Abstract
The efficiency of texture analysis parameters, describing the organization of grey level variations of an image, was studied for lung scintigraphic data classification. Twenty one patients received a99mTc-MAA perfusion scan and81mKr and and127 Xe ventilation scans. Scans were scaled to 64 grey levels and 100 k events for inter subject comparison. The texture index was the average of the absolute difference between a pixel and its neighbors. Energy, entropy, correlation, local homogeneity and inertia were computed using co-occurence matrices. A principal component analysis was carried out on each parameter for each type of scan and the first principal components were selected as clustering indices. Validation was achieved by simulating 2 series of 20 increasingly heterogeneous perfusion and ventilation scans. For most of the texture parameters, one principal component could summarize the patients data since it corresponded to the relative variances of 67%-88% for perfusion scans, 53%–99% for81mKr scans and 38%–97% for127Xe scans. The simulated series demonstrated a linear relationship between the heterogeneity and the first principal component for texture index, energy, entropy and inertia. This was not the case for correlation and local homogeneity. We conclude that heterogeneity of lung scans may be quantified by texture analysis. The texture index is the easiest to compute and provides the most efficient results for clinical purpose.
Similar content being viewed by others
References
Cinotti L, Susskind H, Di Paola R, Kahn E, Brill AB (1987) Texture analysis of lung scintigraphy for patient clustering. Proceedings of the Symposium on Medical Imaging Research, 58:16 Paris
Conners RW, Harlow CA (1980) A theoretical comparison of texture algorithms. IEEE Trans Pattern Anal Machine Intell. PAMI 2:204–222
Haralick RM (1979) Statistical and structural to approacjes to texture. Proc. IEEE 67:786–804
Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern SMC 3:610–621
Harman HH (1976) Modern factor analysis. The University of Chicago Press, Chicago, Illinois
Homma K, Takenaka E (1985) An image processing method for feature extraction of space occupying lesions. J Nucl. Med 26:1472–1477
Kruger RP, Thompson WB, Turner AF (1974) Computer diagnosis of pneumoconiosis. IEEE. Trans Syst Man Cybern SMC 4:40–49
McGeechan CS, Gemmell HG, Dendy PP (1985) Texture analysis in radionuclide tomographic liver imaging. Phys Med Biol 30:669–676
Sirr SA, Elliott GR, Regelmann WE, Juenemann PJ, Morin RL, Boudreau RJ, Warwick WJ, Loken MK (1986) Aerosol penetration ratio: a new index of ventilation. J Nucl Med 27:1343–1346
Susskind H, Iwai J, Acevedo JC, Rasmussen DL, Heydinger DK, Pate HR, Yonekura Y, Harold WH, Brill AB (1982) Lung impairment in nonsmoking and smoking coal miners. Am Rev Resp Dis 125:159
Sutton RN, Hall EL (1972) Texture measures for automatic classification of pulmonary disease. IEEE Trans Comput C21:667–676
Weszka JS, Dyer CR, Rosenfeld A (1976) A comparative study to texture measures for terrain classification. IEEE Trans Syst Man Cybern SMC 6:269–285
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Cinotti, L., Edery, S., Kahn, E. et al. Luna scintigraphy clustering by texture analysis. Eur J Nucl Med 16, 353–359 (1990). https://doi.org/10.1007/BF00842792
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF00842792