Echocardiographic image denoising and objective fidelity criteria estimation using entropy paramounted linear regression filter

The paper proposes a new filter called Entropy Paramounted Linear Regression Filter with the chief idea of speckle reduction in medical ultrasound images. The speckle pattern is to be eliminated to perquisite human explication of ultrasound images as it is the preprocessing step for many ultrasound image processing tasks. The proposed filter´s efficacy is demonstrated and compared with the median filter, based on the essential image quality metrics, specifically Peak Signal to Noise Ratio (PSNR), Root Mean Square Error (RMSE) and Correlation Coefficient(CC). The method is implemented on four-chamber view B-mode echocardiographic images and the proposed filter has the competence to illuminate the actual anatomical facts without degrading the edges.