Texture Analysis Using Gabor Filter Based on Transcranial Sonography Image
Transcranial sonography (TCS) is a new tool for the diagnosis of Parkinson’s disease (PD) at a very early state. The TCS image of the mesencephalon shows a distinct hyperechogenic pattern in about 90% PD patients. This pattern is usually manually segmented and the substantia nigra (SN) region can be used as an early PD indicator. However this method is based on manual evaluation of examined images. We propose a texture analysis method using Gabor filters for the early PD risk assessment. The features are based on the local spectrum, which is obtained by a bank of Gabor filters, and the performance of these features is evaluated by feature selection method. The results show that the accuracy of the classification with the feature subset is reaching 92.73%.
Unable to display preview. Download preview PDF.
- 1.Kier C, Seidel G, Bregemann N, et al. Transcranial sonography as early indicator for genetic Parkinson’s disease. Proc IFMBE. 2009; p. 456–9.Google Scholar
- 2.Spiegel J, Storch A, Jost WH. Early diagnosis of Parkinson’s disease. J Neurol. 2006;253[Suppl 4].Google Scholar
- 3.Behnke S, Berg D, Becker G. Does ultrasound disclose a vulnerability factor for Parkinson’s disease? J Neurol. 2006;250:24–7.Google Scholar
- 5.Chen L, Seidel G, Mertins A. Multiple feature extraction for early parkinson risk assessment based on transcranial sonography image. In: Proc ICIP; 2010.Google Scholar
- 9.Hu, K M. Visual pattern recognition by moments invariants. IEEE Trans Inf Theory. 1962;8:456–9.Google Scholar
- 10.Manjunath BS, Ma WY. Texture features for browsing and retrieval of image data. IEEE Trans Pattern Anal Mach Intell. 1996;18(8).Google Scholar
- 11.Devendran V, Thiagarajan H, Wahi A. SVM based hybrid moment features for natural scene categorization. Int Conf Comput Sci Eng. 2009;1:356–61.Google Scholar