Medical Computer Vision Research Articles

Active contours using global models for medical image segmentation

Accurate segmentation with denoising is the subject of research in the field of medical imaging and computer vision. This paper presents an enhanced energy based active contour model with a level set detailing. Local energy fitting term impacts neighbourhood drive to pull the shape and restrict it to protest limits. Thus, the global intensity fitting term drives the movement of contour at distant from the object boundaries. The global energy term depends on worldwide division calculation, which can better catch energy data of picture than Chan-Vese (CV) model. Both neighbourhood and worldwide terms are commonly absorbed to build a vitality work in light of a level set plan to portion images with force inhomogeneity, experiments demonstrate that the proposed model has the upside of commotion resistance and is better than conventional image segmentation. Results demonstrate that the proposed method performs better both subjectively and quantitatively contrasted with other best in class methods.

Active contours using global models for medical image segmentation

Accurate segmentation with denoising is the subject of research in the field of medical imaging and computer vision. This paper presents an enhanced energy based active contour model with a level set detailing. Local energy fitting term impacts neighbourhood drive to pull the shape and restrict it to protest limits. Thus, the global intensity fitting term drives the movement of contour at distant from the object boundaries. The global energy term depends on worldwide division calculation, which can better catch energy data of picture than Chan-Vese (CV) model. Both neighbourhood and worldwide terms are commonly absorbed to build a vitality work in light of a level set plan to portion images with force inhomogeneity, experiments demonstrate that the proposed model has the upside of commotion resistance and is better than conventional image segmentation. Results demonstrate that the proposed method performs better both subjectively and quantitatively contrasted with other best in class methods.

An Edge Exposure using Caliber Fuzzy C-means With Canny Algorithm

<p>Edge exposure or edge detection is an important and classical study of the medical field and computer vision. Caliber Fuzzy C-means (CFCM) clustering Algorithm for edge detection depends on the selection of initial cluster center value. This endeavor to put in order a collection of pixels into a cluster, such that a pixel within the cluster must be more comparable to every other pixel. Using CFCM techniques first cluster the BSDS image, next the clustered image is given as an input to the basic canny edge detection algorithm. The application of new parameters with fewer operations for CFCM is fruitful. According to the calculation, a result acquired by using CFCM clustering function divides the image into four clusters in common. The proposed method is evidently robust into the modification of fuzzy c-means and canny algorithm. The convergence of this algorithm is very speedy compare to the entire edge detection algorithms. The consequences of this proposed algorithm make enhanced edge detection and better result than any other traditional image edge detection techniques.</p>

Features based image registration using cross correlation and Radon transform

In many research fields, like Medical image analysis, pattern recognition, computer vision and remote sensed data processing, it is required to align the images. This article describes and compares two different methods to register images. In the first method, the Fourier Merlin transform based on the phase correlation of the two images in the Log-polar domain. However, it suffers from non-uniform sampling which makes it not suitable for applications causing losses in image information which will decrease the registration accuracy. The second method is to use the Radon transform proprieties to extract the rotation angle. Experiments show that the proposed method can detect the angle of rotation efficiently for different types of images without the SAR complex images.

Gaussian Process Morphable Models.

Models of shape variations have become a central component for the automated analysis of images. An important class of shape models are point distribution models (PDMs). These models represent a class of shapes as a normal distribution of point variations, whose parameters are estimated from example shapes. Principal component analysis (PCA) is applied to obtain a low-dimensional representation of the shape variation in terms of the leading principal components. In this paper, we propose a generalization of PDMs, which we refer to as Gaussian Process Morphable Models (GPMMs). We model the shape variations with a Gaussian process, which we represent using the leading components of its Karhunen-Loève expansion. To compute the expansion, we make use of an approximation scheme based on the Nyström method. The resulting model can be seen as a continuous analog of a standard PDM. However, while for PDMs the shape variation is restricted to the linear span of the example data, with GPMMs we can define the shape variation using any Gaussian process. For example, we can build shape models that correspond to classical spline models and thus do not require any example data. Furthermore, Gaussian processes make it possible to combine different models. For example, a PDM can be extended with a spline model, to obtain a model that incorporates learned shape characteristics but is flexible enough to explain shapes that cannot be represented by the PDM. We introduce a simple algorithm for fitting a GPMM to a surface or image. This results in a non-rigid registration approach whose regularization properties are defined by a GPMM. We show how we can obtain different registration schemes, including methods for multi-scale or hybrid registration, by constructing an appropriate GPMM. As our approach strictly separates modeling from the fitting process, this is all achieved without changes to the fitting algorithm. To demonstrate the applicability and versatility of GPMMs, we perform a set of experiments in typical usage scenarios in medical image analysis and computer vision: The model-based segmentation of 3D forearm images and the building of a statistical model of the face. To complement the paper, we have made all our methods available as open source.

Riemannian Gaussian Distributions on the Space of Symmetric Positive Definite Matrices

Data, which lie in the space $\mathcal {P}_{m\,}$ , of $m \times m$ symmetric positive definite matrices, (sometimes called tensor data ), play a fundamental role in applications, including medical imaging, computer vision, and radar signal processing. An open challenge, for these applications, is to find a class of probability distributions, which is able to capture the statistical properties of data in $\mathcal {P}_{m\,}$ , as they arise in real-world situations. The present paper meets this challenge by introducing Riemannian Gaussian distributions on $\mathcal {P}_{m\,}$ . Distributions of this kind were first considered by Pennec in 2006. However, the present paper gives an exact expression of their probability density function for the first time in existing literature. This leads to two original contributions. First, a detailed study of statistical inference for Riemannian Gaussian distributions, uncovering the connection between the maximum likelihood estimation and the concept of Riemannian centre of mass, widely used in applications. Second, the derivation and the implementation of an expectation-maximisation algorithm, for the estimation of mixtures of Riemannian Gaussian distributions. The paper applies this new algorithm, to the classification of data in $\mathcal {P}_{m\,}$ , (concretely, to the problem of texture classification, in computer vision), showing that it yields significantly better performance, in comparison to recent approaches.

Conditional local distance correlation for manifold-valued data.

Manifold-valued data arises frequently in medical imaging, surface modeling, computational biology, and computer vision, among many others. The aim of this paper is to introduce a conditional local distance correlation measure for characterizing a nonlinear association between manifold-valued data, denoted by X, and a set of variables (e.g., diagnosis), denoted by Y, conditional on the other set of variables (e.g., gender and age), denoted by Z. Our nonlinear association measure is solely based on the distance of the space that X, Y, and Z are resided, avoiding both specifying any parametric distribution and link function and projecting data to local tangent planes. It can be easily extended to the case when both X and Y are manifold-valued data. We develop a computationally fast estimation procedure to calculate such nonlinear association measure. Moreover, we use a bootstrap method to determine its asymptotic distribution and p-value in order to test a key hypothesis of conditional independence. Simulation studies and a real data analysis are used to evaluate the finite sample properties of our methods.

Particle Swarm Optimization based Edge Detection Algorithms for Computer Tomography Images

Background/Objectives: Detection of image edges plays an important role in medical image processing, segmentation and computer vision applications. Methods: It is necessary to have a better edge detection algorithm for the diagnosis of the abnormalities in the images and based on the diagnosis, a treatment procedure can be decided. The existing edge detection algorithms like Canny and Sobel are lack in Edge Preservation Factor (EPF) and they pose a low Signal to Noise Ratio (SNR). These algorithms are not good for noisy images. Findings: To overcome these issues, in this paper a Particle Swarm Optimization (PSO) based algorithm is proposed. Improvements/Applications: Experimental result proves that the PSO is better when compared with the existing edge detection techniques.

Regression Models on Riemannian Symmetric Spaces.

The aim of this paper is to develop a general regression framework for the analysis of manifold-valued response in a Riemannian symmetric space (RSS) and its association with multiple covariates of interest, such as age or gender, in Euclidean space. Such RSS-valued data arises frequently in medical imaging, surface modeling, and computer vision, among many others. We develop an intrinsic regression model solely based on an intrinsic conditional moment assumption, avoiding specifying any parametric distribution in RSS. We propose various link functions to map from the Euclidean space of multiple covariates to the RSS of responses. We develop a two-stage procedure to calculate the parameter estimates and determine their asymptotic distributions. We construct the Wald and geodesic test statistics to test hypotheses of unknown parameters. We systematically investigate the geometric invariant property of these estimates and test statistics. Simulation studies and a real data analysis are used to evaluate the finite sample properties of our methods.

Riemannian Laplace Distribution on the Space of Symmetric Positive Definite Matrices

The Riemannian geometry of the space Pm, of m × m symmetric positive definite matrices, has provided effective tools to the fields of medical imaging, computer vision and radar signal processing. Still, an open challenge remains, which consists of extending these tools to correctly handle the presence of outliers (or abnormal data), arising from excessive noise or faulty measurements. The present paper tackles this challenge by introducing new probability distributions, called Riemannian Laplace distributions on the space Pm. First, it shows that these distributions provide a statistical foundation for the concept of the Riemannian median, which offers improved robustness in dealing with outliers (in comparison to the more popular concept of the Riemannian center of mass). Second, it describes an original expectation-maximization algorithm, for estimating mixtures of Riemannian Laplace distributions. This algorithm is applied to the problem of texture classification, in computer vision, which is considered in the presence of outliers. It is shown to give significantly better performance with respect to other recently-proposed approaches.

Using Data Mining Techniques for Children Brain Tumors Classification based on Magnetic Resonance Imaging

Magnetic resonance Imaging) is one source of brain tumors detection tools, but using MRI in children brain tumors classification is considered to be difficult process according to the variance and complexity of tumors. This paper presents a technique for the classification of brain tumors based on children MRI. The proposed system consists of four stages, namely, MRI preprocessing stage, Segmentation stage, Feature extraction, and Classification stage. In the first stage, the main task is to eliminate the medical resonance images (MRI) noise found in images due to light reflections or operator performance which may cause inaccuracies in the classification process. The second stage, which is the stage where ROI is extracted (tumor region). In the third stage, the features related with MRI images using Haar wavelet transform (HWT) will be obtained. The features of magnetic resonance images (MRI) have been decreased using (HWT) to essential features only. And finally the fourth stages, where new classifier will be presented and finally the result will compare the proposed classifier with six other classifiers have been used. Image classification is an important task in the medical field and computer vision. Image classification refers to the process of labeling images into one of a number of predefined categories. In this survey, the test of various classification techniques against each other will be present. And it is expected that TANNN will provide better results in terms of sensitivity, specificity, accuracy and overall running time.

Multi-resolution MRI Brain Image Segmentation Based on Morphological Pyramid and Fuzzy C-mean Clustering

Image segmentation is a vital step in many imaging applications, such as medical images and computer vision. Image segmentation is considered as a challenging problem, so we need to develop an efficient, fast technique for medical image segmentation. In this paper, we propose a new system for a multi-resolution MRI brain image segmentation, which is based on a morphological pyramid with fuzzy C-mean (FCM) clustering. In the first stage, we use a wavelet multi-resolution to maintain spatial context between pixels. Secondly, we use the morphological pyramid to fuse the resulting multi-resolution images with the original image to increase sharpness and decrease noise in the processed image. Finally, we use FCM technique to segment the processed images. We compared our proposed system with some state of the art segmentation techniques on two different brain data sets. Experimental results showed that the proposed system improves the accuracy of the MRI brain image segmentation.

3D Face Modeling using Face Image

Purpose It has been stated that patient satisfaction is the crucial factor for determining success in plastic surgery. The convergence of medical science and computer vision has made easier to satisfy patients who wants to have plastic surgery. In this paper, we try to apply 3D face modeling in plastic surgical area. Materials and Methods The author introduces a method for accurate 3D face modeling techniques using a statistical model-based 3D face modeling approach in a mirror system. Results We could successfully obtain highly accurate 3D face shape results. Conclusion The method suggested could be used for acquiring 3D face models from 2D face image and the result obtained from this could be effectively used for plastic surgical areas.

Comparative Study on Multi-focus Image Fusion Techniques in Dynamic Scene

In this paper, study of various image fusion techniques especially for multi-focus images has been introduced. With the increased development of technology, it is necessary to retrieve information from multi source images in order to produce a high quality fused image with spatial and spectral information. Image Fusion is the process that allows the combination of the significant information from a bunch of images into a single image, where the resultant fused image will be more qualitable informative than any other input images. Thus this technique is useful in improving the quality of data in images. Important applications of Image Fusion contain medical imaging, remote sensing, microscopic imaging, computer vision and robotics applications. Even if the fused image can have balancing spatial and spectral resolution characteristics, the existing image fusion techniques can distort the sprectral information of the multisprectal data while merging.

Analysis of Discrepancy Metrics Used in Medical Image Segmentation

Evaluation of medical image segmentation methods is an important task, frequently ignored in the medical image and computer vision community. Several scalar evaluation metrics have been proposed in the literature. Nevertheless, few efforts have been made to characterize the evaluation metrics. It is well-known that metrics measure different characteristics, in such way they might vary greatly among problem domains. Therefore, some of them will be more suitable in particular situations. In this paper, we analyze the behavior and ability of 17 discrepancy metrics to retain its value under a set of changes in a confusion matrix. We also perform an analysis of the consistency among peer metrics by using Pearson's correlation. Our aim is to provide a valuable insight to select the most suitable .discrepancy metric and show their advantages and weakness

MRI BRAIN IMAGE SEGMENTATION BASED ON CASCADED FRACTIONAL-ORDER DARWINIAN PARTICLE SWARM OPTIMIZATION AND MEAN SHIFT

Image segmentation is an initiative with massive interest in many imaging applications, suchas medical images and computer vision. It is considered as a challenging problem, so we need todevelop an efficient, fast technique for medical image segmentation. In this paper, the proposedframework is based on two segmentation methods: Fractional-order Darwinian Particle SwarmOptimization (FODPSO) and Mean Shift segmentation (MS). FODPSO is a favorable method forspecifying a predefined number of clusters and it can find the optimal set of thresholds with a higherbetween-class variance in less computational time. In the pre-processing phase,the MRI image isfiltered and the skull is removed. In the segmentation phase, the result of FODPSO is used as the inputto MS. Finally, we make a validation to thesegmented image. We compared our proposed system withsome state of the art segmentation techniques using brain benchmark data set. The experimental resultsshow that the proposed system enhances the accuracy of the MRI brain image segmentation.

Stitching and Surface Reconstruction From Endoscopic Image Sequences: A Review of Applications and Methods.

Endoscopic procedures form part of routine clinical practice for minimally invasive examinations and interventions. While they are beneficial for the patient, reducing surgical trauma and making convalescence times shorter, they make orientation and manipulation more challenging for the physician, due to the limited field of view through the endoscope. However, this drawback can be reduced by means of medical image processing and computer vision, using image stitching and surface reconstruction methods to expand the field of view. This paper provides a comprehensive overview of the current state of the art in endoscopic image stitching and surface reconstruction. The literature in the relevant fields of application and algorithmic approaches is surveyed. The technological maturity of the methods and current challenges and trends are analyzed.

Bag-of-frequencies: a descriptor of pulmonary nodules in computed tomography images.

We present a novel descriptor for the characterization of pulmonary nodules in computed tomography (CT) images. The descriptor encodes information on nodule morphology and has scale-invariant and rotation-invariant properties. Information on nodule morphology is captured by sampling intensity profiles along circular patterns on spherical surfaces centered on the nodule, in a multi-scale fashion. Each intensity profile is interpreted as a periodic signal, where the Fourier transform is applied, obtaining a spectrum. A library of spectra is created and labeled via unsupervised clustering, obtaining a Bag-of-Frequencies, which is used to assign each spectra a label. The descriptor is obtained as the histogram of labels along all the spheres. Additional contributions are a technique to estimate the nodule size, based on the sampling strategy, as well as a technique to choose the most informative plane to cut a 2-D view of the nodule in the 3-D image. We evaluate the descriptor on several nodule morphology classification problems, namely discrimination of nodules versus vascular structures and characterization of spiculation. We validate the descriptor on data from European screening trials NELSON and DLCST and we compare it with state-of-the-art approaches for 3-D shape description in medical imaging and computer vision, namely SPHARM and 3-D SIFT, outperforming them in all the considered experiments.

Comparative Performance Analysis of Hamming, Hanning and Blackman Window

In the emerging field of medical image processing, computer vision, pattern recognition and other digital signal processing applications, window technique is vastly used. A window function is a mathematical function that is zero-valued outside of some chosen interval. When another function is multiplied by a window function, the product is also zero-valued outside the interval. In this paper, the performance of Hamming, Hanning and Blackman window have been mainly compared considering their magnitude response, phase response, equivalent noise bandwidth, sidelobe transition width, response in time and frequency domain using MATLAB simulation. To observe the responses, a FIR filter of low pass, high pass, band pass and band stop type have been designed and encountered them with each parameters stated above. The results that have been found is as same as its to be as stated in the theory. Comparing simulation results of different window, this paper has found Blackman window with best performance among them which is also expected from the theory. These windows have also been encountered with speech signal using MATLAB simulation and found the same expected result.

Architecture Support for Domain-Specific Accelerator-Rich CMPs

This work discusses hardware architectural support for domain-specific accelerator-rich CMPs. First, we present a hardware resource management scheme for sharing of loosely coupled accelerators and arbitration of multiple requesting cores. Second, we present a mechanism for accelerator virtualization. This allows multiple accelerators to efficiently compose a larger virtual accelerator out of multiple smaller accelerators, as well as to collaborate as multiple copies of a simple accelerator. All of this work is supported by a fully automated simulation tool-chain for both accelerator generation and management. We present the applicability of our approach to four different application domains: medical imaging, commercial, computer vision, and navigation. Our results demonstrate large performance improvements and energy savings over a software implementation. We also show additional improvements that result from enhanced load balancing and simplification of the communication between the core and the arbitration mechanism.