Abstract
Computer-assisted interpretation of computer radiography (CR) chest images including lung nodules detection, quantitative texture analysis, etc requires a lung delineation algorithm that restricts the area to be analyzed. This report presents a new lung-segmentation technique. It is performed in three phases. First, a histogram analysis finds a threshold value that eliminates the densest anatomic regions. Then, a gradient analysis separates the lungs from parts of thorax attached to the lungs that have not been removed in the previous phase. A smoothing routine yields the final image. By imposing a testing condition that results from the histogram analysis, underexposed images are not being considered. If being segmented, they exhibit a significant lung penetration. The test increases the accuracy of the procedure and makes it safer for an unsupervised application. The segmentation procedure has been implemented together with preprocessing functions in our clinical picture archiving and communication system.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Lampeter W, Wandtke JC: Computerized searched of chest radiographs for nodules. Invest Radiol 21:384–390, 1986
Chiles C, Sherrier RH: Analysis if the solitary pulmonary nodule by means of digital techniques. J Thorac Imaging 5:55–60, 1990
Giger ML, Doi K, MacMahon H: Image feature analysis and computer-aided diagnosis in digital radiography. Automated detection of nodules in peripheral lung fields. Med Phys 15:158–166, 1988
Giger ML, Ahn N, Doi K, MacMahon H: Computerized detection of pulmonary nodules in digital chest images: Use of morphological filters in reducing false-positive detections. Med Phys 17:861–865, 1990
Desage JF, Dengler J, Wolf T, et al: Filmdigitalisierung und Texturanalyse für die digitale Klassifizierung von Lungenfleckschatten. Röntgen-Bl. 41:147–151, 1988
Katsuragawa S, Doi K, Nakamori N, et al: Image feature analysis and computer-aided diagnosis in digital radiography: Effect of digital parameters on the accuracy of computerized analysis of interstitial disease in digital chest radiographs. Med Phys 17:72–78, 1990
Katsuragawa S, Doi K, Nakamori N, et al: Image feature analysis and computer-aided diagnosis in digital radiography: Detection and characterization of interstitial lung disease in digital chest radiographs. Med Phys 15:311–319, 1988
Daponte JS, Fox MD: Enhancement of chest radiographs with gradient operators. IEEE Trans Med Imaging 7:109–117, 1988
Sanada S, Doi K, MacMahon H: Image feature analysis and computer-aided diagnosis in digital radiography: Automated delineation of posterior ribs in chest images. Med Phys 18:964–971, 1991
Wechsler H, Sklansky J: Finding the rib cage in chest radiographs. Pattern Recognition 9:21–30, 1977
Davis LS: A survey of edge detection techniques. Comput Graphics Image Process 4:248–270, 1975
Gonzalez RC, Wintz P: Digital Image Processing (ed 2). Reading, MA, Addison-Wesley, 1987
Canny J: A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 8:679–714, 1986
Sotak GE, Boyer KL: The Laplacian-of-Gaussian kernel: A formal analysis and design procedure for fast, accurate convolution and full-frame output. Comput Vision Graphics Image Processing 48:147–189, 1989
Petron M, Kittler J: Optimal edge detectors for ramp edges. IEEE Trans Pattern Anal Mach Intell 13:483–491, 1991
McNitt-Gray ME, Sayre JW, Huang HK: Pattern classification approach to chest radiographs. Radiology 185:301, 1992
Sherrier RH, Johnson GA: Regionally adaptive histogram equalization of the chest. IEEE Trans Med Imaging 6:1–7, 1987
Sezan MI, Tekalp AM, Schaetzing R: Automatic anatomically selective image enhancement in digital chest radiography. IEEE Trans Med Imaging MI 8:154–162, 1989
McNitt-Gray MF, Taira RK, Eldredge SE, Razavi M: Brightness and contrast adjustments for different tissue densities for digital chest radiographs. Proc SPIE 1445:468–478, 1991
Cheng D, Goldberg M: An algorithm for segmenting chest radiographs. Proc SPIE 1001:261–268, 1988
Turner AF, Kruger RP, Thompson WB: Automated computer screening of chest radiographs for pneumoconiosis. Invest Radiol 11:258–266, 1976
Pietka E, Huang HK: Orientation correction of chest images. J Digit Imaging 5:183–189, 1992
McNitt-Gray M, Pietka E, Huang HK: Image preprocessing for picture archiving and communication system. Invest Radiology 27:529–535, 1992
Ratib O, Appel R, Scherrer JR: Papyrus: A multimodality image file format for PACS and teleradiology. Radiology 177:320, 1990
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Pietka, E. Lung segmentation in digital radiographs. J Digit Imaging 7, 79–84 (1994). https://doi.org/10.1007/BF03168427
Issue Date:
DOI: https://doi.org/10.1007/BF03168427