RULE BASED DETECTION OF LUNG NODULES IN CT IMAGES

Abstract

In this paper, we present a computer aided diagnosis (CAD) system for lung nodule detection in computed tomography (CT) images. Here, the density values of pixels in CT image slices are used and scanning the pixels in 8 directions is evaluated. By using various thresholds while scanning the pixels, lung nodule shapes and parts of the normal structure shapes (blood vessels, bronchus etc.) are found. All shapes are labeled using connected component labeling (CCL). Two rules are used to distinguish lung nodules from normal structures. In the first rule, the euclidean distance of the shape, and in the second rule the regularity which is the ratio of euclidean distance to thickness of the shape is considered. The performance of the system is evaluated using a test set which contains totally 35 normal and abnormal images, with 61 nodules. When results are compared with the second look reviews of a chest radiologist, it is seen that  the system achieved 89% sensitivity with 0.457 false positives (FPs) per image. The proposed system which obtains high sensitivity with acceptable low number of false positives per image, may improve the computerized analysis of lung CTs and early diagnosis of lung nodules.

Keywords

• Computer aided diagnosis, lung nodule detection, computed tomography

References

1. Austin J. H., Muller N. L., Friedman P. J., vd. “Glossary of terms for CT of the lungs: Recommendations of the Nomenclature Committee of the Fleischner Society”, Radiology, 200: 327-331, 1996.
2. Keagy B. A., Starek P. J., Murray G. F., vd. “Major pulmonary resection for suspected but unconfirmed malignancy”, Ann Thorac Surg, 38, 314-316, 1984.
3. Siegeman S. S., Khouri N. F., Leo F. P., vd. “Solitary pulmonary nodules: CT assessment”, Radiology, 160, 307-312, 1986.
4. Ko J. P., Naidich D. P., “Lung nodule detection and characterization with multislice CT”, Radiologic Clinics of North America, 41, 575-597, 2003.
5. Röntgen W., “Über eine neue art von strahlen”, in Sitzungsberichte der PhysikalischMedicinisch Gesellschaft zu Würzburg, pp. 132– 141, 1895.
6. Paik D. S., Beaulieu C. F., Rubin G. D., Acar B., Jeffrey R. B., Yee Jr., J., Dey J., and Napel S., “Surface Normal Overlap: A Computer-Aided Detection Algorithm With Application to Colonic Polyps and Lung Nodules in Helical CT”, IEEE Trans. Med. Imag., vol. 23, no. 6, June 2004.
7. Giger M. L., Bae K. T., and MacMahon H., “Computerized detection of pulmonary nodules in computed tomography images,” Investigat. Radiol., vol. 29, pp. 459–465, 1994.
8. Armato S. G., Giger M. L.,.Moran C. J, Blackburn J. T., Doi K., and MacMahon H., “Computerized detection of pulmonary nodules on CT scans,” Radiographics, vol. 19, pp. 1303– 1311, 1999.

9. Armato S. G., Giger M. L., and MacMahon H., “Automated detection of lung nodules in CT scans: Preliminary results,” Med. Phys., vol. 28, pp. 1552–1561, 2001.
10. Brown M. S., McNitt-Gray M. F., Goldin J. G., Suh R. D., Sayre J. W., and Aberle D. R., “Patient-specific models for lung nodule detection and surveillance in CT images,” IEEE Trans. Med. Imag., vol. 20, pp. 1242–1250, Dec. 2001.
11. Hounsfield GN., “Computed medical imaging”, Med Phys., 7(4):283-90, 1980.
12. Ronse C. and Devijver P. A., Connected components in binary images: the detection problem, Research Studies Press, NY: Wiley, 1984.
13. Manohar M. and Ramapriyan H. K., “Connected Component Labeling of Binary Images on a Mesh Connected Massively Parallel Processor,” Computer Vision, Graphics, and Image Processing, vol. 45, 1989, pp. 133-149.
14. Stefano L. D. and Bulgarelli A., “A simple and efficient connected components labeling algorithm,” in Proceedings of International Conference on Image Analysis and Processing, 1999, pp. 322-327.