Deep Convolution Neural Networks for Medical Image Analysis

  • Authors

    • Myung Jae Lim
    • Da Eun Kim
    • Dong Kun Chung
    • Hoon Lim
    • Young Man Kwon
    2018-08-29
    https://doi.org/10.14419/ijet.v7i3.33.18588
  • Deep Learning, Convolutional Neural Network, Medical Image, Breast Cancer, GoogLeNet, VGGNet
  • Breast cancer is a highly contagious disease that has killed many people all over the world. It can be fully recovered from early detection. To enable the early detection of the breast cancer, it is very important to classify accurately whether it is breast cancer or not. Recently, the deep learning approach method on the medical images such as these histopathologic images of the breast cancer is showing higher level of accuracy and efficiency compared to the conventional methods. In this paper, the breast cancer histopathological image that is difficult to be distinguished was analyzed visually. And among the deep learning algorithms, the CNN(Convolutional Neural Network) specialized for the image was used to perform comparative analysis on whether it is breast cancer or not. Among the CNN algorithms, VGG16 and InceptionV3 were used, and transfer learning was used for the effective application of these algorithms.

    The data used in this paper is breast cancer histopathological image dataset classifying the benign and malignant of BreakHis. In the 2-class classification task, InceptionV3 achieved 98% accuracy. It is expected that this deep learning approach method will support the development of disease diagnosis through medical images.

     

     

  • References

    1. [1] “Latest world cancer statisticsâ€, World Health Organization, 2013

      [2] Jeonghun Yoon, YoungJu Jeong, Giwon Lee, Seongju Ryu, Noa Seo, Jihun Yoon, Jihun Noh, Jugyeon Lim, Donggyun Kim, “A Study on the Estimation of pathology Result from Gastroscopy Image Using Deep Learningâ€, Korean Department of Internal Medicine Association, 2017

      [3] Hansang Lee, Minseok Park, Junmo Kim, “Deep Learning in Medical Imageâ€, Journal of Korean Medical Imaging, 2014

      [4] http://cs231n.github.io/transfer-learning/

      [5] Janowczyk A1, Madabhushi A1., "Breast Cancer Histopathological Image Classiï¬cation: A Deep Learning Approach", doi: https://doi.org/10.1101/242818, 2018

      [6] Jeong Won Min, Dong Joong Kang. "Deep Meta Learning Based Classification Problem Learning Method for Skeletal Maturity Indication." Journal of Korea Multimedia Society, 21.2, 2018

      [7] G. E. Dahl, T. N. Sainath, and G. E. Hinton, “Improving deep neural networks for LVCSR using rectified linear units and dropout,†IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2013

      [8] Karen Simonyan, Andrew Zisserman, “VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITIONâ€, arXiv:1409.1556v6 [cs.CV], 2015

      [9] http://machinethink.net/blog/convolutional-neural-networks-on-the-iphone-with-vggnet/

      [10] Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jon Shlens, Zbigniew Wojna; “Rethinking the Inception Architecture for Computer Visionâ€, The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818-2826, 2016

      [11] https://adeshpande3.github.io/The-9-Deep-Learning-Papers-You-Need-To-Know-About. Html

      [12] Jeong Won Min, Dong Joong Kang. "Deep Meta Learning Based Classification Problem Learning Method for Skeletal Maturity Indication." Journal of Korea Multimedia Society, 21.2, 2018

      [13] Dongjin Lee, Jaehong Kim, Han Seungjun, Choi Jeongdan, Cheong Hee Park. "Traffic light recognition using the LISA traffic light dataset.", Korean Industrial Engineering Association, 2016

      [14] S. Pan and Q. Yang. “A survey on transfer learning. Knowledge and Data Engineeringâ€, IEEE Transactions on, 22(10):1345–1359, 2010.

      [15] https://keras.io/applications

      [16] https://web.inf.ufpr.br/vri/databases/breast-cancer-histopathological-database-breakhis/

      [17] Se-Ho Lim, Yong-Goo Shin, Cheol-Hwan Yoo, Han-Kyu Lee, Sung-Jea Ko. "Data Augmentation method using WGAN." Korean Electronic Engineering Society, 2017

      [18] In-kyu Choi, Hyok Song, Sangyong Lee, Jisang Yoo. "Facial Expression Classification Using Deep Convolutional Neural Network." JOURNAL OF BROADCAST ENGINEERING, 22.2, 2017

      [19] Pilseong Kang, Seongjun Cho, “EUS SVMs: Ensemble of Under-Sampled SVMs for Data Imbalance Problems,“ Korean Industrial Engineering Association, 2006

      [20] Antonio Guilli, “TensorFlow 1.x Deep Learning Cookbookâ€, 2017

      [21] Jungbeom Lee, Sungroh Yoon. "Video Sequence Prediction using Optical Flow.", Korean Information Science Association, 2017

      [22] M. Sokolova and G. Lapalme. A systematic analysis of performance measures for classiï¬cation tasks. Inf. Process. Manage., 45(4):427–437, 2009

      [23] http://shuuki4.github.io/deep%20learning/2016/05/20/Gradient-Descent-Algorithm-Overview.html

      [24] Jaewan Yang, Youngdoo Lee, Insoo Koo, “Sensor Fault Detection Scheme based on Deep Learning and Support Vector Machineâ€, The Journal of The Institute of Internet, Broadcasting and Communication, 2018

      [25] Seokcheon Park, “Design and Implementation of Personal Information Identification and Masking System Based on Image Recognitionâ€, The Journal of The Institute of Internet, Broadcasting and Communication, 2017

      [26] Youngdo Joo, “Drone Image Classification based on Convolutional Neural Networksâ€, The Journal of The Institute of Internet, Broadcasting and Communication, 2017

      [27] Minsoo Kang, Yonggyu Jung, Duhwan Jang, “A study on the Search of Optimal Aquaculture fram condition based on Machine Learningâ€, The Journal of The Institute of Internet, Broadcasting and Communication, 2017

      [28] Dohyeon Choi, Jungoh Park, “A study on Security Authentication Vector Generation of Virtualized Internal Environment using Machine Learning Algorithmâ€, The Journal of The Institute of Internet, Broadcasting and Communication, 2016

      [29] Sebastian Ruder, “An overview of gradient descent optimization algorithmsâ€, http://arxiv.org/abs/1609.04747, 2016

      [30] Diederik P. Kingma, Jimmy Lei Ba, “ADAM: A METHOD FOR STOCHASTIC OPTIMIZATIONâ€, a conference paper at the 3rd International Conference for Learning Representations, San Diego, 2015

      [31] https://flonelin.wordpress.com/2017/12/22/global-average-pooling/

  • Downloads

  • How to Cite

    Jae Lim, M., Eun Kim, D., Kun Chung, D., Lim, H., & Man Kwon, Y. (2018). Deep Convolution Neural Networks for Medical Image Analysis. International Journal of Engineering & Technology, 7(3.33), 115-119. https://doi.org/10.14419/ijet.v7i3.33.18588