肺癌為全球癌症死亡的主因，因此早期偵測肺結節相當重要，若能夠盡早診斷、觀察及治療，即可提高個體的生存機會。已有許多學者針對肺結節進行電腦輔偵測系統之開發與研究，但礙於肺結節包含低亮度之毛玻璃狀陰影及高亮度之固體結節，此兩種情況灰階值相差甚大，導致影像處理相當困難，以致於目前大部分之快速輔助系統僅能用於檢測單一種固體結節。因此本研究提出一套影像處理方法用於胸腔電腦斷層毛玻璃狀陰影、部分固體及固體結節之快速檢測，過程分別是影像前處理、肺部分割、結節強化、候選點偵測及結節篩選。肺部分割提出以邊緣搜尋法取代補洞法，解決疊代計算時間較久的問題。為了能夠以同一套方法提取灰階值分佈廣泛之結節，本研究於結節強化的步驟採用影像疊和法，快速增強結節灰階值。結節篩選部分，分別使用了兩次支持向量機來快速獲取結果，第一次採用四個特徵初步分類，第二次則採用十一個特徵進階分類。
本研究採用177個肺結節進行實驗及評估，提出的系統能夠偵測毛玻璃狀陰影、部分固體及固體結節，檢測速度單張影像僅需0.1秒，系統總靈敏度為90.96%，每張影像約誤判0.1個，其中特別優於檢測小於10毫米之小結節與毛玻璃狀陰影，靈敏度分別為92.31%與96.83%，藉此提升不易觀察之兩種肺結節檢出率。本研究之快速偵測系統同時保有高靈敏度低誤判之優點，有助於輔助臨床醫師診斷。

Lung cancer is the leading cause of death from cancer in the world. Therefore, early detection of pulmonary nodules is very important. If it can be diagnose, observe and treat as soon as possible, which can improve the survival of individuals. Many researchers have conducted research and development of computer aided detection system. However, due to pulmonary nodule contains low brightness of ground glass opacity and high brightness of solid nodule. The two cases of grayscale values vary greatly, resulting in image processing is quite difficult. So most of the current rapid aided system can only be used to detect solid nodules. Therefore, this study proposes an image processing method for detecting ground glass opacity, part solid and solid nodules in chest computed tomography. The process comprises image preprocessing, lung segmentation, nodule enhancement, candidate detection and reducing false positives. For lung segmentation, the edge searching method replaces hole-filling method which needs iterations leading to long computing time. In order to use the same method to extract the nodules with extensively distributed gray levels, the image accumulation is used in the step of nodule enhancement to enhance the gray level of nodule rapidly. For reducing false positives, the support vector machine is used twice. For the first time, the candidate nodules are obtained by using 4 two-dimensional features, and the classification result is obtained by using 11 three-dimensional features for the second time.
This study uses 177 lung nodules for experiment and evaluation. The proposed system can detect ground glass opacity, part solid and solid nodule. It only takes 0.1 sec to detect one single image. The total sensitivity of system is 90.96% with 0.1 false positives per image. It is particularly superior to the detection of small nodules less than 10 mm which the sensitivity is 92.31% and ground glass opacity which the sensitivity is 96.83%. It can enhance the detection rate of these two kinds of lung nodules which are not easy to observe. This rapid detection system has high sensitivity and low false positives, contributing to helping the clinicians' diagnosing.

[1]Wang, H., Naghavi, M., Allen, C., et al, “GBD 2015 mortality and causes of death collaborators. global, regional, and national life expectancy, all-cause mortality, and cause-specific mortality for 249 causes of death, 1980-2015: a systematic analysis for the global burden of disease study 2015,” Lancet, Vol. 388, No. 10053, pp. 1459-1544, 2016.
[2]Heron, M., Anderson, R. N., “Changes in the leading cause of death: recent patterns in heart disease and cancer mortality,” NCHS Data Brief, No. 254, pp. 1-8, 2016.
[3]Siegel, R. L., Miller, K. D., Jemal, A., “Cancer statistics, 2017,” CA: A Cancer Journal for Clinicians, Vol. 67, No. 1, pp. 7-30, 2017.
[4]衛生福利部，105年國人死因統計結果，2017。
[5]Brown, M. S., Goldin, J. G., Suh, R. D., McNitt-Gray, M. F., Sayre, J. W., Aberle, D. R., “Lung micronodules: automated method for detection at thin-section CT-initial experience,” Radiology, Vol. 226, No. 1, pp. 256-262, 2003.
[6]Das, M., Mühlenbruch, G., Mahnken, A. H., Flohr, T. G., Gündel, L., Stanzel, S., Kraus, T., Günther, R. W., Wildberger, J. E., “Small pulmonary nodules: effect of two computer-aided detection systems on radiologist performance,” Radiology, Vol. 241, No. 2, pp. 564-571, 2006.
[7]Godoy, M. C., Kim, T. J., White, C. S., Bogoni, L., de Groot, P., Florin, C., Obuchowski, N., Babb, J. S., Salganicoff, M., Naidich, D. P., Anand, V., Park, S., Vlahos, I., Ko, J. P., “Benefit of computer-aided detection analysis for the detection of subsolid and solid lung nodules on thin- and thick-section CT,” American Journal of Roentgenology, Vol. 200, No. 1, pp. 74-83, 2013.
[8]Marten, K., Engelke, C., Seyfarth, T., Grillhosl, A., Obenauer, S., Rummeny, E. J., “Computer-aided detection of pulmonary nodules: influence of nodule characteristics on detection performance,” Clinical Radiology, Vol. 60, No. 2, pp. 196-206, 2005.
[9]Austin, J. H., Müller, N. L., Friedman, P. J., Hansell, D. M., Naidich, D. P., Remy-Jardin, M., Webb, W. R., Zerhouni, E. A., “Glossary of terms for CT of the lung: recommendations of the Nomenclature Committee of the Fleischner Society,” Radiology, Vol. 200, No. 2, pp. 327-331, 1996.
[10]Jose, D., Chithara, A. N., Kumar, P. N., Kareemulla, H., “Automatic detection of lung cancer nodules in computerized tomography images,” National Academy Science Letters, Vol. 40, No. 3, pp. 161-166, 2017.
[11]Magalhães Barros Netto, S., Corrêa Silva, A., Acatauassú Nunes, R., Gattass, M., “Automatic segmentation of lung nodules with growing neural gas and support vector machine,” Computer Methods and Programs in Biomedicine, Vol. 42, No. 11, pp. 1110-1121, 2012.
[12]Sousa, J. R., Silva, A. C., de Paiva, A. C., Nunes, R. A., “Methodology for automatic detection of lung nodules in computerized tomography images,” Computer Methods and Programs in Biomedicine, Vol. 98, No. 1, pp. 1-14, 2010.
[13]Ye, X., Lin, X., Dehmeshki, J., Slabaugh, G., Beddoe, G., “Shape-based computer-aided detection of lung nodules in thoracic CT images,” IEEE Transactions on Biomedical Engineering, Vol. 56, No. 7, 2009.
[14]Shao, H., Cao, L., Liu, Y., “A detection approach for solitary pulmonary nodules based on CT images,” 2012 2nd International Conference on Computer Science and Network Technology, pp. 1253-1257, 2012.
[15]Kuruvilla, J., Gunavathi, K., “Lung cancer classification using neural networksfor CT images,” Computer Methods and Programs in Biomedicine, Vol. 113, No. 1, pp. 202-209, 2014.
[16]Song, J., Yang, C., Fan, L., Wang, K., Yang, F., Liu, S., Tian, J., “Lung lesion extraction using a toboggan based growing automatic segmentation approach,” IEEE Transactions on Medical Imaging, Vol. 35, No. 1, pp. 337-353, 2016.
[17]Choi, W. J., Choi, T. S., “Automated pulmonary nodule detection system in computed tomography images: a hierarchical block classification approach,” Entropy, Vol. 15, No. 2, pp. 507-523, 2013.
[18]Manikandan, T., Bharathi, N., “Lung cancer detection using fuzzy auto-seed cluster means morphological segmentation and SVM classifier,” Journal of Medical Systems, Vol. 40, No. 7, 2016.
[19]Cao, L., Wang, K., Xing, Q., Lin, B., Zhang, Yu., “Auto detection of lung ground-glass opacity nodules based on high-pass filter and gaussian mixture model,” Journal of Medical Imaging and Health Informatics, Vol. 6, pp. 320-327, 2016.
[20]Setio, A. A. A, Jacobs, C., Gelderblom, J., van Ginneken, B, “Automatic detection of large pulmonary solid nodules in thoracic CT images”, Medical Physics, Vol. 42, No. 10, pp. 5642-5653, 2015.
[21]Zhang, W., Wang, X., Li, X., Chen, J., “3D skeletonization feature based computer-aided detection system for pulmonary nodules in CT datasets,” Computers in Biology and Medicine, Vol. 92, pp. 64-72, 2018.
[22]Setio, A. A., Ciompi, F., Litjens, G., Gerke, P., Jacobs, C., van Riel, S. J., Wille, M. M., Naqibullah, M., Sanchez, C. I., van Ginneken, B., “Pulmonary nodule detection in CT images: false positive reduction using multi-view convolutional networks,” IEEE Transactions on Medical Imaging, Vol. 35, No. 5, pp. 1160-1169, 2016.
[23]Jacobs, C., van Rikxoort, E. M., Twellmann, T., Scholten, E. T., de Jong, P. A., Kuhnigk, J. M., Oudkerk, M., de Koning, H. J., Prokop, M., Schaefer-Prokop, C., van Ginneken , B., “Automatic detection of subsolid pulmonary nodules in thoracic computed tomography images,” Medical Image Analysis, Vol. 18, No. 2, pp. 374-384, 2014.
[24]Choi, W. J., Choi, T. S., “Automated pulmonary nodule detection based on three-dimensional shape-based feature descriptor,” Computer Methods and Programs in Biomedicine, Vol. 113, No. 1, pp. 37-54, 2014.
[25]Manikandan, T., Bharathi, N., “Lung nodule detection using fuzzy clustering and support vector machines,” International Journal of Engineering and Technology, Vol. 5, No. 1, 2013.
[26]Madero Orozco, H., Vergara Villegas, O. O., Cruz Sánchez, V. G., Ochoa Domínguez Hde, J., Nandayapa Alfaro Mde, J., “Automated system for lung nodules classification based on wavelet feature descriptor and support vector machine,” Biomedical Engineering Online, Vol. 14, No. 9, 2015.
[27]Filho, A. O. C., Silva, A. C., de Paiva, A. C., Nunes, R. A., Gattass, M., “3D shape analysis to reduce false positives for lung nodule detection systems,” Medical and Biological Engineering and Computing, Vol. 55, No. 8, pp. 1199-1213, 2017.
[28]Shaukat, F., Raja, G., Gooya, A., Frangi, A. F., “Fully automatic detection of lung nodules in CT images using a hybrid feature set,” Medical Physics, Vol. 44, No. 7, pp. 3615-3629, 2017.
[29]Otsu, N., “A threshold selection method from gray-level histograms,” IEEE Transactions on Systems, Man, and Cybernetics, Vol. 9, No. 1, pp. 62-66, 1979.
[30]Forgy, C., “Rete: a fast algorithm for the many pattern/many object pattern match problem,” Artificial Intelligence, Vol. 19, No. 1, pp. 17-37, 1982.
[31]Bezdek, J. C., Ehrlich, R., Full, W., “FCM: the fuzzy c-means clustering algorithm,” Computers and Geosciences, Vol. 10, No. 2, pp. 191-203, 1984.
[32]Gonzalez, R. C., Woods, R. E., “Digital Image Processing, 2nd Edition”, Prentice Hall, New Jersey, 2002.
[33]Li, Q., Sone, S., Doi, K., “Selective enhancement filters for nodules, vessels, and airway walls in two- and three-dimensional CT scans,” Medical physics, Vol. 30, No. 8, pp. 2040-2051, 2003.
[34]Teramoto, A., Fujita, H., “Fast lung nodule detection in chest CT images using cylindrical nodule-enhancement filter,” International Journal of Computer Assisted Radiology and Surgery, Vol. 8, No. 2, pp. 193-205, 2013.
[35]Cristianini, N., Shawe-Taylor, J., “An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods,” Cambridge University, Cambridge, 2000.
[36]Burges, C. J. C., “Tutorial on support vector machines for pattern recognition,” Data Mining and Knowledge Discovery, Vol. 2, No. 2, pp. 121-167, 1998.
[37]AlSaeed, D., Bouridane, A., El-Zaart, A., “A novel fast otsu digital image segmentation method,” International Arab Journal of Information Technology, Vol. 13, No. 4, pp. 427-434, 2016.
[38]Javaid, M., Javid, M., Rehman, M. Z., Shah, S. I., “A novel approach to CAD system for the detection of lung nodules in CT images,” Computer Methods and Programs in Biomedicine, Vol. 135, pp. 125-139, 2016.
[39]Han, H., Li, L., Han, F., Song, B., Moore, W., Liang, Z., “Fast and adaptive detection of pulmonary nodules in thoracic CT images using a hierarchical vector quantization scheme,” IEEE Journal of Biomedical and Health Informatics, Vol. 19, No. 2, pp. 684-659, 2015.
[40]Santos, A. M., de Carvalho Filho, A. O., Silva, A. C., dePaiva, A. C., Nunes, R. A., Gattass, M., “Automatic detection of small lung nodules in 3D CT data using Gaussian mixture models, Tsallis entropy and SVM,” Engineering Applications of Artificial Intelligence, Vol. 36, pp. 27-39, 2014.
[41]Henschke, C. I., Yankelevitz, D. F., Mirtcheva, R., McGuinness, G., McCauley, D., Miettinen, O. S., ELCAP Group, “CT screening for lung cancer: frequency and significance of part-solid and nonsolid nodules,” American Journal of Roentgenology, Vol. 178, No. 5, pp. 1053-1057, 2002.
[42]Standring, S., “Gray's Anatomy: The Anatomical Basis of Clinical Practice, 41e,” Elsevier, 2015.
[43]Ferretti, G., Félix, L., Serra-Tosio, G., Brambilla, C., Brichon, P. Y., Coulomb, M., Lantuejoul, S., “Nonsolid and part-solid pulmonary nodules,” Revue des Maladies Respiratoires, Vol. 26, pp. 48-59, 2009.
[44]Khouri, N. F., Meziane, M. A., Zerhouni, E. A., Fishman, E. K., Siegelman, S. S., “The solitary pulmonary nodule: assessment, diagnosis, and management,” Chest, Vol. 91, No. 1, pp. 128-133, 1987.
[45]Godoy, M. C. B., Naidich, D. P., “Overview and strategic management of subsolid pulmonary nodules,” Journal of Thoracic Imaging., Vol. 27, No. 4, pp. 240-248, 2012.
[46]Naidich, D. P., Bankier, A. A., MacMahon, H., et al., “Recommendations for the management of subsolid pulmonary nodules detected at CT: a statement from the Fleischner society,” Radiology, Vol. 266, No. 1, pp. 304-317, 2013.
[47]Hansell, D. M., Bankier, A. A., MacMahon, H., McLoud, T. C., Müller, N. L., Remy, J., “Fleischner Society: glossary of terms for thoracic imaging,” Radiology, Vol. 246, No.3, pp. 697-722, 2008.
[48]Herman, G. T., “Fundamentals of Computerized Tomography: Image Reconstruction from Projection 2nd edition, Springer, 2009.
[49]Lim, J. S., “Two-Dimensional Signal and Image Processing,” Prentice Hall, Englewood Cliffs, 1990.
[50]Bellman, R., “Dynamic programming and lagrange multipliers,” Proceedings of the National Academy of Sciences of the United States of America, Vol. 42, No. 10, pp. 767-769, 1956.
[51]Seni, G., Elder, J., “Ensemble Methods in Data Mining: Improving Accuracy Through Combining Predictions,” CA, San Rafael: Morgan and Claypool, 2010.
[52]Refaeilzadeh, P., Tang, L., Liu, H., “Cross-validation,” Encyclopedia of Database Systems, pp. 532-538, 2009.
[53]Rubin, G. D., “Lung nodule and cancer detection in computed tomography screening,” Journal of Thoracic Imaging, Vol. 30, No. 2, pp. 130-138, 2015.
[54]Aberle, D. R., DeMello, S., Berg, C. D., et al., “Results of the two incidence screenings in the National Lung Screening Trial,” The New England Journal of Medicine, Vol. 369, No. 10, pp. 920-931, 2013.