Recognition of COVID-19 disease from X-ray images by hybrid model consisting of 2D curvelet transform, chaotic salp swarm algorithm and deep learning technique

The novel coronavirus disease 2019 (COVID-19), detected in Wuhan City, Hubei Province, China in late December 2019, is rapidly spreading and affecting all countries in the world. Real-time reverse transcription-polymerase chain reaction (RT-PCR) test has been described by the World Health Organization (WHO) as the standard test method for the diagnosis of the disease. However, considering that the results of this test are obtained between a few hours and two days, it is very important to apply another diagnostic method as an alternative to this test. The fact that RT-PCR test kits are limited in number, the test results are obtained in a long time, and the high probability of healthcare personnel becoming infected with the disease during the test, necessitates the use of other diagnostic methods as an alternative to these test kits. In this study, a hybrid model consisting of two-dimensional (2D) curvelet transformation, chaotic salp swarm algorithm (CSSA) and deep learning technique is developed in order to determine the patient infected with coronavirus pneumonia from X-ray images. In the proposed model, 2D Curvelet transformation is applied to the images obtained from the patient's chest X-ray radiographs and a feature matrix is formed using the obtained coefficients. The coefficients in the feature matrix are optimized with the help of the CSSA and COVID-19 disease is diagnosed by the EfficientNet-B0 model, which is one of the deep learning methods. Experimental results show that the proposed hybrid model can diagnose COVID-19 disease with high accuracy from chest X-ray images.

Methods for Quantifying Fibrillar Collagen Alignment

Recent evidence has implicated collagen, particularly fibrillar collagen, in a number of diseases ranging from osteogenesis imperfecta and asthma to breast and ovarian cancer. A key property of collagen that has been correlated with disease has been the alignment of collagen fibers. Collagen can be visualized using a variety of imaging techniques including second-harmonic generation (SHG) microscopy, polarized light microscopy, and staining with dyes or antibodies. However, there exists a great need to easily and robustly quantify images from these modalities for individual fibers in specified regions of interest and with respect to relevant boundaries. Most currently available computational tools rely on calculation of pixel-wise orientation or global window-wise orientation that do not directly calculate or give visible fiber-wise information and do not provide relative orientation against boundaries. We describe and detail how to use a freely available, open-source MATLAB software framework that includes two separate but linked packages "CurveAlign" and "CT-FIRE" that can address this need by either directly extracting individual fibers using an improved fiber tracking algorithm or directly finding optimal representation of fiber edges using the curvelet transform. This curvelet-based framework allows the user to measure fiber alignment on a global, region of interest, and fiber basis. Additionally, users can measure fiber angle relative to manually or automatically segmented boundaries. This tool does not require prior experience of programming or image processing and can handle multiple files, enabling efficient quantification of collagen organization from biological datasets.

Breast cancer diagnosis in digitized mammograms using curvelet moments

BACKGROUND

Feature extraction is a key issue in designing a computer aided diagnosis system. Recent researches on breast cancer diagnosis have reported the effectiveness of multiscale transforms (wavelets and curvelets) for mammogram analysis and have shown the superiority of curvelet transform. However, the curse of dimensionality problem arises when using the curvelet coefficients and therefore a reduction method is required to extract a reduced set of discriminative features.

METHODS

This paper deals with this problem and proposes a feature extraction method based on curvelet transform and moment theory for mammogram description. First, we performed discrete curvelet transform and we computed the four first-order moments from curvelet coefficients distribution. Hence, two feature sets can be obtained: moments from each band and moments from each level. In this work, both sets are studied. Then, the t-test ranking technique was applied to select the best features from each set. Finally, a k-nearest neighbor classifier was used to distinguish between normal and abnormal breast tissues and to classify tumors as malignant or benign. Experiments were performed on 252 mammograms from the Mammographic Image Analysis Society (mini-MIAS) database using the leave-one-out cross validation as well as on 11553 mammograms from the Digital Database for Screening Mammography (DDSM) database using 2×5-fold cross validation.

RESULTS

Experimental results prove the effectiveness and the superiority of curvelet moments for mammogram analysis. Indeed, results on the mini-MIAS database show that curvelet moments yield an accuracy of 91.27% (resp. 81.35 %) with 10 (resp. 8) features for abnormality (resp. malignancy) detection. In addition, empirical comparisons of the proposed method against state-of-the-art curvelet-based methods on the DDSM database show that the suggested method does not only lead to a more reduced feature set, but it also statistically outperforms all the compared methods in terms of accuracy.

CONCLUSIONS

In summary, curvelet moments are an efficient and effective way to extract a reduced set of discriminative features for breast cancer diagnosis.

Automated characterization of fatty liver disease and cirrhosis using curvelet transform and entropy features extracted from ultrasound images

Fatty liver disease (FLD) is reversible disease and can be treated, if it is identified at an early stage. However, if diagnosed at the later stage, it can progress to an advanced liver disease such as cirrhosis which may ultimately lead to death. Therefore, it is essential to detect it at an early stage before the disease progresses to an irreversible stage. Several non-invasive computer-aided techniques are proposed to assist in the early detection of FLD and cirrhosis using ultrasound images. In this work, we are proposing an algorithm to discriminate automatically the normal, FLD and cirrhosis ultrasound images using curvelet transform (CT) method. Higher order spectra (HOS) bispectrum, HOS phase, fuzzy, Kapoor, max, Renyi, Shannon, Vajda and Yager entropies are extracted from CT coefficients. These extracted features are subjected to locality sensitive discriminant analysis (LSDA) feature reduction method. Then these LSDA coefficients ranked based on F-value are fed to different classifiers to choose the best performing classifier using minimum number of features. Our proposed technique can characterize normal, FLD and cirrhosis using probabilistic neural network (PNN) classifier with an accuracy of 97.33%, specificity of 100.00% and sensitivity of 96.00% using only six features. In addition, these chosen features are used to develop a liver disease index (LDI) to differentiate the normal, FLD and cirrhosis classes using a single number. This can significantly help the radiologists to discriminate FLD and cirrhosis in their routine liver screening.

Retinal blood vessel extraction using tunable bandpass filter and fuzzy conditional entropy

BACKGROUND AND OBJECTIVES

Extraction of blood vessels on retinal images plays a significant role for screening of different opthalmologic diseases. However, accurate extraction of the entire and individual type of vessel silhouette from the noisy images with poorly illuminated background is a complicated task. To this aim, an integrated system design platform is suggested in this work for vessel extraction using a sequential bandpass filter followed by fuzzy conditional entropy maximization on matched filter response.

METHODS

At first noise is eliminated from the image under consideration through curvelet based denoising. To include the fine details and the relatively less thick vessel structures, the image is passed through a bank of sequential bandpass filter structure optimized for contrast enhancement. Fuzzy conditional entropy on matched filter response is then maximized to find the set of multiple optimal thresholds to extract the different types of vessel silhouettes from the background. Differential Evolution algorithm is used to determine the optimal gain in bandpass filter and the combination of the fuzzy parameters. Using the multiple thresholds, retinal image is classified as the thick, the medium and the thin vessels including neovascularization.

RESULTS

Performance evaluated on different publicly available retinal image databases shows that the proposed method is very efficient in identifying the diverse types of vessels. Proposed method is also efficient in extracting the abnormal and the thin blood vessels in pathological retinal images. The average values of true positive rate, false positive rate and accuracy offered by the method is 76.32%, 1.99% and 96.28%, respectively for the DRIVE database and 72.82%, 2.6% and 96.16%, respectively for the STARE database. Simulation results demonstrate that the proposed method outperforms the existing methods in detecting the various types of vessels and the neovascularization structures.

CONCLUSIONS

The combination of curvelet transform and tunable bandpass filter is found to be very much effective in edge enhancement whereas fuzzy conditional entropy efficiently distinguishes vessels of different widths.

Curvelet Transform-based volume fusion for correcting signal loss artifacts in Time-of-Flight Magnetic Resonance Angiography data

Flow fields in cerebral aneurysms can be measured in vivo with phase-contrast MRI (4D Flow MRI), providing 3D anatomical magnitude images as well as 3-directional velocities through the cardiac cycle. The low spatial resolution of the 4D Flow MRI data, however, requires the images to be co-registered with higher resolution angiographic data for better segmentation of the blood vessel geometries to adequately quantify relevant flow descriptors such as wall shear stress or flow residence time. Time-of-Flight Magnetic Resonance Angiography (TOF MRA) is a non-invasive technique for visualizing blood vessels without the need to administer contrast agent. Instead TOF uses the blood flow-related enhancement of unsaturated spins entering into an imaging slice as means to generate contrast between the stationary tissue and the moving blood. Because of the higher resolutions, TOF data are often used to assist with the segmentation process needed for the flow analysis and Computational Fluid Dynamics (CFD) modeling. However, presence of slow moving and recirculating blood flow such as in brain aneurysms, especially regions where the blood flow is not perpendicular to the image plane, causes signal loss in these regions. In this work a 3D Curvelet Transform-based image fusion approach is proposed for signal loss artifact reduction of TOF volume data. Experiments show the superiority of the proposed approach in comparison to other multi-resolution 3D Wavelet-based image fusion methodologies. The proposed approach can further facilitate model-based fluid analysis and pre/post-operative treatment of patients with brain aneurysms.

An Efficient Cancer Classification Model for CT/MRI/PET Fused Images

OBJECTIVE

The aim was to study image fusion-based cancer classification models used to diagnose cancer and assess medical problems in earlier stages that help doctors or health care professionals to make the treatment plan accordingly.

METHODS

In this work, a novel image fusion method based on Curvelet transform is developed. CT and PET scan images of benign type tumors were fused together using the proposed fusion algorithm and the same way, MRI and PET scan images of malignant type tumors were fused together to achieve the combined benefits of individual imaging techniques. Then, the marker-controlled watershed algorithm was applied on fused images to segment cancer affected area. The various color features, shape features and texture-based features were extracted from the segmented image. Following this, a data set was formed with various features, given as input to different classifiers namely neural network classifier, Random forest classifier, and K-NN classifier to determine the nature of cancer. The results of the classifier showed normal, benign or malignant category of cancer.

RESULTS

The performance of the proposed fusion algorithm was compared with the existing fusion techniques based on the parameters PSNR, SSIM, Entropy, Mean and Standard Deviation. Curvelet transform based fusion method performs better than already existing methods in terms of five parameters. The performances of the classifiers were evaluated using three parameters: accuracy, sensitivity, and specificity. The K-NN Classifier performed better compared to the other two classifiers and it provided an overall accuracy of 94%, sensitivity of 88% and specificity of 84%.

CONCLUSION

The proposed Curvelet transform based image fusion method combined with the KNN classifier provides better results compared to other two classifiers when two input images were used individually.

Reconstruction of compressively sampled MR images based on a local shrinkage thresholding algorithm with curvelet transform

To reduce the magnetic resonance imaging (MRI) data acquisition time and improve the MR image reconstruction performance, reconstruction algorithms based on the iterative shrinkage thresholding algorithm (ISTA) are widely used. However, these traditional algorithms use global threshold shrinkage, which is not efficient. In this paper, a novel algorithm based on local threshold shrinkage, which is called the local shrinkage thresholding algorithm (LSTA), was proposed. The LSTA can shrink differently for different elements from the residual matrix to adjust the shrinkage speed for each element of the image during the iterative process. Then, by taking advantage of the sparser characteristics of the curvelet transform, the LSTA combined with the curvelet transform (CLSTA) can make the construction process more efficient. Finally, compared with ISTA, the generalized thresholding iterative algorithm (GTIA) and the fast iterative shrinkage threshold algorithm (FISTA), when analysing human (brain and cervical) MR images, a conclusion can be drawn that the proposed method has better reconstruction performance in terms of the mean square error (MSE), the peak signal to noise ratio (PNSR), the structural similarity index measure (SSIM), the normalized mutual information (NMI), the transferred edge information (TEI) and the number of iterations. The proposed method can better maintain the detailed information of the reconstructed images and effectively decrease the blurring of the images edges. Graphical abstract.

Forming Optimal Projection Images from Intra-Retinal Layers Using Curvelet-Based Image Fusion Method

Background

Image fusion is the process of combining the information of several input images into one image. Projection images obtained from three-dimensional (3D) optical coherence tomography (OCT) can show inlier retinal pathology and abnormalities that are not visible in conventional fundus images. In recent years, the projection image is often made by an average on all retina that causes to lose many intraretinal details.

Methods

In this study, we focus on the formation of optimum projection images from retinal layers using Curvelet-based image fusion. The latter consists of three main steps. In the earlier studies, macular spectral 3D data using diffusion map-based OCT were segmented into 12 different boundaries identifying 11 retinal layers in three dimensions. In the second step, projection images are attained using conducting some statistical methods on the space between each pair of boundaries. In the next step, retinal layers are merged using Curvelet transform to make the final projection images.

Results

These images contain integrated retinal depth information as well as an ideal opportunity to better extract retinal features such as vessels and the macula region. Finally, qualitative and quantitative evaluations show the superiority of this method to the average-based and wavelet-based fusion methods. Overall, our method obtains the best results for image fusion in all terms such as entropy (6.7744) and AG (9.5491).

Conclusion

Creating an image with more and detailed information made by the Curvelet-based image fusion has significantly higher contrast. There are also many thin veins in Curvelet-based fused image, which are absent in average-based and wavelet-based fused images.

An accurate unsupervised extraction of retinal vasculature using curvelet transform and classical morphological operators

BACKGROUND

Many ophthalmic disorders such as diabetic retinopathy and hypertension can be early diagnosed by analyzing changes related to the vascular structure of the retina. Accuracy and efficiency of the segmentation of retinal blood vessels are important parameters that can help the ophthalmologist to better characterize the targeted anomalies.

METHOD

In this work, we propose a new method for accurate unsupervised automatic segmentation of retinal blood vessels based on a simple and adequate combination of classical filters. Initially, contrast of vessels in retinal image is significantly improved by adding the Curvelet Transform to commonly used Contrast-Limited Adaptive Histogram Equalization technique. Afterwards, a morphological operator using Top Hat is applied to highlight vascular network. Then, a global threshold-based Otsu technique using minimum of intra-class variance is applied for vessel detection. Finally, a cleanup operation based on Match Filter and First Derivative Order Gaussian with fixed parameters is used to remove unwanted or isolated segments. We test the proposed method on images from two publicly available STARE and DRIVE databases.

RESULTS

We achieve in terms of sensitivity, specificity and accuracy the respective average performances of 0.7407, 0.9878 and 0.9667 on the DRIVE database, then 0.7028, 0.9755 and 0.9507 on the STARE database.

CONCLUSIONS

Compared to some recent similar work, the obtained results are quite promising and can thus contribute to the optimization of automatic tools to aid in the diagnosis of eye disorders.

An improved semi-supervised segmentation of the retinal vasculature using curvelet-based contrast adjustment and generalized linear model

Diagnosis of most ophthalmic conditions, such as diabetic retinopathy, generally relies on an effective analysis of retinal blood vessels. Techniques that depend solely on the visual observation of clinicians can be tedious and prone to numerous errors. In this article, we propose a semi-supervised automated approach for segmenting blood vessels in retinal color images. Our method effectively combines some classical filters with a Generalized Linear Model (GLM). We first apply the Curvelet Transform along with the Contrast-Limited Histogram Adaptive Equalization (CLAHE) technique to significantly enhance the contrast of vessels in the retinal image during the preprocessing phase. We then use Gabor transform to extract features from the enhanced image. For retinal vasculature identification, we use a GLM learning model with a simple link identity function. Binarization is then performed using an automatic optimal threshold based on the maximum Youden index. A morphological cleaning operation is applied to remove isolated or unwanted segments from the final segmented image. The proposed model is evaluated using statistical parameters on images from three publicly available databases. We achieve average accuracies of 0.9593, 0.9553 and 0.9643, with Receiver Operating Characteristic (ROC) analysis yielding Area Under Curve (AUC) values of 0.9722, 0.9682 and 0.9767 for the CHASE_DB1, STARE and DRIVE databases, respectively. Compared to some of the best results from similar approaches published recently, our results exceed their performance on several datasets.

Metal Artifact Reduction in Dental Computed Tomography Images Based on Sinogram Segmentation Using Curvelet Transform Followed by Hough Transform

In X-ray computed tomography (CT), the presence of metal objects in a patient's body produces streak artifacts in the reconstructed images. During the past decades, many different methods were proposed for the reduction or elimination of the streaking artifacts. When scanning a patient, the projection data affected by metal objects (missing projections) appear as regions with high intensities in the sinogram. In spiral fan beam CT, these regions are sinusoid-like curves on sinogram. During the first time, if the metal curves are detected carefully, then, they can be replaced by corresponding unaffected projections using other slices or opposite views; therefore, the CT slices regenerated by the modified sonogram will be imaged with high quality. In this paper, a new method of the segmentation of metal traces in spiral fan-beam CT sinogram is proposed. This method is based on a sinogram curve detection using a curvelet transform followed by 2D Hough transform. The initial enhancement of the sinogram using modified curvelet transform coefficients is performed by suppressing all the coefficients of one band and applying 2D Hough transform to detect more precisely metal curves. To evaluate the performance of the proposed method for the detection of metal curves in a sinogram, precision and recall metrics are calculated. Compared with other methods, the results show that the proposed method is capable of detecting metal curves, with better precision and good recovery.

CurveletTransform-Based Texture Analysis of Carotid B-mode Ultrasound Images in Asymptomatic Men With Moderate and Severe Stenoses: A Preliminary Clinical Study

The curvelet transform, which represents images in terms of their geometric and textural characteristics, was investigated toward revealing differences between moderate (50%-69%, n = 11) and severe (70%-100%, n = 14) stenosis asymptomatic plaque from B-mode ultrasound. Texture features were estimated in original and curvelet transformed images of atheromatous plaque (PL), the adjacent arterial wall (intima-media [IM]) and the plaque shoulder (SH) (i.e., the boundary between plaque and wall), separately at end systole and end diastole. Seventeen features derived from the original images were significantly different between the two groups (4 for IM, 3 for PL and 10 for SH; 9 for end diastole and 8 for end systole); 19 of 234 features (2 for IM and 17 for SH; 8 for end systole and 11 for end diastole) derived from curvelet transformed images were significantly higher in the patients with severe stenosis, indicating higher magnitude, variation and randomness of image gray levels. In these patients, lower body height and higher serum creatinine concentration were observed. Our findings suggest that (a) moderate and severe plaque have similar curvelet-based texture properties, and (b) IM and SH provide useful information about arterial wall pathophysiology, complementary to PL itself. The curvelet transform is promising for identifying novel indices of cardiovascular risk and warrants further investigation in larger cohorts.

Computer-Aided Detection of Human Lung Nodules on Computer Tomography Images via Novel Optimized Techniques

BACKGROUND

Globally, the most general reason for huge number of passings is Lung disease. The lung malignancy is the most shocking amongst the tumor types and it plays a significant role for the increase of death rate. It is assessed that nearly 1.2 million persons are determined to have this illness and about 1.1 million individuals are losing their lives due to this sickness in every year. The survival rate is superior if the growth is recognized at earlier periods. The premature identification of lung malignant growth isn't a simple task. Various imaging algorithms are available for detecting the lung cancer.

AIM

Computer aided diagnosis scheme is more useful for radiologist in detecting and identifying irregularities in advance and more rapidly. The CAD systems usually focus on identifying and detecting the lung nodules. Staging the lung cancer at its detection need to be focused as the treatment is based on the stage of the cancer. The major drawbacks of existing CAD systems are less accuracy in segmenting the nodule and staging the lung cancer.

OBJECTIVE

The most important intention of this work is to divide the lung nodule from CT image and classify as tumorous cells in order to identify the cancer's position with greater sensitivity, precision, and accuracy than other strategies.

METHODS

The primary role is defined as follows (i) for de-noising and edge sharpening of lung image, the curvelet transform is used. (ii) The Fuzzy thresholding technique is used to perform lung image binarization and lung boundary corrections. (iii) Segmentation is performed by using K-means algorithm. (iv) By using convolutional neural network (CNN), different stages of lung nodules such as benign and malignant are identified.

RESULTS

The proposed classifier achieves a 97.3 percent accuracy. The proposed approach is helpful in detecting lung cancer in its early stages. The proposed classifier achieved a sensitivity of 98.6 percent and a specificity of 96.1 percent.

CONCLUSION

The results demonstrated that the established algorithms can be used to assist a radiologist in classifying lung images into various stages, thus supporting the radiologist in decision making.

Speckle Noise Reduction in Optical Coherence Tomography Using Two-dimensional Curvelet-based Dictionary Learning

The process of interpretation of high-speed optical coherence tomography (OCT) images is restricted due to the large speckle noise. To address this problem, this paper proposes a new method using two-dimensional (2D) curvelet-based K-SVD algorithm for speckle noise reduction and contrast enhancement of intra-retinal layers of 2D spectral-domain OCT images. For this purpose, we take curvelet transform of the noisy image. In the next step, noisy sub-bands of different scales and rotations are separately thresholded with an adaptive data-driven thresholding method, then, each thresholded sub-band is denoised based on K-SVD dictionary learning with a variable size initial dictionary dependent on the size of curvelet coefficients' matrix in each sub-band. We also modify each coefficient matrix to enhance intra-retinal layers, with noise suppression at the same time. We demonstrate the ability of the proposed algorithm in speckle noise reduction of 100 publically available OCT B-scans with and without non-neovascular age-related macular degeneration (AMD), and improvement of contrast-to-noise ratio from 1.27 to 5.12 and mean-to-standard deviation ratio from 3.20 to 14.41 are obtained.

Visual defect inspection of touch screens using multi-angle filtering in curvelet domain

Touch screens are widely used in smartphones and tablets. These screens exhibit a pattern of directional, regular lines on their surface. The intricate texture of this background, which quickly causes interference, poses a significant challenge in detecting surface defects. Surface defects can be mainly classified into two types: linear and planar. Existing methods cannot effectively detect both types of defects. This study proposes a curvelet transform-based multi-angle filtering method. It can effectively attenuate regular patterns from panel images with textural backgrounds and preserve fine linear and planar defects in the reconstructed image. Curvelet transform is a multi-scale directional transformation that can capture the curved edges of objects well. The filtered curvelet coefficients are then reconstructed into the spatial domain and binarized using a threshold based on the interval estimation skill. The results of the trial show that the suggested approach can precisely locate and identify defects in touch panels. The rate of defect detection (1-β) stands at 93.33 %. The rate of defect misjudgment (α) is at a low of 1.26 %. The correct classification rate (CR) is impressively high at 98.69 %, indicating that the proposed method provides fine-grained segmentation results over existing methods for detecting surface defects on touch panels.