Robustness Analysis of Texture Features with Different Beamforming Techniques

Texture features are often used on ultrasound images in various applications to give forth important clinical information. Recently, many beamforming techniques have been developed to provide better resolution and contrast in the final image. It is currently unknown, however, how these different techniques may also alter pixel intensity spatial distribution, known as texture. We provide here a robustness analysis of first and second order texture features using six beamforming techniques, on both phantom and in vivo musculoskeletal images. We show that second order texture features are more robust compared to first order features, especially when considering in vivo musculoskeletal images.