JETI Admin
Abstract
Breast Cancer is the leading cause of death in women as the virus
called cancer itself has no premature cure. Early detection and diagnosis are
the best and most effective strategies to control the tumor’s progression.
Mammography is the currently recommended imaging method for early determination
and diagnosis of breast malignancy. Classifications of masses in mammograms are
still a big challenge and plays a crucial role in assisting radiologist with an
accurate diagnosis. We propose a convolution neural network CNN-based
classification technique which is one of the deep learning techniques. The
architectural models of CNN like Mobile Net and Inception V3 are used for the classification
of mammograms into normal and abnormal images. Due to the rapid growth and
development in the field of artificial intelligence, convolutional neural
networks CNN-based classification technique which is one of the deep learning
techniques can be built to help solve this challenge. Computer vision makes use
of convolutional neural networks to detect patterns in images and extract
certain features from them in order to predict images using the features it has
trained upon. In this study, images were collected from Kaggle, processed, and
then used to train a neural network before testing the accuracy on the test
set. Google colab was used in executing the model due
to the dataset size and intricacy. Three convolutional neural network models were trained to
classify the breast cancer mammogram images. These networks are MobileNetV2,
VGG16, and Inception-ResNet-v2. The models, on training with over 55000
mammogram images were able to accurately classify the test images into benign (Non-cancerous)
and malignancy (Cancerous). VGG16 gave the best result with an accuracy of
92.22% and a precision of 90%. MobileNetV2 and Inception-ResNet-v2 yielded accuracies
of 89.8% and 90.68% respectively with both having a per-image precision of 91%.
The high accuracy of the results derived from the research gives a promising
outlook in detecting and classifying breast cancer. The major advantage and
application of the model is to help medical institutions across the world in detecting
breast cancer even at the lowest of all odds.
References
[1] Miljković ,O. (2009). Image preprocessing tools. Kragujevac J. Math, 32, 97–107.
[2] Deng L., & Yu, D. (2014). Deep learning: methods and applications. Foundations and trends in signal processing, 7(3–4), 197-387.
[3] Doi, K. (2007). Computer-aided diagnosis in medical imaging: Historical review, current status and future potential. Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society, 31 (4-5), 198-211.
[4] Shen, L., Margolies, L.R., Rothstein, J., Fluder, E., McBride, R.B., & Sieh, W. (2017). Deep Learning to Improve Breast Cancer Detection on Screening Mammography. Scientific Reports, 9(1), 3-12.
[5] S. Mishra, A. Prakash, S. K. Roy, P. Sharan, and N. Mathur (2020). Breast Cancer Detection using Thermal Images and Deep Learning. 7th International Conference on Computing for Sustainable Global Development (INDIACom), New Delhi, India, pp. 211-216.
[6] Hamed, G., Marey, M.A., Amin, S.E., & Tolba, M.F. (2020). Deep Learning in Breast Cancer Detection and Classification. International Conferences on Artificial Intelligence and Computer Vision, (pp.322–333).
[7] Cruz-Roa, A., Gilmore, H., Basavanhally, A., Feldman, M.D., Ganesan, S., Shih, N., Tomaszewski, J.E., González, F.A., & Madabhushi, A. (2017). Accurate and reproducible invasive breast cancer detection in whole-slide images: A Deep Learning approach for quantifying tumor extent. Scientific Reports, 7.
[8] Wang, X., Ahmad, I., Javeed, D., Zaidi, S.A., Alotaibi, F.M., Ghoneim, M.E., Daradkeh, Y.I., Asghar, J., & Eldin, E.M. (2022). Intelligent Hybrid Deep Learning Model for Breast Cancer Detectio. Electronics.
[9] Hagos, Y.B., Gubern-Mérida, A., & Teuwen, J. (2018). Improving Breast Cancer Detection using Symmetry Information with Deep Learning. ArXiv, abs/1808.08273, 1-8.
[10] Sui, D., Liu, W., Chen, J., Zhao, C., Ma, X., Guo, M., & Tian, Z. (2021). A Pyramid Architecture-Based Deep Learning Framework for Breast Cancer Detection. BioMed Research International, 1-10.
[11] Hijab, A., Rushdi, M.A., Gomaa, M.M., & Eldeib, A.M. (2019). Breast Cancer Classification in Ultrasound Images using Transfer Learning. Fifth International Conference on Advances in Biomedical Engineering (ICABME), 1-4.
[12] Lotter, W., Diab, A.F., Haslam, B., Kim, J., Grisot, G., Wu, E., Wu, K., Onieva, J.O., Boxerman, J.L., Wang, M., Bandler, M., Vijayaraghavan, G.R., & Sorensen, A.G. (2021). Robust breast cancer detection in mammography and digital breast tomosynthesis using annotation-efficient deep learning approach. Nature medicine 27, 244-249.
[13] Mohapatra, S., Muduly, S., Mohanty, S., Rabindra, J.V., & Mohanty, S.N. (2022). Evaluation of Deep Learning Models for Detecting Breast Cancer using Mammograms. Sustainable Operations and Computers ,3, 296-302.
[14] https://www.kagle.com/datasets/skooch/ddsm-mammography.
[15] Towards Datascience. (2018). A simple Convolutional Neural Network. https://towardsdatascience.com/a-comprehensive-guide-to-convolutionalneural-networks-the-eli5-way-3bd2b1164a53
[16] Wikimedia Commons. (2005). [Simple Neural Network]. https://upload.wikimedia.org/ wikipedia/commons/6/60/ArtificialNeuronModel_english.png
[17] Super Datascience. (2016). An Overview of the Model’s Architecture Convolutional Neural Network. https://sds-platform-private.s3-us-east2.amazonaws.com/uploads/75_blog_image_1.png
[18] Ajitesh, K. (2022). Overfitting & Underfitting in Machine Learning. https://vitalflux.com/wp-content/uploads/2022/06/overfitting-vsunderfitting.png
Al-masni, M.A., Al-antari, M., Park, J.-M.P., Gi, G., Kim, T.-Y.K., Rivera, P.,Valarezo, E., Choi, M.-T., Han, S.-M., Kim, T.-S. (2018).Simultaneous detection andclassification of breast masses in digital mammograms via a deep learning YOLO-based CAD system. Comput. Methods Programs Biomed. 157, 85–94