Support Vector Machine Based Diagnostic System for Thyroid Cancer using Statistical Texture Features


Objective: The aim of this study was to develop an automated computer-aided diagnostic system for diagnosisof thyroid cancer pattern in fine needle aspiration cytology (FNAC) microscopic images with high degree ofsensitivity and specificity using statistical texture features and a Support Vector Machine classifier (SVM).Materials and
Methods: A training set of 40 benign and 40 malignant FNAC images and a testing set of 10 benignand 20 malignant FNAC images were used to perform the diagnosis of thyroid cancer. Initially, segmentation ofregion of interest (ROI) was performed by region-based morphology segmentation. The developed diagnosticsystem utilized statistical texture features derived from the segmented images using a Gabor filter bank at variouswavelengths and angles. Finally, the SVM was used as a machine learning algorithm to identify benign andmalignant states of thyroid nodules.
Results: The SVMachieved a diagnostic accuracy of 96.7% with sensitivityand specificity of 95% and 100%, respectively, at a wavelength of 4 and an angle of 45.
Conclusion: The resultsshow that the diagnosis of thyroid cancer in FNAC images can be effectively performed using statistical textureinformation derived with Gabor filters in association with an SVM.