Automated breast cancer detection and classification using ultrasound images: A survey

Article history: Received 9 September 2008 Received in revised form 16 April 2009 Accepted 14 May 2009

Automated breast cancer detection and classification using ultrasound images A survey

A new speckle reduction method, i.e., Laplacian pyramid-based nonlinear diffusion (LPND), is proposed for medical ultrasound imaging. With this method, speckle is removed by nonlinear diffusion filtering of bandpass ultrasound images in Laplacian pyramid domain. For nonlinear diffusion in each pyramid layer, a gradient threshold is automatically determined by a variation of median absolute deviation (MAD) estimator. The performance of the proposed LPND method has been compared with that of other speckle reduction methods, including the recently proposed speckle reducing anisotropic diffusion (SRAD) and nonlinear coherent diffusion (NCD). In simulation and phantom studies, an average gain of 1.55 dB and 1.34 dB in contrast-to-noise ratio was obtained compared to SRAD and NCD, respectively. The visual comparison of despeckled in vivo ultrasound images from liver and carotid artery shows that the proposed LPND method could effectively preserve edges and detailed structures while thoroughly suppressing speckle. These preliminary results indicate that the proposed speckle reduction method could improve image quality and the visibility of small structures and fine details in medical ultrasound imaging

https://dr.ntu.edu.sg/bitstream/10220/6337/1/nonlinear diffusion in laplacian pyramid domain for ultrasonic speckle reduction.pdf

Nonlinear Diffusion in Laplacian Pyramid Domain for Ultrasonic Speckle Reduction

Ultrasound image enhancement: A review

Probability density difference-based active contour for ultrasound image segmentation

https://www.eecs.wsu.edu/~shira/papers/chen02.pdf

Aggressive region growing for speckle reduction in ultrasound images

Acoustic holography is a transmission mode imaging technique which was first proposed in the 1970s. As with optical holography, an image is obtained using coherent interference of the transmitted acoustic signal with a reference signal. The interference pattern is illuminated with a laser, and the resulting image is digitized. However, since image reconstruction is performed optically, acoustic holography introduces a focusing problem characteristic of optical systems. Ideally, an image is focused on tissues at a given depth along the optical axis—that is, in one planar slice of the object. In practice, the image is focused over a range of depths so that objects at different depths are blurred but still visible. In this paper, we consider several postprocessing algorithms developed to improve images obtained using an acoustic holography system. First, a focus measure technique is used to determine when the object of interest is best focused. Second, a technique called depth from focus is used to determine the depth of an object. Third, a technique is developed to increase the ‘‘in focus’’ interval, or focusing range. These techniques will be discussed and imaging results will be presented. [Work supported by the National Science Foundation and the Carl M. Hansen Foundation.]

Focus‐directed processing of acoustic holography images

Speckle noise is present in all conventional ultrasound images, and complicates the process of diagnosis as it can mask small but diagnostically significant features. Speckle reduction techniques can be applied prior to image formation [e.g., Chen et al., J. Ultrasound Imag. 18(2), 122–139 (1996)] or after image formation. Post‐formation techniques can be implemented in software, whereas pre‐formation techniques generally require hardware modifications. The approach described here is applied after image formation, and consists of two steps. In the first step, small ‘‘seed’’ regions are defined around each pixel in the image, and a homogeneity criterion is used to guide a procedure which identifies the maximal‐size homogeneous region containing the pixel of interest. Once determined, this region is smoothed using a truncated arithmetic mean filter. Results on synthetic and real images demonstrate that this method preserves the sharpness of image edges yet reduces speckle noise, and compares well with weigh...

Ruming Yin

Papers

Aggressive region growing for speckle reduction in ultrasound images

Focus‐directed processing of acoustic holography images

Aggressive region growing filtering for speckle reduction in ultrasound images