Please use this identifier to cite or link to this item:
標題: 利用CNN進行白血球細胞之偵測與分類
Detection and classification of white blood cells using convolutional neural networks (CNN)
作者: 謝東陞
Tung-Sheng Hsieh
關鍵字: 捲積神經網路;白血球;影像辨識;Faster R-CNN;Convolutional neural networks (CNN);white blood cell (WBC);image recognition;Faster R-CNN
引用: [1] C. Cortes and V. Vapnik, 'Support-Vector Networks', Kluwer Academic Publishers, Boston, Manufactured in The Netherlands, 1995. [2] N. S. Altman, 'An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression', The American Statistician, vol. 46, no. 3, pp. 175-185, 1992. [3] C. M. Bishop, 'Neural Networks for Pattern Recognition', Oxford University Press, Inc. New York, NY, USA, 1995. [4] M. T. Hagan, H. B. Demuth, and M. H. Beale, 'Neural Network Design', PWS Publishing Company, 1996. [5] Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Habbard, and L. D. Jackel, 'Handwritten Digit Recognition with a Back-Propagation Network', Advances in neural information processing systems 2, pp. 396-404, 1990. [6] Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel, 'Backpropagation Applied to Handwritten Zip Code Recognition', Neural Computation, vol. 1, no. 4, pp. 541-551, 1989. [7] F. Schroff., D. Kalenichenko, and J. Philbin, 'FaceNet: A unified embedding for face recognition and clustering', IEEE Conference on Computer Vision and Pattern Recognition, pp. 815-823, 2015. [8] Y. Taigman, M. Yang, M. A. Ranzato, and L. Wolf, 'DeepFace: Closing the Gap to Human-Level Performance in Face Verification', IEEE Conference on Computer Vision and Pattern Recognition, pp. 1701-1708, 2014. [9] A. Krizhevsky, I. Sutskever, and G. E. Hinton, 'ImageNet classification with deep convolutional neural networks', 25th International Conference on Neural Information Processing Systems, vol. 1, pp. 1097-1105, 2012. [10] S. Ren, K. He, R. Girshick, and J. Sun, 'Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks', 28th International Conference on Neural Information Processing Systems, vol. 1, pp. 91-99, 2015. [11] R. Girshick, 'Fast R-CNN', IEEE International Conference on Computer Vision, pp. 1440-1448, 2015. [12] R. Girshick, J. Donahue, T. Darrell, and J. Malik, 'Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation', IEEE Conference on Computer Vision and Pattern Recognition, pp. 580-587, 2014. [13] M. Leach, M. Drummond, and A. Doig, 'Practical Flow Cytometry in Haematology Diagnosis', Wiley-Blackwell, 2013. [14] B. J. Bain, 'Blood Cells: A Practical Guide, 5th Edition', Wiley-Blackwell, 2015. [15] R. Kohavi, 'A study of cross-validation and bootstrap for accuracy estimation and model selection', 14th international joint conference on Artificial intelligence, vol. 2, pp. 1137-1143, 1995. [16] S. Arlot and A. Celisse, 'A survey of cross-validation procedures for model selection', Statistics Surveys, vol. 4, pp. 40-79, 2010. [17] T. Ahonen, A. Hadid, and M. Pietikäinen, 'Face Recognition with Local Binary Patterns', European Conference on Computer Vision, pp. 469-481, 2004. [18] N. Dalal and B. Triggs, 'Histograms of Oriented Gradients for Human Detection', IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 886-893, 2005. [19] R. C. Gonzalez and R. E. Woods, 'Digital Image Processing', Prentice Hall, 2002. [20] R. C. Gonzalez, R. E. Woods, and S. L. Eddins, 'Digital Image Processing Using MATLAB', Pearson Prentice Hall, 2013.
近年來,深度學習在機器學習中變得熱門,其中包含了捲積神經網路。捲積神經網路在影像辨識上的效果良好,本文以此方法來偵測與分類白血球細胞。我們使用了自己從台中慈濟醫院取得的資料庫來做實驗。為了能夠找出最有效率的網路,我們嘗試了各種不同的神經網路架構。除此之外,我們使用了Faster R-CNN來幫助我們偵測白血球細胞在血片影像上的位置。另外,我們也使用了Holdout驗證方法來確保我們實驗結果的可信度,而我們的辨識率能達到超過99%。

Blood film examination has many kinds of clinical application, including blood cell classification, blood cell count, and bone marrow examination. From the blood film, we can know the patient's blood condition. In addition, it can help doctors to diagnose the patient's condition and understand the effect of treatment. However, these jobs take a lot of time and labor. Therefore, we hope that the research in this thesis can help them for the white blood cell (WBC) examination. In recent years, deep learning has become popular in machine learning, including the convolutional neural networks (CNN). Convolutional neural networks have good performances on image recognition. In this thesis, we use this method to detect and classify white blood cells. The experiments were conducted by using the dataset that was taken from Taichung Tzu Chi Hospital. In order to find the most effective neural network, we have tried many different neural networks. In addition, we use the Faster R-CNN to help us to detect the white blood cells on the blood film image. Moreover, we also use the Holdout validation method to ensure the credibility of the experimental results, and the probability of the recognition can reach more than 99%.
Rights: 同意授權瀏覽/列印電子全文服務,2018-08-21起公開。
Appears in Collections:通訊工程研究所

Files in This Item:
File SizeFormat Existing users please Login
nchu-107-7105093016-1.pdf2.37 MBAdobe PDFThis file is only available in the university internal network    Request a copy
Show full item record

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.