Automatic Data Extraction in Computed Tomography

Abstract

This experimental study was conducted to study automatic data extraction in computed tomography images using morphology matching filtering using MatLab program. The objectives of this study were to evaluate contrast enhancement pattern in different computed tomography images as such. In addition to evaluate the usage of new nonlinear approach for contrast enhancement of soft tissues in computed tomography images in order to study automatic extraction of lung tissues. Thus the lung CT image is subjected to various processing steps and features are extracted for a set of images. Pre-processing is to improve their quality of images. If these images are too noisy or blurred they should be filtered and sharpened. In this thesis the following programming steps were used firstly preservation of image's overall look; secondly preservation of the diagnostic content in the image and thirdly detection of small low contrast details in diagnostic content of the image. The new approach is funded on an attempt to interpret the problem from the view of blind source separation (BSS), thus to see the panoramic image as a simple mixture of background information, diagnostic information and noise. The median filter is normally used to reduce noise in an image, somewhat like the mean filter. The processing steps include thresholding, morphological operations and feature extraction. By using these steps the lungs are detected and some features are extracted. The extracted features are tabulated for future classification.