[A new algorithm for ultrasound image speckle suppression].

Ultrasound image has a lot of speckle noise, which brings great difficulties to the feature extraction, recognition and analysis. Especially in the edge extraction, the conventional extraction algorithms are difficult to achieve the desired results because of the speckle noise. To solve this problem, an algorithm based on the anisotropic diffusion equation is presented.

[Diagnosis of prostate cancer using SVM-based ultrasound images].

This paper presents a computer-aided diagnosis method for prostate cancer detection using Trans-rectal ultrasound(TRUS) images. Firstly, statistical texture analysis is implemented in every ROI in segmented prostate images. From each ROI, grey level difference vector features, edge-frequency features and texture features in frequency domain are constructed.

[Three domains filtering for medical ultrasound images denoising].

A filtering algorithm is proposed to deal with the medical ultrasonic image series in video format, which uses the relativity in spatial domain, gray value domain and temporal domain simultaneously. For each frame image, the relativity in spatial domain and gray value domain is utilized to construct the adaptive neighborhood first. Then the spatial weighted and gray value weighted filtering is performed in this neighborhood.

[Segmentation of the prostate ultrasound image based on an improved geodesic active contour model].

In this paper, we propose that, the need of the costly re-initialization procedure can be completely eliminated by using the variation formulation, thus increasing the speed of computing operations. The edge detecting function in the geodesic active contour model is improved by incorporating a prior knowledge. The accuracy of the segmentation algorithm can be enhanced by using the minimal variance.

[Breast tumor classification based on serial grayscale ultrasound images].

This paper proposes an algorithm of evaluating the compression depth, and then to extract four normalized mammary elasticity characteristic parameters with respect to the compression depth. The classification experiments show that these elasticity parameters have a good capability in determining whether the tumor is benign or malignant, and if combined with morphological parameters, the accuracy, sensitivity and specificity can be improved and increased to 95.19%, 98.

[Segmentation of breast tumor ultrasound images based on an improved C-V model].

This paper proposes an improved C-V model, which can avoid the step of re-initialization and simplify the formation of the initial level set function, thus the speed of segmentation can be accelerated greatly. Furthermore, based on the grayscale distribution characteristics of the breast tumor ultrasound images and on the hypothesis of piecewise constant in the C-V model, a semiautomatic segmentation flow has been presented, in which the rough contour is sketched first, and then a subimage would be obtained for the refined segmentation algorithm. This flow has improved not only the accuracy, but also the efficiency of the segmentation algorithm.

[Brain CT texture classification with tree-structured wavelet transform].

This paper proposes a tree-structured wavelet algorithm for brain CT texture feature extraction. This algorithm is used to analyse subimages automatically and to choose the optimum subimage for feature extraction. Experimental results show that this algorithm can improve the performance of brain CT texture feature extraction.

[Algorithm for automatic quantification of brain atrophy with computed tomography].

In this paper, a new, fully-automatic method for the quantification of brain atrophy based on CT volume data is put forward by taking advantage of the characteristics of cerebral CT images in combination with the prior medical knowledge. This algorithm has been verified through the calculation of 2388 cases of normal and brain atrophy subjects.