Shearlet Features Research Articles

Detection and Segmentation of Glioma Tumors Utilizing a UNet Convolutional Neural Network Approach with Non-Subsampled Shearlet Transform.

The prompt and precise identification and delineation of tumor regions within glioma brain images are critical for mitigating the risks associated with this life-threatening ailment. In this study, we employ the UNet convolutional neural network (CNN) architecture for glioma tumor detection. Our proposed methodology comprises a transformation module, a feature extraction module, and a tumor segmentation module. The spatial domain representation of brain magnetic resonance imaging images undergoes decomposition into low- and high-frequency subbands via a non-subsampled shearlet transform. Leveraging the selective and directive characteristics of this transform enhances the classification efficacy of our proposed system. Shearlet features are extracted from both low- and high-frequency subbands and subsequently classified using the UNet-CNN architecture to identify tumor regions within glioma brain images. We validate our proposed glioma tumor detection methodology using publicly available datasets, namely Brain Tumor Segmentation (BRATS) 2019 and The Cancer Genome Atlas (TCGA). The mean classification rates achieved by our system are 99.1% for the BRATS 2019 dataset and 97.8% for the TCGA dataset. Furthermore, our system demonstrates notable performance metrics on the BRATS 2019 dataset, including 98.2% sensitivity, 98.7% specificity, 98.9% accuracy, 98.7% intersection over union, and 98.5% disc similarity coefficient. Similarly, on the TCGA dataset, our system achieves 97.7% sensitivity, 98.2% specificity, 98.7% accuracy, 98.6% intersection over union, and 98.4% disc similarity coefficient. Comparative analysis against state-of-the-art methods underscores the efficacy of our proposed glioma brain tumor detection approach.

Reproducibility of radiomics features from ultrasound images: influence of image acquisition and processing.

To systematically assess the reproducibility of radiomics features from ultrasound (US) images during image acquisition and processing. A standardized phantom was scanned to obtain US images. Reproducibility of radiomics features from US images, also known as ultrasomics features, was explored via (a) intra-US machine: changing the US acquisition parameters including gain, focus, and frequency; (b) inter-US machine: comparing three different scanners; (c) changing segmentation locations; and (d) inter-platform: comparing features extracted by the Ultrasomics and PyRadiomics algorithm platforms. Reproducible ultrasomics features were selected based on coefficients of variation. A total of 108 US images from three scanners were obtained; 5253 ultrasomics features including seven categories of features were extracted and evaluated for each US image. From intra-US machine analysis, 37.0-38.8% of features showed good reproducibility. From inter-US machine analysis, 42.8% (2248/5253) of features exhibited good reproducibility. From segmentation location analysis, 55.7-57.6% of features showed good reproducibility. No significant difference in the normalized feature ranges was found between the 100 features extracted by the Ultrasomics and PyRadiomics platforms with the same algorithm (p = 0.563). A total of 1452 (27.6%) ultrasomics features were reproducible whenever intra-/inter-US machine or segmentation location were changed, most of which were wavelet and shearlet features. Different acquisition parameters, US scanners, segmentation locations, and feature extraction platforms affected the reproducibility of ultrasomics features. Wavelet and shearlet features showed the best reproducibility across all procedures. • Different acquisition parameters, US scanners, segmentation locations, and feature extraction platforms affected the reproducibility of ultrasomics features. • A total of 1452 (27.6%) ultrasomics features were reproducible whenever intra-/inter-US machine or segmentation location were changed. • Wavelet and shearlet features showed the best reproducibility across all procedures.

River detection in high-resolution SAR data using the Frangi filter and shearlet features

ABSTRACTRiver extraction plays an important role in several applications such as monitoring and navigation, and synthetic aperture radar (SAR) is one of the major sensors of remote sensing. This paper proposes an algorithm to detect a river from high-resolution SAR images mainly based on the Frangi filter and shearlet features with the help of an active contour model (ACM). The Frangi filter is firstly applied to enhance the river and then the shearlet features are computed by the shearlet transform. A rule of feature selection is then proposed to acquire the corresponding features of the river. Finally, binarization and an active contour model are implemented to extract the river. The approach is tested on SAR images and the experimental results demonstrate that the proposed method is effective.

The grade classification algorithm of breast tumor based on ultrasound RF signals

A novel efficient method based on the ultrasound radio frequency (RF) signals is proposed to distinguish the breast tumors grades. First, we utilize the multi-scale geometric characteristic of Shearlet transformation to extract the multi-scale and multi-directional features of ultrasound RF signal, and then reduce the high-dimensional Shearlet features by multi-scale directional binary pattern which can effectively preserve the sufficient discriminated information. At last, we draw on the feature difference between different grades of breast tumors to design a cascade binary tree SVM classifier which not only overcome the problem of sample quantity disequilibrium but also conform to the subjective diagnosis rule of sonographer. Extensive experiments on 928 breast ultrasound RF signals collected from the hospital demonstrate the effectiveness of the new proposed method and its precision, sensitivity, specificity, PPV, NPV and MCC are 89.29%, 75.62%, 94.54%, 97%, 98.3% and 81.01%, respectively.

Shearlet feature manifold for face recognition

Face recognition is one of the major challenging problems in image processing. To effectively deal with this issue, a novel Shearlet feature manifold method for face recognition is introduced in this paper. Specially, the Shearlet feature is first extracted to capture the geometry and edge structures of face image; then the obtained high-dimensional Shearlet features are projected into low-dimensional subspace by using local geometry analysis which can simultaneously consider intraclass geometry and interclass discrimination information; finally, the face recognition is realized in the feature space by using the nearest-neighbor classifier. The experimental results on two face datasets show the effectiveness of this proposed algorithm.

Shearlet Features for Pedestrian Detection

A long-time, hand-crafted features governed by a directional image analysis have been the base for the best performing pedestrian detection algorithms. In the past few years, approaches using convolutional neural networks have taken over the leadership concerning detection quality. We investigate in which way shearlets can be used for an improved hand-crafted feature computation in order to reduce the gap to CNNs. Shearlets are a relatively new mathematical framework for multiscale signal analysis, which can be seen as an extension of the wavelet framework. Shearlets are designed to capture directional information and can therefore be used for detecting the orientation of edges in images. We use this characteristic to compute image features with high informative content for pedestrian detection. Furthermore, we provide experimental results using these features and show that they outperform the results obtained by the currently best performing hand-crafted features for pedestrian detection.

Surface Defects Classification of Hot-Rolled Steel Strips Using Multi-directional Shearlet Features

In this paper, a method combining the use of discrete shearlet transform (DST) and the gray-level co-occurrence matrix (GLCM) is presented to classify surface defects of hot-rolled steel strips into the six classes of rolled-in scale, patches, crazing, pitted surface, inclusion and scratches. Feature extraction involves the extraction of multi-directional shearlet features from each input image followed by GLCM calculations from all extracted sub-bands, from which a set of statistical features is extracted. The resultant high-dimensional feature vectors are then reduced using principal component analysis. A supervised support vector machine classifier is finally trained to classify the surface defects. The proposed feature set is compared against the Gabor, wavelets and the original GLCM in order to evaluate and validate its robustness. Experiments were conducted on a database of hot-rolled steel strips consisting of 1800 grayscale images whose defects exhibit high inter-class similarity as well as high intra-class appearance variations. Results indicate that the proposed DST–GLCM method is superior to other methods and achieves classification rates of 96.00%.

A novel glomerular basement membrane segmentation using neutrsophic set and shearlet transform on microscopic images

Glomerular basement membrane segmentation is an ultimate step in several image processing applications for kidney diseases and abnormalities in microscopic images. However, extracting the glomerular basement membrane (GBM) regions accurately is considered challenging because of the large variants in the microscopic images. The contribution of this work is to propose a computer-aided detection system to provide accurate GBM segmentation. A novel GBM segmentation algorithm is developed based on neutrsophic set and shearlet transform. Firstly, the shearlet features are extracted from the microscopic image samples using shearlet transform. Afterward, the neutrosophic image is defined using shearlet features, and the indeterminacy on the neutrosophic image is reduced using an α-mean operation. Lastly, the k-means clustering algorithm is applied to segment the neutrsophic image and the GBM is identified using its intensity feature. Three metrics, namely the average distance (AvgDist), the Hausdorff distance (Hdist), and percentage overlap area (POA); were employed to assess the proposed method performance. The results established that the proposed method achieved smaller distance errors and larger POAs. For the tested image, the average of AvgDist, HDist and POA are 1.99204, 4.59535 and 0.67857, respectively. The results established that the cases were segmented accurately using the proposed NS based shearlet transform. The new method utilizing the shearlet features and neutrosophic set improved the accuracy of GBM segmentation. Further study is underway to improve an automated CAD system using the refined segmentation results.

Microscopic medical image classification framework via deep learning and shearlet transform.

Cancer is the second leading cause of death in US after cardiovascular disease. Image-based computer-aided diagnosis can assist physicians to efficiently diagnose cancers in early stages. Existing computer-aided algorithms use hand-crafted features such as wavelet coefficients, co-occurrence matrix features, and recently, histogram of shearlet coefficients for classification of cancerous tissues and cells in images. These hand-crafted features often lack generalizability since every cancerous tissue and cell has a specific texture, structure, and shape. An alternative approach is to use convolutional neural networks (CNNs) to learn the most appropriate feature abstractions directly from the data and handle the limitations of hand-crafted features. A framework for breast cancer detection and prostate Gleason grading using CNN trained on images along with the magnitude and phase of shearlet coefficients is presented. Particularly, we apply shearlet transform on images and extract the magnitude and phase of shearlet coefficients. Then we feed shearlet features along with the original images to our CNN consisting of multiple layers of convolution, max pooling, and fully connected layers. Our experiments show that using the magnitude and phase of shearlet coefficients as extra information to the network can improve the accuracy of detection and generalize better compared to the state-of-the-art methods that rely on hand-crafted features. This study expands the application of deep neural networks into the field of medical image analysis, which is a difficult domain considering the limited medical data available for such analysis.

Automatic Image Registration of Multi-Modal Remotely Sensed Data with Global Shearlet Features.

Automatic image registration is the process of aligning two or more images of approximately the same scene with minimal human assistance. Wavelet-based automatic registration methods are standard, but sometimes are not robust to the choice of initial conditions. That is, if the images to be registered are too far apart relative to the initial guess of the algorithm, the registration algorithm does not converge or has poor accuracy, and is thus not robust. These problems occur because wavelet techniques primarily identify isotropic textural features and are less effective at identifying linear and curvilinear edge features. We integrate the recently developed mathematical construction of shearlets, which is more effective at identifying sparse anisotropic edges, with an existing automatic wavelet-based registration algorithm. Our shearlet features algorithm produces more distinct features than wavelet features algorithms; the separation of edges from textures is even stronger than with wavelets. Our algorithm computes shearlet and wavelet features for the images to be registered, then performs least squares minimization on these features to compute a registration transformation. Our algorithm is two-staged and multiresolution in nature. First, a cascade of shearlet features is used to provide a robust, though approximate, registration. This is then refined by registering with a cascade of wavelet features. Experiments across a variety of image classes show an improved robustness to initial conditions, when compared to wavelet features alone.