A GU-Net-Based Architecture Predicting Ligand-Protein-Binding Atoms.

Background: The first step in developing new drugs is to find binding sites for a protein structure that can be used as a starting point to design new antagonists and inhibitors. The methods relying on convolutional neural network for the prediction of binding sites have attracted much attention. This study focuses on the use of optimized neural network for three-dimensional (3D) non-Euclidean data. Methods: A graph, which is made from 3D protein structure, is fed to the proposed GU-Net model based on graph convolutional operation. The features of each atom are considered as attributes of each node. The results of the proposed GU-Net are compared with a classifier based on random forest (RF). A new data exhibition is used as the input of RF classifier. Results: The performance of our model is also examined through extensive experiments on various datasets from other sources. GU-Net could predict the more number of pockets with accurate shape than RF. Conclusions: This study will enable future works on a better modeling of protein structures that will enhance knowledge of proteomics and offer deeper insight into drug design process.

3D U-Net: A voxel-based method in binding site prediction of protein structure.

Binding site prediction for new proteins is important in structure-based drug design. The identified binding sites may be helpful in the development of treatments for new viral outbreaks in the world when there is no information available about their pockets with COVID-19 being a case in point. Identification of the pockets using computational methods, as an alternative method, has recently attracted much interest. In this study, the binding site prediction is viewed as a semantic segmentation problem. An improved 3D version of the U-Net model based on the dice loss function is utilized to predict the binding sites accurately. The performance of the proposed model on the independent test datasets and SARS-COV-2 shows the segmentation model could predict the binding sites with a more accurate shape than the recently published deep learning model, i.e. DeepSite. Therefore, the model may help predict the binding sites of proteins and could be used in drug design for novel proteins.

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.

Three-dimensional curvelet-based dictionary learning for speckle noise removal of optical coherence tomography.

Optical coherence tomography (OCT) is a recently emerging non-invasive diagnostic tool useful in several medical applications such as ophthalmology, cardiology, gastroenterology and dermatology. One of the major problems with OCT pertains to its low contrast due to the presence of multiplicative speckle noise, which limits the signal-to-noise ratio (SNR) and obscures low-intensity and small features. In this paper, we recommend a new method using the 3D curvelet based K-times singular value decomposition (K-SVD) algorithm for speckle noise reduction and contrast enhancement of the intra-retinal layers of 3D Spectral-Domain OCT (3D-SDOCT) images. In order to benefit from the near-optimum properties of curvelet transform (such as good directional selectivity) on top of dictionary learning, we propose a new plan in dictionary learning by using the curvelet atoms as the initial dictionary. For this reason, the curvelet transform of the noisy image is taken and then the noisy coefficients matrix in each scale, rotation and spatial coordinates is passed through the K-SVD denoising algorithm with predefined 3D initial dictionary that is adaptively selected from thresholded coefficients in the same subband of the image. During the denoising of curvelet coefficients, we can also modify them for the purpose of contrast enhancement of intra-retinal layers. We demonstrate the ability of our proposed algorithm in the speckle noise reduction of 17 publicly available 3D OCT data sets, each of which contains 100 B-scans of size 512×1000 with and without neovascular age-related macular degeneration (AMD) images acquired using SDOCT, Bioptigen imaging systems. Experimental results show that an improvement from 1.27 to 7.81 in contrast to noise ratio (CNR), and from 38.09 to 1983.07 in equivalent number of looks (ENL) is achieved, which would outperform existing state-of-the-art OCT despeckling methods.

The Ellipselet Transform.

BACKGROUND: A fair amount of important objects in natural images have circular and elliptical shapes. For example, the nucleus of most of the biological cells is circular, and a number of parasites such as Oxyuris have elliptical shapes in microscopic images. Hence, atomic representations by two-dimensional (2D) basis functions based on circle and ellipse can be useful for processing these images. The first researches have been done in this domain by introducing circlet transform. METHODS: The main goal of this article is expanding the circlet to a new one with elliptical basis functions. RESULTS: In this article, we first introduce a new transform called ellipselet and then compare it with other X-let transforms including 2D-discrete wavelet transform, dual-tree complex wavelet, curvelet, contourlet, steerable pyramid, and circlet transform in the application of image denoising. CONCLUSION: Experimental results show that for noises under 30, the ellipselet is better than other geometrical X-lets in terms of Peak Signal to Noise Ratio, especially for Lena which contains more circular structures. However, for Barbara which has fine structures in its texture, it has worse results than dual-tree complex wavelet and steerable pyramid.

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.

Three-dimensional Segmentation of Retinal Cysts from Spectral-domain Optical Coherence Tomography Images by the Use of Three-dimensional Curvelet Based K-SVD.

This paper presents a new three-dimensional curvelet transform based dictionary learning for automatic segmentation of intraretinal cysts, most relevant prognostic biomarker in neovascular age-related macular degeneration, from 3D spectral-domain optical coherence tomography (SD-OCT) images. In particular, we focus on the Spectralis SD-OCT (Heidelberg Engineering, Heidelberg, Germany) system, and show the applicability of our algorithm in the segmentation of these features. For this purpose, we use recursive Gaussian filter and approximate the corrupted pixels from its surrounding, then in order to enhance the cystoid dark space regions and future noise suppression we introduce a new scheme in dictionary learning and take curvelet transform of filtered image then denoise and modify each noisy coefficients matrix in each scale with predefined initial 3D sparse dictionary. Dark pixels between retinal pigment epithelium and nerve fiber layer that were extracted with graph theory are considered as cystoid spaces. The average dice coefficient for the segmentation of cystoid regions in whole 3D volume and with-in central 3 mm diameter on the MICCAI 2015 OPTIMA Cyst Segmentation Challenge dataset were found to be 0.65 and 0.77, respectively.

Nucleus and cytoplasm segmentation in microscopic images using K-means clustering and region growing.

BACKGROUND: Segmentation of leukocytes acts as the foundation for all automated image-based hematological disease recognition systems. Most of the time, hematologists are interested in evaluation of white blood cells only. Digital image processing techniques can help them in their analysis and diagnosis. MATERIALS AND METHODS: The main objective of this paper is to detect leukocytes from a blood smear microscopic image and segment them into their two dominant elements, nucleus and cytoplasm. The segmentation is conducted using two stages of applying K-means clustering. First, the nuclei are segmented using K-means clustering. Then, a proposed method based on region growing is applied to separate the connected nuclei. Next, the nuclei are subtracted from the original image. Finally, the cytoplasm is segmented using the second stage of K-means clustering. RESULTS: The results indicate that the proposed method is able to extract the nucleus and cytoplasm regions accurately and works well even though there is no significant contrast between the components in the image. CONCLUSIONS: In this paper, a method based on K-means clustering and region growing is proposed in order to detect leukocytes from a blood smear microscopic image and segment its components, the nucleus and the cytoplasm. As region growing step of the algorithm relies on the information of edges, it will not able to separate the connected nuclei more accurately in poor edges and it requires at least a weak edge to exist between the nuclei. The nucleus and cytoplasm segments of a leukocyte can be used for feature extraction and classification which leads to automated leukemia detection.

Detection and classification of Breast Cancer in Wavelet Sub-bands of Fractal Segmented Cancerous Zones.

Recent studies on wavelet transform and fractal modeling applied on mammograms for the detection of cancerous tissues indicate that microcalcifications and masses can be utilized for the study of the morphology and diagnosis of cancerous cases. It is shown that the use of fractal modeling, as applied to a given image, can clearly discern cancerous zones from noncancerous areas. In this paper, for fractal modeling, the original image is first segmented into appropriate fractal boxes followed by identifying the fractal dimension of each windowed section using a computationally efficient two-dimensional box-counting algorithm. Furthermore, using appropriate wavelet sub-bands and image Reconstruction based on modified wavelet coefficients, it is shown that it is possible to arrive at enhanced features for detection of cancerous zones. In this paper, we have attempted to benefit from the advantages of both fractals and wavelets by introducing a new algorithm. By using a new algorithm named F1W2, the original image is first segmented into appropriate fractal boxes, and the fractal dimension of each windowed section is extracted. Following from that, by applying a maximum level threshold on fractal dimensions matrix, the best-segmented boxes are selected. In the next step, the segmented Cancerous zones which are candidates are then decomposed by utilizing standard orthogonal wavelet transform and db2 wavelet in three different resolution levels, and after nullifying wavelet coefficients of the image at the first scale and low frequency band of the third scale, the modified reconstructed image is successfully utilized for detection of breast cancer regions by applying an appropriate threshold. For detection of cancerous zones, our simulations indicate the accuracy of 90.9% for masses and 88.99% for microcalcifications detection results using the F1W2 method. For classification of detected mictocalcification into benign and malignant cases, eight features are identified and utilized in radial basis function neural network. Our simulation results indicate the accuracy of 92% classification using F1W2 method.

An Automatic Algorithm for Segmentation of the Boundaries of Corneal Layers in Optical Coherence Tomography Images using Gaussian Mixture Model.

Diagnosis of corneal diseases is possible by measuring and evaluation of corneal thickness in different layers. Thus, the need for precise segmentation of corneal layer boundaries is inevitable. Obviously, manual segmentation is time-consuming and imprecise. In this paper, the Gaussian mixture model (GMM) is used for automatic segmentation of three clinically important corneal boundaries on optical coherence tomography (OCT) images. For this purpose, we apply the GMM method in two consequent steps. In the first step, the GMM is applied on the original image to localize the first and the last boundaries. In the next step, gradient response of a contrast enhanced version of the image is fed into another GMM algorithm to obtain a more clear result around the second boundary. Finally, the first boundary is traced toward down to localize the exact location of the second boundary. We tested the performance of the algorithm on images taken from a Heidelberg OCT imaging system. To evaluate our approach, the automatic boundary results are compared with the boundaries that have been segmented manually by two corneal specialists. The quantitative results show that the proposed method segments the desired boundaries with a great accuracy. Unsigned mean errors between the results of the proposed method and the manual segmentation are 0.332, 0.421, and 0.795 for detection of epithelium, Bowman, and endothelium boundaries, respectively. Unsigned mean errors of the inter-observer between two corneal specialists have also a comparable unsigned value of 0.330, 0.398, and 0.534, respectively.

Hybrid method for prediction of metastasis in breast cancer patients using gene expression signals.

Using primary tumor gene expression has been shown to have the ability of finding metastasis-driving gene markers for prediction of breast cancer recurrence (BCR). However, there are some difficulties associated with analysis of microarray data, which led to poor predictive power and inconsistency of previously introduced gene signatures. In this study, a hybrid method was proposed for identifying more predictive gene signatures from microarray datasets. Initially, the parameters of a Rough-Set (RS) theory based feature selection method were tuned to construct a customized gene extraction algorithm. Afterward, using RS gene selection method the most informative genes selected from six independent breast cancer datasets. Then, combined set of these six signature sets, containing 114 genes, was evaluated for prediction of BCR. In final, a meta-signature, containing 18 genes, selected from the combination of datasets and its prediction accuracy compared to the combined signature. The results of 10-fold cross-validation test showed acceptable misclassification error rate (MCR) over 1338 cases of breast cancer patients. In comparison to a recent similar work, our approach reached more than 5% reduction in MCR using a fewer number of genes for prediction. The results also demonstrated 7% improvement in average accuracy in six utilized datasets, using the combined set of 114 genes in comparison with 18-genes meta-signature. In this study, a more informative gene signature was selected for prediction of BCR using a RS based gene extraction algorithm. To conclude, combining different signatures demonstrated more stable prediction over independent datasets.

Using protein interaction database and support vector machines to improve gene signatures for prediction of breast cancer recurrence.

Numerous studies used microarray gene expression data to extract metastasis-driving gene signatures for the prediction of breast cancer relapse. However, the accuracy and generality of the previously introduced biomarkers are not acceptable for reliable usage in independent datasets. This inadequacy is attributed to ignoring gene interactions by simple feature selection methods, due to their computational burden. In this study, an integrated approach with low computational cost was proposed for identifying a more predictive gene signature, for prediction of breast cancer recurrence. First, a small set of genes was primarily selected as signature by an appropriate filter feature selection (FFS) method. Then, a binary sub-class of protein-protein interaction (PPI) network was used to expand the primary set by adding adjacent proteins of each gene signature from the PPI-network. Subsequently, the support vector machine-based recursive feature elimination (SVMRFE) method was applied to the expression level of all the genes in the expanded set. Finally, the genes with the highest score by SVMRFE were selected as the new biomarkers. Accuracy of the final selected biomarkers was evaluated to classify four datasets on breast cancer patients, including 800 cases, into two cohorts of poor and good prognosis. The results of the five-fold cross validation test, using the support vector machine as a classifier, showed more than 13% improvement in the average accuracy, after modifying the primary selected signatures. Moreover, the method used in this study showed a lower computational cost compared to the other PPI-based methods. The proposed method demonstrated more robust and accurate biomarkers using the PPI network, at a low computational cost. This approach could be used as a supplementary procedure in microarray studies after applying various gene selection methods.

Detection and segmentation of erythrocytes in blood smear images using a line operator and watershed algorithm.

Most of the erythrocyte related diseases are detectable by hematology images analysis. At the first step of this analysis, segmentation and detection of blood cells are inevitable. In this study, a novel method using a line operator and watershed algorithm is rendered for erythrocyte detection and segmentation in blood smear images, as well as reducing over-segmentation in watershed algorithm that is useful for segmentation of different types of blood cells having partial overlap. This method uses gray scale structure of blood cell, which is obtained by exertion of Euclidian distance transform on binary images. Applying this transform, the gray intensity of cell images gradually reduces from the center of cells to their margins. For detecting this intensity variation structure, a line operator measuring gray level variations along several directional line segments is applied. Line segments have maximum and minimum gray level variations has a special pattern that is applicable for detections of the central regions of cells. Intersection of these regions with the signs which are obtained by calculating of local maxima in the watershed algorithm was applied for cells' centers detection, as well as a reduction in over-segmentation of watershed algorithm. This method creates 1300 sign in segmentation of 1274 erythrocytes available in 25 blood smear images. Accuracy and sensitivity of the proposed method are equal to 95.9% and 97.99%, respectively. The results show the proposed method's capability in detection of erythrocytes in blood smear images.

Analysis of foveal avascular zone for grading of diabetic retinopathy severity based on curvelet transform.

INTRODUCTION: Diabetes disturbs many parts of the body. One of the most common and serious complications of this disease is Diabetic Retinopathy (DR). In this process, blood vessels of the retina are damaged and leak into the retina. In later stages, DR affects the fovea. In these cases, the shape and size of the Foveal Avascular Zone (FAZ), which is responsible for central vision, can become abnormal and contribute to loss of vision. METHODS: In this paper, appropriate features are extracted from the FAZ by means of Digital Curvelet Transform (DCUT) and used to grade of retina images into normal and abnormal classes. For this reason, DCUT is applied on enhanced color fundus images and its coefficients are modified to highlight vessels and the optic disc (OD). Through the use of this information about the anatomical location of the FAZ related to the OD and detected end points of segmented vessels, the FAZ is extracted. Then, the area and regularity of the extracted FAZ is determined and used for DR grading. RESULTS: Our method was tested on a database including 45 normal and 30 abnormal color fundus images, and showed sensitivity of 93 % for DR grading and specificity of 86 % for distinguishing between normal and abnormal cases. CONCLUSIONS: This technique showed high reproducibility in characterizing the size and contour of the FAZ in diabetic maculopathy, thus it has the potential to serve as a powerful tool in the automated assessment and grading of images in a routine clinical setting.

Investigation of the bnp level changes in blood stream in different modes and lead locations after pacemaker implementation.

As has been proven, increase of mechanical strain could result in an increase of brain natriuretic peptide (BNP) in the blood stream of implanted patient pacemakers. We measured the BNP concentration in blood due to different mode and lead implantation location of pacemaker in the time period of 3 months. The aim of this study was to investigate the changing trend of BNP level after pacemaker implantation. One hundred and three pacemaker implanted patients were monitored. Patients were in the age span of 54±12 years, including 48 men and 55 women. A group of 44 were programmed in Dual Chamber Rate Adaptive (DDDR) Pacemaker mode and a group of 59 were programmed in Ventricular Rate Modulated Pacing (VVIR) mode by the recommendation of the cardiologist. Between these two groups, the pacing levels of pacemakers was divided to under and above 50%. Some of these pacemaker leads were located at the apex of the right ventricle and the others were located in the septum wall in the right ventricle. To evaluate BNP changes during a period of 3 months, the BNPs were measured in pg/ml within 24 h of implantation (BNP1) and after 3 months (BNP2). For different classes of pacemaker implantations, the ratio of final measurement (BNP2) is divided to after implantation measurements (BNP1). Results showed that in VVIR mode, the ratio is 1.54±0.3 and in DDDR mode, the ratio is 0.38±0.17, with acceptable standard error means (<0.04). Also, comparisons are made for lead location at two modes of DDDR and VVIR separately. In the DDDR mode, the ratio for apex location is 0.49±0.12 and for septum location is 0.22±0.34, with acceptable standard error means (<0.02). In the VVIR mode, the ratio for apex location is 1.71±0.27 and for septum location is 1.28±0.09, with acceptable standard error means (<0.04). Therefore, BNP decrease in DDDR mode is more than in VVIR mode programming. In both cases of DDDR and VVIR modes, the septum location of the leads would result in a greater decrease of BNP.

Ischemia detection by electrocardiogram in wavelet domain using entropy measure.

BACKGROUND: Ischemic heart disease is one of the common fatal diseases in advanced countries. Because signal perturbation in healthy people is less than signal perturbation in patients, entropy measure can be used as an appropriate feature for ischemia detection. METHODS: Four entropy-based methods comprising of using electrocardiogram (ECG) signal directly, wavelet sub-bands of ECG signals, extracted ST segments and reconstructed signal from time-frequency feature of ST segments in wavelet domain were investigated to distinguish between ECG signal of healthy individuals and patients. We used exercise treadmill test as a gold standard, with a sample of 40 patients who had ischemic signs based on initial diagnosis of medical practitioner. RESULTS: The suggested technique in wavelet domain resulted in the highest discrepancy between healthy individuals and patients in comparison to other methods. Specificity and sensitivity of this method were 95% and 94% respectively. CONCLUSIONS: The method based on wavelet sub-bands outperformed the others.