Classification of clustered microcalcifications using different variants of backpropagation training algorithms
Authors: 
Baljit Singh Khehra, Amar Partap Singh Pharwaha, Balkrishan Jindal, Bhupinder Singh MaviAuthors Info & Claims
Pages 17509 - 17526
Abstract
In mammography, the most frequently type of breast cancer recognized is DCISand the most frequent signs of DCIS are MCCs. In the proposed research work, MCs are enhanced using fuzzy approach. In this approach Gaussian fuzzy membership function is used and its parameters are optimized by TLBO. After this, the local window based statistical texture features are extracted from ROIs of enhanced mammograms. At the end, different variants of Back propagation are explored to divide MCCs into two categories, one is benign and other is malignant. Here, the main goal is to select an optimal classifier for classifying MCCs as benign or malignant because the performance of CAD system depends on classifier. In this study,the performance of different variants of Back propagationtraining algorithms is not only examined from the accuracy point of view, but also examined from computational point of view. For evaluating the performance of different variants of Back propagation training algorithms, texture features are extracted from mammograms. For experimental results, mammograms of mini-MIAS database are considered.The accuracy is calculated from ROC.88.24% accuracy is achieved by Levenberg-Marquardt training algorithm that is the highest among other variants of Back propagation. Mean Square Error in Levenberg-Marquardt training algorithm case is 3.68e-16 that is the lowest among other variants of Back propagation. Levenberg-Marquardt training algorithm is trained in only 23 iterations for obtaining the above said accuracy. Thus, from experimental results, it is observed that the performance of Levenberg-Marquardt training algorithm is better than other variants of Backpropagation from the accuracy point of view and the computational complexity point of view.
References
[1]
Alam N, Denton ERE, and Zwiggelaar R Classification of microcalcification clusters in digital mammograms using a stack generalization based classifier Journal of Imaging 2019 5 76 1-24
[2]
Arodz T, Kurdziel M, Sevre EOD, and Yuen DA Pattern recognition techniques for automatic detection of suspicious-looking anomalies in mammograms Comput Methods Prog Biomed 2005 79 2 135-149
[3]
Aslan AA, Gultekin S, Yilmaz GK, and Kurukahvecioglu O Is there any association between mammographic features of microcalcifications and breast Cancer subtypes in ductal carcinoma in situ? Acad Radiol 2021 28 7 963-968
[4]
Basilea TMA, Fanizzic A, Losurdoc L, Bellottia R, Bottiglid U, Dentamaroc R, Didonnac V, Faustoe A, Massafrac R, Moschettaf M, Tamborrac P, Tangarob S, and La Forgiac D Microcalcification detection in full-field digital mammograms: a fully automated computer-aided system Physica Medica: European Journal of Medical Physics 2019 64 1-9
[5]
Cascio D, Taormina V, Abbene L, Raso G (Nov. 10-17, 2018) A Microcalcification Detection System in Mammograms based on ANN Clustering. Proc. 2018 IEEE Nuclear Science Symposium and Medical Imaging Conference Proceedings (NSS/MIC), Sydney, NSW, Australia, pp. 1–4.
[6]
Cheng HD, Xu HJ (Aug 16–20, 1998) Fuzzy approach to contrast enhancement. Proc. the 14th IEEE International Conference on Pattern Recognition, Brisbane, Australia, vol. 2, pp. 1549–1551
[7]
Cheng HD, Shi XJ, Min R, Hu LM, Cai XP, and Du HN Approaches for automated detection and classification of masses in mammograms Pattern Recogn 2006 39 4 646-668
[8]
Christopher D and Simon P A novel approach for mammogram enhancement using nonlinear Unsharp masking and L0 gradient minimization Proc Comput Sci 2020 167 285-292
[9]
Cronin KA, Lake AJ, Scott S, Sherman RL, Noone A-M, Howlader N, Henley SJ, Anderson RN, Firth AU, Ma J, et al. Annual report to the nation on the status of cancer, Part I: National cancer statistics Cancer 2018 124 13 2785-2800
[10]
Dhawan AP, Buelloni G, and Gordon R Enhancement of mammographic features by optimal adaptive neighborhood image processing IEEE Trans Med Imaging 1986 5 1 8-15
[11]
Fu JC, Lee SK, Wong ST, Yeh JY, Wang AH, and Wu HK Image segmentation features selection and pattern classification for mammographic microcalcifications Comput Med Imaging Graph 2005 29 6 419-429
[12]
Gordon R and Rangayyan RM Feature enhancement of film mammograms using fixed and adaptive neighborhood Appl Opt 1984 23 4 560-564
[13]
Gulsrud TO and Husoy JH Optimal filter-based detection of microcalcifications IEEE Trans Biomed Eng 2001 48 11 1272-1280
[14]
Hamid SZ, Farshid RR, and Siamak PND Comparison of multiwavelet, wavelet, Haralick, and shape features for microcalcification classification in mammograms Pattern Recogn 2004 37 10 1973-1986
[15]
Howell A The merging breast cancer epidemic: early diagnosis and treatment Breast Cancer Res 2010 12 S4 1-10
[16]
Idokob JB and Abiyevb RH Machine learning techniques for classification of breast tissue Proc Comput Sci 2017 120 402-410
[17]
Jebathangam J, Shanthi C, Sharmila K, Devi R (May 6-8, 2021) Implementation of fuzzy logic in identification of calcification in mammogram image”, Proc. 2021 IEEE 5th international conference on intelligent computing and control systems (ICICCS), Madurai, India, pp. 806–810
[18]
Jenifer S and Parasuraman S AmudhaKadirvelu, “contrast enhancement and brightness preserving of digital mammograms using fuzzy clipped contrast-limited adaptive histogram equalization algorithm” Appl Soft Comput 2016 42 167-177
[19]
Jia H, Sun K, Song W, Peng X, Lang C, and Li Y Multi-strategy emperor penguin optimizer for RGB histogram-based color satellite image segmentation using Masi entropy IEEE Open Access J 2019 7 134448-134474
[20]
Jiang J, Yao B, and Wason AM Integration of fuzzy logic and structure tensor towards mammogram contrast enhancement Comput Med Imaging Graph 2005 29 1 83-90
[21]
Khairuzzaman AKM and Chaudhury S Masi entropy based multilevel thresholding for image segmentation Multimed Tools Appl 2019 78 33573-33591
[22]
Kim JK, Park JM, Song KS, Park HW (Sep 24–26, 1997) Texture analysis and artificial neural network for detecting of clustered microcalcifications on mammograms”, Proc. the 7th IEEE Workshop on Neural Networks for Signal Processing, Amelia Island, FL, USA, pp. 199–206
[23]
McSweeney MB, Sprawls P, and Egan RL Enhanced image mammography Am J Roentgenol 1983 140 1 9-14
[24]
Mohanalin J, Kalra PK, Kumar N (March 6–7, 2009) Extraction of microcalcifications using non extensive property of mammograms. Proc. IEEE International Conference on Advance Computing (IACC-09), Patiala, Punjab, India, pp. 636–641
[25]
Mohanalin J, Kalra PK, Kumar N (Apr 3–5, 2009) Tsallis entropy based contrast enhancement of microcalcifications. Proc. IEEE International Conference on Signal Acquisition and Processing (ICSAP-09), Kuala Lumpur, Malaysia, pp. 3–7
[26]
Mohanalin J, Kalra PK, and Kumar N A novel automatic microcalcification detection technique using Tsallis entropy & a type II fuzzy index Comput Math Appl 2010 60 8 2426-2432
[27]
Mohanalin J, Kalra PK, and Kumar N An automatic method to enhance microcalcifications using normalized Tsallis entropy Signal Process 2010 90 3 952-958
[28]
Morrow WM, Paranjape RB, Rangayyan RM, and Desautels JEL Region-based contrast enhancement of mammograms IEEE Trans Med Imaging 1992 11 3 392-406
[29]
Muthuvel M, Thangaraju B, and Chinnasamy G MicrocalciÞcation cluster detection using multiscale products based hessian matrix via the Tsallis thresholding scheme Pattern Recogn Lett 2017 94 15 127-133
[30]
National Cancer Institute Cancer stat facts: female breast cancer. URL: https://seer.cancer.gov/statfacts/html/breast.html
[31]
Pal NR, Bhowmick B, Patel SK, Pal S, and Das J A multi-stage neural network aided system for detection of microcalcifications in digitized mammograms Neurocomputing 2008 71 13–15 2625-2634
[32]
Rao RV and More KC Optimal Design of the Heat Pipe using TLBO (teaching-learning-based optimization) algorithm Energy 2015 80 535-544
[33]
Rao RV, Savsani VJ, and Vakharia DP Teaching–learning-based optimization: a novel method for constrained mechanical design optimization problems Comput Aided Des 2011 43 3 303-315
[34]
Ren J, Wang D, and Jiang J Effective recognition of MCC using an improved neural classifier Eng Appl Artif Intell 2011 24 4 638-645
[35]
Saada G, Khadoura A, and Kanafan Q ANN and Adaboost application for automatic detection of microcalcifications in breast cancer Egypt J Rad Nucl Med 2016 47 1803-1814
[36]
Sahu BK, Pati S, Mohanty PK, and Panda S Teaching–learning based optimization algorithm based fuzzy-PID controller for automatic generation control of multi-area power system Appl Soft Comput 2015 27 240-249
[37]
Shachor Y, Greenspan H, Goldberger J (April 8-11, 2019) A mixture of views network with applications to the classification of breast microcalcifications. Proc. 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), Venice, Italy, pp. 1065–1069
[38]
Sheshadri HS and Kandaswamy A Experimental investigation on breast tissue classification based on statistical feature extraction of mammograms Comput Med Imaging Graph 2007 31 1 46-48
[39]
Sickles E Breast calcifications: mammographic evaluation J Radiol 1986 160 289-293
[40]
Sujatha K, Durgadevi G, Senthil Kumar K, Karthikeyan V, Ponmagal RS, Hari R, Bhavani NPG, Srividhya V, Cao S-Q (2020) Screening and early identification of microcalcifications in breast using texture-based ANFIS classification”, Advances in ubiquitous sensing applications for healthcare, vol. 7, pp. 115–140.
[41]
Sundaram M, Ramar K, Arumugam N, and Prabin G Histogram modified local contrast enhancement for mammogram images Appl Soft Comput 2011 11 8 5809-5816
[42]
Tawani SS, Gurjar AA (Dec 27-28, 2019) A Novel Algorithm for the Automatic Detection and Classification of Microcalcification Clusters Using Wavelets. Proc. 2019 IEEE international conference on innovative trends and advances in engineering and technology (ICITAET), Shegoaon, India, pp. 47–52.
[43]
Thurfjell EL, Lernevall KA, and Taube AAS Benefit of independent double reading in a population-based mammography screening program Radiology 1994 191 1 241-244
[44]
Touil A, Kalti K, Conze P-H, Solaiman B, and Mahjoub MA Automatic detection of microcalcification based on morphological operations and structural similarity indices Biocybern Biomed Eng 2020 40 1155-1173
[45]
Tripathy S and Swarnkar T Unified preprocessing and enhancement technique for mammogram images Proc Comput Sci 2020 171 1848-1857
[46]
Verma B, McLeod P, and Klevansky A Classification of benign and malignant patterns in digital mammogramsfor the diagnosis of breast cancer Expert Syst Appl 2010 37 4 3344-3351
[47]
Wirth MA, Nikitenko D (June 26–28, 2005) Quality evaluation of fuzzy contrast enhancement algorithms. Proc. the Annual Meeting of the North American Fuzzy Information Processing Society, Detroit, MI, USA, USA, pp. 436–441
[48]
World Health Organization (WHO) (n.d.) URL: https://www.who.int/cancer/prevention/diagnosis-screening/breast-cancer/en/
[49]
Yu S-N and Huang Y-k Detection of microcalcifications in digital mammograms using combined model-based and statistical textural features Expert Syst Appl 2010 37 7 5461-5469
Index Terms
- Classification of clustered microcalcifications using different variants of backpropagation training algorithms
Index terms have been assigned to the content through auto-classification.
Recommendations
Computerized Detection and Classification of Malignant and Benign Microcalcifications on Full Field Digital Mammograms
IWDM '08: Proceedings of the 9th international workshop on Digital MammographyThe purpose of the study is to develop an automated system for detecting microcalcifications within a predefined region of interest (ROI), and classifying the clusters as malignant and benign on full-filled digital mammograms (FFDM). Our system ...
Texture-based analysis of clustered microcalcifications detected on mammograms
The need for early detection of breast cancer has led to establishing screening programs that generate large volumes of mammograms to be analyzed. These analysis are time consuming and labor intensive. Computerized analysis of mammograms has been ...
A Method for Microcalcifications Detection in Breast Mammograms
Breast cancer is the most cause of death for women above age 40 around the world. In this paper, we propose a method to detect microcalcifications in digital mammography images using two-dimensional Discrete Wavelets Transform and image enhancement ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022.
Publisher
Kluwer Academic Publishers
United States
Publication History
Published: 01 May 2022
Accepted: 03 January 2022
Revision received: 22 July 2021
Received: 24 November 2020
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 09 Jan 2025