Tardi Tjahjadi

Publications (2)2.29 Total impact

• Article: Image texture analysis of sonograms in chronic inflammations of thyroid gland.

  Daniel Smutek, Radim Sára, Petr Sucharda, Tardi Tjahjadi, Martin Svec
  [show abstract] [hide abstract]
  ABSTRACT: The current practice in assessing sonographic findings of chronic inflamed thyroid tissue is mainly qualitative, based just on a physician's experience. This study shows that inflamed and healthy tissues can be differentiated by automatic texture analysis of B-mode sonographic images. Feature selection is the most important part of this procedure. We employed two selection schemes for finding recognition-optimal features: one based on compactness and separability and the other based on classification error. The full feature set included Muzzolini's spatial features and Haralick's co-occurrence features. These features were selected on a set of 2430 sonograms of 81 subjects, and the classifier performance was evaluated on a test set of 540 sonograms of 18 independent subjects. A classification success rate of 100% was achieved with as few as one optimal feature among the 129 texture characteristics tested. Both selection schemes agreed on the best features. The results were confirmed on the independent test set. The stability of the results with respect to sonograph setting, thyroid gland segmentation and scanning direction was tested.
  Ultrasound in Medicine & Biology 12/2003; 29(11):1531-43. · 2.29 Impact Factor
• Article: Image Texture Analysis of Sonograms in Chronic Inflammations of Thyroid Gland

  Daniel Smutek, Tardi Tjahjadi, Petr Sucharda, Stepan Svacina
  [show abstract] [hide abstract]
  ABSTRACT: The assessment of sonographic findings of chronic inflamed thyroid tissue in medical praxis is based just on examiner's experience. This paper shows that exact evaluation is possible and that inflamed and healthy tissues can be differentiated by automatic texture analysis of B-mode sonographic images. Classification success rate of 96.6% was achieved with as few as five features automatically selected from a set of 129 spatial and co-occurrence textural characteristics. The rate was evaluated on a validation set of 580 sonograms taken in three types of cross-sections from 39 persons. Two feature selection schemes were proposed. The first was based on compactness and separability criterion computed independently for individual features. The second was based on minimal classification error evaluated on an independent validation set. We observed the first scheme performed significantly worse by achieving only 90.75% recognition success rate and requiring ten features.
  05/2001;