Image Intensity Gradient Research Articles

An operator-independent quality assurance system for automatically generated structure sets

Objective. This study describes geometry-based and intensity-based tools for quality assurance (QA) of automatically generated structures for online adaptive radiotherapy, and designs an operator-independent traffic light system that identifies erroneous structure sets. Approach. A cohort of eight head and neck (HN) patients with daily CBCTs was selected for test development. Radiotherapy contours were propagated from planning computed tomography (CT) to daily cone beam CT (CBCT) using deformable image registration. These propagated structures were visually verified for acceptability. For each CBCT, several error scenarios were used to generate what were judged unacceptable structures. Ten additional HN patients with daily CBCTs and different error scenarios were selected for validation. A suite of tests based on image intensity, intensity gradient, and structure geometry was developed using acceptable and unacceptable HN planning structures. Combinations of one test applied to one structure, referred to as structure-test combinations, were selected for inclusion in the QA system based on their discriminatory power. A traffic light system was used to aggregate the structure-test combinations, and the system was evaluated on all fractions of the ten validation HN patients. Results. The QA system distinguished between acceptable and unacceptable fractions with high accuracy, labeling 294/324 acceptable fractions as green or yellow and 19/20 unacceptable fractions as yellow or red. Significance. This study demonstrates a system to supplement manual review of radiotherapy planning structures. Automated QA is performed by aggregating results from multiple intensity- and geometry-based tests.

Deteksi Tepi Sederhana Pada Citra Menggunakan Operator Sobel

implemented and evaluated the edge detection method using the Sobel Operator, which calculates the gradient of image intensity through two convoluted kernels for horizontal (Gx) and vertical directions. (Gy). The magnitudo gradient is obtained from the combination of both such directional gradients to represent the edge force on each pixel. The main steps include image pre-processing, the application of the Sobel kernel, the calculation of magnitudo gradients, and the filtering of results to extract significant edges. The results show that the Sobel Operator is effective in highlighting intensity differences that indicate the boundary of the object, although it is sensitive to noise and less accurate for fine edges. Despite its limitations, this method is simple to implement and useful as an initial step in image processing applications such as segmentation, pattern identification, and object shape analysis.

Natural surface floaters in image-based river surface velocimetry: Insights from a case study

This study focuses on utilizing image techniques for river velocity measurement, with a specific emphasis on natural surface floating patterns. Employing a multi-camera system, we conducted 3D measurements on river surfaces, including surface velocity and water surface reconstruction. A pattern-based tracking approach has been adopted to improve the performance of image measurements on different types of natural floating tracers. The study employs the following approaches: 3D Lagrangian Pattern Tracking Velocimetry (3D-LPTV), 2D Lagrangian Pattern Velocimetry (2D- LPTV), and Large-scale Particle Image Velocimetry (LSPIV), for surface velocity estimation. The outcomes revealed that all three approaches yielded consistent results in terms of averaged velocity. However, the LSPIV method produced about two times higher uncertainty in measured velocities compared to the other methods. A strategy to assess the quality of river surface patterns in velocity estimation is presented. Specifically, the sum of squared interrogation area intensity gradient (SSIAIG) was found to be strongly correlated with measurement uncertainty. Additionally, a term related to the peak sidelobe ratio (PSR) of the cross-correlation map was found as an effective constraint, ensuring the image-tracking process achieves high reliability. The precision of measurements increases corresponding to the increase of image intensity gradient and PSR.

Unified digital image correlation under meshfree framework

AbstractThe implementation of digital image correlation (DIC) involves several different problems, such as image prefiltering, image intensity gradient calculation, image intensity interpolation at subpixel positions, shape function construction and strain calculation. This paper offers a unified insight into the nature of several key problems in DIC technique. We treat all the problems involved in the former mentioned key steps as fundamentally the same problem, that is, reconstructing an analytical description from a discrete and noisy sampling of a signal, such as discrete image intensity and displacement at some scattered nodes. From the reconstructed analytical description, the gradient and physical value at subpixel or integral pixel position can be analytically calculated without extra error. Here, we solve all these problems using the same mathematical tool, the meshfree method, leading to a unified DIC (U‐DIC) method. This method introduces errors solely during the steps involving the determination of the continuous description. However, it effectively avoids errors in the remaining steps. It holds the best balance between spatial resolution and measurement resolution for both displacement and strain measurements compared to 28 state‐of‐the‐art DIC algorithms based on the benchmark tests on DIC Challenge 2.0. It also holds all the unique advantages of the advanced meshfree DIC (MF‐DIC) compared to conventional local DIC and global DIC. The novel concept and excellent balance between spatial resolution and measurement resolution make U‐DIC an attractive replacement for conventional DIC methods. Additionally, the consistency of the implementation procedures in U‐DIC can simplify the parameter selection in DIC, which is of potential for the standardization of DIC technique.

IMAGE FEATURE EXTRACTION AND FRACTALITY EVALUATION BASED ON TWO-DIMENSIONAL CONTINUOUS WAVELET TRANSFORM: APPLICATION TO DIGITAL ELEVATION MODEL DATA

A new method to extract image features and to evaluate fractality is proposed based on two-dimensional (2D) continuous wavelet transform (CWT). Multi-directional 2D CWT coefficients are used to determine the direction and magnitude of image intensity gradients directly unlike other methods using gradient components in the horizontal and vertical directions. Image feature points are detected by comparing candidate directional 2D CWT coefficients at candidate points and their neighbors instead of gradient magnitudes or 2D CWT moduli used by traditional methods. It enables us to extract multiscale image features including line singularities such as corners which are recognized to be hardly extracted by traditional methods. This offers an advantage condition to study fractal objects consisting of lots of line singularities. It is suggested that the detected multiscale image features can reflect multiscale fractal measures to be used to evaluate fractality, that is, self-similarity across scales. From this suggestion, the method to evaluate fractality and calculate fractal dimensions using multiscale image features is proposed. The proposed method is applied to theoretical fractal models to show that the method is convenient and effective in extracting image features of them consisting of many line singularities and calculating their fractal dimensions. Finally, the method is validated using a case study dealing with fractality evaluation of geoscientific objects such as coastlines and stream networks from the digital elevation model (DEM) data.

UTILIZATION OF MULTITEMPORAL LANDSAT DATA FOR COASTLINE CHANGE ANALYSIS USING CANNY EDGE DETECTOR

The development of remote sensing technology has experienced significant progress. This progress is marked by the availability of images of various resolutions with complete channels, open-source, and their development in various image classification techniques such as edge detection techniques. This study aims to examine changes in the coastline in Banmaleng Village, Gili Raja Island, Sumenep Regency using the Canny edge detection algorithm on multitemporal Landsat 7 and 8 imagery in 2005 - 2020. The edging process includes (a) minimize noise by applying a Gaussian filter, (b) determine the image intensity gradient, (c) apply non-maximum emphasis to eliminate spurious responses to objects, (d) define multiple thresholds for determining potential image edges, (e) Track edge hysteresis by pressing all other weak edges that are not connected to firm edges. Canny edge detection produces sharp edges to analyze coast line changes quite well. Every five years, the coastline of Banmaleng Village experienced shifting from 0 , 4 to 2 , 3 meters in several areas. Keywords : Edge Detection, Landsat, Coastline, Canny Algorithm, Gili Raja

Development of GUI for Malaysian herbs plant image identification

In the previous era, sickness and diseases were treated using traditional herbs since medical technology had yet to be developed. Due to massive development in medicine, more herbs species are facing the risk of extinction due to not being well conserved. This paper describes the development of a graphical user interface (GUI) for identification of Malaysian Herbs Plant from image data using MATLAB. Besides, the GUI development will contribute to the database development of herbs species that are much needed to systematically stores relevant information. It can provide valuable knowledge for society. It is quite challenging for people including the herbs’ expert, to differentiate herbs’ plants since there are too many of them and limited knowledge and experiences. Fortunately, this can be overcome by using image processing approaches specifically image segmentation and classification. A set of image data consists of five types of Malaysian herbs plants is used in this study. The types are Rerama, Sirih, Mexican Mint, Belalai Gajah dan Senduduk. Sobel edge detection operator is a segmentation approach that works by computing the gradient of image intensity at each point and measuring the pixel value changes in horizontal and vertical directions by using two convolution masks. The shape and texture features are used in multiclass Support Vector Machine (SVM) model to classify the species of the herbs. Results show that performance of model are 95.56% for accuracy and sensitivity, 98.89% for specificity, 95.78% for precision, and 94.53% for Matthews correlation. The demonstration of image data shows the effectiveness of the developed GUI in classifying the five types of herbs.

Quantifying Optically Derived Two-Dimensional Wave-Averaged Currents in the Surf Zone

Complex two-dimensional nearshore current patterns are generated by feedbacks between sub-aqueous morphology and momentum imparted on the water column by breaking waves, winds, and tides. These non-stationary features, such as rip currents and circulation cells, respond to changing environmental conditions and underlying morphology. However, using fixed instruments to observe nearshore currents is limiting due to the high costs and logistics necessary to achieve adequate spatial sampling resolution. A new technique for processing surf-zone imagery, WAMFlow, quantifies fluid velocities to reveal complex, multi-scale (10 s–1000 s meters) nearshore surface circulation patterns. We apply the concept of a wave-averaged movie (WAM) to measure surf-zone circulation patterns on spatial scales of kilometers in the alongshore and 100 s of meters in the cross-shore. The approach uses a rolling average of 2 Hz optical imagery, removing the dominant optical clutter of incident waves, to leave the residual foam or water turbidity features carried by the flow. These residual features are tracked as quasi-passive tracers in space and time using optical flow, which solves for u and v as a function of image intensity gradients in x, y, and t. Surf zone drifters were deployed over multiple days with varying nearshore circulations to validate the optically derived flow patterns. Root mean square error are reduced to 0.1 m per second after filtering based on image attributes. The optically derived patterns captured longshore currents, rip currents, and gyres within the surf zone. Quantifying nearshore circulation patterns using low-cost image platforms and open-source computer vision algorithms presents the potential to further our understanding of fundamental surf zone dynamics.

Reproducible kernel Hilbert space based global and local image segmentation

Image segmentation is the task of partitioning an image into individual objects, and has many important applications in a wide range of fields. The majority of segmentation methods rely on image intensity gradient to define edges between objects. However, intensity gradient fails to identify edges when the contrast between two objects is low. In this paper we aim to introduce methods to make such weak edges more prominent in order to improve segmentation results of objects of low contrast. This is done for two kinds of segmentation models: global and local. We use a combination of a reproducing kernel Hilbert space and approximated Heaviside functions to decompose an image and then show how this decomposition can be applied to a segmentation model. We show some results and robustness to noise, as well as demonstrating that we can combine the reconstruction and segmentation model together, allowing us to obtain both the decomposition and segmentation simultaneously.

Maximum Likelihood Estimation for Disk Image Parameters

We present a novel technique for estimating disk parameters (the centre and the radius) from its 2D image. It is based on the maximal likelihood approach utilising both edge pixels coordinates and the image intensity gradients. We emphasise the following advantages of our likelihood model. It has closed-form formulae for parameter estimating, requiring less computational resources than iterative algorithms therefore. The likelihood model naturally distinguishes the outer and inner annulus edges. The proposed technique was evaluated on both synthetic and real data.

Automatic tandem and ring reconstruction using MRI for cervical cancer brachytherapy.

The MRI-guided cervical cancer brachytherapy provides unparalleled soft-tissue contrast for target and normal tissue contouring, but eliminates the ability to use conventional metallic fiducials for radiation source path reconstruction as required for treatment planning. Instead, the source path is reconstructed by manually aligning a library model to the signal void produced by the applicator, which takes time intraoperatively and precludes fully automated treatment planning. The purpose of this study is to present and validate an algorithm to automatically reconstruct tandem and ring applicators using MRI for cervical cancer brachytherapy treatment planning. Applicators were reconstructed using T2-weighted MR images acquired at 1.5T from 33 brachytherapy fractions including 10 patients using a model-to-image registration algorithm. The algorithm involves (a) image filtering and maximum intensity projection to highlight the applicator, (b) ring center identification using the circular Hough transform, and (c) three-dimensional surface model registration, optimized by maximizing the image intensity gradient normal to the model surface. Two independent observers manually reconstructed all applicators, enabling the calculation of interobserver variability and establishing a ground truth. Algorithm variability was calculated by comparing algorithm results to each individual observer, and algorithm accuracy was calculated by comparing algorithm results to the ground truth. The algorithm variability and accuracy were compared to the interobserver variability using paired t-tests. Mean±SD interobserver variability was 0.83±0.31mm and 0.78±0.29mm for the ring and tandem, respectively. The algorithm had mean±SD variability and accuracy of 0.72±0.32mm (P=0.02) and 0.60±0.24mm (P=0.0005) for the ring, and 0.70±0.29mm (P=0.11) and 0.58±0.24mm (P=0.004) for the tandem, respectively. The algorithm variability and accuracy were within the interobserver variability measured in this study. The algorithm accuracy and mean execution time of 10.0s are sufficient for clinical tandem and ring reconstruction, and are a step toward fully automated tandem and ring brachytherapy treatment planning.

Deep convolutional reconstruction for gradient-domain rendering

It has been shown that rendering in the gradient domain, i.e., estimating finite difference gradients of image intensity using correlated samples, and combining them with direct estimates of pixel intensities by solving a screened Poisson problem, often offers fundamental benefits over merely sampling pixel intensities. The reasons can be traced to the frequency content of the light transport integrand and its interplay with the gradient operator. However, while they often yield state of the art performance among algorithms that are based on Monte Carlo sampling alone, gradient-domain rendering algorithms have, until now, not generally been competitive with techniques that combine Monte Carlo sampling with post-hoc noise removal using sophisticated non-linear filtering. Drawing on the power of modern convolutional neural networks, we propose a novel reconstruction method for gradient-domain rendering. Our technique replaces the screened Poisson solver of previous gradient-domain techniques with a novel dense variant of the U-Net autoencoder, additionally taking auxiliary feature buffers as inputs. We optimize our network to minimize a perceptual image distance metric calibrated to the human visual system. Our results significantly improve the quality obtained from gradient-domain path tracing, allowing it to overtake state-of-the-art comparison techniques that denoise traditional Monte Carlo samplings. In particular, we observe that the correlated gradient samples --- that offer information about the smoothness of the integrand unavailable in standard Monte Carlo sampling --- notably improve image quality compared to an equally powerful neural model that does not make use of gradient samples.

Quantum Image Edge Extraction Based on Improved Sobel Operator

Edge extraction is a basic task in image processing. This paper proposes a quantum image edge extraction algorithm based on improved sobel operator for the generalized quantum image representation (GQIR) to solve the real-time problem. The quantum image model of GQIR can store arbitrary quantum images with a size of H × W. Our scheme can calculate the gradients of image intensity of all the pixels simultaneously. Then, the concrete circuits of quantum image edge extraction algorithm are implemented by using a series of quantum operators which have been designed. Compared with existing quantum edge extraction algorithms, our scheme can achieve more accurate edge extraction, especially for diagonal edges. Finally, the complexity of the quantum circuits were been analyzed based on the basic quantum gates and give the simulation experiment results on classical computer.

A new adaptive-weighted total variation sparse-view computed tomography image reconstruction with local improved gradient information.

Inspired by the compressed sensing (CS) theory, introducing priori information of sparse image into sparse-view reconstruction algorithm of computed tomography (CT) can improve image quality. In recent years, as a special case of CS, total variation (TV) reconstruction algorithm that uses both image sparsity and prior information of edge direction have attracted much research interest in sparse-view image reconstruction due to its ability to preserve image edges. In this paper, we propose a new adaptive-weighted total variation (NAWTV) algorithm for CT image reconstruction, which is derived by considering local gradient direction continuity and the anisotropic edge property. The anisotropic edge property is used to consolidate the image sparsity, where the associated weights are expressed as a combination of exponential and cosine function. The weights can also be adjusted adaptively according the local image intensity gradient. The NAWTV algorithm is numerically implemented with gradient descent method. The typical Shepp-Logan phantom and FORBILD head phantom are employed to perform image reconstruction simulation. To evaluate performance of NAWTV algorithm, we compared it with TV and AwTV reconstruction algorithms in experiments. Numerical experimental results verified the effectiveness and feasibility of the proposed algorithm. Comparison results also showed that the NAWTV algorithm achieved a satisfactory performance in suppressing artifacts and preserving the edge structure details information of the reconstructed image.

Feature and Intensity Based Medical Image Registration Using Particle Swarm Optimization.

Image registration is an important aspect in medical image analysis, and kinds use in a variety of medical applications. Examples include diagnosis, pre/post surgery guidance, comparing/merging/integrating images from multi-modal like Magnetic Resonance Imaging (MRI), and Computed Tomography (CT). Whether registering images across modalities for a single patient or registering across patients for a single modality, registration is an effective way to combine information from different images into a normalized frame for reference. Registered datasets can be used for providing information relating to the structure, function, and pathology of the organ or individual being imaged. In this paper a hybrid approach for medical images registration has been developed. It employs a modified Mutual Information (MI) as a similarity metric and Particle Swarm Optimization (PSO) method. Computation of mutual information is modified using a weighted linear combination of image intensity and image gradient vector flow (GVF) intensity. In this manner, statistical as well as spatial image information is included into the image registration process. Maximization of the modified mutual information is effected using the versatile Particle Swarm Optimization which is developed easily with adjusted less parameter. The developed approach has been tested and verified successfully on a number of medical image data sets that include images with missing parts, noise contamination, and/or of different modalities (CT, MRI). The registration results indicate the proposed model as accurate and effective, and show the posture contribution in inclusion of both statistical and spatial image data to the developed approach.

Myocardium Segmentation From DE MRI Using Multicomponent Gaussian Mixture Model and Coupled Level Set.

Objective: In this paper, we propose a fully automatic framework for myocardium segmentation of delayed-enhancement (DE) MRI images without relying on prior patient-specific information. Methods: We employ a multicomponent Gaussian mixture model to deal with the intensity heterogeneity of myocardium caused by the infarcts. To differentiate the myocardium from other tissues with similar intensities, while at the same time maintain spatial continuity, we introduce a coupled level set (CLS) to regularize the posterior probability. The CLS, as a spatial regularization, can be adapted to the image characteristics dynamically. We also introduce an image intensity gradient based term into the CLS, adding an extra force to the posterior probability based framework, to improve the accuracy of myocardium boundary delineation. The prebuilt atlases are propagated to the target image to initialize the framework. Results: The proposed method was tested on datasets of 22 clinical cases, and achieved Dice similarity coefficients of 87.43 ± 5.62% (endocardium), 90.53 ± 3.20% (epicardium) and 73.58 ± 5.58% (myocardium), which have outperformed three variants of the classic segmentation methods. Conclusion: The results can provide a benchmark for the myocardial segmentation in the literature. Significance: DE MRI provides an important tool to assess the viability of myocardium. The accurate segmentation of myocardium, which is a prerequisite for further quantitative analysis of myocardial infarction (MI) region, can provide important support for the diagnosis and treatment management for MI patients.Objective: In this paper, we propose a fully automatic framework for myocardium segmentation of delayed-enhancement (DE) MRI images without relying on prior patient-specific information. Methods: We employ a multicomponent Gaussian mixture model to deal with the intensity heterogeneity of myocardium caused by the infarcts. To differentiate the myocardium from other tissues with similar intensities, while at the same time maintain spatial continuity, we introduce a coupled level set (CLS) to regularize the posterior probability. The CLS, as a spatial regularization, can be adapted to the image characteristics dynamically. We also introduce an image intensity gradient based term into the CLS, adding an extra force to the posterior probability based framework, to improve the accuracy of myocardium boundary delineation. The prebuilt atlases are propagated to the target image to initialize the framework. Results: The proposed method was tested on datasets of 22 clinical cases, and achieved Dice similarity coefficients of 87.43 ± 5.62% (endocardium), 90.53 ± 3.20% (epicardium) and 73.58 ± 5.58% (myocardium), which have outperformed three variants of the classic segmentation methods. Conclusion: The results can provide a benchmark for the myocardial segmentation in the literature. Significance: DE MRI provides an important tool to assess the viability of myocardium. The accurate segmentation of myocardium, which is a prerequisite for further quantitative analysis of myocardial infarction (MI) region, can provide important support for the diagnosis and treatment management for MI patients.

Crowded Cluster Cores: An Algorithm for Deblending in Dark Energy Survey Images

Deep optical images are often crowded with overlapping objects. This is especially true in the cores of galaxy clusters, where images of dozens of galaxies may lie atop one another. Accurate measurements of cluster properties require deblending algorithms designed to automatically extract a list of individual objects and decide what fraction of the light in each pixel comes from each object. In this article, we introduce a new software tool called the Gradient And Interpolation based (GAIN) deblender. GAIN is used as a secondary deblender to improve the separation of overlapping objects in galaxy cluster cores in Dark Energy Survey images. It uses image intensity gradients and an interpolation technique originally developed to correct flawed digital images. This paper is dedicated to describing the algorithm of the GAIN deblender and its applications, but we additionally include modest tests of the software based on real Dark Energy Survey co-add images. GAIN helps to extract an unbiased photometry measurement for blended sources and improve detection completeness, while introducing few spurious detections. When applied to processed Dark Energy Survey data, GAIN serves as a useful quick fix when a high level of deblending is desired.

Thalamic segmentation based on improved fuzzy connectedness in structural MRI

Thalamic segmentation serves an important function in localizing targets for deep brain stimulation (DBS). However, thalamic nuclei are still difficult to identify clearly from structural MRI. In this study, an improved algorithm based on the fuzzy connectedness framework was developed. Three-dimensional T1-weighted images in axial orientation were acquired through a 3D SPGR sequence by using a 1.5T GE magnetic resonance scanner. Twenty-five normal images were analyzed using the proposed method, which involved adaptive fuzzy connectedness combined with confidence connectedness (AFCCC). After non-brain tissue removal and contrast enhancement, the seed point was selected manually, and confidence connectedness was used to perform an ROI update automatically. Both image intensity and local gradient were taken as image features in calculating the fuzzy affinity. Moreover, the weight of the features could be automatically adjusted. Thalamus, ventrointermedius (Vim), and subthalamic nucleus were successfully segmented. The results were evaluated with rules, such as similarity degree (SD), union overlap, and false positive. SD of thalamus segmentation reached values higher than 85%. The segmentation results were also compared with those achieved by the region growing and level set methods, respectively. Higher SD of the proposed method, especially in Vim, was achieved. The time cost using AFCCC was low, although it could achieve high accuracy. The proposed method is superior to the traditional fuzzy connectedness framework and involves reduced manual intervention in time saving.

A novel automated segmentation method for retinal layers in OCT images proves retinal degeneration after optic neuritis

AimThe evaluation of inner retinal layer thickness can serve as a direct biomarker for monitoring the course of inflammatory diseases of the central nervous system such as multiple sclerosis (MS)....

SU-E-J-237: Image Feature Based DRR and Portal Image Registration

Purpose: Two-dimensional (2D) matching of the kV X-ray and digitally reconstructed radiography (DRR) images is an important setup technique for image-guided radiotherapy (IGRT). In our clinics, mutual information based methods are used for this purpose on commercial linear accelerators, but with often needs for manual corrections. This work proved the feasibility that feature based image transform can be used to register kV and DRR images. Methods: The scale invariant feature transform (SIFT) method was implemented to detect the matching image details (or key points) between the kV and DRR images. These key points represent high image intensity gradients, and thus the scale invariant features. Due to the poor image contrast from our kV image, direct application of the SIFT method yielded many detection errors. To assist the finding of key points, the center coordinates of the kV and DRR images were read from the DICOM header, and the two groups of key points with similar relative positions to their corresponding centers were paired up. Using these points, a rigid transform (with scaling, horizontal and vertical shifts) was estimated. We also artificially introduced vertical and horizontal shifts to test the accuracy of our registration method on anterior-posterior (AP) and lateral pelvic images. Results: The results provided a satisfactory overlay of the transformed kV onto the DRR image. The introduced vs. detected shifts were fit into a linear regression. In the AP image experiments, linear regression analysis showed a slope of 1.15 and 0.98 with an R2 of 0.89 and 0.99 for the horizontal and vertical shifts, respectively. The results are 1.2 and 1.3 with R2 of 0.72 and 0.82 for the lateral image shifts. Conclusion: This work provided an alternative technique for kV to DRR alignment. Further improvements in the estimation accuracy and image contrast tolerance are underway.