胸部数字化X线影像（DR）中肺部小结节的自动检测技术及临床应用探讨
|
摘要
在胸部疾病的诊断中，影像诊断占有很重要的地位。传统的胸部X线摄影作为临床常规检查之一，在临床实践中仍然普遍应用。但由于胶片／增感屏成像系统的局限性，使传统胸片的解读比较困难。
近年来，数字化X线摄影，尤其是直接数字化X线摄影系统的应用，使传统的X线摄影技术进入数字化领域。它与传统的X线摄影相比，具有更高的影像质量，包含更多的影像信息。这种数字化信息经过后处理后，可以获得更多的临床诊断应用。随着计算机技术和图像处理技术的迅速发展，计算机辅助诊断技术在医学影像中的应用也将逐步走向临床。
本文回顾了胸部X线影像计算机辅助诊断技术的发展及其应用的主要数字图像处理技术，并提出了在此基础上开展基于直接数字化X线摄影技术，对胸部数字化X线影像中的结节病灶进行计算机自动检测的应用研究，主要内容是对肺部边界的检测来获得用于进一步检测的感兴趣区，以及在感兴趣区内进行肺部小结节的自动检测，以达到肺癌早期发现的目的。另外，在临床应用实验中对含有小结节的和正常的胸部数字化X线影像各100例进行了放射医师临床诊断结果的ROC曲线分析，住院医师组和有经验医师组在无、有辅助诊断系统帮助的情况下，其诊断结果分析的ROC曲线下面积Az平均值分别为0.857和0.951、0.892和0.959。这一结果表明，放射医师在临床诊断中使用辅助诊断系统可以在一定程度上提高诊断率，缺乏经验的住院医师更能从中得到很大的帮助，使自己的诊断水平得到很大的提高。较好的实验结果激励我们继续进一步的研究，并预期在本项研究基础上开发出能在大批体检人群中，利用数字化X线影像自动、快速、准确地筛选胸片中的小结节病灶的应用软件。
Imaging diagnosis is possessed of very important in diagnosis of the breast disease. Being regarded as one of the general clinical examination, the traditional chest radiography is still ubiquitous in clinical practice. Yet, its interpretation is notoriously difficult because of the limit of the film/screen system.
Recently, digital radiography, especially the application of the DR (direct digital radiography) system leads the traditional radiography into digital field. To compare with traditional radiography image, direct digital radiography image have higher quantity and include further more information. After image manipulation, the digital information can be applied in further more clinical diagnosis. Along with the rapid develop of the technique of computer and image manipulation, the application of the technique of the CAD (computer-aided diagnosis) in the medical image gradually take to clinic.
This paper reviews the development of the technique of CAD on chest image and the application of main technique of the digital image manipulation. Based on this, this paper brings forward the DR-based technique to make application research about small nodules automatic detection on digital radiography; the main is about detection of lung edge to obtain the ROI (region of interest), and then detect the small lung nodules automatically in the ROI so that it can find the pneumonic cancer early. On the other hand, we do a analysis of ROC (receiver operating characteristic) curve about the clinical diagnostic result of the radiologists to the cases that include 100 digital chest images with nodules and normal respectively in the clinical application experiment. The results of clinical diagnosis without and with CAD system is that the average area under the ROC curve (Az) value for residents and radiologists respectively are from 0.857 to 0.951 and from 0.892 to 0.959.This shows that radiologists can improve their rate of diagnosis by applying CAD system in the clinic. And the residents without experience may obtain so much from this. The better results of experiment inspirit us to make further researches. And then, we expect to develop the application software that can filter the nodules automatically and rapidly and accurately in chest DR images take from a mass screening.
近年来，数字化X线摄影，尤其是直接数字化X线摄影系统的应用，使传统的X线摄影技术进入数字化领域。它与传统的X线摄影相比，具有更高的影像质量，包含更多的影像信息。这种数字化信息经过后处理后，可以获得更多的临床诊断应用。随着计算机技术和图像处理技术的迅速发展，计算机辅助诊断技术在医学影像中的应用也将逐步走向临床。
本文回顾了胸部X线影像计算机辅助诊断技术的发展及其应用的主要数字图像处理技术，并提出了在此基础上开展基于直接数字化X线摄影技术，对胸部数字化X线影像中的结节病灶进行计算机自动检测的应用研究，主要内容是对肺部边界的检测来获得用于进一步检测的感兴趣区，以及在感兴趣区内进行肺部小结节的自动检测，以达到肺癌早期发现的目的。另外，在临床应用实验中对含有小结节的和正常的胸部数字化X线影像各100例进行了放射医师临床诊断结果的ROC曲线分析，住院医师组和有经验医师组在无、有辅助诊断系统帮助的情况下，其诊断结果分析的ROC曲线下面积Az平均值分别为0.857和0.951、0.892和0.959。这一结果表明，放射医师在临床诊断中使用辅助诊断系统可以在一定程度上提高诊断率，缺乏经验的住院医师更能从中得到很大的帮助，使自己的诊断水平得到很大的提高。较好的实验结果激励我们继续进一步的研究，并预期在本项研究基础上开发出能在大批体检人群中，利用数字化X线影像自动、快速、准确地筛选胸片中的小结节病灶的应用软件。
Imaging diagnosis is possessed of very important in diagnosis of the breast disease. Being regarded as one of the general clinical examination, the traditional chest radiography is still ubiquitous in clinical practice. Yet, its interpretation is notoriously difficult because of the limit of the film/screen system.
Recently, digital radiography, especially the application of the DR (direct digital radiography) system leads the traditional radiography into digital field. To compare with traditional radiography image, direct digital radiography image have higher quantity and include further more information. After image manipulation, the digital information can be applied in further more clinical diagnosis. Along with the rapid develop of the technique of computer and image manipulation, the application of the technique of the CAD (computer-aided diagnosis) in the medical image gradually take to clinic.
This paper reviews the development of the technique of CAD on chest image and the application of main technique of the digital image manipulation. Based on this, this paper brings forward the DR-based technique to make application research about small nodules automatic detection on digital radiography; the main is about detection of lung edge to obtain the ROI (region of interest), and then detect the small lung nodules automatically in the ROI so that it can find the pneumonic cancer early. On the other hand, we do a analysis of ROC (receiver operating characteristic) curve about the clinical diagnostic result of the radiologists to the cases that include 100 digital chest images with nodules and normal respectively in the clinical application experiment. The results of clinical diagnosis without and with CAD system is that the average area under the ROC curve (Az) value for residents and radiologists respectively are from 0.857 to 0.951 and from 0.892 to 0.959.This shows that radiologists can improve their rate of diagnosis by applying CAD system in the clinic. And the residents without experience may obtain so much from this. The better results of experiment inspirit us to make further researches. And then, we expect to develop the application software that can filter the nodules automatically and rapidly and accurately in chest DR images take from a mass screening.
引文
[1] W.Rontgen, Uber eine neue art von strahlen, in Sitzungsberichte der Physikalisch-Medicinisch Gesellschaft zu Wurzburg, pp. 132-141,1895.
[2] R.Daffner, Clinical Radiology, the Essentials, 2nd ed. Baltimore, MD: Williams & Wilkins, 1999.
[3] R.Bunge and C.Herman, "Use of diagnostic imaging procedures: A nationwide hospital study," Radiology, vol. 163.no.2, pp.569-573, 1987.
[4] L. Quekel, A. Kessels, R.Goi, and J.V.Engelshoven, "Misstate of lung cancer on the chest radiograph in clinical practice." Chest, vol. 115, no.3, pp.720-724,1999.
[5] L. Garland, "On the scientific revolution of diagnostic procedures," Radiology, vol.52,no.3, pp.309-328,1949.
[6] J. Yerushalmy, "The statistical assessment of the variability in observer perception and description of Roentgen graphic pulmonary shadows," Radiological Clinics N. Amer, vol.7, no.3, pp.381-392,1969.
[7] H. Becker, W. Nettleton, P. Meyers, J.Sweeney, and C.Nice,Jr, "Digital computer determination of a medical diagnostic index directly from chest X-ray images," IEEE Trans. Biomed, Eng., vol.BME-11, pp.67-72, 1964.
[8] P.Meyers, C.Nice, Jr, H.becker, W.Nettleton, J.Sweeney, and G.Meckstroth, "Automated computer analysis of radiographic images," Radiology, vol. 83, pp. 1029-1034,1964.
[9] J.Duncan and N.Ayache, "Medical image analysis: Progress over two decades and the challenges ahead," IEEE Trans. Pattern Anal. Machine Intel., vol. 22, pp. 85-106, Jan. 2000.
[10] R. conners, C. Harlow, and S. Dwyer Ⅲ, "Radiographic image analysis Past and present," in Proc. 6th. Int. Conf. Pattern Recognition, Munich, Germany, 1982, pp. 1152-1168.
[11] R.Engle,Jr., "Attempts to use computers as diagnostic aids in medical decision making: A thirty-year experiment, " in Perspectives Biol. Med., vol.35, 1992. pp. 207-217.
[12] M.Cocklin, A. Gourlay, P. Jackson,G.Kaye,I.kerr, and P.Lams, "Digital processing of chest radiographs," Image vis. Comput.,vol. 1, no.2.pp. 67-78,1983.
[13] C.Schaefer-Prokop and M. Prokop, "Digital radiography of the chest: Comparison of the selenium detector with other imaging systems," Medical-Mundi, vol.41, no. 1, pp.2-11,1997.
[14] J. Frija, E. D. Kerviler, A. -M. Zagdanski, C. Feger, P. Attal, and M. Laval-Jeantet, "Radiologie numerique du thorax," Journal de Radiologie, vol.78, pp. 193-207, 1997.
[15] L.Cook, G. Cox, M. Insana, M. McFadden, T. Hall, R.Gaborski, and F. Lure, "Comparison of a cathode-ray-tube and film for display of computed radiographic images." Med Phys.,vol.25, no.7, pp. 1132-1138,1998.
[16] J.-T.Ho and R.Kruger, comparison of dual and single exposure technique in dualenergy chest radiography," Med Phys., vol. 16, no.2,pp. 202-208, 1989.
[17] D.Ergun, W. Peppler, J. Dobbin Ⅲ, F. Zink, D. Kruger, F. Kelcz, F. D. Bruijn, E. Beliers, Y. Wang, R. Althof, and M.Wind, "Dual-energy computer radiography," Proc. SPIE, vol. 2167, pp.663-671, 1994.
[18] D. Guantt and O. Barnes, "X-ray tube potential, filtration, and detector consideractions in dual-energy chest radiography," Med Phys., vol. 21,no.2,pp. 203-218, 1994.
[19] Y.Asai, Y.Tanabe,Y. Ozaki, H. Kubota, M. Matsumoto, and H. Kanamori, "Optimum tube voltage for chest radiographs obtained by psychophysical analysis," Med Phys., vol. 25, no. 11, pp. 2170-2175, 1998.
[20] H.Kundel, C. Nodine, positive and false-negative decisions," Investigate. Radio.,vol.24, pp. 424-427,1989.
[21] E. Krupinsky, C. Nodine, and H. Kundel, "A perceptually based method for enhancing pulmonary nodule recognition," Investigate. Radiological., vol.28, no. 4, pp. 289-294, 1993.
[22] H. MacMahon, C. Vyborny, V. Sabeti, C. Metz, and K. Doi, "The effect of digital, unsharp masking on the detect ability of interstitial infiltrates and pneumothorace" Proc. SPIE, vol. 555, pp. 246-252. 1985.
[23] H. MacMahon, C. Vyborny, C. Metz, K. Doi, V. Saheti, and S.Solomon, "Digital radiography of subtle pulmonary abnormalities: An ROC study of the effect of pixel size on observer performance," Radiology, vol. 158, pp. 21-26,1986.
[24] L.-N.Loo, K.Doi, and C Metz, "Investigation of basic imaging properties in digital radiography: Effect of unsharp masking on the detect ability of simple patterns," Med Phys., vol. 12, no. 2, pp. 209-214, 1985.
[25] R.-D.von Muller, H.Hirche, M.Vob, B.Buddenbrock,V.John, and P.Gocke, "ROC-Analyze zur Bildvernacharbeitung digitaler Thoraxaufnah-men," Fortschr. Rontgenstr., vol 162, no. 2, pp. 163-169,1995.
[26] L. Cook, M. Insana, M. McFadden, T. Hall, and G.Cox, "Contrast-detail analysis of image degradation due to lossy compression," Med Phys., vol. 22, no. 6, pp. 715-721, 1995.
[27] G.Cox, L.Cook. M.Insana, M.McFadden,T. Hall, L. Harrison, D.Eckard, and N. Martin, "The effects of lossy compression on the detection of subtle pulmonary nodules." Med Phys., vol. 23, no. 1, pp.127-112, 1996.
[28] E. Samei, "The Performance of Digital X-Ray Imaging Systems in Detection of Subtle Lung Nodules," Ph. D. dissertation, Univ. Michigan, Ann Arbor, May 1997.
[29] G.Lodwick, T.Keats, and J.Dorst, "The coding of Roentgen images for computer analysis as applied to lung cancer," Radiology, vol. 81, no. 2, pp. 185-200, 1963.
[30] A Templeton, C.Jansen, J.Lehr, and R.Hufft, "Solitary, pulmonary lesions," Radiology, vol.89, no. 4, pp. 605-613, 1967.
[31] N.Asada, K.Doi, H.MacMahon, S.Montner, M.Giger, C.Abe,and Y.Wu, "Potential usefulness of an artificial neural network for differential diagnosis of interstitial lung diseases: Pilot study," Radiology, vol. 177,no.13, pp. 857-860, 1990.
[32] K.Ashizawa, T. isida, H. MacMahon, C.Vybomy, S.Katsuragawa, and K.Doi,
"Artificial neural network in chest radiography," Academic Radiol., vol. 6, pp. 2-9,1999.
[33] K.AshiTawa, H.MacMahon, T.Ishida, K.Nakamura, C.Vyborny, S.Katsuragawa, and K.Doi, "Effect of an artificial neural network on radiologists," performance in the differential diagnosis of interstitial lung disease using chest radiographs," Amer. J. Roentgenol, vol. 172, pp. 1311-1315, 1999.
[34] K.Abe, K. Doi, H. MacMahon, M. Giger, H. Jia, X.Chen, A.Kano, and T. Yanagisawa," Computer-aided diagnosis in chest radiography, preliminary experience," Investigate Radial., vol.28, no. 11, pp. 987-993,1993.
[35] K.Doi, M.Giger, R. Nishikawa, K. Hoffmann, H. MacMahon, R. Schmidt, and K.-G. Chua, "Digital radiography: A useful clinical tool for computer-aided diagnosis by quantitative analysis of radiographic images," Acta Radiological, vol. 34, pp. 425-439,1993.
[36] K.Doi, M.Gigee, R. Nishikawa, K. Hoffwann, H.MacMahon, and R.Schmidt, "Potential usefulness of digital imaging in clinical diagnostic radiology: Computer-aided diagnosis," J.Digital Imag., vol.8, no. 1, pp. 2-7,1995.
[37] K.Doi, M.Giger, H.Nishikawa, K.Hoffwann, H.MacMahon, R.Schmidt, and C. Metz, "Recent progress in development of computer-aided diagnostic (CAD) schemes in radiology,"Med.Imag.Technol.,vol. 13,no.6,pp.822--835,1995.
[38] K.Doi, "Perspectives on digital image analysis in medical imaging: Needs for a new science concerning technical understanding of the contents of medical images," ICRU News, vol.1, pp. 10-14, June 1996.
[39] K.Doi, H. MacMahon, S. Katsuragawa, R. Nishikawa, and Y. Jiang, "computeraided diagnosis in radiology: Potential and Pitfalls," Eur. J. Radiol.,vol.31, pp. 97-109,1997.
[40] K.Doi, Computer-aided Diagnosis in Medical Imaging. Amsterdam, The Netherlands: Elsevier, 1999. Computer-aided diagnosis and its potential impact on diagnostic radiology.
[41] Handbook of Medical Imaging, 2: Medical Image Processing and Analysis, M.S onka, and J. Fitzpatrick, Eds., SPIE Press, Bellingham, Wa, 2000, pp. 399-445. Medical Image interpretation.
[42] M. Giger and H. MacMahon, "Image processing and computer-aided diagnosis," Radiological Clinic N. Amer., vol.34,no.3, pp.565-596, 1996.
[43] H.Swett, M. Giger, and K. Doi, "Computer vision and decision surport," in Perception of Visual Information, 2nd ed. W. Hendee and P.Wells, Eds. Berlin, Germany: Springer-Verlag, 1997, ch. 10, pp.297-342.
[44] K.Doi, H.MacMahon, M. Giger, and K. Hoffmann, Eds., Computer Aided Diagnosis in Medical Imaging. Amsterdam, The Netherlands: Elsevier, 1999.
[45] A.Reeves and W.Kostis, "Computer-aided diagnosis for lung cancer," Radiological Clinics N.Amer., vol. 38, no. 3, pp. 497-509, 2000.
[46] C.Vyborny, M.Giger, and R. Nishikawa, " Computer-aided detection and diagnosis of breast cancer," Radiological Clinics N.Amer., vol.38, no. 4, pp. 725-740, 2000.
[47] Handbook of Medical Imaging, 2: Medical Processing and analysis, M. Sonka and J. Fitzpatrick, Eds., SPIE Press Bellingham, Wa, 2000, pp. 915-1004. Computer-aided diagnosis in mammography.
[48] L.Squire and R.Novelline, Fundamentals of Radiology, 4th ed. Cambridge, MA: Harvard Univ. Press, 1998.
[49] S.Lange, Radiology of Chest Diseases, Stuttgard: Georg Thieme Verlag, 1990.
[50] R.Weissleder, M. Rieumont, and J. Wittenberg of Diagnostic Imaging, 2nd ed. St.Louis, MO: Mosby-Year Book, 1997.
[51] W. Weiser, "Sorting out interstitial lung disease," Appl.Radiol., pp.58-65, Apr. 1993.
[52] E.Hall, R. Kruger, S. Dwyer Ⅲ, D. Hall, R.McLaren and G. Lodwick, "A survey of preprocessing and feature extraction techniques for radiographic images," IEEE Trans.Comput., vol. C-20, pp. 1032-1044, Sept.1971.
[53] R.Conners and C.Harlow, "Equal probability quantizing and texture analysis of radiographic images,"Comput.Graph.Image Processing, vol. 8, pp. 447-463,1978.
[54] H.McAdams, G. Johnson, S.Suddarth and C.Ravin, " Histograms-directed processing of digits chest images," Investigate. Radiol., vol. 21, pp. 253-259,1986.
[55] S. Pizer, E. Amburn, J. Austin, R. Cromartie, A. Geselowitz, T. Greer, B.T.H. Romeny, J.Zimmeman, and K.Zuiderveld, "Adaptive histogram equalization and its variations,"Comput.Vis.,Graph., Image Processing, vol. 39, pp. 355-368, 1987.
[56] R.Sherrier and G. Johnson, "Regionally adaptive histogram equalization of the chest," IEEE Trans. Meal Imag., vol. 6, pp. 1-7, Feb. 1987.
[57] M. I. Sezan, A. M. Tekalp, and R.Schaetzing, "Automatic anatomically selective image enhancement in digital chest radiography," IEEE Trans.Med. lmag.,vol. 8, pp. 154-161,Apr. 1989.
[58] K.Rehm, G. SeeLEy, W. Dallas, R.Ovit, and J. Seeger," Design and testing of artifact-suppressed histogram equalization: A contrast enhancement technique for display of digital chest radiographs," J. Thoracic Imag., vol. 5, no. 1, pp. 85-91, 1990.
[59] M.McNitt-Gray, R.Taira, S. Eldredge, and M. Razavi, "Brightness and contract adjustments for different tissue densities in digital chest radiographs," Proc. SPIE, vo1.1445, pp. 468-478, 1991.
[60] J.-P. Bolet, A.Cowen, J.Launders, A. Davies, and R. Bury, "progress with an 'all-wavelet' approach to image enhancement and de-noising of direct digital thorax radiographic images," in Proc. IPA'97, 1997, pp.244-248.
[61] J.Suzuki, I.Funtkawa, S. Oho, M. Kitamura, and Y. Ando, "Contrast mapping and evaluation for electronic X-ray images on CRT display monitor," IEEE Trans. Med. Imag., vol. 16, pp. 772-784, June 1997.
[62] J.Boone and J.Dyryea, "Filter wheel equalization for chest radiography: A computer simulation,"MedPhys.,vol.22,no.7,pp. 1029-1037, 1995.
[63] R.Geluk, "Digital equalization radiography," Proc. SPIE, vol. 3659, pp.471-477, 1999.
[64] A.Kano, K.Doi, H.MacMahon, D.Hassell, and M.Giger, " Digital image
subtraction of temporally sequential chest images for detection of interval change,"MedPhys.,vol.21, no. 3, pp. 453-461, 1994.
[65] T.Ishida, K. Ashizawa, R.Engelmann,S.Katsuragawa, H.MacMahon, and K.Doi,"Application of temporal subtraction for detection of interval changes on chest radiographs: Improvement of subtraction images using automated initial image matching,"J.Digital Imag., vol. 12,no.2, pp. 77-86,1999.
[66] T.Ishida, S.Katsuragawa, K.Nakamura, H.MacMahon, and K.Doi, "Iterative image warping technique for temporal subtraction of sequential chest radiographs to detect interval change," Med Phys., vol. 26, pp.1320-1329, 1999.
[67] S.Katsuragawa, H.Tagashira, Q.Li, H.MacMahon, and K.Doi, "Comparison of the quality of temporal subtraction images obtained with manual and automated methods of digital chest radiography," J.Digital Imag.,vol.12,no. 4, pp. 166-172.1999.
[68] M.Difazio, H.MacMahon, X.-W.Xu, P.Tsai, J.Shiraishi, S.Armato Ⅲ,and K.Doi, "Digital chest radiography: Effect of temporal subtraction images on detection accuracy," Radiology, vol. 202, pp. 447-452, 1997.
[69] H.Zhao, S. Lo, M. Freedman, and S.Mun, "On automatic temporal subtraction of chest radiographs and its enhancement for lung cancers," Proc. SPIE, vol.4322, pp. 1867-1872, 2001.
[70] Q. Li, S. Katsuragawa, T. Ishida, H. Yoshida, S.Tsukuda, H.MacMahon, and K.Doi, "Contra lateral subtraction: A novel technique for detection of asymmetric abnormalities on digital chest radiographs," MedPhys.,vol. 27, no. 1, pp. 47-55, 2000.
[71] Q.Li, S.Katsuragawa, and K.Doi, "Improved contra lateral subtraction images by use of elastic matching technique," Med Phys., vol. 27, no. 8,pp. 1934-1942, 2000.
[72] Duryea J, Boone, JM.Afully automated algorithm for the segmentation of lung fields on digital chest radiographic images. Med Phys 1995;22:183-191.
[73] E.O.Briham, The Fast Fourier Transform and its Applications, Prentice-Hall, Inc. Englewood Cliffs, New Jersey, 1988.
[74] I.Pitas, Digital Image processing Algorithms, Prentice Hall International (UK)Ltd, 1993.
[75] Rockette HE, King JL, Medina JL, et al. Imaging systems evaluation: effect of subtle cases on the design and analysis of receiver operating characteristic studies. A JR, 1995,165:679-683
[2] R.Daffner, Clinical Radiology, the Essentials, 2nd ed. Baltimore, MD: Williams & Wilkins, 1999.
[3] R.Bunge and C.Herman, "Use of diagnostic imaging procedures: A nationwide hospital study," Radiology, vol. 163.no.2, pp.569-573, 1987.
[4] L. Quekel, A. Kessels, R.Goi, and J.V.Engelshoven, "Misstate of lung cancer on the chest radiograph in clinical practice." Chest, vol. 115, no.3, pp.720-724,1999.
[5] L. Garland, "On the scientific revolution of diagnostic procedures," Radiology, vol.52,no.3, pp.309-328,1949.
[6] J. Yerushalmy, "The statistical assessment of the variability in observer perception and description of Roentgen graphic pulmonary shadows," Radiological Clinics N. Amer, vol.7, no.3, pp.381-392,1969.
[7] H. Becker, W. Nettleton, P. Meyers, J.Sweeney, and C.Nice,Jr, "Digital computer determination of a medical diagnostic index directly from chest X-ray images," IEEE Trans. Biomed, Eng., vol.BME-11, pp.67-72, 1964.
[8] P.Meyers, C.Nice, Jr, H.becker, W.Nettleton, J.Sweeney, and G.Meckstroth, "Automated computer analysis of radiographic images," Radiology, vol. 83, pp. 1029-1034,1964.
[9] J.Duncan and N.Ayache, "Medical image analysis: Progress over two decades and the challenges ahead," IEEE Trans. Pattern Anal. Machine Intel., vol. 22, pp. 85-106, Jan. 2000.
[10] R. conners, C. Harlow, and S. Dwyer Ⅲ, "Radiographic image analysis Past and present," in Proc. 6th. Int. Conf. Pattern Recognition, Munich, Germany, 1982, pp. 1152-1168.
[11] R.Engle,Jr., "Attempts to use computers as diagnostic aids in medical decision making: A thirty-year experiment, " in Perspectives Biol. Med., vol.35, 1992. pp. 207-217.
[12] M.Cocklin, A. Gourlay, P. Jackson,G.Kaye,I.kerr, and P.Lams, "Digital processing of chest radiographs," Image vis. Comput.,vol. 1, no.2.pp. 67-78,1983.
[13] C.Schaefer-Prokop and M. Prokop, "Digital radiography of the chest: Comparison of the selenium detector with other imaging systems," Medical-Mundi, vol.41, no. 1, pp.2-11,1997.
[14] J. Frija, E. D. Kerviler, A. -M. Zagdanski, C. Feger, P. Attal, and M. Laval-Jeantet, "Radiologie numerique du thorax," Journal de Radiologie, vol.78, pp. 193-207, 1997.
[15] L.Cook, G. Cox, M. Insana, M. McFadden, T. Hall, R.Gaborski, and F. Lure, "Comparison of a cathode-ray-tube and film for display of computed radiographic images." Med Phys.,vol.25, no.7, pp. 1132-1138,1998.
[16] J.-T.Ho and R.Kruger, comparison of dual and single exposure technique in dualenergy chest radiography," Med Phys., vol. 16, no.2,pp. 202-208, 1989.
[17] D.Ergun, W. Peppler, J. Dobbin Ⅲ, F. Zink, D. Kruger, F. Kelcz, F. D. Bruijn, E. Beliers, Y. Wang, R. Althof, and M.Wind, "Dual-energy computer radiography," Proc. SPIE, vol. 2167, pp.663-671, 1994.
[18] D. Guantt and O. Barnes, "X-ray tube potential, filtration, and detector consideractions in dual-energy chest radiography," Med Phys., vol. 21,no.2,pp. 203-218, 1994.
[19] Y.Asai, Y.Tanabe,Y. Ozaki, H. Kubota, M. Matsumoto, and H. Kanamori, "Optimum tube voltage for chest radiographs obtained by psychophysical analysis," Med Phys., vol. 25, no. 11, pp. 2170-2175, 1998.
[20] H.Kundel, C. Nodine, positive and false-negative decisions," Investigate. Radio.,vol.24, pp. 424-427,1989.
[21] E. Krupinsky, C. Nodine, and H. Kundel, "A perceptually based method for enhancing pulmonary nodule recognition," Investigate. Radiological., vol.28, no. 4, pp. 289-294, 1993.
[22] H. MacMahon, C. Vyborny, V. Sabeti, C. Metz, and K. Doi, "The effect of digital, unsharp masking on the detect ability of interstitial infiltrates and pneumothorace" Proc. SPIE, vol. 555, pp. 246-252. 1985.
[23] H. MacMahon, C. Vyborny, C. Metz, K. Doi, V. Saheti, and S.Solomon, "Digital radiography of subtle pulmonary abnormalities: An ROC study of the effect of pixel size on observer performance," Radiology, vol. 158, pp. 21-26,1986.
[24] L.-N.Loo, K.Doi, and C Metz, "Investigation of basic imaging properties in digital radiography: Effect of unsharp masking on the detect ability of simple patterns," Med Phys., vol. 12, no. 2, pp. 209-214, 1985.
[25] R.-D.von Muller, H.Hirche, M.Vob, B.Buddenbrock,V.John, and P.Gocke, "ROC-Analyze zur Bildvernacharbeitung digitaler Thoraxaufnah-men," Fortschr. Rontgenstr., vol 162, no. 2, pp. 163-169,1995.
[26] L. Cook, M. Insana, M. McFadden, T. Hall, and G.Cox, "Contrast-detail analysis of image degradation due to lossy compression," Med Phys., vol. 22, no. 6, pp. 715-721, 1995.
[27] G.Cox, L.Cook. M.Insana, M.McFadden,T. Hall, L. Harrison, D.Eckard, and N. Martin, "The effects of lossy compression on the detection of subtle pulmonary nodules." Med Phys., vol. 23, no. 1, pp.127-112, 1996.
[28] E. Samei, "The Performance of Digital X-Ray Imaging Systems in Detection of Subtle Lung Nodules," Ph. D. dissertation, Univ. Michigan, Ann Arbor, May 1997.
[29] G.Lodwick, T.Keats, and J.Dorst, "The coding of Roentgen images for computer analysis as applied to lung cancer," Radiology, vol. 81, no. 2, pp. 185-200, 1963.
[30] A Templeton, C.Jansen, J.Lehr, and R.Hufft, "Solitary, pulmonary lesions," Radiology, vol.89, no. 4, pp. 605-613, 1967.
[31] N.Asada, K.Doi, H.MacMahon, S.Montner, M.Giger, C.Abe,and Y.Wu, "Potential usefulness of an artificial neural network for differential diagnosis of interstitial lung diseases: Pilot study," Radiology, vol. 177,no.13, pp. 857-860, 1990.
[32] K.Ashizawa, T. isida, H. MacMahon, C.Vybomy, S.Katsuragawa, and K.Doi,
"Artificial neural network in chest radiography," Academic Radiol., vol. 6, pp. 2-9,1999.
[33] K.AshiTawa, H.MacMahon, T.Ishida, K.Nakamura, C.Vyborny, S.Katsuragawa, and K.Doi, "Effect of an artificial neural network on radiologists," performance in the differential diagnosis of interstitial lung disease using chest radiographs," Amer. J. Roentgenol, vol. 172, pp. 1311-1315, 1999.
[34] K.Abe, K. Doi, H. MacMahon, M. Giger, H. Jia, X.Chen, A.Kano, and T. Yanagisawa," Computer-aided diagnosis in chest radiography, preliminary experience," Investigate Radial., vol.28, no. 11, pp. 987-993,1993.
[35] K.Doi, M.Giger, R. Nishikawa, K. Hoffmann, H. MacMahon, R. Schmidt, and K.-G. Chua, "Digital radiography: A useful clinical tool for computer-aided diagnosis by quantitative analysis of radiographic images," Acta Radiological, vol. 34, pp. 425-439,1993.
[36] K.Doi, M.Gigee, R. Nishikawa, K. Hoffwann, H.MacMahon, and R.Schmidt, "Potential usefulness of digital imaging in clinical diagnostic radiology: Computer-aided diagnosis," J.Digital Imag., vol.8, no. 1, pp. 2-7,1995.
[37] K.Doi, M.Giger, H.Nishikawa, K.Hoffwann, H.MacMahon, R.Schmidt, and C. Metz, "Recent progress in development of computer-aided diagnostic (CAD) schemes in radiology,"Med.Imag.Technol.,vol. 13,no.6,pp.822--835,1995.
[38] K.Doi, "Perspectives on digital image analysis in medical imaging: Needs for a new science concerning technical understanding of the contents of medical images," ICRU News, vol.1, pp. 10-14, June 1996.
[39] K.Doi, H. MacMahon, S. Katsuragawa, R. Nishikawa, and Y. Jiang, "computeraided diagnosis in radiology: Potential and Pitfalls," Eur. J. Radiol.,vol.31, pp. 97-109,1997.
[40] K.Doi, Computer-aided Diagnosis in Medical Imaging. Amsterdam, The Netherlands: Elsevier, 1999. Computer-aided diagnosis and its potential impact on diagnostic radiology.
[41] Handbook of Medical Imaging, 2: Medical Image Processing and Analysis, M.S onka, and J. Fitzpatrick, Eds., SPIE Press, Bellingham, Wa, 2000, pp. 399-445. Medical Image interpretation.
[42] M. Giger and H. MacMahon, "Image processing and computer-aided diagnosis," Radiological Clinic N. Amer., vol.34,no.3, pp.565-596, 1996.
[43] H.Swett, M. Giger, and K. Doi, "Computer vision and decision surport," in Perception of Visual Information, 2nd ed. W. Hendee and P.Wells, Eds. Berlin, Germany: Springer-Verlag, 1997, ch. 10, pp.297-342.
[44] K.Doi, H.MacMahon, M. Giger, and K. Hoffmann, Eds., Computer Aided Diagnosis in Medical Imaging. Amsterdam, The Netherlands: Elsevier, 1999.
[45] A.Reeves and W.Kostis, "Computer-aided diagnosis for lung cancer," Radiological Clinics N.Amer., vol. 38, no. 3, pp. 497-509, 2000.
[46] C.Vyborny, M.Giger, and R. Nishikawa, " Computer-aided detection and diagnosis of breast cancer," Radiological Clinics N.Amer., vol.38, no. 4, pp. 725-740, 2000.
[47] Handbook of Medical Imaging, 2: Medical Processing and analysis, M. Sonka and J. Fitzpatrick, Eds., SPIE Press Bellingham, Wa, 2000, pp. 915-1004. Computer-aided diagnosis in mammography.
[48] L.Squire and R.Novelline, Fundamentals of Radiology, 4th ed. Cambridge, MA: Harvard Univ. Press, 1998.
[49] S.Lange, Radiology of Chest Diseases, Stuttgard: Georg Thieme Verlag, 1990.
[50] R.Weissleder, M. Rieumont, and J. Wittenberg of Diagnostic Imaging, 2nd ed. St.Louis, MO: Mosby-Year Book, 1997.
[51] W. Weiser, "Sorting out interstitial lung disease," Appl.Radiol., pp.58-65, Apr. 1993.
[52] E.Hall, R. Kruger, S. Dwyer Ⅲ, D. Hall, R.McLaren and G. Lodwick, "A survey of preprocessing and feature extraction techniques for radiographic images," IEEE Trans.Comput., vol. C-20, pp. 1032-1044, Sept.1971.
[53] R.Conners and C.Harlow, "Equal probability quantizing and texture analysis of radiographic images,"Comput.Graph.Image Processing, vol. 8, pp. 447-463,1978.
[54] H.McAdams, G. Johnson, S.Suddarth and C.Ravin, " Histograms-directed processing of digits chest images," Investigate. Radiol., vol. 21, pp. 253-259,1986.
[55] S. Pizer, E. Amburn, J. Austin, R. Cromartie, A. Geselowitz, T. Greer, B.T.H. Romeny, J.Zimmeman, and K.Zuiderveld, "Adaptive histogram equalization and its variations,"Comput.Vis.,Graph., Image Processing, vol. 39, pp. 355-368, 1987.
[56] R.Sherrier and G. Johnson, "Regionally adaptive histogram equalization of the chest," IEEE Trans. Meal Imag., vol. 6, pp. 1-7, Feb. 1987.
[57] M. I. Sezan, A. M. Tekalp, and R.Schaetzing, "Automatic anatomically selective image enhancement in digital chest radiography," IEEE Trans.Med. lmag.,vol. 8, pp. 154-161,Apr. 1989.
[58] K.Rehm, G. SeeLEy, W. Dallas, R.Ovit, and J. Seeger," Design and testing of artifact-suppressed histogram equalization: A contrast enhancement technique for display of digital chest radiographs," J. Thoracic Imag., vol. 5, no. 1, pp. 85-91, 1990.
[59] M.McNitt-Gray, R.Taira, S. Eldredge, and M. Razavi, "Brightness and contract adjustments for different tissue densities in digital chest radiographs," Proc. SPIE, vo1.1445, pp. 468-478, 1991.
[60] J.-P. Bolet, A.Cowen, J.Launders, A. Davies, and R. Bury, "progress with an 'all-wavelet' approach to image enhancement and de-noising of direct digital thorax radiographic images," in Proc. IPA'97, 1997, pp.244-248.
[61] J.Suzuki, I.Funtkawa, S. Oho, M. Kitamura, and Y. Ando, "Contrast mapping and evaluation for electronic X-ray images on CRT display monitor," IEEE Trans. Med. Imag., vol. 16, pp. 772-784, June 1997.
[62] J.Boone and J.Dyryea, "Filter wheel equalization for chest radiography: A computer simulation,"MedPhys.,vol.22,no.7,pp. 1029-1037, 1995.
[63] R.Geluk, "Digital equalization radiography," Proc. SPIE, vol. 3659, pp.471-477, 1999.
[64] A.Kano, K.Doi, H.MacMahon, D.Hassell, and M.Giger, " Digital image
subtraction of temporally sequential chest images for detection of interval change,"MedPhys.,vol.21, no. 3, pp. 453-461, 1994.
[65] T.Ishida, K. Ashizawa, R.Engelmann,S.Katsuragawa, H.MacMahon, and K.Doi,"Application of temporal subtraction for detection of interval changes on chest radiographs: Improvement of subtraction images using automated initial image matching,"J.Digital Imag., vol. 12,no.2, pp. 77-86,1999.
[66] T.Ishida, S.Katsuragawa, K.Nakamura, H.MacMahon, and K.Doi, "Iterative image warping technique for temporal subtraction of sequential chest radiographs to detect interval change," Med Phys., vol. 26, pp.1320-1329, 1999.
[67] S.Katsuragawa, H.Tagashira, Q.Li, H.MacMahon, and K.Doi, "Comparison of the quality of temporal subtraction images obtained with manual and automated methods of digital chest radiography," J.Digital Imag.,vol.12,no. 4, pp. 166-172.1999.
[68] M.Difazio, H.MacMahon, X.-W.Xu, P.Tsai, J.Shiraishi, S.Armato Ⅲ,and K.Doi, "Digital chest radiography: Effect of temporal subtraction images on detection accuracy," Radiology, vol. 202, pp. 447-452, 1997.
[69] H.Zhao, S. Lo, M. Freedman, and S.Mun, "On automatic temporal subtraction of chest radiographs and its enhancement for lung cancers," Proc. SPIE, vol.4322, pp. 1867-1872, 2001.
[70] Q. Li, S. Katsuragawa, T. Ishida, H. Yoshida, S.Tsukuda, H.MacMahon, and K.Doi, "Contra lateral subtraction: A novel technique for detection of asymmetric abnormalities on digital chest radiographs," MedPhys.,vol. 27, no. 1, pp. 47-55, 2000.
[71] Q.Li, S.Katsuragawa, and K.Doi, "Improved contra lateral subtraction images by use of elastic matching technique," Med Phys., vol. 27, no. 8,pp. 1934-1942, 2000.
[72] Duryea J, Boone, JM.Afully automated algorithm for the segmentation of lung fields on digital chest radiographic images. Med Phys 1995;22:183-191.
[73] E.O.Briham, The Fast Fourier Transform and its Applications, Prentice-Hall, Inc. Englewood Cliffs, New Jersey, 1988.
[74] I.Pitas, Digital Image processing Algorithms, Prentice Hall International (UK)Ltd, 1993.
[75] Rockette HE, King JL, Medina JL, et al. Imaging systems evaluation: effect of subtle cases on the design and analysis of receiver operating characteristic studies. A JR, 1995,165:679-683