Speckle reducing diffusion for ultrasound image enhancement using the structural similarity image measure

An adaptive approach to enhancing images obtained from an array of ultrasonic transducer elements is proposed and evaluated. The basic algorithm is driven by a system of partial differential equations that 1) reduce speckle by way of the instantaneous (local) coefficient of variation and 2) force congruence with an anatomical model using a well-known perceptual quality metric. A differential form of the quality metric, the structural similarity image measure (SSIM), is derived and applied. This update mechanism registers the image data to the model, thus solving segmentation simultaneously with enhancement. The algorithm, called SSIM diffusion, is tested on a needle placement application in phlebotomy in which delineation of a vessel boundary is required. A group of images obtained from a portable C-scan ultrasonic sensor is used to evaluate the enhancement and segmentation algorithm. Comparisons to a standard speckle reducing diffusion algorithm show that the modelAbased SSIM diffusion superior enhancement with a 67% increase in measurable image quality over the original.