Showing papers by "Heng-Da Cheng published in 2010"
TL;DR: Generally, a CAD system consists of four stages: preprocessing, segmentation, feature extraction and selection, and classification, and their advantages and disadvantages are discussed.
628 citations
TL;DR: In this article, neutrosophy is applied to image processing by defining a neutrosophic domain, which is described by three subsets T, I, and F. And then, the watershed algorithm is employed to perform segmentation of the image in the neutro-ophoric domain. And the experiments show that the proposed method can get better results comparing with that obtained by the existing methods.
183 citations
TL;DR: A novel fully automatic classification method for BUS images is proposed which is very robust to the segmentation of BUS images, and very effective and useful for classifying breast tumors.
151 citations
TL;DR: The experimental results demonstrate that the proposed novel level set-based active contour model for breast ultrasound (BUS) image segmentation can model the BUS images well, be robust to noise, and segment theBUS images accurately and reliably.
147 citations
TL;DR: A novel CAD system based on fuzzy support vector machine to automatically detect and classify mass using ultrasound (US) images and the experimental results show that the proposed system greatly improves the five objective measurements and the area under the ROC curve compared with those of other classification methods, and radiologist assessments.
114 citations
TL;DR: Comparisons of the experimental results show that the proposed FSFPD can preserve edges and structural details of ultrasound images well while removing speckle noise and demonstrate that the discrimination rate of breast cancers has been highly improved after employing the proposed method.
37 citations
TL;DR: A novel approach to automatic selecting wavelet bases and parameters which is an important and essential issue for implementing wavelet algorithms is proposed and it is superior to some other existing methods.
35 citations
TL;DR: This paper employs neutrosophy and develops a fully automatic algorithm for BUS image segmentation that integrates two conflicting opinions about Speckle in ultrasound image: speckle is noise and speckel includes pattern information.
Abstract: Breast cancer is one of the leading cancers of women. Ultrasound is often used for breast cancer diagnosis because it is harmless, portable, and low-cost. However, the segmentation of breast ultrasound (BUS) images is a difficult task due to their low contrast and speckle noise. Neutrosophy studies the origin, nature, and scope of neutralities and their interactions with different ideational spectra. It is a new philosophy to extend fuzzy logic and is the basis of neutrosophic logic, neutrosophic probability theory, neutrosophic set theory, and neutrosophic statistics. In this paper, we employ neutrosophy and develop a fully automatic algorithm for BUS image segmentation. By using neutrosophy, we integrate two conflicting opinions about speckle in ultrasound image: speckle is noise and speckle includes pattern information. The experiments demonstrate that the proposed approach is accurate, effective, and robust.
28 citations
DOI•
01 Jan 2010TL;DR: This dissertation applies neutrosophy to three types of image segmentation: gray level images, breast ultrasound images, and color images and shows the advantage of using neutrosophical theory.
Abstract: Neutrosophy studies the origin, nature, scope of neutralities, and their interactions with different ideational spectra. It is a new philosophy that extends fuzzy logic and is the basis of neutrosophic logic, neutrosophic probability, neutrosophic set theory, and neutrosophic statistics.
Because the world is full of indeterminacy, the imperfection of knowledge that a human receives/observes from the external world also causes imprecision. Neutrosophy introduces a new concept , which is the representation of indeterminacy. However, this theory is mostly discussed in physiology and mathematics. Thus, applications to prove this theory can solve real problems are needed.
Image segmentation is the first and key step in image processing. It is a critical and essential component of image analysis and pattern recognition. In this dissertation, I apply neutrosophy to three types of image segmentation: gray level images, breast ultrasound images, and color images. In gray level image segmentation, neutrosophy helps reduce noise and extend the watershed method to normal images. In breast ultrasound image segmentation, neutrosophy integrates two controversial opinions about speckle: speckle is noise versus speckle includes pattern information. In color image segmentation, neutrosophy integrates color and spatial information, global and local information in two different color spaces: RGB and CIE (L*u*v*), respectively. The experiments show the advantage of using neutrosophy.
22 citations
TL;DR: It is concluded that the proposed CAD method is more helpful for the junior radiologists than for the senior ones and it also showed the advantage of decreasing interobserver variability.
Abstract: For a successful computer-aided diagnosis (CAD) approach, investigating the benefit of the output for radiologist diagnosis is as important as developing the computer algorithm itself. To evaluate the accuracy and the interobserver variability of two newly developed CAD algorithms for breast mass discrimination, eight radiologists with varied experience in breast ultrasonography (US) independently reviewed the lesions according to Breast Imaging Reporting and Data System (BI-RADS)-US. They interpreted the original ultrasound images, provided a final assessment category to indicate the probability of malignancy and then made a further diagnosis using the images processed by the proposed CAD algorithms. The receiver operating characteristic (ROC) curve and Cohen's kappa statistics were employed to evaluate the effect of the CAD algorithms on radiologist diagnoses. By using the proposed CAD approach, the quality of the images was improved and more information was provided to the observers. With the processed images, the areas under the ROC (Az) of each reader (0.86 approximately 0.89) were greater than those with the original ultrasound images (0.81 approximately 0.86) and all the radiologists improved their performance significantly (p 0.05). The Az values of the junior radiologists with CAD were comparable to those of the senior radiologists. Cohen's kappa statistics showed that better interobserver agreement was obtained by using the processed images. We conclude that the proposed CAD method is more helpful for the junior radiologists than for the senior ones and it also showed the advantage of decreasing interobserver variability.
19 citations
TL;DR: The results demonstrate the promising performance of the proposed speckle reduction algorithm in distinguishing malignant from benign breast lesions which will be useful for breast cancer diagnosis.
03 Dec 2010
TL;DR: A novel segmentation method for BUS images which is fully automatic without any human intervention is proposed by incorporating empirical knowledge and characteristics of breast structure and a ROI is generated automatically.
Abstract: Because of ultrasound images' low quality, fully automated segmentation of breast ultrasound (BUS) image is a challenging task. In this paper, a novel segmentation method for BUS images which is fully automatic without any human intervention is proposed. By incorporating empirical knowledge and characteristics of breast structure, a ROI is generated automatically. Then two newly proposed lesion features: phase in max-energy orientation (PMO) and radial distance (RD), combined with the commonly used intensity and texture feature, are extracted. Then the new feature set is used to distinguish lesion region from the background by a trained ANN. The proposed segmentation method was tested on a BUS database composed of 60 cases. We use the manually outlined lesions by an experienced radiologist as the golden standard and evaluated the performance by both area error metrics and boundary error metrics. Quantitative results demonstrate the efficiency of the proposed fully automatic BUS segmentation method.
29 Aug 2010
TL;DR: Experimental results show that the proposed novel approach for human action recognition in a video sequence with whatever length, which requires no annotations and no pre-temporal-segmentations, is effective to recognize both isolated actions and continuous actions no matter how long a videosequence is.
Abstract: In recent years, most action recognition researches focuson isolated action analysis for short videos, but ignore theissue of continuous action recognition for a long videosequence in real time. This paper proposes a novelapproach for human action recognition in a video sequencewith whatever length, which, unlike previous works,requires no annotations and no pre-temporal-segmentations.Based on the bag of words representation and theprobabilistic Latent Semantic Analysis (pLSA) model, therecognition process goes frame by frame and the decisionupdates from time to time. Experimental results show thatthis approach is effective to recognize both isolated actionsand continuous actions no matter how long a videosequence is. This is very useful for real time applicationslike video surveillance. Besides, we also test our approachfor real time temporal video segmentation and real time keyframe extraction.
TL;DR: The proposed CAD method has potential to be a good aid to radiologists in distinguishing malignant breast solid masses from benign ones and should be used to improve radiologists’ accuracy.
Abstract: The objective of this study is to retrospectively investigate whether using the newly developed algorithms would improve radiologists’ accuracy for discriminating malignant masses from benign ones on ultrasonographic (US) images. Five radiologists blinded to the histological results and clinical history independently interpreted 226 cases according to the sonographic lexicon of the fourth edition of the Breast Imaging Reporting and Data System and assigned a final assessment category to indicate the probability of malignancy. For each case, each radiologist provided three diagnoses: first with the original images, subsequently with the assistant of the resulting images processed by the proposed CAD algorithms which are called as processed images, and another using the processed images only. Observers’ malignancy rating data were analyzed with the receiver operating characteristic (ROC) curve. For reading only with the processed images, areas under the ROC curve (A
z) of each reader (0.863, 0.867, 0.859, 0.868, 0.878) were better than that with the original images (0.772, 0.807, 0.796, 0.828, 0.846), difference of the average A
z between the twice reading was significant (p < 0.001). Compared with the results single used processed images, A
z of utilizing the combined images were increased (0.866, 0.885, 0.872, 0.894, 0.903), but the difference is not statistically significant (p = 0.081). The proposed CAD method has potential to be a good aid to radiologists in distinguishing malignant breast solid masses from benign ones.
03 Dec 2010
TL;DR: The experimental results demonstrate that the proposed novel fuzzy anisotropic diffusion approach for speckle reduction and contrast enhancement can preserve the edges and enhance the structural details of the BUS images well while removingSpeckle noise.
Abstract: Two major problems of ultrasound imaging are low-contrast and speckle noise. Traditionally, before speckle reduction, an enhancement algorithm is employed to improve the quality of the image. However, the noise is enhanced as well. To overcome this drawback, we introduce a novel fuzzy anisotropic diffusion approach for speckle reduction and contrast enhancement. Maximum fuzzy entropy principle is used to map the image from space domain to fuzzy domain. Then, fractional-order partial differential equation is used to remove noise and to preserve edges. Finally, the subpixel operator is utilized as a tuning parameter to achieve the optimal result. We test the proposed method on synthetic and real breast ultrasound (BUS) images. The experimental results demonstrate that the proposed method can preserve the edges and enhance the structural details of the BUS images well while removing speckle noise.
03 Dec 2010
TL;DR: A novel mask based shape matching method for action recognition that does not need human detection or segmentation, and it can be used in both clean and crowed backgrounds is proposed.
Abstract: This paper discusses the task of human action detection in crowded videos. First, we propose a novel mask based shape matching method for action recognition. Our method does not need human detection or segmentation, and it can be used in both clean and crowed backgrounds. Next, shape and flow based features are combined due to their complementary nature. For each action, a binary sequence is used as the template for both shape and flow matching. For a testing sequence and a template sequence, dynamic time warping technique is first applied for time alignment, then shape and flow matching distances are computed between matched frames. We test our algorithm on the CMU dataset and achieve an encouraging performance.
TL;DR: A novel density gradient-based method that locates the edges using the density gradients of image pixels instead of the color/intensity gradients and can be applied more effectively to all types of images: gray level, color and multispectral images.
Abstract: The intensity gradient-based methods are commonly used in edge detection of images. However, these methods are not very suitable for color images and they change the shapes of object contours in large scales. In this paper, a novel density gradient-based method is proposed to solve these problems. The proposed method locates the edges using the density gradients of image pixels instead of the color/intensity gradients. Comparing with the traditional methods, the proposed approach can be applied more effectively to all types of images: gray level, color and multispectral images; and the detection results are invariant to the detection scales as well. It may find wide applications in computer vision and image processing.
TL;DR: This work presents a novel noise removal algorithm based on fuzzy logic and anisotropic diffusion theory that has the advantage of maximizing noise reduction and preserving fine details of the images.
Abstract: Anisotropic diffusion is widely used for noise reduction. The performance of anisotropic diffusion, in general, depends on the shape of the energy surface. The partial differential equation model is established and analyzed in the continuous domain while is implemented in the dis- crete domain. Therefore, the anisotropic diffusion bears some fuzziness due to the approximation. We present a novel noise removal algorithm based on fuzzy logic and anisotropic diffusion theory. The experimen- tal results demonstrate that the proposed method has the advantage of maximizing noise reduction and preserving fine details of the images. In addition, the method can enhance the contrast of the images well. C 2010