Multi-View Combination using Mutual Information and 3‐D Euclidean Distance for Breast Cancer Classification
Article Sidebar
Main Article Content
Abstract
The most popular method of early breast cancer detection is mammography, which uses two views: the Medio Lateral Oblique (MLO) and the Cranio Caudal (CC). In practice, experienced radiologists interpret both mammography views in order to categorize them as normal or abnormal. However, human error has been found in classification. This study proposes multi-view combination using mutual information and 3‐D Euclidean distance for breast cancer classification. The public dataset Breast Cancer Digital Repository (BCDR) including 600 CC-view and 600 MLO-view was used in this study. Our method divides into five steps. First, pre-training with deep convolutional network was used to extract the significant feature. Second, principal component analysis (PCA) was simultaneously computed the principal components. Third, mutual information (MI) was measured the mutual dependence between components and class label for selecting the best component group. Fourth, 3‐dimensional Euclidean distance merging was established to merge both views. Finally, the support vector machine was performed to classify breast lesion in normal, benign or malignant. The model accuracy is 99.33%, and AUC is 0.98. The results demonstrate that the performance of our strategy is more improved when compared with other combination studies.
Article Details
References
M. Giger, M. Inciardi, A. Edwards, J. Papaioannou, K Drukker, Y. Jiang, R. Brem, and J. Brown, Automated Breast Ultrasound in Breast Cancer Screening of Women With Dense Breasts: Reader Study of Mammography-Negative and Mammography-Positive Cancers. American Journal of Roentgenology, Vol. 206, No. 6, pp.1341-1350, 2016.
L. Bassett, J. Diamond, R. Gold, and R. McLelland, "Survey of mammography practices", American Journal of Roentgenology, Vol. 149, No. 6, pp. 1149-1152, 1987. Available: 10.2214/ajr.149.6.1149.
R. Blanks, M. Wallis, and S. Moss, "A comparison of cancer detection rates achieved by breast cancer screening programmes by number of readers, for one and two view mammography: results from the UK National Health Service breast screening programme". Journal of Medical Screening, Vol. 5, No. 4, pp. 195-201, 1998. Available: 10.1136/jms.5.4.195.
M. Michell, R. Wasan, A. Iqbal, C. Peacock, D. Evans, and J. Morel, "Two-view 2D digital mammography versus one-view digital breast tomosynthesis". Breast Cancer Research, Vol. 12, No. 3, 2010. Available: 10.1186/bcr2656.
S. Roberts-Klein, E. Iuanow, and P. Slanetz, "Avoiding Pitfalls in Mammographic Interpretation". Canadian Association of Radiologists Journal, Vol. 62, No. 1, pp. 50-59, 2011. Available: 10.1016/j.carj.2010.07.004.
M. Popli, R. Teotia, M. Narang, and H. Krishna, "Breast Positioning during Mammography: Mistakes to be Avoided". Breast Cancer: Basic and Clinical Research, Vol. 8, p. BCBCR.S17617, 2014. Available: 10.4137/bcbcr.s17617.
O. Russakovsky et al., "ImageNet Large Scale Visual Recognition Challenge". International Journal of Computer Vision, Vol. 115, No. 3, pp. 211-252, 2015. Available: 10.1007/s11263-015-0816-y.
N. Tajbakhsh et al., "Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?". IEEE Transactions on Medical Imaging, Vol. 35, No. 5, pp. 1299-1312, 2016. Available: 10.1109/tmi.2016.2535302.
M. Salvi, and F. Molinari, "Multi-tissue and multi-scale approach for nuclei segmentation in H&E stained images". BioMedical Engineering OnLine, Vol. 17, No. 1, 2018. Available: 10.1186/s12938-018-0518-0.
A. Jouirou, A. Baâzaoui, and W. Barhoumi, "Multi-view information fusion in mammograms: A comprehensive overview". Information Fusion, Vol. 52, pp. 308-321, 2019. Available: 10.1016/j. inffus.2019.05.001.
R. Lavanya, and N. Nagarajan, "Information Fusion in CAD Systems for Breast Cancer Diagnosis Using Mammography and Ultrasound Imaging: A Survey". Journal of Artificial Intelligence, Vol. 7, No. 3, pp. 113-122, 2014. Available: 10.3923/jai. 2014.113.122.
Y. Mao, H. Lim, M. Ni, W. Yan, D. Wong, and J. Cheung, "Breast Tumour Classification Using Ultrasound Elastography with Machine Learning: A Systematic Scoping Review". Cancers, Vol. 14, No. 2, pp. 367, 2022. Available: 10.3390/cancers 14020367.
S. Huang, Y. Yang, X. Jin, Y. Zhang, Q. Jiang, and S. Yao, "Multi-Sensor Image Fusion Using Optimized Support Vector Machine and Multiscale Weighted Principal Component Analysis". Electronics, Vol. 9, No. 9, pp. 1531, 2020. Available: 10.3390/electronics 9091531.
I. Jolliffe, and J. Cadima, "Principal component analysis: a review and recent developments". Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 374, No. 2065, p. 20150202, 2016. Available: 10.1098/rsta.2015.0202.
R. Ledesma, P. Valero-Mora, and G. Macbeth, "The Scree Test and the Number of Factors: a Dynamic Graphics Approach". The Spanish Journal of Psychology, Vol. 18, 2015. Available: 10.1017/sjp.2015.13.
J. Trewn, “Multivariate statistical methods in quality management,” 5.2: Principal Component Analysis Based on Covariance Matrices | Engineering360. Available Online at https://www.globalspec.com/reference/71521/203279/5-2-principal-component-analysis-based-on-covariance-matrices, accessed on 26 March 2022.
Y. Le Cun, Y. Bengio, and G. Hinton, “Deep Learning”. Nature, Vol. 521, pp. 436-44, 2015. 10.1038/nature14539.
G. Litjens et al., "A survey on deep learning in medical image analysis". Medical Image Analysis, Vol. 42, pp. 60-88, 2017. Available: 10.1016/j.media. 2017.07.005.
G. de la Cruz, Y. Du, and M. Taylor, "Pre-training with non-expert human demonstration for deep reinforcement learning", The Knowledge Engineering Review, Vol. 34, 2019. Available: 10.1017/s 0269888919000055.
A. Krizhevsky, I. Sutskever, and G. Hinton, "ImageNet classification with deep convolutional neural networks". Communications of the ACM, Vol. 60, No. 6, pp. 84-90, 2017. Available: 10.1145/3065386.
P. Sermanet, D. Eigen, X. Zhang, et al., “OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks”. Computer Vision and Pattern Recognition, pp. 1-16, 2014.
USF Digital Mammography Home Page, DDSM: Digital Database for Screening Mammography. Available Online at http://www.eng.usf.edu/cvprg/Mammography/Database.html, accessed on 26 March 2022.
G. Lee et al., "Supervised Multi-View Canonical Correlation Analysis (sMVCCA): Integrating Histologic and Proteomic Features for Predicting Recurrent Prostate Cancer". IEEE Transactions on Medical Imaging, Vol. 34, No. 1, pp. 284-297, 2015. Available: 10.1109/tmi.2014.2355175.
D. Ratkowsky, "Choosing the number of principal coordinates when using CAP, the canonical analysis of principal coordinates". Austral Ecology, Vol. 41, No. 7, pp. 842-851, 2016. Available: 10.1111/aec.12378.
V. Gray. Principal Component Analysis. Hauppauge: Nova Science Publishers, Inc., 2017.
R. Canuto, S. Camey, D. Gigante, A. Menezes, and M. Olinto, "Focused Principal Component Analysis: a graphical method for exploring dietary patterns", Cadernos de Saúde Pública, Vol. 26, No. 11, pp. 2149-2156, 2010. Available: 10.1590/s0102-311x2010001100016.
R. Abdesselam, "A Topological Approach of Principal Component Analysis". International Journal of Data Science and Analysis, Vol. 7, No. 2, pp. 20, 2021. Available: 10.11648/j.ijdsa.20210702.11.
B. ALKAN, "Robust Principal Component Analysis Based On Modified Minimum Covariance Determinant In The Presence Of Outliers". Alphanumeric Journal, Vol. 4, No. 2, 2016. Available: 10.17093/aj.2016. 4.2.5000189525.
A. Becker, M. Marcon, S. Ghafoor, M. Wurnig, T. Frauenfelder, and A. Boss, "Deep Learning in Mammography", Investigative Radiology, Vol. 52, No. 7, pp. 434-440, 2017. Available: 10.1097/rli. 0000000000000358.
G. Carneiro, J. Nascimento, and A. Bradley, "Automated Analysis of Unregistered Multi-View Mammograms With Deep Learning". IEEE Transactions on Medical Imaging, Vol. 36, No. 11, pp. 2355-2365, 2017. Available: 10.1109/tmi.2017. 2751523.
L. Shen, L. Margolies, J. Rothstein, E. Fluder, R. McBride, and W. Sieh, "Deep Learning to Improve Breast Cancer Detection on Screening Mammography". Scientific Reports, Vol. 9, No. 1, 2019. Available: 10.1038/s41598-019-48995-4.
S. Sasikala, and M. Ezhilarasi, "Fusion of k-Gabor features from medio-lateral-oblique and craniocaudal view mammograms for improved breast cancer diagnosis". Journal of Cancer Research and Therapeutics, Vol. 14, No. 5, pp. 1036, 2018. Available: 10.4103/jcrt.jcrt_1352_16.
S. Sasikala, and M. Ezhilarasi, "Comparative Analysis of Serial and Parallel Fusion on Texture Features for Improved Breast Cancer Diagnosis". Current Medical Imaging Reviews, Vol. 14, No. 6, pp. 957-968, 2018. Available: 10.2174/1573405613 666170926164625.
A. Bommert, T. Welchowski, M. Schmid and J. Rahnenführer, "Benchmark of filter methods for feature selection in high-dimensional gene expression survival data", Briefings in Bioinformatics, Vol. 23, No. 1, 2021. Available: 10.1093/bib/bbab354.
A. Jouirou, A. Baâzaoui, and W. Barhoumi, "Multi-view information fusion in mammograms: A comprehensive overview". Information Fusion, Vol. 52, pp. 308-321, 2019. Available: 10.1016/j.inffus. 2019.05.001.
N. Derbel, H. Tmar, and A. Mahfoudhi, “A multi-view deep convolutional neural network for reduction of false positive findings in breast cancer screening,” 2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), 2020.