HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Abstract Full Text Full Text (PDF) Submit a response Alert me when this article is cited Alert me when eLetters are posted Alert me if a correction is posted Citation Map Services Email this article to a friend Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via HighWire Citing Articles via Google Scholar Google Scholar Articles by Armato, S. G. Articles by MacMahon, H. Search for Related Content PubMed PubMed Citation Articles by Armato, S. G., III Articles by MacMahon, H. Related Collections Physics and Basic Science Chest Radiology Computed Tomography

Computerized Detection of Pulmonary Nodules on CT Scans¹

¹ From the Kurt Rossmann Laboratories for Radiologic Image Research, Department of Radiology, MC 2026, University of Chicago, 5841 S Maryland Ave, Chicago, IL 60637. Recipient of an Excellence in Design award for a scientific exhibit at the 1998 RSNA scientific assembly. Received February 15, 1999; revision requested March 18 and received May 4; accepted May 7. Supported in part by grants CA48985, CA62625, CA64370, and RR11459 from the U.S. Public Health Service; funding from the University of Chicago Cancer Research Center; and a grant from the American Lung Association of Metropolitan Chicago. Address reprint requests to S.G.A.

View larger version (23K): [in a new window]   Figure 1.   Overall scheme for automated detection of pulmonary nodules on CT scans.

View larger version (116K): [in a new window]   Figures 2-4.   (2) Original section image shows the diagonal along which a gray-level profile is constructed for segmentation of the thorax. (3) Cumulative gray-level profile constructed from pixels along the diagonal shown in Figure 2. Pixel location 0 represents the upper left corner of the image. Arrow = selected threshold for segmentation of the thorax. (4) Binary image that results after gray-level thresholding is performed in the original section. The thoracic segmentation contour is also shown.

View larger version (16K): [in a new window]   Figures 2-4.   (2) Original section image shows the diagonal along which a gray-level profile is constructed for segmentation of the thorax. (3) Cumulative gray-level profile constructed from pixels along the diagonal shown in Figure 2. Pixel location 0 represents the upper left corner of the image. Arrow = selected threshold for segmentation of the thorax. (4) Binary image that results after gray-level thresholding is performed in the original section. The thoracic segmentation contour is also shown.

View larger version (65K): [in a new window]   Figures 2-4.   (2) Original section image shows the diagonal along which a gray-level profile is constructed for segmentation of the thorax. (3) Cumulative gray-level profile constructed from pixels along the diagonal shown in Figure 2. Pixel location 0 represents the upper left corner of the image. Arrow = selected threshold for segmentation of the thorax. (4) Binary image that results after gray-level thresholding is performed in the original section. The thoracic segmentation contour is also shown.

View larger version (114K): [in a new window]   Figure 5.   Segmented thoracic region used to construct a gray-level histogram for lung thresholding.

View larger version (13K): [in a new window]   Figures 6, 7.   (6) Gray-level histogram constructed from pixels in the thorax. Arrow = selected threshold for lung segmentation. (7) Binary image that results after gray-level thresholding is performed in the segmented thorax. The lung segmentation contours are also shown.

View larger version (54K): [in a new window]   Figures 6, 7.   (6) Gray-level histogram constructed from pixels in the thorax. Arrow = selected threshold for lung segmentation. (7) Binary image that results after gray-level thresholding is performed in the segmented thorax. The lung segmentation contours are also shown.

View larger version (115K): [in a new window]   Figure 8.   Original section image with lung segmentation contours superimposed. A juxtapleural nodule and hilar vessels have been excluded from the right lung contour.

View larger version (21K): [in a new window]   Figures 9-11.   (9) Initial placement of the rolling ball filter for each lung segmentation contour. The inset shows the filter spanning a contour indentation. (10) Lung segmentation contours after interpolation is used to bridge indentations. White areas indicate regions that have been included within the new lung segmentation regions. (11) Segmented lung regions after implementation of the rolling ball algorithm. These regions are subjected to multiple gray-level thresholding for initial nodule identification.

View larger version (17K): [in a new window]   Figures 9-11.   (9) Initial placement of the rolling ball filter for each lung segmentation contour. The inset shows the filter spanning a contour indentation. (10) Lung segmentation contours after interpolation is used to bridge indentations. White areas indicate regions that have been included within the new lung segmentation regions. (11) Segmented lung regions after implementation of the rolling ball algorithm. These regions are subjected to multiple gray-level thresholding for initial nodule identification.

View larger version (92K): [in a new window]   Figures 9-11.   (9) Initial placement of the rolling ball filter for each lung segmentation contour. The inset shows the filter spanning a contour indentation. (10) Lung segmentation contours after interpolation is used to bridge indentations. White areas indicate regions that have been included within the new lung segmentation regions. (11) Segmented lung regions after implementation of the rolling ball algorithm. These regions are subjected to multiple gray-level thresholding for initial nodule identification.

View larger version (70K): [in a new window]   Figure 12a.   Pixels that remain on in the section from Figure 11 after thresholding at two of the 36 gray-level thresholds. The threshold used to create a was lower than the threshold used to create b.

View larger version (11K): [in a new window]   Figure 12b.   Pixels that remain on in the section from Figure 11 after thresholding at two of the 36 gray-level thresholds. The threshold used to create a was lower than the threshold used to create b.

View larger version (99K): [in a new window]   Figure 13a.   MIP images show the structures that remain on within the complete lung volume at the two gray-level thresholds depicted in Figure 12. These images represent the thresholded volumes as viewed from below with the patient's left on the right side of the images. The threshold used to create the volume shown in a was lower than the threshold used to create the volume shown in b.

View larger version (71K): [in a new window]   Figure 13b.   MIP images show the structures that remain on within the complete lung volume at the two gray-level thresholds depicted in Figure 12. These images represent the thresholded volumes as viewed from below with the patient's left on the right side of the images. The threshold used to create the volume shown in a was lower than the threshold used to create the volume shown in b.

View larger version (24K): [in a new window]   Figure 14.   Ten-point connectivity scheme for grouping pixels in three dimensions. The pixel of interest (shown in gray) is identified as belonging to the same structure as all other on pixels within the 10-pixel neighborhood indicated.

View larger version (109K): [in a new window]   Figure 15.   MIP image shows the structures that satisfy the maximum volume criterion at any of the 36 threshold levels. These structures form the set of nodule candidates. (A base section that contained a false-positive finding caused by a portion of the left hemidiaphragm was manually eliminated to improve visualization.)

View larger version (45K): [in a new window]   Figures 16, 17.   (16) Relationship between sphericity and maximum circularity for nodule candidates that correspond to actual nodules (°) and nodule candidates that correspond to nonnodules (stippling). (17) Relationship between maximum eccentricity and maximum compactness for nodule candidates that correspond to actual nodules (°) and nodule candidates that correspond to nonnodules (stippling).

View larger version (43K): [in a new window]   Figures 16, 17.   (16) Relationship between sphericity and maximum circularity for nodule candidates that correspond to actual nodules (°) and nodule candidates that correspond to nonnodules (stippling). (17) Relationship between maximum eccentricity and maximum compactness for nodule candidates that correspond to actual nodules (°) and nodule candidates that correspond to nonnodules (stippling).

View larger version (77K): [in a new window]   Figure 18.   MIP image shows the nodule candidates that remain after linear discriminant analysis is used to reduce the number of structures that correspond to nonnodules. (A base section that contained a false-positive finding caused by a portion of the left hemidiaphragm was manually eliminated to improve visualization.)

View larger version (12K): [in a new window]   Figure 19.   ROC curve shows the performance of linear discriminant analysis in distinguishing true nodules from nonnodules.