Classification and Retrieval of Focal and Diffuse Liver from Ultrasound Images Using Machine Learning Techniques

Abstract

Medical Diagnosis has been gaining importance in everyday life. The diseases and their symptoms are highly varying and there is always a need for a continuous update of knowledge needed for the doctors. This forces lots of challenges as the diagnostic tools need to visualize organs and soft tissues and further classify them for diagnosis. One such application of diagnostic ultrasound is liver imaging. The existing approaches for classification & retrieval system have the following issues: speckle noise, semantic gap, computational time, dimensionality reduction and accuracy of retrieved images from large dataset. This paper proposes a new method for the classification & retrieval of liver diseases from ultrasound image dataset. The proposed work concentrates on diagnosing both focal and diffuse liver diseases from ultrasound images. The contribution of this paper relies on the following areas. Speckle reduction by Modified Laplacian Pyramid Nonlinear Diffusion (MLPND), Mutual Information (MI) based image registration, Image texture analysis by Haralick’s features, Image Classification & retrieval by machine learning algorithms. The dataset used in each phase of the work are authenticated dataset provided by doctors. The results at each phase have been evaluated with doctors in the relevant field.

The CNR value for MLPND has improved 95% compared to existing speckle reduction methods. The MI based registration with optimization techniques to reduce the computation time & monitor the growth of the liver diseases. The results retrieved from different machine learning techniques indicate that the proposed methods improve the image quality and overcome the fuzzy nature of dataset.