Ultrasound medical image enhancement and segmentation using adaptive homomorphic filtering and histogram thresholding

Ultrasound images, though easy to obtain, have inherent flaws due to low frequency tissue image aberrations such as poor contrast caused by the presence of the granular speckle noise. The proposed algorithm aims to improve the ability to differentiate between healthy and malignant conditions via the use of homomorphic filtering and Otsu's gray-level histogram thresholding. The characteristics of the Gaussian window function are adaptively changed based on the input ultrasound image samples taken from different medical ultrasonography scans. A cost estimation function helps establish the adaptability of the filter by means of calculating the mean and variance of local windows and correspondingly evaluate the most discriminative part of the image sample in process. Signal to noise ratio is adopted as an image quality measure of the enhancement operation. Experimental results show the effectiveness of the homomorphic filtering and the robustness of the overall system as a useful diagnostic tool.