Intensity Inhomogeneity Research Articles

Hepatic vessels segmentation using deep learning and preprocessing enhancement.

Liver hepatic vessels segmentation is a crucial step for the diagnosis process in patients with hepatic diseases. Segmentation of liver vessels helps to study the liver internal segmental anatomy that helps in the preoperative planning of surgical treatment. Recently, the convolutional neural networks (CNN) have been proved to be efficient for the task of medical image segmentation. The paper proposes an automatic deep learning-based system for liver hepatic vessels segmentation of Computed Tomography (CT) datasets from different sources. The proposed work focuses on the combination of different steps; it starts by a preprocessing step to improve the vessels appearance within the liver region of interest in the CT scans. Coherence enhancing diffusion filtering (CED) and vesselness filtering methods are used to improve vessels contrast and intensity homogeneity. The proposed U-net based network architecture is implemented with modified residual block to include concatenation skip connection. The effect of enhancement using filtering step was studied. Also, the effect of data mismatch used in training and validation is studied. The proposed method is evaluated using many CT datasets. Dice similarity coefficient (DSC) is used to evaluate the method. The average DSC score achieved a score 79%. The proposed approach succeeded to segment liver vasculature from the liver envelope accurately, which makes it as potential tool for clinical preoperative planning.

A hybrid deep learning pavement crack semantic segmentation

Automatic pavement crack segmentation plays a critical role in the field of defect inspection. Although recent segmentation-based CNNs studies showed a promising pavement crack segmentation performance, a challenging task is still remaining due to the inhomogeneity of crack intensity, the complexity of pavement environments, a limited number of labeled training datasets, and the presence of noise in the majority of images in the crack dataset, which makes it difficult to distinguish the cracks from the noise. To overcome these challenges, this study aims to exploit the inherent relationship between classification and segmentation tasks to improve pavement crack segmentation. A hybrid deep learning pavement crack semantic segmentation is proposed based on knowledge transfer among the Class Activation Maps (KTCAM) and the encoder–decoder segmentation network (KTCAM-Net) via the capability of the revised CAM strategy. An adopted trained pavement crack classification network is used to produce high-quality crack localization maps. These localization abilities are fused with the encoder’s image features and fed into the decoder network to provide an accurate pavement crack segmentation. Furthermore, a hybrid loss function is developed to optimize the segmentation network, capture information about thin cracks, and tackle the problem of class imbalance. Afterward, a novel refinement process is applied to purify the segmented crack boundaries. A comprehensive experimental comparison is conducting using four benchmark datasets: DeepCrack, Crack500, CFD, and CrackSC. The proposed KTCAM-Net demonstrates the state-of-the-art segmentation results.

Fast, cheap and sensitive: Homogenizer-based RNA extraction free method for SARS-CoV-2 detection by RT-qPCR.

The SARS-CoV-2 gold standard detection method is an RT-qPCR with a previous step of viral RNA extraction from the patient sample either by using commercial automatized or manual extraction kits. This RNA extraction step is expensive and time demanding. The aim of our study was to evaluate the clinical performance of a simple SARS-CoV-2 detection protocol based on a fast and intense sample homogenization followed by direct RT-qPCR. 388 nasopharyngeal swabs were analyzed in this study. 222 of them tested positive for SARS-CoV-2 by the gold standard RNA extraction and RT-qPCR method, while 166 tested negative. 197 of those 222 positive samples were also positive for the homogenization protocol, yielding a sensitivity of 88.74% (95% IC; 83.83 - 92.58). 166 of those negative samples were also negative for the homogenization protocol, so the specificity obtained was 97% (95% IC; 93.11 - 99.01). For Ct values below 30, meaning a viral load of 103 copies/uL, only 4 SARS-CoV-2 positive samples failed for the RNA extraction free method; for that limit of detection, the homogenizer-based method had a sensitivity of 97.92% (95% CI; 96.01 - 99.83). Our results show that this fast and cheap homogenization method for the SARS-CoV-2 detection by RT-qPCR is a reliable alternative of high sensitivity for potentially infectious SARS-CoV-2 positive patients. This RNA extraction free protocol would help to reduce diagnosis time and cost, and to overcome the RNA extraction kits shortage experienced during COVID-19 pandemic.

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.

Diffraction of a Laguerre-Gaussian beam in Raman interaction with a spatially periodic pump field

We studied Fresnel diffraction of a Laguerre-Gaussian beam ${\text{LG}}_{p,l}$ with arbitrary azimuthal $l$ and radial $p$ indices on a grating induced during its Raman interaction with a spatially periodic pump field in an atomic medium. The diffraction pattern turned out to be more complex than the classical Talbot effect observed when a plane wave illuminates a two-dimensional grating. The simulation results show that, under certain conditions, at distances corresponding to the classical Talbot planes (integer and fractional), periodic amplitude-phase distributions appear. The diffraction patterns are not a probe-field image in the induced grating plane, but a regular array of vortex annular-shaped microbeams with an inhomogeneous intensity distribution depending on the $l$ and $p$ indices and with a topological charge equal to that of the initial probe beam. The intensity and spatial distribution of diffraction patterns can be controlled by Raman amplification in the induced grating by varying the pump-field intensity or the Raman detuning.

Segmentation of Brain Tissues from MRI Images Using Multitask Fuzzy Clustering Algorithm.

In recent years, brain magnetic resonance imaging (MRI) image segmentation has drawn considerable attention. MRI image segmentation result provides a basis for medical diagnosis. The segmentation result influences the clinical treatment directly. Nevertheless, MRI images have shortcomings such as noise and the inhomogeneity of grayscale. The performance of traditional segmentation algorithms still needs further improvement. In this paper, we propose a novel brain MRI image segmentation algorithm based on fuzzy C-means (FCM) clustering algorithm to improve the segmentation accuracy. First, we introduce multitask learning strategy into FCM to extract public information among different segmentation tasks. It combines the advantages of the two algorithms. The algorithm enables to utilize both public information among different tasks and individual information within tasks. Then, we design an adaptive task weight learning mechanism, and a weighted multitask fuzzy C-means (WMT-FCM) clustering algorithm is proposed. Under the adaptive task weight learning mechanism, each task obtains the optimal weight and achieves better clustering performance. Simulated MRI images from McConnell BrainWeb have been used to evaluate the proposed algorithm. Experimental results demonstrate that the proposed method provides more accurate and stable segmentation results than its competitors on the MRI images with various noise and intensity inhomogeneity.

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.

Segmenting lung parenchyma from CT images with gray correlation‐based clustering

AbstractLung segmentation, a prerequisite step of lung disease detection in computer‐aided diagnosis system, is a challenging task because of noises, complex structures, as well as large individual differences of lung CT scans. Here, an automatic algorithm for segmenting lungs from thoracic CT images accurately is presented. This scheme consists of three principal steps: image preprocessing, lung extracting and contour correcting. To cope with inhomogeneous intensities of CT images, a novel preprocessing approach based on empirical mode decomposition and bilateral filter is proposed, which has abilities of denoising, smoothing and edge keeping. Lung region is then extracted with a novel gray correlation‐based clustering approach. A new lung contour correction technology is finally employed to repair the concave regions caused by pulmonary nodules, vessels and so on. Experimental results show that the preprocessing approach outperforms other methods on image denoising and smoothing. Meanwhile, the lung segmentation algorithm is tested on a group of lung CT images affected with interstitial lung diseases and achieves a high segmentation accuracy. Compared with several existing lung segmentation methods, this algorithm exhibits a better performance on lung segmentation.

Brain tumor segmentation of the FLAIR MRI images using novel ResUnet

New technologies are growing faster and now play a key role in analysing new ways of looking at the morphology of the brain. It is difficult to diagnose a brain tumor. Accurate diagnosis and segmentation of the brain tumor used for early treatment planning. Different neuroimaging modalities are used to provide better tissue resolution and provide assistance to the radiologist. Manual segmentation of the brain tumor is a complicated task as it faces problems with noise, intensity inhomogeneity, merging of tissues, and overlapping of tissue intensity. This makes manual segmentation a time consuming approach. In recent CAD systems are developed using deep learning models. In this paper, we used residual models and form as a Unet to perform segmentation of the tissues. To perform segmentation, we used the Kaggle LGG dataset, which contains 110 patient datasets. We designed a novel residual modelused as the backbone to design Unet from scratch and perform segmentation of multi spectral images. The Proposed model works well, and the performance of the model is analysed using the Dice coefficient, Jaccard index/IoU. The model yields a dice coefficient of 0.9056 and a jaccard index/ IoU of 0.8293. This model gives better tissue segmentation using FLAIR modality compared to the existing frame work.

An active contour model reinforced by convolutional neural network and texture description

Active contour models (ACMs)are popular and widely used for many image segmentationapplications and obtain promising results. However, these methods are unable to achieve the highest performance in the presence ofintensity inhomogeneity. To address this issue, this paper presents an ACM based on the combination of a convolutional neural network (CNN) and a texture descriptor approach.This study uses a CNN model to generate parameter maps more effectively for ACM. Compared to conventional global techniques, these parameter maps increase the speed of movement of the contour into the target. In this approach, the Local Word Directional Pattern (LWDP) is applied as the texture descriptor. LWDP is a texture descriptor that uses the angle between two gradients for exploring the texture structure inside the image. In the proposed method both the original image and the new image obtained bythe LWDP texture descriptor(encoded image) are provided as inputs to the CNN. The experimental outcomes show that the proposed strategy consistently outperforms thestate-of-the-art in accuracy and robustness for segmenting images with fuzzy boundaries and intensity inhomogeneity.

Lung and Infection CT-Scan-Based Segmentation with 3D UNet Architecture and Its Modification.

COVID-19 is the disease that has spread over the world since December 2019. This disease has a negative impact on individuals, governments, and even the global economy, which has caused the WHO to declare COVID-19 as a PHEIC (Public Health Emergency of International Concern). Until now, there has been no medicine that can completely cure COVID-19. Therefore, to prevent the spread and reduce the negative impact of COVID-19, an accurate and fast test is needed. The use of chest radiography imaging technology, such as CXR and CT-scan, plays a significant role in the diagnosis of COVID-19. In this study, CT-scan segmentation will be carried out using the 3D version of the most recommended segmentation algorithm for bio-medical images, namely 3D UNet, and three other architectures from the 3D UNet modifications, namely 3D ResUNet, 3D VGGUNet, and 3D DenseUNet. These four architectures will be used in two cases of segmentation: binary-class segmentation, where each architecture will segment the lung area from a CT scan; and multi-class segmentation, where each architecture will segment the lung and infection area from a CT scan. Before entering the model, the dataset is preprocessed first by applying a minmax scaler to scale the pixel value to a range of zero to one, and the CLAHE method is also applied to eliminate intensity in homogeneity and noise from the data. Of the four models tested in this study, surprisingly, the original 3D UNet produced the most satisfactory results compared to the other three architectures, although it requires more iterations to obtain the maximum results. For the binary-class segmentation case, 3D UNet produced IoU scores, Dice scores, and accuracy of 94.32%, 97.05%, and 99.37%, respectively. For the case of multi-class segmentation, 3D UNet produced IoU scores, Dice scores, and accuracy of 81.58%, 88.61%, and 98.78%, respectively. The use of 3D segmentation architecture will be very helpful for medical personnel because, apart from helping the process of diagnosing someone with COVID-19, they can also find out the severity of the disease through 3D infection projections.

AXanthoceras sorbifoliumcrack segmentation method based on an improved level set

AbstractThe dehiscence of theXanthoceras sorbifolium (X. sorbifolium)may lead to seeds jump out and economic loss. The shape and the degree of the crack will provide the relevant elements for the study of theX. sorbifoliumdehiscence and duly picked. Therefore, an improved level set method is proposed forX. sorbifoliumcrack segmentation. The problems of intensity inhomogeneity and so on, which pose challenges for accurate crack segmentation. The local Gaussian distribution fitting method has a good segmentation effect, but it is sensitive to the initial contour and does not use gradient information, which affects the accurate location of the edge. Aiming at the above problems and the scene of crack segmentation, this paper firstly adopts histogram threshold method to obtain the initial contour automatically. Secondly, the energy function is constructed by combining local and edge information. Finally, the double‐well potential function is used to reduce the oscillation and distortion of the method. In this paper, the experiment results show that the average boundary precision is 88.25% and average segmentation time of each image is 12.7s of the proposed method. After comprehensive analysis of IoU and boundary recall, the method in this paper achieves better results.

Fuzzy Sparse Subspace Clustering for Infrared Image Segmentation.

Infrared image segmentation is a challenging task, due to interference of complex background and appearance inhomogeneity of foreground objects. A critical defect of fuzzy clustering for infrared image segmentation is that the method treats image pixels or fragments in isolation. In this paper, we propose to adopt self-representation from sparse subspace clustering in fuzzy clustering, aiming to introduce global correlation information into fuzzy clustering. Meanwhile, to apply sparse subspace clustering for non-linear samples from an infrared image, we leverage membership from fuzzy clustering to improve conventional sparse subspace clustering. The contributions of this paper are fourfold. First, by introducing self-representation coefficients modeled in sparse subspace clustering based on high-dimensional features, fuzzy clustering is capable of utilizing global information to resist complex background as well as intensity inhomogeneity of objects, so as to improve clustering accuracy. Second, fuzzy membership is tactfully exploited in the sparse subspace clustering framework. Thereby, the bottleneck of conventional sparse subspace clustering methods, that they could be barely applied to nonlinear samples, can be surmounted. Third, as we integrate fuzzy clustering and subspace clustering in a unified framework, features from two different aspects are employed, contributing to precise clustering results. Finally, we further incorporate neighbor information into clustering, thus effectively solving the uneven intensity problem in infrared image segmentation. Experiments examine the feasibility of proposed methods on various infrared images. Segmentation results demonstrate the effectiveness and efficiency of the proposed methods, which proves the superiority compared to other fuzzy clustering methods and sparse space clustering methods.

Efficient convex region-based segmentation for noising and inhomogeneous patterns

Image segmentation, under the broader area of computer vision and digital image processing, facilitates comprehending a digital image by partitioning it into small and meaningful segments, regions or objects. Researchers have come up with numerous solutions, which have produced promising results. However, these results are compromised when applied to global segmentation, where all the objects/features are needed to be segmented for inhomogeneous and severe noisy images. The reasons are many including (ⅰ) the use of region-based active contour method, especially when its noise distribution is unknown; (ⅱ) lack of robustness to handle images corrupted by some multiplicative and additive noise; (ⅲ) inability to handle convex images at local minima. To fill this gap in the literature and come up with a more effective solution, this paper proposes a global segmentation model that implements a local image difference technique combined with average convolution local factor based on spatial distances and intensity differences in the local region. The proposed model has been tested and evaluated on outdoor, synthetic, and medical images, where it has outperformed the latest baselines. The model is capable of tackling efficiently noise/outliers and coping with intensity inhomogeneity issues.

Modulation Learning on Fourier-Domain for Road Extraction From Remote Sensing Images

Extraction road from remote sensing (RS) images is a challenging topic because of the inhomogeneous intensity, non-consistent contrast, and very cluttered background of satellite images. Most previous approaches, relying on convolutions or self-attention, are built on local operation or global modeling on spatial domain, but are difficult to capture weak and continuous road objects. The spectral representation of road image features and modulation learning on it provide a novel long-range dependent and fine-grained feature representation mechanism. Based on it, we propose a novel road extraction network on RS images, called an adaptive Fourier filtered U-shaped network (AFU-Net) in this letter, which relies on modulation learning on the Fourier-domain. The AFU-Net is composed of modulation learner (MoL) basic blocks and follows the pipeline of classical U-Net model. The basic MoL block includes a global modulation learner (GML) block for global spectral modulation learning and an attentive modulation learner (AML) block which contains two parallel layers, i.e. phase-modulated filter (PMF) and magnitude-modulated filter (MMF), for fine-grained spectral modulation on the Fourier spectrum. The experiments on two public datasets, such as Massachusetts Roads and DeepGlobe Road Datasets have shown outstanding performance of AFU-Net on the metrics of accuracy, precision, recall and mIoU etc.

Spectral Intensity of Electron Cyclotron Radiation Emerging from the Plasma to the First Wall in ITER

It is predicted that in ITER, due to high values of electron temperature and magnetic field strength, electron cyclotron (EC) radiation emitted by plasma will be a significant source (together with external EC radiation injected for auxiliary plasma heating and non-inductive current drive) of additional thermal and electromagnetic loads for microwave and optical diagnostics. The spectral distribution of plasma EC radiation is particularly important to consider in millimeter-wave diagnostics, namely for high- and low-magnetic-field side reflectometry, plasma position reflectometry, and collective Thomson scattering diagnostic, because the transmission lines of these diagnostics yield the transport of EC waves emitted by the plasma. The development of semi-analytical methods used to describe the spectral distribution of plasma-generated EC radiation in tokamaks, starting from the work of S. Tamor, is based on the dominance of multiple reflections of this radiation from the first wall in a toroidal axially symmetric vacuum chamber. Here, we present calculations using the CYNEQ code of the spectral intensity of the EC radiation emerging from the plasma to the first wall and port plugs for five scenarios of ITER operation. This code uses the symmetry-based effect of approximate isotropy and homogeneity of radiation intensity in a substantial part of the phase space and has been successfully tested by comparison with first-principles codes. The energy flux density in the range of 30–200 kW/m2 is predicted for wall reflectance in the range of 0.6–0.95. The possible effect of this radiation on in-vessel components and diagnostics is assessed by calculating the surface density of the energy absorbed by various materials of the ITER first wall.

ALVLS: Adaptive local variances-Based levelset framework for medical images segmentation

Medical image segmentation is a very challenging task, not only because the intensity of the medical image itself is not uniform, but also it may be accompanied by the impact of noise. Although mathematics, computer science, medicine, and other interdisciplinary fields have begun to study the problem of medical image segmentation, and have put forward a variety of segmentation algorithms, there is still much room for further improvement and enhancement. In the process of medical image collection and reconstruction, it is easy to produce intensity inhomogeneity and noises, as well as interference from other tissues, resulting in the difficulty of accurate segmentation. In this paper, we propose the adaptive local variances-based level set (ALVLS) model to segment medical images with intensity inhomogeneity and noises, including cardiac MR images, brain MR images, and breast ultrasound images. According to the variance difference information, the ALVLS model can adjust the effect of the area term adaptively. The local intensity variances are designed to optimize the ability to resist noise, which improves the segmentation accuracy of medical images. We also propose the two-layer level set model for segmenting left ventricles and left epicardium simultaneously. Experimental results for medical images and synthetic images show the desirable performance of the ALVLS model in accuracy, efficiency, and robustness to noise. In medical image competition, the Dice coefficient is used to calculate the similarity between the segmentation result and the ground truth. Thus we do comparisons with other methods and show that the Dice coefficient of the proposed method is higher than other testing methods.

Adaptive weighted curvature-based active contour for ultrasonic and 3T/5T MR image segmentation

Image segmentation is a complex and core technique for disease diagnosis or image-guided surgery in the medical image domain. However, low-quality images, such as images with weak edges and intensity inhomogeneities, may bring considerable challenges for radiologists. In this paper, we propose an adaptive weighted curvature-based active contour model by coupling heat kernel convolution and adaptively weighted high-order total variation for medical image segmentation to improve diagnosis effectiveness. To reduce the computational complexity, the heat kernel convolution operation is applied to approximate the perimeter of a segmentation curve. In addition, the weighted parameter included in the high-order total variation term can be automatically evaluated based on an adaptive input image to emphasize local structures and increase segmentation accuracy. Since the proposed method is a smoothing optimization model, the alternating direction method of multipliers is introduced to translate the original problems into several easily solvable subproblems. The numerical experimental results on ultrasonic and 3T/5T MRI datasets demonstrate that the proposed model is quite efficient and robust compared with several traditional segmentation methods.

Power mean based image segmentation in the presence of noise

In image segmentation and in general in image processing, noise and outliers distort contained information posing in this way a great challenge for accurate image segmentation results. To ensure a correct image segmentation in presence of noise and outliers, it is necessary to identify the outliers and isolate them during a denoising pre-processing or impose suitable constraints into a segmentation framework. In this paper, we impose suitable removing outliers constraints supported by a well-designed theory in a variational framework for accurate image segmentation. We investigate a novel approach based on the power mean function equipped with a well established theoretical base. The power mean function has the capability to distinguishes between true image pixels and outliers and, therefore, is robust against outliers. To deploy the novel image data term and to guaranteed unique segmentation results, a fuzzy-membership function is employed in the proposed energy functional. Based on qualitative and quantitative extensive analysis on various standard data sets, it has been observed that the proposed model works well in images having multi-objects with high noise and in images with intensity inhomogeneity in contrast with the latest and state-of-the-art models.

Automatic segmentation of ultrasound images using SegNet and local Nakagami distribution fitting model

Automatic and accurate segmentation of ultrasound (US) images plays a vital role in computer-aided diagnosis of many diseases. However, multiple degradations within US images, such as speckle noise, intensity inhomogeneity, shadows, low contrast, and low signal-to-noise ratio, often cover up the details of imaging tissues and blur the edges of lesions, resulting in limited accuracy for existing segmentation algorithms. To tackle these issues, a coarse-to-fine segmentation method combining deep learning with an active contour model (ACM) is proposed in this paper. At the first stage, a SegNet is trained and employed to predict the segmentation mask because it not only has a superior boundary delineation capability, but also has high efficiency in terms of memory and computational time during inference. Due to the multiple degradations of US images, the unavailability of large-scale US image datasets, and the loss of spatial information during downsampling, the SegNet may only infer the coarse object boundaries, especially for the tissue with blurred edges. At the second stage, the segmentation mask of the SegNet is refined to locate the accurate object boundaries by a novel ACM termed the local Nakagami distribution fitting (LNDF) model, which takes advantage of discrepancies between Nakagami distributions of different tissues around the boundaries within US images. Experimental results on two US image datasets demonstrate that, compared with some state-of-the-art segmentation methods, our proposed method achieves the highest segmentation accuracy at the cost of acceptable running time, and thereby adapts to the automatic segmentation of US images in clinical applications.