Showing papers by "Heng-Da Cheng published in 2011"

Quantitative Measurement for Thyroid Cancer Characterization Based on Elastography

Abstract: OBJECTIVES The purpose of this study was to evaluate color thyroid elastograms quantitatively and objectively and select more effective features to differentiate benign from malignant thyroid nodules. METHODS The study was approved by the Ethics Committee of Harbin Medical University. A total of 125 cases (56 malignant and 69 benign) were analyzed in this retrospective study. The original color thyroid elastograms were transferred from the red-green-blue color space to the hue-saturation-value color space. The elasticity information was represented by the hue component of color elastograms. The lesion regions were delineated by radiologists, and statistical and textural features were extracted. Then the most effective and reliable features among them were selected by using a minimum redundancy-maximum relevance algorithm. The selected features were input to a support vector machine to differentiate benign from malignant thyroid nodules. RESULTS The classification accuracy was 93.6% when the hard area ratio and textural feature (energy) of the lesion region were used. The area under the receiver operating characteristic curve for the hard area ratio was higher than that for the strain ratio (0.97 versus 0.87; P < .01), and the area under the curve for the hard area ratio was also higher than that for the color score (0.97 versus 0.80; P < .001). The results also showed that the features were robust for lesion region delineation. CONCLUSIONS The hard area ratio is an important and quantitative metric for elastograms. Quantitative analysis of elastograms using computer-aided diagnostic techniques can improve diagnostic accuracy.

A novel image segmentation approach based on neutrosophic set and improved fuzzy c-means algorithm

Abstract: Image segmentation is an important component in image processing, pattern recognition and computer vision. Many segmentation algorithms have been proposed. However, segmentation methods for both noisy and noise-free images have not been studied in much detail. Neutrosophic set (NS), a part of neutrosophy theory, studies the origin, nature, and scope of neutralities, as well as their interaction with different ideational spectra. However, neutrosophic set needs to be specified and clarified from a technical point of view for a given application or field to demonstrate its usefulness. In this paper, we apply neutrosophic set and define some operations. Neutrosphic set is integrated with an improved fuzzy c-means method and employed for image segmentation. A new operation, α-mean operation, is proposed to reduce the set indeterminacy. An improved fuzzy c-means (IFCM) is proposed based on neutrosophic set. The computation of membership and the convergence criterion of clustering are redefined accordingly. We have conducted experiments on a variety of images. The experimental results demonstrate that the proposed approach can segment images accurately and effectively. Especially, it can segment the clean images and the images having different gray levels and complex objects, which is the most difficult task for image segmentation.

A fully automatic segmentation method for breast ultrasound images

Abstract: Breast cancer is the second leading cause of death of women worldwide. Accurate lesion boundary detection is important for breast cancer diagnosis. Since many crucial features for discriminating benign and malignant lesions are based on the contour, shape, and texture of the lesion, an accurate segmentation method is essential for a successful diagnosis. Ultrasound is an effective screening tool and primarily useful for differentiating benign and malignant lesions. However, due to inherent speckle noise and low contrast of breast ultrasound imaging, automatic lesion segmentation is still a challenging task. This research focuses on developing a novel, effective, and fully automatic lesion segmentation method for breast ultrasound images. By incorporating empirical domain knowledge of breast structure, a region of interest is generated. Then, a novel enhancement algorithm (using a novel phase feature) and a newly developed neutrosophic clustering method are developed to detect the precise lesion boundary. Neutrosophy is a recently introduced branch of philosophy that deals with paradoxes, contradictions, antitheses, and antinomies. When neutrosophy is used to segment images with vague boundaries, its unique ability to deal with uncertainty is brought to bear. In this work, we apply neutrosophy to breast ultrasound image segmentation and propose a new clustering method named neutrosophic l-means. We compare the proposed method with traditional fuzzy c-means clustering and three other well-developed segmentation methods for breast ultrasound images, using the same database. Both accuracy and time complexity are analyzed. The proposed method achieves the best accuracy (TP rate is 94.36%, FP rate is 8.08%, and similarity rate is 87.39%) with a fairly rapid processing speed (about 20 seconds). Sensitivity analysis shows the robustness of the proposed method as well. Cases with multiple-lesions and severe shadowing effect (shadow areas having similar intensity values of the lesion and tightly connected with the lesion) are not included in this study.

A novel quantitative measurement for thyroid cancer detection based on elastography

Abstract: At present, the widely methods used to evaluate elastograms clinically are color score and strain ratio. The color score is a qualitative measure estimated by radiologists, and its high subjectiveness may lead to error. Although the strain ratio is a quantitative method, the region selected to calculate the value is subjective and its accuracy is still quite low. A new effective, accurate, and quantitative metric using computer aided diagnosis (CAD) techniques is proposed in this paper. The statistical features and texture features are extracted from the lesion region on the elastogram. The important and reliable features are selected by using Minimum-Redundancy-Maximum-Relevance (mRMR) algorithm. The selected features were input to the SVM to classify the thyroid nodules. The experiment results confirm that the method is more accurate and robust than color score and strain ratio.

A novel noise removal method based on fractional anisotropic diffusion and subpixel approach

Abstract: Partial differential equations (PDE) have been successfully and widely applied to image processing and computer vision. Anisotropic diffusion is an approach to remove noise based on nonlinear PDE. Many anisotropic methods have been studied; however, they suffer two major drawbacks: blurring and staircasing effects degrading the performance of noise removal filters. To overcome such problems, in this paper, a novel and efficient method for image denoising based on fractional-order anisotropic diffusion and subpixel approach is proposed. Numerical computation is implemented by using the subpixel fractional partial difference (SFPD) approach to increase the flexibility and accuracy. The experimental results demonstrate that the proposed approach can achieve higher signal-to-noise ratio (SNR) and its performance is much better than that of the existing filters.

Breast ultrasound image segmentation based on particle swarm optimization and the characteristics of breast tissue

Abstract: Breast cancer occurs in over 8% of women during their lifetime, and is the leading cause of death among women. Sonography is superior to mammography because it has the ability to detect focal abnormalities in the dense breasts and has no side-effect. In this paper, we propose a novel automatic segmentation algorithm based on the characteristics of breast tissue and eliminating particle swarm optimization (EPSO) clustering analysis. The characteristics of mammary gland in breast ultrasound (BUS) images are analyzed and utilized, and a method based on step-down threshold technique is employed to locate the mammary gland area. The EPSO clustering algorithm utilizes the idea of "survival of the superior and weeding out the inferior". The experimental results demonstrate that the proposed approach can segment BUS image with high accuracy and low computational time. The EPSO clustering method reduces the computational time by 32.75% compared with the standard PSO clustering algorithm. The proposed approach would find wide applications in automatic lesion classification and computer aided diagnosis (CAD) systems of breast cancer.

A novel approach to image thresholding based on 2d homogeneity histogram and maximum fuzzy entropy

Abstract: Image thresholding is an important topic for image processing, pattern recognition and computer vision. Fuzzy set theory has been successfully applied to many areas, and it is generally believed that image processing bears some fuzziness in nature. In this paper, we employ the newly proposed 2D homogeneity histogram (homogram) and the maximum fuzzy entropy principle to perform thresholding. We have conducted experiments on a variety of images. The experimental results demonstrate that the proposed approach can select the thresholds automatically and effectively. Especially, it not only can process "clean" images, but also can process images with different kinds of noises and images with multiple kinds of noise well without knowing the type of the noise, which is the most difficult task for image thresholding. It will be useful for applications in computer vision and image processing.