Developing a Recognition System for Classifying COVID-19 Using a Convolutional Neural Network Algorithm

The COVID-19 pandemic poses an additional serious public health threat due to little or no pre-existing human immunity, and developing a system to identify COVID-19 in its early stages will save millions of lives. This study applied support vector machine (SVM), k-nearest neighbor (K-NN) and deep learning convolutional neural network (CNN) algorithms to classify and detect COVID-19 using chest X-ray radiographs. To test the proposed system, chest X-ray radiographs and CT images were collected from different standard databases, which contained 95 normal images, 140 COVID-19 images and 10 SARS images. Two scenarios were considered to develop a system for predicting COVID-19. In the first scenario, the Gaussian filter was applied to remove noise from the chest X-ray radiograph images, and then the adaptive region growing technique was used to segment the region of interest from the chest X-ray radiographs. After segmentation, a hybrid feature extraction composed of 2D-DWT and gray level co-occurrence matrix was utilized to extract the features significant for detecting COVID-19. These features were processed using SVM and K-NN. In the second scenario, a CNN transfer model (ResNet 50) was used to detect COVID-19. The system was examined and evaluated through multiclass statistical analysis, and the empirical results of the analysis found significant values of 97.14%, 99.34%, 99.26%, 99.26% and 99.40% for accuracy, specificity, sensitivity, recall and AUC, respectively. Thus, the CNN model showed significant success; it achieved optimal accuracy, effectiveness and robustness for detecting COVID-19.     

Investigation of multi-frame image super-resolution based on adaptive self-learning methods

The goal of this paper is to introduce and demonstrate a new high-performance super-resolution (SR) method for multi-frame images. By combining learning-based and reconstruction-based SR methods, this paper proposes a multi-frame image super-resolution method based on adaptive self-learning. Using the adaptive self-learning method and recovery of high-frequency edge information, an initial high-resolution (HR) image containing effective texture information is obtained. The edge smoothness prior is then used to satisfy the global reconstruction constraint and enhance the quality of the HR image. Our results indicate that this method achieves better performance than several other methods for both simulated data and real-scene images.     

基于自相似性与稀疏表示的超分辨率算法

目的为了解决当前稀疏表示的超分辨率算法效果依赖参与训练的数据的问题,结合图像的自相似性,提出一种基于自相似性与稀疏表示相结合的超分辨率算法。方法算法利用图像的多维自相似性,构建多维图像金字塔,采用改进的相似块搜索策略,得到对应的高低分辨率图像块作为训练样本,然后对样本进行字典训练,最后根据稀疏表示得到超分辨率图像。结果实验结果显示,文中算法在峰值信噪比(PSNR)和结构相似度(SSIM)上优于其他算法,对于实验图像而言,PSNR平均提升了0.5 dB。结论提出的超分辨率算法未引入外部数据库,具有较好的效果,能够用于超分辨率重建。     

Image SR-based NLM and DCNN improved IBP with cubic B-spline

ABSTRACT

Image super-resolution (SR) techniques aim to estimate high-resolution (HR) image from low-resolution (LR) image. Existing SR method has slow convergence and recovery of high-frequency details are inaccurate. To overcome these issues, two algorithms have been proposed for image SR based on non-local means improved iterative back projection (NLM-IIBP), deep convolutional neural network improved iterative back projection (DCNN-IIBP) to produce high-resolution images with low noise, minimal blur by restoring high-frequency details. In NLM-IIBP denoised images have been interpolated using cubic B-spline interpolation and processed using IIBP based on guided bilateral method. NLM preserves the edges effectively, but does not consider high dimensional information and over smoothing during noise minimization. To further improve the resolution, NLM is replaced by DCNN. DCNN denoising method suppresses different noises at different noise levels. The proposed algorithms have been analysed and compared with existing approaches using various parameters to prove the effectiveness.     

A novel multimodal medical image fusion using sparse representation and modified spatial frequency

Fusion of multimodal imaging data supports medical experts with ample information for better disease diagnosis and further clinical investigations. Recently, sparse representation (SR)‐based fusion algorithms has been gaining importance for their high performance. Building a compact, discriminative dictionary with reduced computational effort is a major challenge to these algorithms. Addressing this key issue, we propose an adaptive dictionary learning approach for fusion of multimodal medical images. The proposed approach consists of three steps. First, zero informative patches of source images are discarded by variance computation. Second, the structural information of remaining image patches is evaluated using modified spatial frequency (MSF). Finally, a selection rule is employed to separate the useful informative patches of source images for dictionary learning. At the fusion step, batch‐OMP algorithm is utilized to estimate the sparse coefficients. A novel fusion rule which measures the activity level in both spatial domain and transform domain is adopted to reconstruct the fused image with the sparse vectors and trained dictionary. Experimental results of various medical image pairs and clinical data sets reveal that the proposed fusion algorithm gives better visual quality and competes with existing methodologies both visually and quantitatively.     

On the Detection of COVID-19 from Chest X-Ray Images Using CNN-Based Transfer Learning

Coronavirus disease (COVID-19) is an extremely infectious disease and possibly causes acute respiratory distress or in severe cases may lead to death. There has already been some research in dealing with coronavirus using machine learning algorithms, but few have presented a truly comprehensive view. In this research, we show how convolutional neural network (CNN) can be useful to detect COVID-19 using chest X-ray images. We leverage the CNN-based pre-trained models as feature extractors to substantiate transfer learning and add our own classifier in detecting COVID-19. In this regard, we evaluate performance of five different pre-trained models with fine-tuning the weights from some of the top layers. We also develop an ensemble model where the predictions from all chosen pre-trained models are combined to generate a single output. The models are evaluated through 5-fold cross validation using two publicly available data repositories containing healthy and infected (both COVID-19 and other pneumonia) chest X-ray images. We also leverage two different visualization techniques to observe how efficiently the models extract important features related to the detection of COVID- 19 patients. The models show high degree of accuracy, precision, and sensitivity. We believe that the models will aid medical professionals with improved and faster patient screening and pave a way to further COVID-19 research.     

A robust variational approach to super-resolution with nonlocal TV regularisation term

Abstract

Multi frame super-resolution (SR) reconstruction algorithms make use of complimentary information among low-resolution (LR) images to yield a high-resolution (HR) image. Inspired by recent development on the video denoising problem, we propose a robust variational approach for SR-based on a constrained variational model that uses the nonlocal total variation (TV) as a regularisation term. In our method, a weighted fidelity term is proposed to take into account inaccurate estimates of the registration parameters and the point spread function. Moreover, we introduce the nonlocal TV as a regularisation term in order to take into account complex spatial interactions within images. In this way, important features and fine details are enhanced simultaneously with noise reduction. Furthermore, an alternative nonlocal TV regularisation is proposed based on a better weight function which integrates gradient similarity and radiometric similarity. Experiments show the effectiveness and practicability of the proposed method.     

彩色图像多尺度引导的深度图像超分辨率重建

为获得更优的深度图像超分辨率重建结果,本文构建了彩色图像多尺度引导深度图像超分辨率重建卷积神经网络。该网络使用多尺度融合方法实现高分辨率(HR)彩色图像特征对低分辨率(LR)深度图像特征的引导,有益于恢复图像细节信息。在对LR深度图像提取特征的过程中,构建了多感受野残差块(MRFRB)提取并融合不同感受野下的特征,然后将每一个MRFRB输出的特征连接、融合,得到全局融合特征。最后,通过亚像素卷积层和全局融合特征,得到HR深度图像。实验结果表明,该算法得到的超分辨率图像缓解了边缘失真和伪影问题,有较好的视觉效果。     

Robust MR image super-resolution reconstruction with cross-modal edge-preserving regularization

In this article, we propose a novel image super-resolution (SR) reconstruction method in the field of magnetic resonance imaging, which is based on a cross-modal edge-preserving regularization integrating the internal gradient prior from the target-modal image itself and the external gradient prior from the reference-modal image obtained by pre-scan in many medical imaging scenes. The reference-modal image is a high-resolution guidance image that has much shareable information such as gradient orientation on edge regions, which can be used to improve the image resolution of the target modal. In addition, to be robust against the misalignment between the target-modal image and reference-modal image, a multimodal registration is incorporated in the SR reconstruction process. In this work, the proposed SR method can be formulated as an alternating optimization problem, that is, the target-modal and reference-modal images are alternately updated through iterations. Experimental results on simulated and realistic images show the superior performance of the proposed approach over several state-of-the-art SR techniques.     

Modified Global Flower Pollination Algorithm‐based image fusion for medical diagnosis using computed tomography and magnetic resonance imaging

Recently, the computed tomography (CT) and magnetic resonance imaging (MRI) medical image fusion have turned into a challenging issue in the medical field. The optimal fused image is a significant component to detect the disease easily. In this research, we propose an iterative optimization approach for CT and MRI image fusion. Initially, the CT and MRI image fusion is subjected to a multilabel optimization problem. The main aim is to minimize the data and smoothness cost during image fusion. To optimize the fusion parameters, the Modified Global Flower Pollination Algorithm is proposed. Here, six sets of fusion images with different experimental analysis are evaluated in terms of different evaluation metrics such as accuracy, specificity, sensitivity, SD, structural similarity index, feature similarity index, mutual information, fusion quality, and root mean square error (RMSE). While comparing to state‐of‐art methods, the proposed fusion model provides best RMSE with higher fusion performance. Experiments on a set of MRI and CT images of medical data set show that the proposed method outperforms a very competitive performance in terms of fusion quality.     

低分辨率多描述编码图像的超分辨率重构

图像的高质量、低帧率传输有较广泛的应用.由于传输信道的不可靠、易丢包或误码等固有特性使传输图像降质甚至无法正常译码.本文对原图像亚采样后进行低分辨率多描述编码以增强传输鲁棒性,接收端再采用多幅解码图像超分辨率重构,可在相同信道条件下得到2～3 dB的PSNR增益.并且可以结合目前几乎所有的图像多描述编码技术和超分辨率重构算法,有很强的应用和推广价值.     

Super-resolution of images: Algorithms,principles, performance

A new facet of image restoration research has begun to emerge in recent years: super-resolution of images, which we define as the processing of an image so as to recover object information from beyond the spatial frequency bandwidth of the optical system that formed the image. Simple Fourier analysis would indicate that super-resolution is not possible. Therefore, it is important to reconcile this simplistic view with the existing algorithms that have been demonstrated to achieve super-resolution. In this article, we consider some of the algorithms that have demonstrated super-resolution and discuss the common principles that they share which makes it possible for them to recover some of the lost bandwidth of the object. We also consider the question of super-resolution performance, which is the measure of how much lost bandwidth can be recovered from a super-resolution algorithm, and how the performance is related to the algorithm principles that allow super-resolution to occur. We conclude with examples of super-resolution.     

基于组合图像特征与分层节点搜索的回环检测方法

目的 文中通过提出一种新的回环解决方案,平衡回环检测系统的高准确率与高运行效率。方法 提出一种利用组合图像特征与分层节点搜索的新方法。首先,计算一种原始图像的下采样二值化全局特征和经过改进的ORB(oriented FAST and rotated BRIEF)局部特征,将其存入图像特征数据库。其次,引入一种分层节点搜索算法,在数据库中搜索与当前图像特征最相似的全局特征作为回环候选。最后,利用改进的ORB特征进行局部特征匹配,验证候选图像,确定回环检测结果。结果 使用该算法在3个不同的数据集上进行验证,测试中每次回环检测的平均处理时间仅需19 ms。结论 实验结果表明,该算法在运行效率、准确率、召回率等方面均达到了领域内的先进水平。     

基于特征能量加权的红外与可见光图像融合

目前红外与可见光图像直接融合存在红外目标取舍和场景信息提取困难,结合非采样Contourlet的多尺度、多方向性和平移不变性的优点,本文提出了一种基于非采样Contourlet变换(NSCT)的红外与可见光图像融合方法.首先对源图像进行分解,然后低频子带通过构造基于区域的特征像素能量,进行加权融合,高频子带直接选用方差取大法融合.使用该算法进行了融合实验,并给出了融合质量评价.实验结果表明,本文提出的基于NSCT的图像融合算法在保留图像细节信息、增加信息量方面都有显著地提高.     

Deep Learning Approach for Analysis and Characterization of COVID-19

Early diagnosis of a pandemic disease like COVID-19 can help deal with a dire situation and help radiologists and other experts manage human resources more effectively. In a recent pandemic, laboratories perform diagnostics manually, which requires a lot of time and expertise of the laboratorial technicians to yield accurate results. Moreover, the cost of kits is high, and well-equipped labs are needed to perform this test. Therefore, other means of diagnosis is highly desirable. Radiography is one of the existing methods that finds its use in the diagnosis of COVID-19. The radiography observes change in Computed Tomography (CT) chest images of patients, developing a deep learning-based method to extract graphical features which are used for automated diagnosis of the disease ahead of laboratory-based testing. The proposed work suggests an Artificial Intelligence (AI) based technique for rapid diagnosis of COVID-19 from given volumetric chest CT images of patients by extracting its visual features and then using these features in the deep learning module. The proposed convolutional neural network aims to classify the infectious and non-infectious SARS-COV2 subjects. The proposed network utilizes 746 chests scanned CT images of 349 images belonging to COVID-19 positive cases, while 397 belong to negative cases of COVID-19. Our experiment resulted in an accuracy of 98.4%, sensitivity of 98.5%, specificity of 98.3%, precision of 97.1%, and F1-score of 97.8%. The additional parameters of classification error, mean absolute error (MAE), root-mean-square error (RMSE), and Matthew’s correlation coefficient (MCC) are used to evaluate our proposed work. The obtained result shows the outstanding performance for the classification of infectious and non-infectious for COVID-19 cases.     

Super-Resolution Reconstruction of Images Based on Microarray Camera

In the field of images and imaging, super-resolution (SR) reconstruction of images is a technique that converts one or more low-resolution (LR) images into a highresolution (HR) image. The classical two types of SR methods are mainly based on applying a single image or multiple images captured by a single camera. Microarray camera has the characteristics of small size, multi views, and the possibility of applying to portable devices. It has become a research hotspot in image processing. In this paper, we propose a SR reconstruction of images based on a microarray camera for sharpening and registration processing of array images. The array images are interpolated to obtain a HR image initially followed by a convolution neural network (CNN) procedure for enhancement. The convolution layers of our convolution neural network are 3×3 or 1×1 layers, of which the 1×1 layers are used to improve the network performance particularly. A bottleneck structure is applied to reduce the parameter numbers of the nonlinear mapping and to improve the nonlinear capability of the whole network. Finally, we use a 3×3 deconvolution layer to significantly reduce the number of parameters compared to the deconvolution layer of FSRCNN-s. The experiments show that the proposed method can not only ameliorate effectively the texture quality of the target image based on the array images information, but also further enhance the quality of the initial high resolution image by the improved CNN.     

Efficient Deep CNN Model for COVID-19 Classification

Coronavirus (COVID-19) infection was initially acknowledged as a global pandemic in Wuhan in China. World Health Organization (WHO) stated that the COVID-19 is an epidemic that causes a 3.4% death rate. Chest X-Ray (CXR) and Computerized Tomography (CT) screening of infected persons are essential in diagnosis applications. There are numerous ways to identify positive COVID-19 cases. One of the fundamental ways is radiology imaging through CXR, or CT images. The comparison of CT and CXR scans revealed that CT scans are more effective in the diagnosis process due to their high quality. Hence, automated classification techniques are required to facilitate the diagnosis process. Deep Learning (DL) is an effective tool that can be utilized for detection and classification this type of medical images. The deep Convolutional Neural Networks (CNNs) can learn and extract essential features from different medical image datasets. In this paper, a CNN architecture for automated COVID-19 detection from CXR and CT images is offered. Three activation functions as well as three optimizers are tested and compared for this task. The proposed architecture is built from scratch and the COVID-19 image datasets are directly fed to train it. The performance is tested and investigated on the CT and CXR datasets. Three activation functions: Tanh, Sigmoid, and ReLU are compared using a constant learning rate and different batch sizes. Different optimizers are studied with different batch sizes and a constant learning rate. Finally, a comparison between different combinations of activation functions and optimizers is presented, and the optimal configuration is determined. Hence, the main objective is to improve the detection accuracy of COVID-19 from CXR and CT images using DL by employing CNNs to classify medical COVID-19 images in an early stage. The proposed model achieves a classification accuracy of 91.67% on CXR image dataset, and a classification accuracy of 100% on CT dataset with training times of 58 min and 46 min on CXR and CT datasets, respectively. The best results are obtained using the ReLU activation function combined with the SGDM optimizer at a learning rate of 10⁻⁵ and a minibatch size of 16.     

Computer‐aided diagnosis system for the detection of bronchiectasis in chest computed tomography images

A computer‐aided diagnosis (CAD) system has been developed for the detection of bronchiectasis from computed tomography (CT) images of chest. A set of CT images of the chest with known diagnosis were collected and these images were first denoised using Wiener filter. The lung tissue was then segmented using optimal thresholding. The Pathology Bearing Regions (PBRs) were then extracted by applying pixel‐based segmentation. For each PBR, a gray level co‐occurrence matrix (GLCM) was constructed. From the GLCM texture features were extracted and feature vectors were constructed. A probabilistic neural network (PNN) was constructed and trained using this set of feature vectors. The images together with the PBRs and the corresponding feature vector and diagnosis were stored in an image database. Rules for diagnosis and for determining the severity of the disease were generated by analyzing the images known to be affected by bronchiectasis. The rules were then validated by a human expert. The validated rules were stored in the Knowledge Base. When a physician gives a CT image to the CAD system, it first transforms the image into a set of feature vectors, one for each PBR in the image. It then performs the diagnosis using two techniques: PNN and mahalanobis distance measure. The final diagnosis and the severity of the disease are determined by correlating the diagnosis determined by both the techniques in consultation with the knowledge base. The system also retrieves similar cases from the database. Thus, this system would aid the physicians in diagnosing bronchiectasis. © 2009 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 19, 290–298, 2009