Jinshan Tang

Computer-Aided Detection and Diagnosis of Breast Cancer With Mammography: Recent Advances

Breast cancer is the second-most common and leading cause of cancer death among women. It has become a major health issue in the world over the past 50 years, and its incidence has increased in recent years. Early detection is an effective way to diagnose and manage breast cancer. Computer-aided detection or diagnosis (CAD) systems can play a key role in the early detection of breast cancer and can reduce the death rate among women with breast cancer. The purpose of this paper is to provide an overview of recent advances in the development of CAD systems and related techniques. We begin with a brief introduction to some basic concepts related to breast cancer detection and diagnosis. We then focus on key CAD techniques developed recently for breast cancer, including detection of calcifications, detection of masses, detection of architectural distortion, detection of bilateral asymmetry, image enhancement, and image retrieval.

Image enhancement using a contrast measure in the compressed domain

An image enhancement algorithm for images compressed using the JPEG standard is presented. The algorithm is based on a contrast measure defined within the discrete cosine transform (DCT) domain. The advantages of the psychophysically motivated algorithm are 1) the algorithm does not affect the compressibility of the original image because it enhances the images in the decompression stage and 2) the approach is characterized by low computational complexity. The proposed algorithm is applicable to any DCT-based image compression standard, such as JPEG, MPEG 2, and H. 261.

A multi-direction GVF snake for the segmentation of skin cancer images

A multi-direction gradient vector flow (GVF) snake-based scheme is proposed in this paper for the segmentation of skin cancer images. Unlike the traditional anisotropic diffusion (AD) filter, which has many disadvantages such as sensitivity to noise, a new AD filter has been developed to remove the noise. The proposed AD filter uses adaptive threshold selection and a new gradient computation method, which is robust to noise and can effectively remove the hairs. After the noise is removed from the skin cancer image, the image is segmented using a multi-direction GVF snake. The multi-direction GVF snake extends the single direction GVF snake and traces the boundary of the skin cancer even if there are other objects near the skin cancer region. Experiments performed on 11 cancer images show the effectiveness of the proposed algorithm.

A Direct Image Contrast Enhancement Algorithm in the Wavelet Domain for Screening Mammograms

In breast cancer diagnosis, the radiologists mainly use their eyes to discern cancer when they screen the mammograms. However, in many cases, cancer is not easily detected by the eyes because of the bad imaging conditions. In order to improve the correct diagnosis rate of cancer, image-enhancement technology is often used to enhance the image and aid the radiologists. In this paper, we develop a new image-enhancement technology in the wavelet domain for radiologists to screen mammograms. The new image-enhancement algorithm has several advantages. First, the proposed image-enhancement technology modifies a multiscale measure which matches the human vision system and thus the enhanced images have better visual quality; second, the image enhancement is accomplished in the wavelet domain and thus it can save time if the image is compressed by wavelet transform based methods; third, the end users can adjust the enhancement by manipulating a single parameter. Experiments were performed on mammograms and the results are progressive.

Image enhancement in the JPEG domain for people with vision impairment

An image enhancement algorithm for low-vision patients was developed for images compressed using the JPEG standard. The proposed algorithm enhances the images in the discrete cosine transform domain by weighting the quantization table in the decoder. Our specific implementation increases the contrast at all bands of frequencies by an equal factor. The enhancement algorithm has four advantages: 1) low computational cost; 2) suitability for real-time application; 3) ease of adjustment by end-users (for example, adjusting a single parameter); and 4) less severe block artifacts as compared with conventional (post compression) enhancements. Experiments with visually impaired patients show improved perceived image quality at moderate levels of enhancement but rejection of artifacts caused by higher levels of enhancement.

Vessel boundary tracking for intravital microscopy via multiscale gradient vector flow snakes

Due to movement of the specimen, vasodilation, and intense clutter, the intravital location of a vessel boundary from video microscopy is a difficult but necessary task in analyzing the mechanics of inflammation and the structure of the microvasculature. This paper details an active contour model for vessel boundary detection and tracking. In developing the method, two innovations are introduced. First, the B-spline model is combined with the gradient vector flow (GVF) external force. Second, a multiscale gradient vector flow (MSGVF) is employed to elude clutter and to reliably localize the vessel boundaries. Using synthetic experiments and video microscopy obtained via transillumination of the mouse cremaster muscle, we demonstrate that the MSGVF approach is superior to the fixed-scale GVF approach in terms of boundary localization. In each experiment, the fixed scale approach yielded at least a 50% increase in root mean squared error over the multiscale approach. In addition to delineating the vessel boundary so that cells can be detected and tracked, we demonstrate the boundary location technique enables automatic blood flow velocity computation in vivo.

Mass Classification in Mammograms Using Selected Geometry and Texture Features, and a New SVM-Based Feature Selection Method

Masses are the primary indications of breast cancer in mammograms, and it is important to classify them as benign or malignant. Benign and malignant masses differ in geometry and texture characteristics. However, not every geometry and texture feature that is extracted contributes to the improvement of classification accuracy; thus, to select the best features from a set is important. In this paper, we examine the feature selection methods for mass classification. We integrate a support vector machine (SVM)-based recursive feature elimination (SVM-RFE) procedure with a normalized mutual information feature selection (NMIFS) to avoid their singular disadvantages (the redundancy in the selected features of the SVM-RFE and the unoptimized classifier for the NMIFS) while retaining their advantages, and we propose a new feature selection method, which is called the SVM-RFE with an NMIFS filter (SRN). In addition to feature selection, we also study the initialization of mass segmentation. Different initialization methods are investigated, and we propose a fuzzy c-means (FCM) clustering, with spatial constraints as the initialization step. In the experiments, 826 regions of interest (ROIs) from the Digital Database for Screening Mammography were used. All 826 were used in the classification experiments, and 413 ROIs were used in the feature selection experiments. Different feature selection methods, including F-score, Relief, SVM-RFE, SVM-RFE with a minimum redundancy-maximum relevance (mRMR) filter [SVM-RFE (mRMR)], and SRN, were used to select features and to compare mass classification results using the selected features. In the classification experiments, the linear discriminant analysis and the SVM classifiers were investigated. The accuracy that is obtained with the SVM classifier using the selected features obtained by the F-score, Relief, SVM-RFE, SVM-RFE (mRMR), and SRN methods are 88%, 88%, 90%, 91%, and 93%, respectively, with a tenfold cross-validation procedure, and 91%, 89%, 92%, 92%, and 94%, respectively, with a leave-one-out (LOO) scheme. We also compared the performance of the different feature selection methods using the receiver operating characteristic analysis and the areas under the curve (AUCs). The AUCs for the F-score, Relief, SVM-RFE, SVM-RFE (mRMR), and SRN methods are 0.9014, 0.8916, 0.9121, 0.9236, and 0.9439, respectively, with a tenfold cross-validation procedure, and are 0.9312, 0.9178, 0.9324, 0.9413, and 0.9615, respectively, with a LOO scheme. Both the accuracy and AUC values show that the proposed SRN feature selection method has the best performance. In addition to the accuracy and the AUC, we also measured the significance between the two best feature selection methods, i.e., the SVM-RFE (mRMR) and the proposed SRN method. Experimental results show that the proposed SRN method is significantly more accurate than the SVM-RFE (mRMR) (p = 0.011).

A contrast based image fusion technique in the DCT domain

Abstract This paper studies image fusion techniques in the discrete cosine transform (DCT) domain. A new image fusion technique based on a contrast measure defined in the DCT domain is presented. The performance of our contrast measure based technique is analyzed and compared with other image fusion techniques. Experimental results show that there is no difference in visual quality between the fused image obtained by our algorithm and that obtained by a wavelet transform based image fusion technique. But because our algorithm is carried out in the DCT domain, it is time-saving and simpler when the fused image needs to be saved or transmitted in JPEG format or when the images to be fused were saved in JPEG format.

Surface extraction and thickness measurement of the articular cartilage from MR images using directional gradient vector flow snakes

The accuracy of the surface extraction of magnetic resonance images of highly congruent joints with thin articular cartilage layers has a significant effect on the percentage errors and reproducibility of quantitative measurements(e.g., thickness and volume) of the articular cartilage. Traditional techniques such as gradient-based edge detection are not suitable for the extraction of these surfaces. This paper studies the extraction of articular cartilage surfaces using snakes, and a gradient vector flow (GVF)-based external force is proposed for this application. In order to make the GVF snake more stable and converge to the correct surfaces, directional gradient is used to produce the gradient vector flow. Experimental results show that the directional GVF snake is more robust than the traditional GVF snake for this application. Based on the newly developed snake model, an articular cartilage surface extraction algorithm is developed. Thickness is computed based on the surfaces extracted using the proposed algorithm. In order to make the thickness measurement more reproducible, a new thickness computation approach, which is called T-norm,is introduced. Experimental results show that the thickness measurement obtained by the new thickness computation approach has better reproducibility than that obtained by the existing thickness computation approaches

3D Protein structure prediction with genetic tabu search algorithm

BackgroundProtein structure prediction (PSP) has important applications in different fields, such as drug design, disease prediction, and so on. In protein structure prediction, there are two important issues. The first one is the design of the structure model and the second one is the design of the optimization technology. Because of the complexity of the realistic protein structure, the structure model adopted in this paper is a simplified model, which is called off-lattice AB model. After the structure model is assumed, optimization technology is needed for searching the best conformation of a protein sequence based on the assumed structure model. However, PSP is an NP-hard problem even if the simplest model is assumed. Thus, many algorithms have been developed to solve the global optimization problem. In this paper, a hybrid algorithm, which combines genetic algorithm (GA) and tabu search (TS) algorithm, is developed to complete this task.ResultsIn order to develop an efficient optimization algorithm, several improved strategies are developed for the proposed genetic tabu search algorithm. The combined use of these strategies can improve the efficiency of the algorithm. In these strategies, tabu search introduced into the crossover and mutation operators can improve the local search capability, the adoption of variable population size strategy can maintain the diversity of the population, and the ranking selection strategy can improve the possibility of an individual with low energy value entering into next generation. Experiments are performed with Fibonacci sequences and real protein sequences. Experimental results show that the lowest energy obtained by the proposed GATS algorithm is lower than that obtained by previous methods.ConclusionsThe hybrid algorithm has the advantages from both genetic algorithm and tabu search algorithm. It makes use of the advantage of multiple search points in genetic algorithm, and can overcome poor hill-climbing capability in the conventional genetic algorithm by using the flexible memory functions of TS. Compared with some previous algorithms, GATS algorithm has better performance in global optimization and can predict 3D protein structure more effectively.