Breast Cancer Detection and Localization Using MobileNet Based Transfer Learning for Mammograms
- 48 Downloads
Breast cancer is the major cause of death among women. The best and most efficient approach for controlling cancer progression is early detection and diagnosis. As opposed to biopsy, mammography helps in early detection of cancer and hence saves lives. Mass classification in mammograms remains a major challenge and plays a vital role in helping radiologists in accurate diagnosis. In this work, we propose a MobileNet based architecture for early breast cancer detection and further classify mass into malignant and benign. It requires less memory space and provides faster computations with 86.8% and 74.5% accurate results for DDSM and CBIS-DDSM, respectively. We have achieved better results than other deep CNN models such as AlexNet, VGG16, GoogleNet, and ResNet.
KeywordsBreast cancer Mammography Deep learning MobileNet Localization
This work has been supported by Higher Education Commission under Grant # 2(1064) and is carried out at Medical Imaging and Diagnostics (MID) Lab at COMSATS University Islamabad, under the umbrella of National Center of Artificial Intelligence (NCAI), Pakistan.
- 5.Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)
- 6.Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
- 7.He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar
- 8.Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)Google Scholar
- 9.Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.-C.: MobileNetV2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)Google Scholar
- 10.Jiang, F., Liu, H., Yu, S., Xie, Y.: Breast mass lesion classification in mammograms by transfer learning. In: Proceedings of the 5th International Conference on Bioinformatics and Computational Biology, pp. 59–62 (2017)Google Scholar
- 12.Rampun, A., Scotney, B.W., Morrow, P.J., Wang, H.: Breast mass classification in mammograms using ensemble convolutional neural networks. In: 2018 IEEE 20th International Conference on e-Health Networking, Applications and Services (Healthcom), pp. 1–6 (2018)Google Scholar
- 13.Hamidinekoo, A., Suhail, Z., Denton, E., Zwiggelaar, R.: Comparing the performance of various deep networks for binary classification of breast tumours. In: 14th International Workshop on Breast Imaging (IWBI 2018), p. 1071807 (2018)Google Scholar
- 16.Carneiro, G., Nascimento, J., Bradley, A.P.: Deep learning models for classifying mammogram exams containing unregistered multi-view images and segmentation maps of lesions. In: Zhou, S.K., Greenspan, H., Shen, D. (eds.) Deep Learning for Medical Image Analysis, pp. 321–339. Elsevier, Amsterdam (2017)CrossRefGoogle Scholar
- 17.Carneiro, G., Nascimento, J., Bradley, A.P.: Unregistered multiview mammogram analysis with pre-trained deep learning models. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 652–660 (2015)Google Scholar
- 18.Heath, M., Bowyer, K., Kopans, D., Moore, R., Kegelmeyer, W.P.: The digital database for screening mammography. In: Proceedings of the 5th International Workshop on Digital Mammography, pp. 212–218 (2000)Google Scholar