Showing papers by "Yi Guo published in 2015"
TL;DR: It’s revealed in the experimental results that classifications of BUS images with the proposed PCBP texture descriptor are efficient and robust, which may be potentially useful for breast ultrasound CADs.
Abstract: Classification of breast ultrasound (BUS) images is an important step in the computer-aided diagnosis (CAD) system for breast cancer. In this paper, a novel phase-based texture descriptor is proposed for efficient and robust classifiers to discriminate benign and malignant tumors in BUS images. The proposed descriptor, namely the phased congruency-based binary pattern (PCBP) is an oriented local texture descriptor that combines the phase congruency (PC) approach with the local binary pattern (LBP). The support vector machine (SVM) is further applied for the tumor classification. To verify the efficiency of the proposed PCBP texture descriptor, we compare the PCBP with other three state-of-art texture descriptors, and experiments are carried out on a BUS image database including 138 cases. The receiver operating characteristic (ROC) analysis is firstly performed and seven criteria are utilized to evaluate the classification performance using different texture descriptors. Then, in order to verify the robustness of the PCBP against illumination variations, we train the SVM classifier on texture features obtained from the original BUS images, and use this classifier to deal with the texture features extracted from BUS images with different illumination conditions (i.e., contrast-improved, gamma-corrected and histogram-equalized). The area under ROC curve (AUC) index is used as the figure of merit to evaluate the classification performances. The proposed PCBP texture descriptor achieves the highest values (i.e. 0.894) and the least variations in respect of the AUC index, regardless of the gray-scale variations. It’s revealed in the experimental results that classifications of BUS images with the proposed PCBP texture descriptor are efficient and robust, which may be potentially useful for breast ultrasound CADs.
64 citations
Patent•
27 May 2015
TL;DR: In this article, an automatic extraction method of regions of interest in three-dimensional breast full-volume images (ABVS) was proposed, which consists of the following steps: processing the continuous cross-section two-dimensional images in 3-dimensional ABVS images by using a maximum direction-based phase information method to obtain the candidate region of interest on each cross-sectional image; removing the unrelated regions according to the prior knowledge such as the continuity and position characteristic of breast tumor on the 2D images; obtaining the shape and texture features of the residual suspected tumor regions, input
Abstract: The invention belongs to the field of image processing, and particularly relates to an automatic extraction method of regions of interest in three-dimensional breast full-volume images (ABVS). The method comprises the following steps: processing the continuous cross section two-dimensional images in three-dimensional ABVS images by using a maximum direction-based phase information method to obtain the candidate regions of interest on each cross section image; removing the unrelated regions according to the prior knowledge such as the continuity and position characteristic of breast tumor on the two-dimensional cross section images; obtaining the shape and texture features of the residual suspected tumor regions, inputting the shape and texture shapes to a two-valued logistic regression classifier to obtain the probability of each region becoming tumor and selecting the region with the maximum probability as the tumor region; obtaining the minimum ellipsoid comprising the region of interest according to the selected region to serve as the region of interest. The automatic extraction method provided by the invention can be used for realizing the automatic extraction of tumor regions of interest in the three-dimensional ABVS images, obtaining the correct positions of tumor, decreasing the workload of the manual operation and providing important reference to further tumor detection.
18 citations
01 Oct 2015
TL;DR: The proposed segmentation method can identify fine and tiny vessel structures, as well as distinguish large AVM nidus in one framework, and performs better than the other state-of-the-art methods in the segmentation of DSA images.
Abstract: Digital subtraction angiography (DSA) plays an important role in the diagnosis and therapy of vascular diseases. Segmentation of nidus and vessel in DSA images is an essential step in the diagnosis of arteriovenous malformations (AVM). In this paper, a novel segmentation method based on the global and iterative local thresholding is proposed to segment the nidus and vessel in DSA images. Firstly, the original image is divided into proper subimages. For each subimage, Ostu's method is primarily used and pixels are classified into two groups by the threshold. Then, according to the variance of the subimage intensities, the mean or median values of two groups are calculated to sort the pixels into three classes. These three classes represent the dark AVM and vessel, the bright background and undetermined regions in the original DSA image. The first two classes are determined directly and will not be processed further. The undetermined regions are processed in the next iteration to segment tiny vessels until the thresholds between two iterations are less than a preset one. Finally, all classes are combined to create the segmentation result. We test this method on DSA images of the AVM. Experimental results show that the proposed method performs better than the other state-of-the-art methods in the segmentation of DSA images. The proposed method can identify fine and tiny vessel structures, as well as distinguish large AVM nidus in one framework.
4 citations