Abstract
Breast cancer is a leading cause of mortality affecting women across the world. Early detection and diagnosis can decrease the mortality rate due to this cancer. Machine learning-based models are gaining popularity for biomedical applications due to the ability of nonlinear mapping between input and output patterns using supervised training phase. The research work in the paper is focused on the optimal adaptive threshold for mammogram mass segmentation, and detection in order to assist radiologist in accurate diagnosis Legendre neural network with single layer is used to develop the model, and the training is performed through Block Based Normalized Sign–Sign Least Mean Square (BBNSSLMS) algorithm. Legendre neural network expands the input vector using standard Legendre polynomial, and the recursive update principle is followed for the weight vector in higher dimension. The optimal threshold is indirectly used for proper segmentation of mammogram mass. The proposed segmentation method involves training phase with 30 images and testing phase by 151 images obtained from standard Mammogram Image Analysis Society (MIAS) database. The proposed model achieved a sensitivity of 95% and accuracy of 96% with false positives per image calculated as 1.19.
Graphical abstract
• Threshold selection is carried out using single-layer Legendre NN with reduced computational complexity. BNSSLMS algorithm process the data samples block wise instead of sample by sample basis. Optimal threshold is generated according to the varying image properties which helps in correct segmentation and detection.
• Due to sparse nature of the adaptive model, more numbers of weight coefficients are tending to zero which also helps in faster convergence.
Mammogram Mass Detection Steps:
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Singh VK, Rashwan HA, Romani S, Akram F, Pandey N, Sarker MMK, Saleh A, Arenas M, Arquez M, Puig D, Torrents-Barrena J (2020) 112855) Breast tumor segmentation and shape classification in mammograms using generative adversial and convolutional neural network. Expert Syst Appl 139:1–14
Ting FF, Tan YJ, Sim KS (2019) Convolutional neural network improvement for breast cancer classification. Expert Syst Appl 120:103–115
Yuvraj K, Ragupathy US (2013) Computer aided segmentation and classification of mass in mammographic images using ANFIS. EJBI 9(2):37–41
Rao TVN, Govardhan A (2015) Efficient segmentation and classification of mammogram images with fuzzy filtering. Indian J Sci Technol 8(15):1–8
Chougrad H, Zouaki H, Alheyane O (2018) Deep convolutional neural networks for breast cancer screening. Comput Methods Prog Biomed 157:19–30
Sun W, Tseng T-L(B), Zhang J, Qian W (2017) Enhancing deep convolutional neural network scheme for breast cancer diagnosis with unlabeled data. Comput Med Imaging Graph 57:4–9
Kanadam KP, Chereddy SR Mammogram classification using sparse-ROI: A novel representation to arbitrary shaped masses. Expert Syst Appl 57(2016):204–213
Diniz JOB, Diniz PHB, Valente TLA, Silva AC, de Paiva AC, Gattas M (2018) Detection of mass regions in mammograms by bilateral analysis adapted to breast density using similarity indexes and convolutional neural networks. Comput Methods Prog Biomed 156:191–207
Pal NR, Bhowmick B, Patel SK, Pal S, Das J (2008) A multi-stage neural network aided system for detection of microcalcification in digitized mammograms. Neurocomputing 71:2625–2634
Verma B (2008) Novel network architecture and learning algorithms for the classification of mass abnormalities in digitized mammograms. Artif Intell Med 42:67–79
Adams R, Bischof L (1994) Seeded region growing, IEEE transactions on pattern analysis and machine intelligence. https://doi.org/10.1109/34.295913
Kom G, Tiedeu A, Kom M (2007) Automated detection of masses in mammograms by local adaptive thresholding. Comput Biol Med 37:37–48
Sudha NS, Dodda RKR (2017) Block based normalized LMS Adaptive filtering technique denoising EEG artefacts. Int J Curr Eng Technol 7(2):386–389
Cao A, Song Q, Yang X (2008) Robust information clustering incorporating spatial information for breast mass detection in digitized mammograms. Comput Vis Image Underst 109:86–96
Hu K, Gao X, Li F (2011) Detection of Suspicious Lesions by Adaptive Thresholding Based on Multiresolution Analysis in Mammograms. IEEE Trans Instrum Meas 60(2):462–472
Kurt B, Nabiyev VV, Turhan K (2014) A novel automatic suspicious mass regions identification using Havrda & Charvat entropy and Otsu’s N thresholding. Comput Methods Prog Biomed 114:349–360
Jen C-C, Yu S-S (2015) Automatic detection of abnormal mammograms in mammographic images. Expert Syst Appl 42:3048–3055
Patra JC, Chin WC, Meher PK, Chakraborty G (2008) Legendre-FLANN-based nonlinear channel equalization in wireless communication system. IEEE international conference on systems, man and cybernetics, Singapore
Shirazi AZ, Chabok SJSM, Mohammadi Z (2018) A novel and reliable computational intelligence system for breast cancer detection. Med Biol Eng Comput 56:721–732
Arora R, Rai PK, Raman B (2020) Deep feature-based automatic classification of mammograms. Med Biol Eng Comput 58:1199–1211
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Sarangi, S., Rath, N.P. & Sahoo, H. Mammogram mass segmentation and detection using Legendre neural network-based optimal threshold. Med Biol Eng Comput 59, 947–955 (2021). https://doi.org/10.1007/s11517-021-02348-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-021-02348-4