Basic Search / Detailed Display

Author: 陳新叡
Hsin-Jui Chen
Thesis Title: 利用深度卷積神經網路在透過對比度增強的胸部X光二值化影像上進行肺部分割方法
Lung X-Ray Segmentation using Deep Convolutional Neural Networks on Contrast-enhanced Binarized Images
Advisor: 阮聖彰
Shanq-Jang Ruan
Committee: 陳筱青
Hsiao-Chin Chen
Yan-Tsung Peng
Degree: 碩士
Department: 電資學院 - 電子工程系
Department of Electronic and Computer Engineering
Thesis Publication Year: 2019
Graduation Academic Year: 107
Language: 中文
Pages: 48
Keywords (in Chinese): 肺部分割X光影像對比度增強卷積神經網路自適應二值化
Keywords (in other languages): Lung Segmentation, X-ray Contrast Enhancement, Convolutional Neural Networks, Adaptive Binarization
Reference times: Clicks: 414Downloads: 0
School Collection Retrieve National Library Collection Retrieve Error Report
  • 長久以來,檢查胸部X光(Chest X-ray, CXR)影像中的肺部輪廓已經廣泛的用於診斷肺部健康。在本論文中,我們提出了一種從CXR影像中分割出肺部輪廓的方法,其中分為三個階段。首先,我們針對CXR影像設計的對比度增強技術能有效的增強肺部與其周圍之間的對比度。接著,使用自適應二值化技術來預處理CXR影像來獲得前景資訊並減少CXR影像儲存空間。最後,使用各種完全卷積網路(Fully Convolutional Network, FCN)來驗證所提出方法的實用性。實驗結果顯示,所提出的方法與現有的模型相比,在CXR上分割肺部區域的精準度相當,但是推論時間與儲存空間分別減少了平均19.10%與94.6%。

    Automatically locating the lung regions effectively and efficiently in digital chest X-ray (CXR) images is crucial in computer-aided diagnosis. In this paper, we propose a method to segment lungs from CXR images, which comprises of three steps. First, a contrast enhancement method specifically designed for CXR images is adopted. Secondly, using adaptive binarization to preprocess CXR images to obtain foreground information and reduce storage space usage. Thirdly, the practicality of the proposed methodology is validated through various fully convolutional neural networks. The experimental results revealed that the proposed method can achieve comparable segmentation accuracy to those of state-of-the-art methods with inferring time and memory consumption for the model input cut by 19.10% and 94.6% on average.


    [1] S. Kligerman, L. Cai, C.S. White, “The effect of computer-aided detection on radiologist performance in the detection of lung cancers previously missed on a chest radiograph,” J. Thorac. Imaging 28 (4):244–252, 2013.
    [2] R.L.F. Cecil, L. Goldman, A.I. Schafer, “Goldman’s Cecil Medicinet,” Saunders Elsevier, Philadelphia, 2012.
    [3] B.J. Hillman, C.A. Catherine, M.R. Mabry, J.H. Sunshine, S.D. Kennedy, M. Noether, “Frequency and costs of diagnostic imaging in office practice a comparison of self-referring and radiologist-referring physicians,” N. Engl. J. Med, 323(23): 1604-1608, 1990.
    [4] J. Paul, M. Levine, R. Fraser, and C. Laszlo, “The measurement of total lung capacity based on a computer analysis of anterior and lateral radiographic chest images,” IEEE Trans. Biomed. Eng., vol. 21, no. 6, pp. 444–451, Nov. 1974.
    [5] F. Carrascal, J. Carreira, M. Souto, P. Tahoces, L. Gomez, and J. Vidal, “Automatic calculation of total lung capacity from automatically traced lung boundaries in postero-anterior and lateral digital chest radiographs,” Med. Phys., vol. 25, no. 7, pp. 1118–1131, 1998.
    [6] H. Becker, W. Nettleton, P. Meyers, J. Sweeney, and C. Nice, “Digital computer determination of a medical diagnostic index directly from chest X-ray images,” IEEE Trans. Biomed. Eng., vol. 11, pp. 67–72, 1964.
    [7] P.Meyers, C. Nice, H. Becker, W. Nettleton, J. Sweeney, and G.Meckstroth,“Automated computer analysis of radiographic images,” Radiology, vol. 83, pp. 1029–1034, 1964.
    [8] G. L. Snider, J. L. Klinerman, W. M. Thurlbeck, and Z. H. Bengali, “The definition of emphysema,” in Rep. Nat. Hearth, Lung, Blood Inst., Div. Lung Disease Workshop, vol. 132, pp. 182–185, 1985.
    [9] M.Miniati, G. Coppini, S. Monti, M. Bottai, M. Paterni, and E.M. Ferdeghini,“Computer-aided recognition of emphysema on digital chest radiography,” Eur. J. Radiol., 2010.
    [10] G. Coppini,M.Miniati, S.Monti, M. Paterni, R. Favilla, and E.M. Ferdeghini, “A computer-aided diagnosis approach for emphysema recognition in chest radiography,” Med. Eng. Phys., vol. 35, no. 1, pp. 63–73, 2013.
    [11] Kampa M, Castanas, “Human health effects of air pollution.” Environ Pollut., 151(2): 362–367, 2008.
    [12] Aluttis, C., Bishaw, T., and Frank, M. W, “The workforce for health in a globalized context - global shortages and international migration.” Global Health Action, 2014.
    [13] D.O. Staiger, D.I. Auerbach, P.I. Buerhaus, “Comparison of physician work- force estimates and supply projections,” J. Am. Med. Assoc., 302(15):1674-1680, 2009.
    [14] P.J. Mazzone, N. Obuchowski, M. Phillips, B. Risius, B. Bazerbashi, M. Meziane, “Lung cancer screening with computer aided detection chest radiography,” Public Libr. Sci., 2013.
    [15] E.B. Cole, Z. Zhang, H.S. Marques, R.E. Hendrick, M.J. Yaffe, E.D. Pisano, “Impact of computer-aided detection systems on radiologist accuracy with digital mammography,” Am. J. Roentgenol., 203(4):909-916, 2014.
    [16] S. Candemir, S. Jaeger, K. Palaniappan, J. Musco, R. Singh, Z. Xue, A. Karargyris, S. Antani, G. Thoma, and C. McDonald, “Lung segmentation in chest radiographs using anatomical atlases with non-rigid registration,” IEEE Trans. Med. Imag., 2014.
    [17] Garcia-Garcia, A., Orts-Escolano, S., Oprea, S., Villena-Martinez, V. & Garcia-Rodriguez, J., “A review on deep learning techniques applied to semantic segmentation,” CoRR, 2017.
    [18] Long, J., Shelhamer, E. & Darrell, T., “Fully convolutional networks for semantic segmentation,” CoRR, 2014.
    [19] Y.-T. Pai, Y.-F. Chang, S.-J. Ruan, “Adaptive thresholding algorithm: efficient computation technique based on intelligent block detection for degraded document images,” Pattern Recogn, 2010.
    [20] C.-S. Hung, S.-J. Ruan, “Efficient adaptive thresholding algorithm for in- homogeneous document background removal,” Multim. Tools Appl, 2014.
    [21] T. Ridler, S. Calvard, “Picture thresholding using an iterative selection method,” IEEE Trans. Syst. Man Cybernet., pp. 630-632, 1978.
    [22] J. Shiraishi, S. Katsuragawa, J. Ikezoe, T. Matsumoto, T. Kobayashi, K. Komatsu, M. Matsui, H. Fujita, Y. Kodera, and K. Doi, “Development of a digital image database for chest radiographs with and without a lung nodule: Receiver operating characteristic analysis of radiologists detection of pulmonary nodules,” Am. J. Roentgenol., vol. 174, pp. 71–74, 2000.
    [23] N. R. S. Parveen and M. M. Sathik, “Enhancement of bone fracture images by equalization methods,” in 2009 International Conference on Computer Technology and Development, vol. 2, pp. 391–394, 2009.
    [24] A. Mustapha, A. Hussain, and S. A. Samad, “A new approach for noise reduction in spine radiograph images using a non-linear contrast adjustment scheme based adaptive factor,” Sci. Res. Essays, vol. 6, no. 20, pp. 4246–4258, 2011,
    [25] Siti Arpah Ahmad, Mohd Nasir Taib, Noor Elaiza Abdul Khalid, and Haslina Taib, “An Analysis of Image Enhancement Techniques for Dental X-ray Image Interpretation,” International Journal of Machine Learning and Computing, vol. 2, no. 3, Jun. 2012.
    [26] W. Niblack, “An Introduction to Digital Image Processing,” International Conference on Document Analysis and Recognition, 2003.
    [27] J. Sauvola and M. Pietikäinen, “Adaptive Document Image Binarization,” Pattern Recognition, vol. 33, pp. 225-236, 2000.
    [28] N. Ostu, “A Threshold Selection Method From Gray-Level Histogram,” IEEE Trans on Systems, Man and Cybernetics, vol. 9, pp. 62-66, 1979.
    [29] B. van Ginneken, B.M.T.H. Romeny, M.A. Viergever, “Computer-aided diagno- sis in chest radiography: a survey.” IEEE Trans. Med. Imaging, 20(12):1228–1241, 2011.
    [30] L. Li, Y. Zheng, M. Kallergi, R.A. Clark, “Improved method for automatic identification of lung regions on chest radiographs,” Acad. Radiol., 8(7):629–638, 2001.
    [31] J. Toriwaki, J. Hasegawa, T. Fukumura, Y. Takagi, “Computer analysis of chest photofluorograms and its applications to automated screening,” Automedica 3, 1980.
    [32] Z. Yue, A. Goshtasby, L.V. Ackerman, “Automatic detection of rib borders in chest radiographs, IEEE Trans.” Med. Imaging, 14(3):525–536, 1995.
    [33] P. Annangi, S. Thiruvenkadam, A. Raja, H. Xu, X. Sun, and L. Mao, “A region based active contour method for X-ray lung segmentation using prior shape and low level features,” Proc. Int. Symp. Biomed. Imag.: From Nano to Macro, pp. 892–895, 2010.
    [34] B. van Ginneken, M.B. Stegmann, M. Loog, “Segmentation of anatomical structures in chest radiographs using supervised method: a comparative study on a public database,” Med. Image Anal., 10(1):19–40, 2006.
    [35] M. Loog, B. Ginneken, “Segmentation of the posterior ribs in chest radiographs using iterated contextual pixel classification,” IEEE Trans. Med. Imag., vol. 25, no. 5, pp. 602–611, May 2006.
    [36] M. Loog, B. Ginneken, “Supervised segmentation by iterated contextual pixel classification,” in Proc. Int. Conf. Pattern Recognit., pp. 925–928, 2002.
    [37] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in CVPR, 2016.
    [38] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu and A.C. Berg, “SSD: Single Shot MultiBox Detector,” in Computer Vision and Pattern Recognition, Cornell University Library, Dec. 2015.
    [39] O. Ronneberger, P. Fischer, T. Brox, “U- Net: Convolutional Networks for Biomedical Image Segmentation,” Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015, pp. 234-241, 2015.
    [40] K. Suzuki, H. Abe, H. McMahon, K. Doi, “Image-processing technique for suppressing ribs in chest radiographs by means of massive training artificial neural network (MTANN),” IEEE Trans. Med. Imaging, 25(4):406–416, 2006.
    [41] T.F. Cootes, C.J. Taylor, D.H. Cooper, J. Graham, “Active shape models - their training and application,” Comput. Vis. Image Underst., 61(1):38–59, 1995.
    [42] T. Yu, J. Luo, N. Ahuja, “Shape regularized active contour using iterative global search and local optimization,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 655–662, 2005.
    [43] B. Ginneken, A. F. Frangi, J. J. Staal, B. M. Romeny, and M. A. Viergever, “Active shape model segmentation with optimal features,” IEEE Trans. Med. Imag., vol. 21, no. 8, pp. 924–933, Aug. 2002.
    [44] B. Ginneken, S. Katsuragawa, B. M. Romeny, K. Doi, and M. A. Viergever, “Automatic detection of abnormalities in chest radiographs using local texture analysis,” IEEE Trans. Med. Imag., vol. 21, no. 2, pp. 139–149, Feb. 2002.
    [45] D. Seghers, D. Loeckx, F. Maes, D. Vandermeulen, P. Suetens, “Minimal shape and intensity cost path segmentation,” IEEE Trans. Med. Imaging, 26(8):1115–1129, 2007.
    [46] Y. Shi, F. Qi, Z. Xue, L. Chen, K. Ito, “Segmentation lung fields in serial chest radiographs using both population-based and patient-specific shape statistics,” IEEE Trans. Med. Imaging, 27(4):481–494, 2008.
    [47] A. Dawoud, “Lung segmentation in chest radiographs by fusing shape information in iterative thresholding,” IET Comput., 5(3):185–190, 2008.
    [48] G. Coppini, M. Miniati, S. Monti, M. Paterni, R. Favilla, E.M. Ferdeghini, “A computer-aided diagnosis approach for emphysema recognition in chest radiography,” Med. Eng. Phys., 35(1):63–73, 2013.
    [49] V. Badrinarayanan, A. Kendall, R. Cipolla, “Segnet: A deep convolutional encoder-decoder architecture for image segmentation,” Computing Research Repository, Oct. 2015.
    [50] A. Rosenfeld, “Digital Picture Processing,” New York: Academic, 1976.
    [51] L. S. Davis, A. Rosenfeld, and J. S. Weszka, “Region extraction by averaging and
    [52] thresholding,” IEEE Trans. Syst., Man, Cybern., vol. SMC-5, pp. 383-388, May. 1975.
    [53] G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, R. R. Salakhutdinov, “Improving neural networks by preventing coadaptation of feature detectors.” Computing Research Repository, 2012.
    [54] S. Jaeger, S. Candemir, S. Antani, Y.X.J. Wang, P.X. Lu, G. Thoma, “Two public chest X-ray datasets for computer-aided screening of pulmonary diseases,” Quant. Imag. Med. Surg., 4(6):475-477, 2014.

    無法下載圖示 Full text public date 2024/08/19 (Intranet public)
    Full text public date This full text is not authorized to be published. (Internet public)
    Full text public date This full text is not authorized to be published. (National library)