Different types of image texture features in ultrasound of patients with lymphocytic thyroiditis

ABSTRACT

Ultrasound is very important imaging modality in diagnosing and monitoring diseases of thyroid gland. We propose using quantifiable indices for texture characterization and classification. Spatial features, co-occurrence texture features, and non-heuristic texture features are compared in this study. The spatial texture features acted as the best descriptors of changed thyroid tissue for texture characterization with a classification success rate of 100%. The co-occurrence features achieved the classification success about 75% and required to be in a group of four or eight features. The results of non-heuristic texture features were on the border between spatial and co-occurrence features. The overall good classification results confirm that the information related to diagnosis can be adequately extracted from sonographic images of subsurface organs. Quantitative indicators enable reproducibility of the sonographic diagnosis, facilitate assessment of changes of the disease and make possible the comparison of different physicians' findings of a sonographic examination.

REFERENCES

• 1: Devroye L., Gyorfi L., Lugosi G. A. Probabilistic Theory of Pattern Recognition. New York: Springer Verlag, 1996.
• 2: Josef Kittler , Mohamad Hatef , Robert P. W. Duin , Jiri Matas, On Combining Classifiers, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.20 n.3, p.226-239, March 1998 [doi>10.1109/34.667881]
• 3: Muzzolini R., Yang YH, Pierson R. Texture characterization using robust statistics. Pattern Recognition 1994; 27(1):119--134
• 4: Haralick R. M. and L. G. Shapiro. Computer and Robot Vision, volume 1, chapter Texture. Addison-Wesley Publishing Company, 1993, pp. 453--507
• 5: Radim Sára , Daniel Smutek , Petr Sucharda , Stepán Svacina, Systematic Construction of Texture Features for Hashimoto's Lymphocytic Thyroiditis Recognition from Sonographic Images, Proceedings of the 8th Conference on AI in Medicine in Europe: Artificial Intelligence Medicine, p.339-348, July 01-04, 2001
• 6: Wartfsky L., Ingbar SH: Disease of the Thyroid. In: Harrison's principles of internal medicine, 12th ed., McGraw-Hill Inc., New York 1991, p. 1712