Detection and classification of breast masses and microcalcifications using a pulse-coupled neural network and ensemble machine learning
Yen Thi Hoang Hua1, Giang Hong Nguyen1 and Liet Van Dang2
Research Scholar, Faculty of Physics and Engineering Physics,University of Science, Ho Chi Minh City, Vietnam; Vietnam National University,Ho Chi Minh City,Vietnam1
Associate Professor, Faculty of Physics and Engineering Physics,University of Science, Ho Chi Minh City, Vietnam; Vietnam National University,Ho Chi Minh City,Vietnam2
Associate Professor, Faculty of Physics and Engineering Physics,University of Science, Ho Chi Minh City, Vietnam; Vietnam National University,Ho Chi Minh City,Vietnam2
Corresponding Author : Yen Thi Hoang Hua
Recieved : 08-February-2025; Revised : 11-October-2025; Accepted : 14-October-2025
Abstract
Breast cancer remains a major global health concern, and although mammography is the standard screening technique, its inherently low contrast often limits diagnostic precision. This study presents a multistage computer-aided diagnosis (CADx) framework for mammographic image enhancement, segmentation, and classification. The pipeline begins with preprocessing, where wavelet-domain denoising and contrast optimization through modified morphological operations are applied to suppress noise and improve visibility. A pulse-coupled neural network (PCNN)—a biologically inspired model of the mammalian visual cortex—is then employed to segment both microcalcifications and masses. For classification, deep features extracted from the “fc8” layer of VGG19 are input to an ensemble learning framework implemented via MATLAB’s fitcensemble function to distinguish between benign and malignant cases. The proposed framework was evaluated on the mammographic image analysis society (MIAS) dataset using 20 images for microcalcification (MC) segmentation, 15 images for various mass types across different background tissues, and 100 images (50 benign, 50 malignant) for classification. Segmentation results for both MCs and masses demonstrated performance comparable to or better than state-of-the-art methods. For classification, Totally Corrective Boosting (TotalBoost) and Linear Programming Boosting (LPBoost) achieved 100% accuracy on both training and test sets, while Adaptive Boosting (AdaBoost) and Bagging attained 100% training accuracy and 94.7% test accuracy. Although tested on a small dataset, the integrated preprocessing and ensemble-based strategy yielded promising outcomes in both segmentation and classification stages.
Keywords
Breast cancer detection, Mammography, Computer-aided diagnosis (CADx), Pulse-coupled neural network (PCNN), Ensemble learning, VGG19 features.
Cite this article
Hua YTH, Nguyen GH, Dang LV. Detection and classification of breast masses and microcalcifications using a pulse-coupled neural network and ensemble machine learning. International Journal of Advanced Technology and Engineering Exploration. 2025;12(131):1504-1526. DOI : 10.19101/IJATEE.2025.121220206
References
[1]
Bray F, Laversanne M, Sung H, Ferlay J, Siegel RL, Soerjomataram I, et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: a Cancer Journal for Clinicians. 2024; 74(3):229-63.
[2]
Siegel RL, Giaquinto AN, Jemal A. Cancer statistics, 2024. CA: A Cancer Journal for Clinicians. 2024; 74(1):12-49.
[3]
Mazza D, Emery J. The early detection of breast cancer: an update from the red book. Australian Journal of General Practice. 2025; 54(5):272-5.
[4]
Liu S, Wu G, Zhou C, Yan S, Cui H. The application of mammography imaging in the diagnosis and prediction of breast diseases. Progress in Medical Devices. 2024; 2(1):1-11.
[5]
Ben AM, Ayachi FL, Cardoso DPA, Ksantini R, Mahjoubi H. Harnessing deep learning for early breast cancer diagnosis: a review of datasets, methods, challenges, and future directions. International Journal of Computing and Digital Systems. 2024; 16(1):1643-61.
[6]
Chen J, Gandomkar Z, Reed WM. Investigating the impact of cognitive biases in radiologists’ image interpretation: a scoping review. European Journal of Radiology. 2023; 166:1-20.
[7]
Loizidou K, Elia R, Pitris C. Computer-aided breast cancer detection and classification in mammography: a comprehensive review. Computers in Biology and Medicine. 2023; 153:106554.
[8]
Sharma BP, Purwar RK. Computer-aided detection and diagnosis of breast cancer: a review. ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal. 2024; 13: e31412.
[9]
Anari S, Sadeghi S, Sheikhi G, Ranjbarzadeh R, Bendechache M. Explainable attention based breast tumor segmentation using a combination of UNet, ResNet, DenseNet, and EfficientNet models. Scientific Reports. 2025; 15(1):1-39.
[10]
Juneja M, Aggarwal N, Saini SK, Pathak S, Kaur M, Jaiswal M. A comprehensive review on artificial intelligence-driven preprocessing, segmentation, and classification techniques for precision furcation analysis in radiographic images. Multimedia Tools and Applications. 2025; 84(19):21467-520.
[11]
Thi HHY, Hong NG, Bao BL, Van LD. Enhancing and denoising mammographic images for tumor detection using bivariate shrinkage and modified morphological transforms. International Journal of Computing and Digital Systems. 2024; 16(1):1055-66.
[12]
https://www.mathworks.com/matlabcentral/answers/834743-how-to-threshold-wavelet-coefficients-of-an-image-using-higher-order-statastics-skewness-kurtosis. 15 September 2025.
[13]
Lindblad T, Kinser JM. Image processing using pulse-coupled neural networks. Berlin, Heidelberg: Springer Berlin Heidelberg; 2005.
[14]
Zine-dine I, Fahfouh A, Riffi J, El FK, El BI, Mahraz MA, et al. Brain tumor classification using feature extraction and ensemble learning. Machine Graphics & Vision. 2024; 33(3/4):3-28.
[15]
Ambika LG, Anitha TN, Jayasudha K, Rafi M. Effective approach for identification and removal of noise in mammographic images. Journal of Harbin Engineering University. 2023; 44(7): 1294-306.
[16]
Mallaparapu K, Ramarao KV. Wavelet transform based image enhancement: a noise reduction approach. Computer and Telecommunication Engineering. 2023; 1(1):1-8.https://aber.apacsci.com/index.php/CTE/article/view/2321
[17]
Jeevitha V, Aroquiaraj IL. Mammogram images using noise removal of filtering techniques. International Research Journal on Advanced Engineering Hub. 2024; 2(02):118-23.
[18]
Ingle S, Vidhate A, Chaudhari S. Noise removal for mammogram images using gaussian based unsharp masking. In 8th international conference on computing, communication, control and automation (ICCUBEA) 2024 (pp. 1-6). IEEE.
[19]
Singh AR, Athisayamani S, Karim FK, Ibrahim AZ, Alshetewi S, Mostafa SM. An enhanced denoising system for mammogram images using deep transformer model with fusion of local and global features. Scientific Reports. 2025; 15(1):1-20.
[20]
Almaremi FA, Eissa HA, Abdelmula HS, Armih KA. Enhancement mammogram image technique for breast cancer detection. Journal of Electronic Systems and Programming. 2023; 1:1-17.
[21]
Härtinger P, Steger C. Adaptive histogram equalization in constant time. Journal of Real-Time Image Processing. 2024; 21(3):1-9.
[22]
Moradzadeh S, Mehrdad V. Improvement of medical images with multi-objective genetic algorithm and adaptive morphological transformations. Scientific Reports. 2025; 15(1):1-14.
[23]
Gangwar S, Devi R, Mat Isa NA. Optimized exposer region-based modified adaptive histogram equalization method for contrast enhancement in CXR imaging. Scientific Reports. 2025; 15(1):6693.
[24]
Masroor I, Zafar U, Hafeez A, Baig S, Saeed SA. Contrast-enhanced mammography (Cem) as a breast imaging modality: initial experience at a tertiary care center. Pakistan Journal of Radiology. 2024; 34(4):220-4.
[25]
Xu W, Chen L, Zeng W, Xu Z, Ma M, Chen W, et al. Addition of contrast-enhanced mammography enhancement patterns and morphology for differentiating benign from malignant papillary breast lesions. British Journal of Radiology. 2025; 98(1167):383-91.
[26]
Saini V, Khurana M, Challa RK. A hybrid model for the segmentation of mammogram images using otsu thresholding, morphology and U-Net. Biomedical and Pharmacology Journal. 2025; 18(1):799-812.
[27]
Vijayalakshmi S, Pandey BK, Pandey D, Lelisho ME. Innovative deep learning classifiers for breast cancer detection through hybrid feature extraction techniques. Scientific Reports. 2025; 15(1):1-16.
[28]
Prodan M, Paraschiv E, Stanciu A. Applying deep learning methods for mammography analysis and breast cancer detection. Applied Sciences. 2023; 13(7):1-18.
[29]
Sannasi CSR, Bharanidharan N, Vinoth KV, Mahesh TR, Alqahtani MS, Guluwadi S. Deep transfer learning with fuzzy ensemble approach for the early detection of breast cancer. BMC Medical Imaging. 2024; 24(1):1-15.
[30]
Geng J, Ji F, Li S, Shen Y, Yang Z. Dynamic-step-size regulation in pulse-coupled neural networks. Entropy. 2025; 27(6):1-20.
[31]
Singh DP, Singh RM, Gopi T, Deepa D, Gandhi KP, Kumar D. Improved pulse coupled neural network based on maximize SNR for vessel extraction. In international conference on advancements in power, communication and intelligent systems (APCI) 2024 (pp. 1-4). IEEE.
[32]
Mugunthan SR. Image processing applications of pulse coupled neural networks. Journal of Innovative Image Processing. 2023; 5(1):69-78.
[33]
Mondal PK, Jahan MK, Byeon H. Mammogram mastery: breast cancer image classification using an ensemble of deep learning with explainable artificial intelligence. Medicine. 2025; 104(22): e42242.
[34]
Jeny AA, Hamzehei S, Jin A, Baker SA, Van RT, Bai J, et al. Hybrid transformer‐based model for mammogram classification by integrating prior and current images. Medical Physics. 2025; 52(5):2999-3014.
[35]
Bahar MS. A novel hybrid attention VGG method for benign and malignant breast cancer classification. Dicle University Journal of Engineering/Dicle Üniversitesi Mühendislik Dergisi. 2025; 16(1):27-47.
[36]
Manigrasso F, Milazzo R, Russo AS, Lamberti F, Strand F, Pagnani A, et al. Mammography classification with multi-view deep learning techniques: investigating graph and transformer-based architectures. Medical Image Analysis. 2025; 99:1-18.
[37]
Guo T, Zhang T, Lim E, Lopez-benitez M, Ma F, Yu L. A review of wavelet analysis and its applications: challenges and opportunities. IEEE Access. 2022; 10:58869-903.
[38]
Starck JL, Fadili J, Murtagh F. The undecimated wavelet decomposition and its reconstruction. IEEE Transactions on Image Processing. 2007; 16(2):297-309.
[39]
Wang Z, Ma Y, Cheng F, Yang L. Review of pulse-coupled neural networks. Image and Vision Computing. 2010; 28(1):5-13.
[40]
https://neuronaldynamics.epfl.ch/. Accessed 15 September 2025.
[41]
Xiao-bo Q, Jing-wen Y, Hong-zhi XI, Zi-qian Z. Image fusion algorithm based on spatial frequency-motivated pulse coupled neural networks in nonsubsampled contourlet transform domain. Acta Automatica Sinica. 2008; 34(12):1508-14.
[42]
Salakhutdinov R. Learning deep generative models. Annual Review of Statistics and Its Application. 2015; 2(1):361-85.
[43]
James G. An introduction to statistical learning with applications in R. New York: Springer; 2023.
[44]
Şendur L, Selesnick IW. A bivariate shrinkage function for wavelet-based denoising. In international conference on acoustics, speech, and signal processing 2002 (pp. 1261-4). IEEE.
[45]
Zebari DA, Haron H, Zeebaree SR, Zeebaree DQ. Enhance the mammogram images for both segmentation and feature extraction using wavelet transform. In international conference on advanced science and engineering (ICOASE) 2019 (pp. 100-5). IEEE.
[46]
Guofeng Z, Hamdulla A. Adaptive morphological contrast enhancement based on quantum genetic algorithm for point target detection. Mobile Networks and Applications. 2021; 26(2):638-48.
[47]
Le VT, Van DL. Enhancement of mammographic images based on wavelet denoise and morphological contrast enhancement. International Journal of Image, Graphics and Signal Processing. 2023; 6:28-40.
[48]
Gupta S, Porwal R. Appropriate contrast enhancement measures for brain and breast cancer images. International Journal of Biomedical Imaging. 2016; 2016(1):4710842.
[49]
Liu H, Liu M, Li D, Zheng W, Yin L, Wang R. Recent advances in pulse-coupled neural networks with applications in image processing. Electronics. 2022; 11(20):1-14.
[50]
Mateen M, Wen J, Nasrullah, Song S, Huang Z. Fundus image classification using VGG-19 architecture with PCA and SVD. Symmetry. 2018; 11(1):1-12.
[51]
http://peipa.essex.ac.uk/info/mias.html. 15 September 2025.
[52]
Iwasa Y, Iwashita T, Takeuchi Y, Ichikawa H, Mita N, Uemura S, et al. Automatic segmentation of pancreatic tumors using deep learning on a video image of contrast-enhanced endoscopic ultrasound. Journal of Clinical Medicine. 2021; 10(16):1-12.
[53]
Civcik L, Yilmaz B, Özbay Y, Emlik GD. Detection of microcalcification in digitized mammograms with multistable cellular neural networks using a new image enhancement method: automated lesion intensity enhancer (ALIE). Turkish Journal of Electrical Engineering and Computer Sciences. 2015; 23(3):853-72.
[54]
Guo YN, Dong M, Yang Z, Gao X, Wang K, Luo C, et al. A new method of detecting micro-calcification clusters in mammograms using contourlet transform and non-linking simplified PCNN. Computer Methods and Programs in Biomedicine. 2016; 130:31-45.
[55]
Zhu L, Guo Y, Tu J, Ma Y, Guo YN, Yang Z, et al. Improved SMQT algorithm and PCNN model for micro-calcification clusters detection in mammograms. In 7th international conference on bioinformatics and computational biology (ICBCB) 2019 (pp. 172-8). IEEE.
[56]
Xie W, Ma Y, Li Y. Breast mass segmentation in digital mammography based on pulse coupled neural network and level set method. In Satellite Data Compression, Communications, and Processing XI 2015 (pp. 147-55). SPIE.
[57]
https://www.mathworks.com/help/deeplearning/ref/vgg19.html. 15 September 2025.
[58]
https://www.mathworks.com/help/stats/classification-ensembles.html 15 September 2025.
[59]
Warmuth MK, Liao J, Rätsch G. Totally corrective boosting algorithms that maximize the margin. In proceedings of the 23rd international conference on machine learning 2006 (pp. 1001-8). ACM.
[60]
El HEM, Yassin NI. Malignant and nonmalignant classification of breast lesions in mammograms using convolutional neural networks. Biomedical Signal Processing and Control. 2021; 70:102954.
[61]
Li J, Shi J, Chen J, Du Z, Huang L. Self-attention random forest for breast cancer image classification. Frontiers in Oncology. 2023; 13:1-14.
[62]
Hayum AA, Jaya J, Sivakumar R, Paulchamy B. An efficient breast cancer classification model using bilateral filtering and fuzzy convolutional neural network. Scientific Reports. 2024; 14(1):1-13.
[63]
Priyaa S. An enhanced approach for preprocessing of mammogram images using inverse daubechies wavelet transform and non-linear diffusion. International Journal of Computer Applications. 2015; 130(5):6-12.
[64]
Benhassine NE, Boukaache A, Boudjehem D. Medical image denoising using optimal thresholding of wavelet coefficients with selection of the best decomposition level and mother wavelet. International Journal of Imaging Systems and Technology. 2021; 31(4):1906-20.
[65]
Balakumaran T, Vennila IL, Shankar CG. Detection of microcalcification in mammograms using wavelet transform and fuzzy shell clustering. International Journal of Computer Science & Information Security. 2010; 7(1):218-24.
[66]
Hosni MHA, Alharbi AH, Alghamdi NS. Breast cancer detection through feature clustering and deep learning. Intelligent Automation & Soft Computing. 2022; 31(2):1273-86.
[67]
https://www.mathworks.com/help/stats/ensemble-algorithms.html. 15 September 2025.
[68]
Chen Y, Chen S, Yang Y, Lu S. Comparison of decision tree and ensemble algorithms. In proceedings of the 4th international conference on signal processing and machine learning 2024 (pp. 1-8). EWA.C10.54254/2755-2721/55/20241535