Search

Haze is one of the major factors that degrade outdoor images, and dehazing becomes an important issue in many applications. In order to address the problems of being unsmooth and the absence of neighbor information for the transmission estimation under Dark Channel Prior (DCP) framework, we proposed a new improved method using Kernel Regression Model (KRM) on local neighbor data. Firstly, the initial transmission in atmospheric light model is estimated by DCP. Secondly, the transmission is refined according to KRM. Experimental results on synthetic and real images show that our method can address this problem and has better dehazing results than several state-of-the-art methods.

Clustering gene expression data are an important problem in bioinformatics because understanding which genes behave similarly can lead to the discovery of important biological information. Many clustering methods have been used in the field of gene clustering. This paper proposed a new method for gene expression data clustering based on an improved expectation maximization(EM) method of multivariate Gaussian mixture models. To solve the problem of over-reliance on the initialization, we propose a remove and add initialization for the classical EM, and make a random perturbation on the solution before continuing EM iterations. The number of clusters is estimated with the Quasi Akaike’s information criterion in this paper. The improved EM method is tested and compared with some other clustering methods; the performance of our clustering algorithm has been extensively compared over several simulated and real gene expression data sets. Our results indicated that improved EM clustering method is superior than other clustering algorithms and can be widely used for gene clustering.

Kernel density estimators (KDE) used for many medical image applications only consider the intensity information of each pixel or its neighbors without the ability of expressing the structure and shape of tissues and organs, and they suffer from boundary bias problem. In this paper, we propose a new first-order kernel density estimation (FOKDE) method for 1D intensity information and 2D spatial information of medical image in two steps. First, the FOKDE of intensity information is estimated and applied to medical image segmentation with the multi-thresholding algorithm. Second, we estimate the FOKDE of spatial information on the initial segmentation, which can express the structure and shape of organs and tissues. In order to evaluate the FOKDE and KDE of the 2D spatial information, we apply them to medical image segmentation with the hill-climbing strategy. Density estimation experiments and segmentation application results on the simulated dataset and real abdomen CT images show us that the FOKDE has smaller boundary bias than the KDE, and that it can estimate the structure and shape of tissues and organs with spatial information effectively.

Clustering gene expression data is an important research topic in bioinformatics because knowing which genes act similarly can lead to the discovery of important biological information. Many clustering algorithms have been used in the field of gene clustering. The multivariate Gaussian mixture distribution function was frequently used as the component of the finite mixture model for clustering, however the clustering cannot be restricted to the normal distribution in the real dataset. In order to make the cluster algorithm strong adaptability, this paper proposes a new scheme for clustering gene expression data based on the multivariate elliptical contoured mixture models (MECMMs). To solve the problem of over-reliance on the initialization, we propose an improved expectation maximization (EM) algorithm by adding and deleting initial value for the classical EM algorithm, and the number of clusters can be treated as a known parameter and inferred with the QAIC criterion. The improved EM algorithm based on the MECMMs is tested and compared with some other clustering algorithms, the performance of our clustering algorithm has been extensively compared over several simulated and real gene expression datasets. Our results indicated that improved EM clustering algorithm is superior to the classical EM algorithm and the support vector machines (SVMs) algorithm, and can be widely used for gene clustering.

Rough-set based multimodal histogram thresholding technique is effective for medical image segmentation. However, it is difficult to obtain the significant peaks and valleys of the roughness measure. Moreover, it is sensitive to the noise for medical image. In this paper, we proposed a new medical image segmentation method using rough set theory and local polynomial regression model to address those disadvantages. Firstly, compute histogram of image intensity information and histon of image intensity and spatial information. Secondly, use the local polynomial regression model to smooth the histogram and histon. The smoothed histogram correlates with lower approximation and the smoothed histon correlates with upper approximation. Lastly, rough measure is calculated with the lower and upper approximations. And then, multimodal thresholding method is applied to medical image segmentation. The local polynomial regression model can obtain a smooth rough measure and has two advantages: first, it is easy to find the real peaks and valleys of the smoothed roughness measure to segment medical image; second, the local polynomial regression reduces the effect of noise and can find the thresholds correctly. The proposed approach is compared with the histogram based approach, histon based approach, and rough set with the histogram and histon based approach. Experimental results demonstrate that our approach can find the real peaks and valleys more easily and yields better segmentation results than those of other three methods.

Objective: To evaluate the efficacy and safety of nimotuzumab combined with gemcitabine and cisplatin as second-line chemotherapy for advanced non-small-cell lung cancer (NSCLC) and to investigate the association of the status of KRAS gene mutation and epidermal growth factor receptor (EGFR) genotype with clinical outcome. Methods: Twenty-eight patients with advanced NSCLC were enrolled in this single center, uncontrolled pilot clinical study. All the patients developed drug resistance or disease progression after first-line chemotherapy of either a docetaxel + cisplatin regimen or a vinorelbine + cisplatin regimen and then received nimotuzumab combined with gemcitabine and cisplatin as second-line chemotherapy. Eight cases were stage IIIB and 20 were stage IV. An i.v. dosage regimen of 200 mg of nimotuzumab was given as a single dose, injected into the patient at days 1, 8 and 15; i.v. gemcitabine was injected at a dose of 1000 mg/m2 at days 1 and 8 and cisplatin (25 mg/m2 i.v.) at days 1, 2 and 3. Each patient received four or more therapeutic cycles. The efficacy and toxic reactions were evaluated, as well as time to progression and overall survival. Results: In total, 28 patients with advanced NSCLC received 101 therapeutic cycles. The mean cycle number was 3.6. Median time to progression was 4.9 (2.5–6.5) months; median overall survival and 1-year survival rate were 9.8 months and 48.5%, respectively. There was one case of complete response, six cases of partial response, 11 cases of stable disease and 10 cases of progressive disease. Response rate was 25%, and clinical benefit rate was 64.3%. Major toxic reactions were bone marrow suppression and gastrointestinal reaction. Only one patient developed grade I acneiform eruption. Conclusion: Nimotuzumab combined with gemcitabine and cisplatin as second-line chemotherapy for advanced NSCLC was active and well-tolerated in this setting. Patients with EGFR amplification and KRAS gene wild type had a better prognosis. Prospective, randomized, controlled, large-scale clinical studies are needed to confirm the results.

Because of too much dependence on prior assumptions, parametric estimation methods using finite mixture models are sensitive to noise in image segmentation. In this study, we developed a new medical image segmentation method based on non-parametric mixture models with spatial information. First, we designed the non-parametric image mixture models based on the cosine orthogonal sequence and defined the spatial information functions to obtain the spatial neighborhood information. Second, we calculated the orthogonal polynomial coefficients and the mixing ratio of the models using expectation-maximization (EM) algorithm, to classify the images by Bayesian Principle. This method can effectively overcome the problem of model mismatch, restrain noise, and keep the edge property well. In comparison with other methods, our method appears to have a better performance in the segmentation of simulated brain images and computed tomography (CT) images.

The Gaussian mixture models (GMMs) is a flexible and powerful density clustering tool. However, the application of it to medical image segmentation faces some difficulties. First, estimation of the number of components is still an open question. Second, the speed of it for large medical image is slow. Moreover, GMMs has the problem of noise sensitivity. In this paper, the kernel density estimation method is used to estimate the number of components K, and three strategies are proposed to improve the segmentation speed of GMMs. First, a histogram stratification sampling strategy is proposed to reduce the size of the training data. Second, a binning strategy is proposed to search the neighbor points of each center data to compute the approximate density function of the samples. Third, a hill-climbing algorithm with the dynamic step size is designed to find the local maxima of the density function. The kernel density estimation method and sampling technology reduce the effect of noise. Experimental results with the simulated brain images and real CT images show that the proposed algorithm has better performance in generating explainable segmentations with faster speed than the common GMMs algorithm.

Locoregional spread of abdominopelvic malignant tumors frequently results in peritoneal carcinomatosis (PC). The prognosis of PC patients treated by conventional systemic chemotherapy is poor, with a median survival of < 6 mo. However, over the past three decades, an integrated treatment strategy of cytoreductive surgery (CRS) + hyperthermic intraperitoneal chemotherapy (HIPEC) has been developed by the pioneering oncologists, with proved efficacy and safety in selected patients. Supported by several lines of clinical evidence from phases I, II and III clinical trials, CRS + HIPEC has been regarded as the standard treatment for selected patients with PC in many established cancer centers worldwide. In China, an expert consensus on CRS + HIPEC has been reached by the leading surgical and medical oncologists, under the framework of the China Anti-Cancer Association. This expert consensus has summarized the progress in PC clinical studies and systematically evaluated the CRS + HIPEC procedures in China as well as across the world, so as to lay the foundation for formulating PC treatment guidelines specific to the national conditions of China.

Gaussian Mixture Models (GMMs) have interesting properties that make them useful for many different image applications because they have powerful probabilistic statistical theory basis. However, the application of GMMs to medical image segmentation faces some difficulties. First, many typical model selection criterions become invalid when they estimate the number of components of medical images. Second, the convergence function of GMMs suffers slow convergence. In this paper, a novel medical image segmentation method based on characteristic function of GMMs is proposed. First, a new model selection criterion using characteristic function of GMMs is proposed to estimate the number of components in medical image. Second, a new convergence function using characteristic function of GMMs is proposed to estimate the parameters of GMMs. The experimental results of CT image segmentation show that our algorithm achieves better results than those from many derivatives of GMMs and needs less computation time.

Texture and color are important features in analyzing images of natural scenes. Fractal descriptors based on quaternion Fourier transform and local polynomial regression are proposed for color texture image analysis. First, considering the relation between the power spectrum and frequency in the quaternion Fourier transform domain, we proposed fractal dimensions of a color image using a fast quaternion Fourier transform. Second, local polynomial regression is applied to estimate log(spectrum)–log(frequency) curve, which is not usually linear in a natural texture image. Finally, a local polynomial regression curve is defined as fractal descriptors for the color image classification problem with multiclasses. The experimental results show that our proposed approach is more effective than other color texture analysis methods both in the correct classification rate and the duration.