 16: 121-32.
[5]
Ferrari RJ, Rangayyan RM, Desautels JEL, Desautels RA. Borges, Frère AF. Automatic identification of the pectoral muscle in mammograms. IEEE Trans Med Imaging 2004; 23(2): 232-45.
[6]
Sze MK, Ramachandran C, Yianni A, Mary TR. Automatic pectoral muscle segmentation on mediolateral oblique view mammograms. IEEE Trans Med Imaging 2004; 23(2): 1129-40.
[7]
Kinoshita SK, Azevedo-Marques PM, Pereira RR Jr, Rodrigues JA, Rangayyan RM. Radon-domain detection of the nipple and the pectoral muscle in mammograms. J Digit Imaging 2008; 21(1): 37-49.
[8]
Lei W, Miao-liang Z, Li-ping D, Xin Y. Automatic pectoral muscle
boundary detection in mammograms based on markov chain and
active contour model. J Zheji Univ-Sci C (Comput & Electron)
2010; 11(2):111-8.
[9]
Mario M, Mislav G. Robust automatic breast and pectoral muscle segmentation from scanned mammograms. Signal Processing 2013; 93(10): 2817-27.
[10]
Karthikeyan G, Rajendra A, Kuang CC, Lim CM, Thomas A. Pectoral muscle segmentation: A review. Comput Methods Programs Biomed 2013; 110: 48-57.
[11]
Ferrari RJ, Rangayyan RM, Desautels JEL, Frère AF. Segmentation of mammograms: Identification of the skin-air boundary, pectoral muscle, and fibro-glandular disc. In: Proceeding of 5th international workshop digital mammography 2000. Canada. 573-9.
[12]
Kamila C, Justyna W. Automatic breast-line and pectoral muscle segmentation. Sched Inform 2012; 20: 195-209.
[13]
Raba D, Oliver A, Mart J, Peracaula M, Espunya J. Breast segmentation with pectoral muscle suppression on digital mammograms. 2005; IbPRIA 2005; 2: 471-8.
[14]
Marti R, Oliver A, Raba D, et al. Breast skin-line segmentation using contour growing. Marti J (Eds) Berlin, Heidelberg: Springer 2007; pp. 564-71.
[15]
Wirth MA, Stapinski A. Segmentation of the breast region in mammograms using active contours. In: Proceedings of SPIE-the international society for optical engineering 2006.
[16]
Chen CL, Chung YT, Jui L, Chun YY, Shyr SY. A pectoral muscle segmentation algorithm for digital mammograms using Otsu thresholding and multiple regression analysis. Comput Math Appl 2012; 64: 1100-7.
[17]
Molinara M, Marrocco C, Tortorella F. Automatic segmentation of the pectoral muscle in mediolateral oblique mammograms. In: Proceedings of the 26th IEEE international symposium on computer-based medical systems. 2013; IEEE Xplore: 506-9.
[18]
Fischler MA, Bolles RC. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM 1981; 24(6): 381-95.
[19]
Yanfeng L, Houjin C, Yongyi Y, Yanga N. Pectoral muscle segmentation in mammograms based on homogenous texture and intensity deviation. Patt Recogn 2013; 46(3): 681-91.
[20]
Arnau O, Xavier L, Albert T, Joan M. One shot segmentation of breast, pectoral muscle, and background in digitized mammograms. In: Proceedings of the IEEE international conference on image processing 2014; pp. 27-30.
[21]
Tzikopoulos SD, Mavroforakis ME, Georgiou HV, Dimitropoulos N, Theodoridis S. A fully automated scheme for mammographic segmentation and classification based on breast density and asymmetry. Comput Methods Programs Biomed 2011; 102(1): 47-63.
[22]
Wirth M, Nikitenko D, Lyon D. Segmentation of the breast region in mammograms using a rule-based fuzzy reasoning algorithm. J Graph Vision Image Process 2005; 5(2): 45-54.
[23]
Li L, Qian L, Wei L. Pectoral muscle detection in mammograms using local statistical features. J Digit Imaging 2014; 27(5): 633-41.
[24]
Zhou C, Wei J, Chan HP, et al. Computerized image analysis: Texture-field orientation method for pectoral muscle identification on MLO-view mammograms. Med Phys 2010; 37: 2289-99.
[25]
Ma F, Bajger M, Slavotinek JP, Bottema MJ. Two graph theory based methods for identifying the pectoral muscle in mammograms. Patt Recogn 2007; 40: 2592-602.
[26]
Iglesias JE, Karssemeijer N. Robust initial detection of landmarks in film-screen mammograms using multiple FFDM atlases. IEEE Trans Med Imaging 2009; 28: 1815-24.
[27]
Nashid A, Mohammed JI. Pectoral muscle elimination on mammogram using K-means clustering approach. Inter J Comp Vis Sig Process 2014; 4(1): 11-21.
[29]
Chen Z, Zwiggelaar R. Segmentation of the breast region with pectoral muscle removal in mammograms. MIUA 2010; pp. 71-6.
[30]
Mustra M, Bozek J, Grgic M. Breast border extraction and pectoral muscle detection using wavelet decomposition. In: IEEE EUROCON. IEEE 2009: St.-Petersburg, Russia; pp. 1426-33.
[31]
Liu L, Wang J, Wang T. Breast and pectoral muscle contours detection based on goodness of fit measure. In: IEEE 15th international conference on bioinformatics and bio-medical engineering. IEEE Press 2011: Wuhan, China; pp. 1-4.
[32]
Bose RSC, Tangaval T, Daniel DAP. Automatic mammogram image breast region extraction and removal of pectoral muscle. Int J Sci Eng Res 2013; 4(5): 229-35.
[33]
Sreedevi S, Elizabeth S. A novel approach for removal of pectoral muscles in digital mammogram. Procedia Comput Sci 2015; 46: 1724-31.
[34]
Chia HW, Chih YG, Pai JH. Identification and segmentation of obscure pectoral muscle in mediolateral oblique mammograms. Br J Radiol 2016; 89: 1-8.
[35]
Vikhe PS, Thool VR. Intensity based automatic boundary identification of pectoral muscle in mammograms. Procedia Comput Sci 2016; 79: 262-9.
[36]
Marijeta S, Ana G, Milan M, Irini R, Branimir R. Breast region segmentation and pectoral muscle removal in mammograms. Telf J 2016; 8(1): 50-5.
[37]
Huang SC, Cheng FC, Chiu YS. Efficient contrast enhancement using adaptive gamma correction with weighting distribution. IEEE Trans Image Process 2013; 22(3): 1032-41.
[38]
Woong BY, Ji EO, Eun YC, Hak HK, Soo YL, Kwang GK. Automatic detection of pectoral muscle region for computer-aided diagnosis using Mia’s mammograms. BioMed Res Int 2016; 2016: 1-6.
[39]
Kwok SM, Chandrasekhar R, Attikiouzel Y. Automatic pectoral muscle segmentation on mammograms by straight line estimation and cliff detection. In: Proceedings of the 7th Australian and New Zealand Intelligent Information Systems Conference (ANZIIS ’01) 2001. IEEE: Perth, Western Australia; pp. 67-72.
[40]
Saeid AT, Yonghuai L, Brandon M, Ghassan H. Geometry-based pectoral muscle segmentation from MLO mammogram views. IEEE Trans Biomed Eng 2017; 64(11): 2662-71.
[41]
Xia R, Liu W, Zhao J, Bian H, Xing F. Robust Algorithm for Detecting the Maximum Inscribed Circle. In: 10th IEEE international conference on computer-aided design and computer graphics 2007. IEEE: Beijing, China; pp. 230-3.
[42]
Andrik R, Philip JM, Bryan WS, John W. Fully automated breast boundary and pectoral muscle segmentation in mammograms. Artif Intell Med 2017; 79: 28-41.
[43]
MatWorks. Filtering and smoothing data; 2016. Available from: https://uk.mathworks.com/help/curvefit/smoothing-data.html#bq_6ys3-8
[44]
Camilus KS, Govindan VK, Sathidevi PS. Pectoral muscle identification in mammograms. J Appl Med Clin Phys 2011; 12: 215-30.
[45]
Peng S, Jing Z, Andrik R, Hui W. A hierarchical pipeline for breast boundary segmentation and calcification detection in mammograms. Comput Biol Med 2018; 96: 178-88.
[47]
Chen Z, Zwiggelaar R. A combined method for automatic identification of the breast boundary in mammograms. In: 5th international conference on Biomedical Engineering and Informatics (BMEI) 2012. IEEE: Chongqing, China; pp. 121-5.
[48]
Maitra IK, Nag S, Bandyopadhyay SK. Technique for preprocessing of digital mammogram. Comput Methods Programs Biomed 2012; 107(2): 175-88.
[49]
Sapate SG, Talbar SN. Pectoral muscle extraction using modified k-means algorithm for digital mammograms. J Med Phys 2016; •••: 19-54.
[50]
Alain T, Christian D, Pierre G, Didier W. Correspondences between microcalcification projections on two mammographic views acquired with digital systems. Comput Med Imaging Graph 2005; 29: 543-53.
[51]
Liyang W, Yongyi Y, Robert M. Nishikawa, Yulei J. A study on several machine-learning methods for classification of malignant and benign clustered microcalcifications. IEEE Trans Med Imaging 2005; 24(3): 371-80.
[52]
Fauci F, Raso G, Magro R, et al. A massive lesion detection algorithm in mammography. Phys Med 2005; 21(1): 21-30.
[53]
Marius GL, Kostas M, Ruth E, Michael B. A biologically inspired algorithm for microcalcification cluster detection. Med Image Anal 2006; 10: 850-62.
[54]
Joseph AC, David SW. Applications of Machine Learning in Cancer Prediction and Prognosis. Cancer Inform 2006; 2: 59-77.
[55]
Stelios H, Taxiarchis B, Maria R. Automatic detection of clustered microcalcifications in digital mammograms using mathematical morphology and neural networks. Signal Processing 2007; 87: 1559-68.
[56]
Lisa EC, Tracy VG, Ryan KR. Bisphosphonate-functionalized gold nanoparticles for contrast-enhanced X-ray detection of breast microcalcifications. Biomaterials 2014; 35: 2312-21.
[57]
Harry S, Zhili C, Erika RED, Reyer Z. Modelling mammographic microcalcification clusters using persistent mereotopology. Pattern Recognit Lett 2014; 47: 157-63.
[58]
Henrot P, Leroux A, Barlier C, Génin P. Breast microcalcifications: The lesions in anatomical pathology. Diagn Interv Imaging 2014; 95: 141-52.
[59]
Sheshachalam A, Chakravarthy AR. The cancer awareness assessment project: A small-scale survey across people with different levels of education in Mysore, India. Ind J Can 2015; 52: 153-5.
[60]
David K, Zsuzsanna V, Heike H. A micro CT study in patients with breast microcalcifications using a mathematical algorithm to assess 3D structure. PLoS One 2017; 1-2.
[61]
Garima V, Maria LL, Alessandro P, et al. Microcalcification morphological descriptors and parenchyma fractal dimension hierarchically interact in breast cancer: A diagnostic perspective. Comput Biol Med 2018; 9: 1-6.
[62]
Athanasios D, Aris G, Sofoklis S, et al. A unique case of total metastatic lobular breast carcinoma, originating from diffused Microcalcifications, presented in a postmenopausal woman, without clinical manifestations. Int J Surg Case Rep 2018; 44: 85-9.
[63]
Sheshadri HS, Kandaswamy A. Detection of breast cancer tumor based on morphological watershed algorithm. GVIP 2005; pp. 17-21.
[64]
Sheshadri HS, Kandaswamy A. Experimental investigation on breast tissue classification based on statistical feature extraction of mammograms. J Comp Med Imaging Graph 2005; 31: 46-8.
[65]
Sheshadri HS, Kandaswamy A. Breast tissue classification using statistical feature extraction of mammogram. Med Imaging Infor Sci 2006; 23(3): 105-7.
[66]
Sheshadri HS, Kandaswamy A. Application of watershed algorithms to mammogram image analysis. IETE Tech Rev 2006; 23: 173-8.
[67]
Sheshadri HS, Kandaswamy A. Computer aided decision system for early detection of breast cancer. Indian J Med Res 2006; 124(2): 149-54.
[68]
Massimo DS, Mario M, Francesco T, Mario V. Automatic classification of clustered microcalcifications by a multiple expert system. Patt Recogn 2003; 36: 1467-77.
[69]
Gholamali R, Sepehr J. Detecting microcalcification clusters in digital mammograms using combination of wavelet and neural network. In: Proceedings of the Computer Graphics, Imaging and Vision: New trends (CGIV’05) 2005. IEEE: Beijing, China; pp. 197-201.
[70]
Ryohei N, Yoshikazu U, Koji Y, Ryoji W, Kiyoshi N. Computer-aided diagnosis scheme using a filter bank for detection of microcalcification clusters in mammograms. IEEE Trans Biomed Eng 2006; 53(2): 273-83.
[71]
Tomasz A, Marcin K, Tadeusz JP, Erik ODS, David AY. Detection of clustered microcalcifications in small field digital mammography. Comput Methods Programs Biomed 2006; 81: 56-65.
[72]
Yonghong P, Bin Y, Jianmin J. Knowledge discovery incorporated evolutionary search for microcalcification detection in breast cancer diagnosis. Artif Intell Med 2006; 37: 43-53.
[73]
Nor AAI, Shahrill S, Umi KN, Kamal ZZ, Masriah MN. The potential use of modified seed based region growing technique for automatic detection of breast microcalcifications and tumour areas. J Teknologi 2006; 44: 151-64.
[74]
Lixin S. Qi-Wang, Jie G. Microcalcification detection using combination of wavelet transform and morphology. ICSP2006 Proceedings 2006. IEEE Xplore: Beijing, China.
[75]
Arnau O, Albert T, Xavier L, et al. Automatic microcalcification and cluster detection for digital and digitized mammograms. Knowl Base Syst 2012; 28: 68-75.
[76]
Mohanalin J, Beenamol MA. New wavelet algorithm to enhance and detect microcalcifications. Signal Processing 2014; 105: 438-48.
[77]
Bria A, Karssemeijer N, Tortorella F. Learning from unbalanced data: a cascade-based approach for detecting clustered microcalcifications. Med Image Anal 2014; 18: 241-52.
[78]
Dheeba J, Albert S, Tamilselvi S. Computer-aided detection of breast cancer on mammograms: A swarm intelligence optimized wavelet neural network approach. J Biomed Inform 2014; 49: 45-52.
[79]
Marcelo AD, Andre VA, Carolina MA, et al. Evaluating geodesic active contours in microcalcifications segmentation on mammograms. Comput Methods Programs Biomed 2015; 122: 304-15.
[80]
Zhili C, Harry S, Arnau O, Erika RED, Caroline B, Reyer Z. Topological modeling and classification of mammographic microcalcification clusters. IEEE Trans Biomed Eng 2015; 62(4): 1203-14.
[81]
Ioannis IA, George MS, Konstantina SN. A CADx scheme for mammography empowered with topological information from clustered microcalcifications’ atlases. IEEE J Biomed Health Inform 2015; 19: 1-8.
[82]
Ghada S, Ahmad K, Qosai K. ANN and adaboost application for automatic detection of microcalcifications in breast cancer. Egypt J Radiol Nuc Med 2016; 47: 1803-14.
[83]
Marimuthu M, Balakumaran T, Gowrishankar C. Microcalcification cluster detection using multiscale products based hessian matrix via the tsallis Thresholding Scheme. Pattern Recognit Lett 2017; 94: 127-33.
[84]
Kai H, Wei Y, Xieping G. Microcalcification diagnosis in digital mammography using extreme learning machine based on hidden markov tree model of dual-tree complex wavelet transform. Expert Syst Appl 2017; 86: 135-44.
[85]
Marcin C. Microcalcification segmentation from mammograms. A morphological approach. J Digit Imaging 2017; 30: 172-84.
[86]
Juan W, Yongyi Y. A Context-sensitive deep learning approach for microcalcification detection in mammograms. Patt Recogn 2018; 78: 12-22.
[87]
Sheshadri HS, Kandaswamy A. Computer aided diagnosis of digital mammograms. Inform Technol J 2006; 5(2): 342-6.
Call for Papers in Thematic Issues
01 August, 2024
Intelligent Information Retrieval for Multispectral and Hyperspectral Imaging
Multispectral and hyperspectral imaging is an interdisciplinary research area, widely focuses on spectral, spatial, and temporal data. It offers a plethora of opportunities to efficiently analyze the vast area of the earth's surface. However, there are numerous factors such as dimensionality and size of the hyperspectral data, lesser training samples, ...read more
18 May, 2024
Machine and Deep Learning in Medical Image Diagnosis
Medical Image Processing regards a set of methodologies that have been developed over recent years with the purpose of improving medical image quality, improving medical data visualization, understanding, and assisting medical diagnosis, and so on. The application of machine and deep learning methods in sensing and imaging can potentially have ...read more
03 September, 2024
Quantum Machine Learning for Medical Data and Imaging
Quantum computing has promised a significant speedup in certain computationally intensive tasks that are intractable on classical computers. Researchers in quantum machine learning, such as those working in computer vision, image processing, biomedical analysis, and related topics, may play an important role in comprehending and working on complicated medical data, ...read more
Article Metrics
50
8