Intensity Inhomogeneity In Images Research Articles

An entropy-weighted local intensity clustering-based model for segmenting intensity inhomogeneous images

An entropy-weighted local intensity clustering-based model for segmenting intensity inhomogeneous images

Local image fitting-based active contour for vector-valued images

<span>Variational active contour seeks to segment or extract desired object boundaries for further analysis. The model can be divided into global segmentation and selective segmentation. Selective segmentation, which focuses on segmenting a particular object, is preferable to the global model. Recently, a number of selective segmentation models have been developed to precisely extract an object on grayscale images. Nevertheless, if the input image is vector-valued (colour), these models merely convert it to a grayscale image, resulting in data loss owing to the reduction in image dimension. Furthermore, they may have poor segmentation performance due to the intensity inhomogeneous images. Therefore, a new model on variational selective active contour for segmenting vector-valued images has been proposed that incorporates the concepts of local image fitting and distance-based fitting terms into a variational minimization energy functional. Moreover, a Gaussian function was used as a regularizer to replace the computationally expensive Total Variation term. Then, the proposed model’s Euler Lagrange equation has been provided to solve the model. When segmenting an object in inhomogeneous intensity images, the result of the proposed model was about 30% more accurate based on the Jaccard value and about 3 times faster than other existing methods.</span>

Bias field correction-based active contour model for region of interest extraction in digital image

The region-based Active Contour Model (ACM) is a widely known variational segmentation model for extracting or segmenting a digital image into numerous sections for further analysis. Distinguishing between global and specific segmentation models within this paradigm is possible. The global segmentation model is incapable of selectively segmenting the region of interest (ROI) from the input image, which leads to an over-segmented problem. A variety of models have been devised to address the task of selective segmentation, which involves the extraction of the boundary of a particular region of interest (ROI) inside a digital image. The Primal Dual Selective Segmentation (PDSS) model has been recently introduced and exhibits significant potential in terms of accuracy. Nevertheless, the presence of intensity inhomogeneity in digital images disrupts the precision and localisation of target regions of segmentation. Therefore, it is important to take into account bias field adjustment, also known as correction for intensity inhomogeneity. So, this study came up with a new selective segmentation model called the Selective Segmentation with Bias Field Correction (SSBF) model by combining the idea of the existing PDSS model with the level set-based bias field correction technique. To solve the proposed SSBF model, we first derived the Euler-Lagrange (EL) equation and solved it in MATLAB software. The Intersection over Union (IOU) coefficient, also known as the Dice (DSC) and Jaccard (JSC) similarity metrics, evaluated the proposed model's accuracy. Experimental results demonstrate that the JSC and DSC values of the proposed model were 13.4% and 7.2% higher, respectively, than the competing model.

Feature extraction from MR images for detection of brain and breast tumors through mathematical modeling

Segmentation of medical images is a critical step to distinguish different regions, especially tumor. The presence of severe intensity inhomogeneity in Magnetic Resonance Imaging (MRI) and Mammogram images makes it difficult to assess and detect the boundaries of tumor. Tumor detection in medical images measures and identifies the structure of the tumor. This challenging task of extracting tumor i.e., region of interest is achieved by proposing a novel fuzzy selective model. The proposed model is mainly based on selective segmentation to detect the tumor in medical images. This model is based on the local Gaussian distribution as a fitting term with fuzzy logic to handle uncertainty and irregular borders in medical images. Due to the usage of fuzzy membership functions, it avoids local minima and converges to the tumor boundary rapidly and efficiently. In addition, to obtain more information of a local intensity, the idea of multi-scale modeling is incorporated to achieve significant results. The proposed segmentation model is applied to diverse MRI and Mammogram datasets containing both the intensity inhomogeneity and noisy images, this data is collected from local hospitals and the ground truths are created by the experts. The extensive simulation results show that the proposed segmentation method significantly outperforms existing state-of-the-art techniques using both the qualitative and quantitative assessment. Loss functions play very important role in CNN architectures, and is well studied research area. In the second part of the paper, we will be introducing a new loss function, which is introduced in the first part of the paper. Deep active contour architectures based Chan-Vese loss function works well in images with homogeneity and may not work well in images with intensity inhomogeneity. We proposed an architecture, whose loss function will be based on this new proposed model. The proposed model is used as a loss function in a newly introduced CNN architecture, which has produced improved results. The results of the new architecture are compared with other existing methods used for segmentation of medical images.

Image Segmentation Based on the Hybrid Bias Field Correction

Image segmentation is the foundation for analyzing and understanding high-level images. How to effectively segment an intensity inhomogeneous image into several meaningful regions in terms of human visual perception and ensure that the segmented regions are consistent at different resolutions is still a very challenging task. In order to describe the structure information of the intensity inhomogeneous efficiently, this paper proposes a novel hybrid bias field correction model by decoupling the multiplicative bias field and the additive bias field. These kinds of bias fields are assumed to be smooth, so can employ the Sobolev space W1,2 to feature them and use a constraint to the multiplicative bias field. Since the proposed model is a constrained optimization problem, we use the Lagrangian multiplier method to transform it into an unconstrained optimization problem, and then the alternating direction method can be used to solve it. In addition, we also discuss some mathematical properties of our proposed model and algorithm. Numerical experiments on the natural images and the medical images demonstrate performance improvement over several state-of-the-art models.

Intensity inhomogeneity image segmentation based on the gradient-based spaces and the prior constraint

Image segmentation is a fundamental task in computer vision and image processing. How to efficiently decrease the effect such as high noise, low resolution and intensity inhomogeneity is the key to improve the accuracy of segmentation. To this end, we propose a novel segmentation model by assuming the image to be the product of a piecewise-constant function and a smooth function and then the model can be proposed based on the suitable gradient spaces. To improve the robustness of the proposed model, we add a prior constraint for the smooth function and then analyse the existence of the solution based on the functional theory. Since the proposed model includes two nonsmooth terms, we use a heat kernel convolution to approximately replace the length regularization term and then the alternating direction method of multipliers can be employed to solve it. Numerical experiments on several testing images demonstrate that the effectiveness and the robustness of the proposed model compared to some state-of-the-art segmentation models.

Breast Abnormality Boundary Extraction in Mammography Image Using Variational Level Set and Self-Organizing Map (SOM)

A mammography provides a grayscale image of the breast. The main challenge of analyzing mammography images is to extract the region boundary of the breast abnormality for further analysis. In computer vision, this method is also known as image segmentation. The variational level set mathematical model has been proven to be effective for image segmentation. Several selective types of variational level set models have recently been formulated to accurately segment a specific object on images. However, these models are incapable of handling complex intensity inhomogeneity images, and the segmentation process tends to be slow. Therefore, this study formulated a new selective type of the variational level set model to segment mammography images that incorporate a machine learning algorithm known as Self-Organizing Map (SOM). In addition to that, the Gaussian function was applied in the model as a regularizer to speed up the processing time. Then, the accuracy of the segmentation’s output was evaluated using the Jaccard, Dice, Accuracy and Error metrics, while the efficiency was assessed by recording the computational time. Experimental results indicated that the new proposed model is able to segment mammography images with the highest segmentation accuracy and fastest computational speed compared to other iterative models.

A novel framework for retinal vessel segmentation using optimal improved frangi filter and adaptive weighted spatial FCM

Medical attention has long been focused on diagnosing diseases through retinal vasculature. However, due to the image intensity inhomogeneity and retinal vessel thickness variability, segmenting the vessels from retinal images is still a tough matter. In this paper, we suggest an optimal improved Frangi-based multi-scale filter for enhancement. The parameters of the Frangi filter are optimised using a modified enhanced leader particle swarm optimization (MELPSO). The enhanced image is segmented using a novel adaptive weighted spatial fuzzy c-means (AWSFCM) clustering technique. The suggested approach is tested on three freely available databases. The results obtained are compared with state-of-the-art procedures. It is observed that the suggested approach outperforms other methods and may serve as an effective approach for retinal vessel segmentation.

Deformable models for image segmentation: A critical review of achievements and future challenges

Image segmentation is a fundamental and tedious task of computer vision. Because of inherent noise and intensity inhomogeneity in real-world images, it remains a difficult problem in practical applications such as image analysis, scene understanding, object detection, and many others. Several mathematical models proposed for image segmentation in the past few decades with an effective policy. Among these models, deformable models earned more attention and are widely used techniques due to their accuracy, efficiency, and robust effectiveness. This study reviews and compares various deformable models for the segmentation of digital images available in the literature. First, for a comprehensive study, these deformable models are classified into two classes such as direct partial differential equation (PDE) based approaches and variational based approaches. Beside this, variational based approaches are further classified into parametric and geometric models. Their advantages as well as shortcomings are discussed in detail from an objective viewpoint. Then, to check the robustness of various discussed classes of deformable models, a set of synthetic, natural, and real medical images are considered along with inhomogeneity and noise. Also, to measure the segmentation accuracy, different quantitative metrics based on contour and region are utilized. Numerical experiments with different classes of images, reveal that both direct PDE based and variation based models perform well in clean and noisy images. Whereas, the variational based approaches are superior for images having intensity inhomogeneity with high computational time. The qualitative and quantitative investigations confirm that the subtle change in model assumptions can have a significant impact on segmentation.

Two-Phase Segmentation for Intensity Inhomogeneous Images by the Allen--Cahn Local Binary Fitting Model

Two-Phase Segmentation for Intensity Inhomogeneous Images by the Allen--Cahn Local Binary Fitting Model

Variational selective segmentation model for intensity inhomogeneous image

Variational selective image segmentation models aim to extract a particular object in an image depending on a set of user-defined prior points. The current model suffers from high computational costs due to the traditional total variation function that results in a slow segmenting process. In addition, it is not designed to segment images with intensity inhomogeneities. In this research, we formulate a new variational selective image segmentation model based on the Gaussian function. A Gaussian function is proposed to replace the traditional total variation function to regularize the variational level set function. To segment images with intensity inhomogeneities, the local image fitting idea was in corporate into the formulation. The efficiency of the proposed model was then assessed by recording the computation time while the accuracy was measured using Jaccard and Dice similarity values. Numerical experiments using synthetic, natural, and medical images demonstrate that the proposed model is about 6 times faster than the existing model, while the Jaccard and Dice values are about 11% and 7% higher, respectively, compared to the existing model. In the future, this research can be extended further into a 3-dimensional modeling and vector-valued image framework.

Bias correction of intensity inhomogeneous images hybridized with superpixel segmentation

Image intensity bias correction is still an open problem. Fuzzy c-means based bias correction methods are popular. However, they are time consuming and the exact clustering number has to be known in advance. To address the above problems, we propose a bias field correction embedded FCM (BCEFCM) method which is hybridized with superpixel clustering. Furthermore, the proposed method is extended to address similar problems existing in colourful images and multiple modality images. Moreover, a histogram based strategy is proposed to estimate the clustering number in advance, which is generally greater than the exact clustering number. The proposed methods have been extensively tested on representative images from BrainWeb and the MICCAI SATA challenge. Results demonstrate advantages of the proposed methods in no need to know the exact clustering number in advance and producing better bias correction and image segmentation results than representative methods in terms of coefficient of variations (CV), coefficient of joint variation (CJV), root mean square error (RMSE), and structural similarity index (SSI).

An active contour model based on local pre-piecewise fitting image

Active contour model (ACM) has been widely used in the field of image segmentation and successfully solved numerous problems. Segmentation of intensity inhomogeneity images is a major focus of current research. To seek a better solution, this paper proposes an active contour model based on local pre-piecewise fitting image. First of all, the piecewise function is pre-fitted by the dilation and erosion operator in gray morphology. Second, a novel energy function is drawn out with a rewritten image fitting function. Third, an optimized gradient descent flow formula is proposed to further improve the robustness of this model. Fourth, an improved regularization term is proposed to optimize the level set function. Experiments have proved that the model can effectively segment images with uneven grayscale. Compared with other models, the proposed model has obvious advantages in robustness to initialization and segmentation efficiency. In addition, the model can also choose various targets by selecting different initial contours.

A neighbor level set framework minimized with the split Bregman method for medical image segmentation

Medical image segmentation has a huge challenge due to intensity inhomogeneity and the similarity of the background and the object. To meet this challenge, we propose an improved active contour model, in which we combine the level set method and the split Bregman method, and provide the two-phase formulation, the multi-phase formulation and 3D formulation. In this paper, the proposed model is presented in a level set framework by including the neighbor region information for segmenting medical images in which the energy functional contains the data fitting term and the length term. The neighbor region and the local intensity variances in the data fitting term are designed to optimize the minimization process. To minimize the energy functional then we apply the split Bregman method which contributes to get faster convergence. Besides, we extend our model to the multi-phase segmentation model and the 3D segmentation model for cardiac MR images, which have all achieved good results. Experimental results show that the new model not only has strong robustness to other cardiac tissue effects and image intensity inhomogeneity, but it also can much better conduce to the extraction of effective tissues. As we expected, our model has higher segmentation accuracy and efficiency for medical image segmentation.

Active contour model driven by optimized energy functionals for MR brain tumor segmentation with intensity inhomogeneity correction

Segmentation of brain tumors is important for medical diagnosis, treatment planning, and disease development. However, the presence of image artifacts such as noise, intensity inhomogeneity, and partial volume effect in real-world images can aggressively affect the segmentation task. The manual segmentation of the tumor is highly error-prone and is a time-consuming task. Hence, in this work, we propose a methodology that can identify and segment the brain tumor slices in magnetic resonance (MRI) images. The work is composed of three main stages namely pre-processing, segmentation, and post-processing. In the pre-processing stage, N4ITK is applied to correct the intensity inhomogeneity and an Anisotropic diffusion filter is used to remove the noise present in MR images. In the segmentation stage, an active contour model that combines the region scalable fitting energy (RSF) and optimized laplacian of gaussian energy (OLoG) is proposed to segment the tumor region from MRI. The proposed segmentation method first presents an LoG energy term optimized by an energy functional that can smooth the homogeneous regions and enhance edge information simultaneously. Next, the optimized LoG energy term is combined with the RSF energy term which utilizes the local region information to drive the curve towards the boundaries. With the addition of the LoG term, the proposed model is insensitive to the positions of the initial contour and produces an accurate segmentation result. Finally, morphological operations and thresholding are used to extract the tumor region from the segmented image which is computed previously. The performance of the proposed segmentation method is evaluated using the BRATS, and J.Cheng dataset. The obtained experimental results demonstrate that our proposed method significantly outperforms the manual process and state of the art methods in brain tumor segmentation.

A level set model by regularizing local fitting energy and penalty energy term for image segmentation

A novel level set model is proposed by regularizing local fitting energy to segment the intensity inhomogeneous images. In proposed model, local image fitting energy information is incorporated with penalty energy function. To segment intensity inhomogeneous images, a circular window filter is used to identify homogeneous regions. In addition, local information of homogeneous regions is constructed in form of local fitting function. A new double well potential function is formulated to regularize the contour curve and is used a penalty energy term which is added with local fitting functional in order to formulate multi-scale energy function. The experimental results show the robustness of proposed method compared to other level set models and deep learning based level set model. The comparative study of Jaccard similarity index (JSI) values and segmentation accuracy also validate the preciseness of the proposed model. Further, the proposed model yields better segmentation results compared to the other state-of-the-art models in terms of higher precision and recall values and lesser computational time. In addition, the proposed model is computationally efficient and robust to noise as well as contour initialization.

Accurate construction of 3-D numerical breast models with anatomical information through MRI scans

The realistic numerical breast model is an important tool for verifying algorithms, improving design concepts, and exploring new technologies related to microwave breast cancer detection. Recently, several numerical breast models have been developed. However, these models do not include the real breast boundary and the chest region, which causes the electromagnetic wave propagation in the breast models to deviate from the actual situation. The proposed breast models in this paper overcome the significant deficiencies of the recent breast models in terms of structure completeness and authenticity. The model construction based on magnetic resonance imaging (MRI) scans is a multistep approach. Firstly, intensity inhomogeneity in MRI images is corrected by an improved nonparametric nonuniform intensity normalization (N4) algorithm. Then, a dual threshold and morphological transformation (DTMT) method is developed to segment the real breast region. Subsequently, a modified maximum inter-class variance (MICV) method is employed to automatically divide the breast region into the fat and the fibroglandular clusters with desired complexity. Finally, the dielectric properties of breast tissues are calculated by a piecewise weighted mapping method. The applicability and effectiveness of the proposed method are verified by constructing four breast models with varying tissue density, shape, and size. The constructed models in this study are significant to achieve reliable and precise effects for microwave breast cancer detection due to the accurate expression of the breast anatomical information and electromagnetic characteristics.

An adaptive level set method based on joint estimation dealing with intensity inhomogeneity

Automatic object segmentation has been a challenging task due to intensity inhomogeneity. The traditional way is to eliminate the intensity inhomogeneity, which causes the object to lose useful intensity information. The authors propose an adaptive level set method for the segmentation of intensity inhomogeneous images. Firstly, global and local features are utilised to collaboratively estimate the image, which devotes to compensating for intensity inhomogeneity. The local estimation retains detailed spatial information, and the global estimation mainly contains the regional information of the partitioned object. Then, during the construction of the energy functional, joint estimation is introduced to create the external energy. To acquire the precise location of the boundary, a weighting factor indicated by the gradient is introduced into the internal energy. Finally, after the numerical calculation of the energy functional by additive operator splitting algorithm, this method achieves the desired performance in terms of accuracy and robustness. Experimental results verify this method outperforms the comparative methods and can be applied to many real-world scenarios.

A Novel Global Energy and Local Energy-Based Legendre Polynomial Approximation for Image Segmentation

Active contour model (ACM) is a powerful segmentation method based on differential equation. This paper proposes a novel adaptive ACM to segment those intensity inhomogeneity images. Firstly, a novel signed pressure force function is presented with Legendre polynomials to control curve contraction. Legendre polynomials can approximate regional intensities corresponding to evolving curve. Secondly, global term of our model characterizes difference of Legendre coefficients, and local energy term characterizes fitting evolution curve of interested region. Final contour evolution will minimize the energy function. Thirdly, a correction term is employed to improve the performance of curve evolution according to the initial contour position, so wherever the initial contour being in the image, the object boundaries can be detected. Fourthly, our model combines the advantages of two classical models such as good topological changes and computational simplicity. The new model can classify regions with similar intensity values. Compared with traditional models, experimental results show effectiveness and efficiently of the new model.

Impurities detection in edible bird’s nest using optical segmentation and image fusion

The cleanliness of edible bird’s nest (EBN) is among the determinative factors for market acceptance. As it is meant for human consumption, EBN should be free of any impurities or matter which are foreign to it, such as bird feathers, egg fragments and droppings. However, natural variations in composition, density and thickness impose inconsistency to the level of translucency and colour of EBN, resulting in intensity inhomogeneity in EBN images that substantially reduce the accuracy of the segmentation and detection of impurities. Consequently, the segmentation and detection of impurities, which are essential to visual automation in the cleaning and inspection processes, remain unsolved. This work proposes a novel optical segmentation method to segment impurities from the EBN, in order to facilitate the detection of impurities. EBN images captured under two different lighting scenarios, namely, low-angle blue-diffused lighting and red-diffused backlighting, were used to prepare the fused image for background-EBN-impurities segmentation. The applicability of the method was demonstrated by comparing the detection results with those of human inspectors. With a simple thresholding operation performed on fused images, the impurities detection algorithm recorded a true positive/recall rate of 93.39%, a precision of 71.17% and a false-negative detection rate of 4.8%. Despite the high misclassification rate of 32.25%, the algorithm was able to detect more than 93% of the impurities, compared to human inspectors, who required a second examination on the EBNs.