Gray Level Co-occurrence Matrix Features Research Articles

Human brain tumor diagnosis using the combination of the complexity measures and texture features through magnetic resonance image

The brain tumor is known as the main reason for death. Hence, knowing the type of brain tumors plays an important role in diagnosis and treatment. Traditional invasive methods like a biopsy, lumbar puncture, and spinal tap have been employed for the detection and classification of these tumors. In this paper, a Computer-Aided Diagnosis (CAD) system is provided for the classification of these tumors in Magnetic Resonance Imaging (MRI). For this purpose, the chaos theory is utilized for estimating the complexity measures such as Lyapunov Exponent (LE), Approximate Entropy (ApEn), and Fractal Dimension (FD). Furthermore, by extraction of Gray-Level Co-occurrence Matrix (GLCM) and Discrete Wavelet Transform (DWT)-based features, the benign and malignant tumors could be distinguished. The calculated features are applied to three classifiers such as Support Vector Machine (SVM), K-Nearest Neighbors (KNN) algorithm, and pattern net. In the validation step, several experiments are carried out on the various combinations of features and classifiers. Accordingly, the best accuracy (98.9%) is attained by incorporating complexity measures with GLCM features and pattern net classifier. Also, the comparison between the results of this study and other similar works with the same dataset demonstrates the efficiency of the proposed method.

Study of classification of breast lesions using texture GLCM features obtained from the raw ultrasound signal

Most of the methods of classification of breast lesions in ultrasound (US) images have been tested on B-mode images from the commercial equipment. The new possibility of further analysis of this problem showed up with the availability of a public database containing original raw radio frequency (RF) signals. In particular, it appeared that the original texture might contain diagnostic information which could be modified in the typical image processing and which is more difficult to perceive than the details of lesion shape/contour. In this paper a detailed analysis of the lesion texture is conducted by means of the decision trees and logistic regression. The decision trees turned out useful mainly for selecting texture features to be used in the stepwise logistic regression. The RF signals database of 200 breast lesions was used for testing the performance of the benign vs malignant lesion classifier. The Gray Level Cooccurrence Matrix (GLCM) was calculated with the vertical/horizontal offset of up to five pixels. For each of these matrices six features were calculated resulting in a total of 210 features. Using these features a sufficient number of decision trees were generated to calculate pseudo-Receiver Operating Characteristics (ROCs). The outcome of this process is a collection of generated trees for which the employed features are known. These features were then used for generating generalized linear model by means of stepwise logistic regression. The analyzed regression models included the coefficients of up-to-the second degree terms. The texture features were further completed by a single shape feature, that is tumor circularity (TC). The automatic procedure for finding the exact mask of a lesion is also provided for the conditions when the acoustic shadowing makes it impossible to obtain the entire contour reliably and a half-contour has to be used. The selected logistic regression models gave ROCs with the Area Under Curve (AUC) of up to 0.83 and the 95 \% confidence region (0.63 0.96). Analyzing classification results one comes to the conclusion that the tumor circularity, which is the most informative among shape/contour features, is not essential against the background of textural features. The reported study shows that a relatively straightforward procedure can be employed to obtain benign vs malignant classifier comparable with that originally used for the database of the raw RF signals and based on the more complicated segmentation of the parameter maps of homodyned K distribution.

Reproducibility of Segmentation-based Myocardial Radiomic Features with Cardiac MRI.

To investigate reproducibility of myocardial radiomic features with cardiac MRI. Test-retest studies were performed with a 3-T MRI system using commonly used cardiac MRI sequences of cine balanced steady-state free precession (cine bSSFP), T1-weighted and T2-weighted imaging, and quantitative T1 and T2 mapping in phantom experiments and 10 healthy participants (mean ± standard deviation age, 29 years ± 13). In addition, this study assessed repeatability in 51 patients (56 years ± 14) who underwent imaging twice during the same session. Three readers independently delineated the myocardium to investigate inter- and intraobserver reproducibility of radiomic features. A total of 1023 radiomic features were extracted by using PyRadiomics (https://pyradiomics.readthedocs.io/) with 11 image filters and six feature families. The intraclass correlation coefficient (ICC) was estimated to assess reproducibility and repeatability, and features with ICCs greater than or equal to 0.8 were considered reproducible. Different reproducibility patterns were observed among sequences in in vivo test-retest studies. In cine bSSFP, the gray-level run-length matrix was the most reproducible feature family, and the wavelet low-pass filter applied horizontally and vertically was the most reproducible image filter. In T1 and T2 maps, intensity-based statistics (first-order) and gray-level co-occurrence matrix features were the most reproducible feature families, without a dominant reproducible image filter. Across all sequences, gray-level nonuniformity was the most frequently identified reproducible feature name. In inter- and intraobserver reproducibility studies, respectively, only 32%-47% and 61%-73% of features were identified as reproducible. Only a small subset of myocardial radiomic features was reproducible, and these reproducible radiomic features varied among different sequences. Supplemental material is available for this article. © RSNA, 2020See also the commentary by Leiner in this issue.

DIAGNOSIS OF LUNG NODULES FROM 2D COMPUTER TOMOGRAPHY SCANS

Cancers typically are both highly dangerous and common. Among these, lung cancer has one of the lowest survival rates compared to other cancers. CT scans can reveal dense masses of different shapes and sizes; in the lungs, these are called lung nodules. This study applied a computer-aided diagnosis (CAD) system to detect candidate nodules — and diagnose it either solitary or juxtapleural — with equivalent diameters, ranging from 7.78[Formula: see text]mm to 22.48[Formula: see text]mm in a 2D CT slice. Pre-processing and segmentation is a very important step to segment and enhance the CT image. A segmentation and enhancement algorithm is achieved using bilateral filtering, Thresholding the gray-level transformation function, Bounding box and maximum intensity projection. Border artifacts are removed by clearing the lung border, erosion, dilation and superimposing. Feature extraction is done by extracting 20 gray-level co-occurrence matrix features from four directions: [Formula: see text], [Formula: see text], [Formula: see text] and [Formula: see text] and one distance of separation ([Formula: see text] pixel). In the classification step, two classifiers are proposed to classify two types of nodules based on their locations: as juxtapleural or solitary nodules. The two classifiers are a deep learning convolutional neural network (CNN) and the K-nearest neighbor (KNN) algorithm. Random oversampling and 10-fold cross-validation are used to improve the results. In our CAD system, the highest accuracy and sensitivity rates achieved by the CNN were 96% and 95%, respectively, for solitary nodule detection. The highest accuracy and sensitivity rates achieved by the KNN model were 93.8% and 96.7%, respectively, and K was set to 1 to detect juxtapleural nodules.

Modelling the steel microstructure knowledge for in-silico recognition of phases using machine learning

The present article demonstrates an effective approach to model the in-silico recognition of phases in steel microstructures using the machine learning and image processing technologies. It is based on a comprehensive microstructure dataset of 192 typical steel SEM images that was created by in-house experimentation, covering a wide variation across types phases and their volume fractions, grain sizes and magnifications. The selective Gray Level Co-occurrence Matrix (GLCM) feature vector extracted from the Simple Linear Iterative Clustering (SLIC) segmented phase patches was effectively used to create a numerical dataset from the microstructure image dataset. A Multi-Layer Perceptron (MLP) model was trained for automatic and accurate recognition of the constituent phases in the microstructure using this GLCM feature vector data. The trained MLP model was able to achieve a network loss of 0.1156 with a prediction accuracy of 83.92% in training dataset and that of 0.25 and 83.5% in the validation dataset, respectively. The prediction accuracy of the proposed MLP model was found to be adequate with the confidence level in automatic recognition of various phases in the range of 77–100%. The quantitative analysis results of the phase regions and phase boundaries from each microstructure appears to be reasonably accurate. The variation in prediction of phase volume fraction against the magnifications were obtained as 16.90 ± 4.0, 70.6 ± 6.0 and 99.97 ± 0.02 (IF steel microstructure) for pearlite, martensite and ferrite phases respectively. The obtained results have been discussed in context of the knowledge of steel microstructures.

Ischemic stroke lesion detection, characterization and classification in CT images with optimal features selection.

Ischemic stroke is the dominant disorder for mortality and morbidity. For immediate diagnosis and treatment plan of ischemic stroke, computed tomography (CT) images are used. This paper proposes a histogram bin based novel algorithm to segment the ischemic stroke lesion using CT and optimal feature group selection to classify normal and abnormal regions. Steps followed are pre-processing, segmentation, extracting texture features, feature ranking, feature grouping, classification and optimal feature group (FG) selection. The first order features, gray level run length matrix features, gray level co-occurrence matrix features and Hu's moment features are extracted. Classification is done using logistic regression (LR), support vector machine classifier (SVMC), random forest classifier (RFC) and neural network classifier (NNC). This proposed approach effectively detects ischemic stroke lesion with a classification accuracy of 88.77%, 97.86%, 99.79% and 99.79% obtained by the LR, SVMC, RFC and NNC when FG12 is opted, which is validated by fourfold cross validation.

Discriminant analysis and interpretation of nuclear chromatin distribution and coarseness using gray-level co-occurrence matrix features for lobular endocervical glandular hyperplasia.

Lobular endocervical glandular hyperplasia (LEGH) is a disease considered to be the origin of tumorigenesis of minimal deviation adenocarcinoma, which has characteristic expression in the gastric pyloric mucosa. It is difficult to diagnose by nuclear findings because of lower nuclear atypia. In this study, nuclei of endocervical (EC) and LEGH cells were digitized, and nuclear information was quantified from nuclear images and objectively evaluated using a computer. We examined whether it is possible to distinguish between EC and LEGH cells, which is difficult by human eyes. Signal intensity, morphological features, Otsu thresholding technique and gray-level co-occurrence matrix (GLCM) features were calculated from nuclei of EC and LEGH cells on cytology microscopic images. Then, discriminant analysis was performed using the significant difference test and linear support vector machine (LSVM). GLCM features in LEGH cells were higher than those in EC cells. The nuclei of LEGH cells had a higher frequency of signal value pairs with a larger signal value difference than that of EC cells. Therefore, LEGH cell nuclei are thought to have more chromatin granules, and the chromatin is coarse and granular. Moreover, in the LSVM discriminant analysis, the accuracy of GLCM calculated using these features was 85.4%. In this study, GLCM accurately demonstrated the nuclear chromatin distribution and coarseness. Discriminant analysis of EC and LEGH cells using GLCM features is useful.

Using near-infrared hyperspectral imaging with multiple decision tree methods to delineate black tea quality.

The evaluation of tea quality tended to be subjective and empirical by human panel tests currently. A convenient analytical approach without human involvement was developed for the quality assessment of tea with great significance. In this study, near-infrared hyperspectral imaging (HSI) combined with multiple decision tree methods was utilized as an objective analysis tool for delineating black tea quality and rank. Data fusion that integrated texture features based on gray-level co-occurrence matrix (GLCM) and short-wave near-infrared spectral features were as the target characteristic information for modeling. Three different types of supervised decision tree algorithms (fine tree, medium tree, and coarse tree) were proposed for the comparison of the modeling effect. The results indicated that the performance of models was enhanced by the multiple perception feature fusion. The fine tree model based on data fusion obtained the best predictive performance, and the correct classification rate (CCR) of evaluating black tea quality was 93.13% in the prediction process. This work demonstrated that HSI coupled with intelligence algorithms as a rapid and effective strategy could be successfully applied to accurately identify the rank quality of black tea.

Integrative Radiogenomics Approach for Risk Assessment of Post-Operative Metastasis in Pathological T1 Renal Cell Carcinoma: A Pilot Retrospective Cohort Study.

Despite the increasing incidence of pathological stage T1 renal cell carcinoma (pT1 RCC), postoperative distant metastases develop in many surgically treated patients, causing death in certain cases. Therefore, this study aimed to create a radiomics model using imaging features from multiphase computed tomography (CT) to more accurately predict the postoperative metastasis of pT1 RCC and further investigate the possible link between radiomics parameters and gene expression profiles generated by whole transcriptome sequencing (WTS). Four radiomic features, including the minimum value of a histogram feature from inner regions of interest (ROIs) (INNER_Min_hist), the histogram of the energy feature from outer ROIs (OUTER_Energy_Hist), the maximum probability of gray-level co-occurrence matrix (GLCM) feature from inner ROIs (INNER_MaxProb_GLCM), and the ratio of voxels under 80 Hounsfield units (Hus) in the nephrographic phase of postcontrast CT (Under80HURatio), were detected to predict the postsurgical metastasis of patients with pathological stage T1 RCC, and the clinical outcomes of patients could be successfully stratified based on their radiomic risk scores. Furthermore, we identified heterogenous-trait-associated gene signatures correlated with these four radiomic features, which captured clinically relevant molecular pathways, tumor immune microenvironment, and potential treatment strategies. Our results of accurate surrogates using radiogenomics could lead to additional benefit from adjuvant therapy or postsurgical metastases in pT1 RCC.

Bridging the gap between micro- and macro-scales in medical imaging with textural analysis – A biological basis for CT radiomics classifiers?

IntroductionStudies suggest there is utility in computed tomography (CT) radiomics for pancreatic disease; however, the precise biological interpretation of its features is unclear. In this manuscript, we present a novel approach towards this interpretation by investigating sub-micron tissue structure using digital pathology. MethodsA classification-to attenuation (CAT) function was developed and applied to digital pathology images to create sub-micron linear attenuation maps. From these maps, grey level co-occurrence matrix (GLCM) features were extracted and compared to pathology features. To simulate the spatial frequency loss in a CT scanner, the attenuation maps were convolved with a point spread function (PSF) and subsequently down-sampled. GLCM features were extracted from these down-sampled maps to assess feature stability as a function of spatial frequency loss. ResultsTwo GLCM features were shown to be strongly and positively correlated (r = 0.8) with underlying characteristics of the tumor microenvironment, namely percent pimonidazole staining in the tumor. All features underwent marked change as a function of spatial frequency loss; progressively larger spatial frequency losses resulted in progressively larger inter-tumor standard deviations; two GLCM features exhibited stability up to a 100 µm pixel size. ConclusionThis work represents a necessary step towards understanding the biological significance of radiomics. Our preliminary results suggest that cellular metrics of pimonidazole-detectable hypoxia correlate with sub-micron attenuation coefficient texture; however, the consistency of these textures in face of spatial frequency loss is detrimental for robust radiomics. Further study in larger data sets may elucidate additional, potentially more robust features of biologic and clinical relevance.

Rotor target recognition method based on radar echo time-frequency map feature

In order to realize the identification of different rotor targets, five typical rotor targets are selected as the research object. five typical single-rotor or twin-rotor targets, AH-64 Apache helicopter, K-50 armed helicopter, K-MAX hoist helicopter, V-22 tilt-rotor aircraft, and WZ-9 armed helicopter, were selected as research objects. the echo signals are obtained according to the rotor target radar echo model in free space, and then the time-frequency image is obtained by short-time fourier transform. According to the difference of the time-frequency images of five types of rotorcraft targets, two typical features that characterize the map differences, namely the histogram of oriented gradient feature and the gray level co-occurrence matrix feature, are extracted. Finally, the support vector machine (SVM) is used to realize the recognition of five types of rotor targets, and recognition accuracy reached 93.3%.

Fruit Fly-Based Artificial Neural Network Classifier with Kernel-Based Fuzzy c-Means Clustering for Satellite Image Classification

Image segmentation and classification are the major challenges to satellite imagery. Also, the identification of unique objects in the satellite image is a significant aspect in the application of remote sensing. Many satellite image classification techniques have been presented earlier. However, the accuracy of the image classification has to be further improved. So that, optimal artificial neural network with kernel-based fuzzy c-means ([Formula: see text]) clustering based satellite image classification is proposed in this paper. Initially, the images are segmented with the help of KFCM algorithm. Then, color features and gray level co-occurrence matrix (GLCM) features to be extracted from the segmented regions. Then, these extracted features are given to the OANN classifier. Based on these features, segmented regions are classified as building, road, shadow, and tree. To enhance the performance of the classifier, the weight values are optimally selected with the help of fruit fly algorithm. Simulation results show that the performance of proposed classifier outperforms that of the existing filters in terms of accuracy.

A Hybrid Method of Textile Defect Detection using GLCM, LBP, SVD and Wavelet Transform

A roll of fabric with defects can have a depreciation of 45 to 65% with respect to the original price. While some commercial solutions exist, automatic fabric defect detection remains an active field of development and research. The goal is to extract the characteristics of the texture of the fabric to detect defects contained using image processing techniques. To date, there is no standard method which ensures the detection of texture defects in fabrics with high precision. In the following work, the use of Singular Value Decomposition (SVD), Local Binary Pattern (LBP) and Gray-Level Co-Occurrence Matrix (GLCM) features of images for the identification of defects in textiles is presented, where the application of techniques for pre-processing is presented, and for the analysis of texture LBP and the GLCM in order to extract features and segmentation is done using SVD approach. This model makes it possible to obtain compact and precise detection of the faulty texture structures. Our method is capable of achieving very precise detection and localization of texture defects in the images of the Fabric-Defect-Inspection-GLSR database, while ensuring a reasonable processing time.

Analysis and Classification of Dermoscopic Images Using Spectral Graph Wavelet Transform

The abnormal growth of skin cells leads to skin cancer which occurs due to the unrepaired DNA impairment to the skin cells. Worldwide every year more than 1.23 lakhs of skin cancers are diagnosed, out of which Melanoma is the deadliest one. The aim of this research work is Recognition of Melanoma and skin lesion classification from the Dermoscopic images. Feature extraction of Dermoscopic images can be done by Shape, Color and Texture features. Texture features comprises of Gray Level Co-occurrence Matrix (GLCM) and statistical texture features calculated from the coefficients of the Multiresolution transforms such as Discrete Wavelet Transform (DWT), Curvelet, Tetrolet, and Spectral Graph Wavelet Transform (SGWT). The novelty in this work is using SGWT for extraction of texture features. The superiority of SGWT over conventional wavelet transform is its ability to work on irregular shaped images. Weighted graphs are the base for the SGWT which can be obtained in the form of meshes for irregular shapes. In the present work, skin lesions are obtained from the International Skin Imaging Collaboration (ISIC) 2016 archive. The features obtained from the Dermoscopic images are classified using Naïve Baye's, K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) classifiers. The proposed method using Shape, Color and Texture based features for Melanoma Recognition with SGWT results in an Area Under the Curve (AUC) of 0.951 with Accuracy of 96.79 %, Sensitivity of 88 % and Specificity of 98.26 %. Further, the AUC of skin lesion classification such as Melanoma vs Nevus, Seborrheic Keratosis vs Squamous Cell Carcinoma, Melanoma vs Seborrheic Keratosis, Melanoma vs Basal Cell Carcinoma and Nevus vs Basal Cell Carcinoma using SGWT is 0.895, 0.945, 0.9645, 0.945 and 0.98 respectively.

Optimization insisted watermarking model: hybrid firefly and Jaya algorithm for video copyright protection

In this digital era, illegitimate redistribution and protection of digital multimedia have to turn out to be the critical issue. Therefore, digital watermarking has been introduced for avoiding illegitimate works and also to ensure security and authentication as well. “Digital video watermarking is a method to hide some kind of data like audio, image, text into digital video sequences which is nothing but orders of successive still images.” This paper intends to formulate a novel video watermarking framework that includes three stages, such as (i) optimal video frame prediction, (ii) watermark embedding process and (iii) watermark extraction process. Very first, the optimal frames are determined using a new hybrid algorithm termed trial-based update on Jaya plus firefly (TU-JF) algorithm, in such a way that the peak signal-to-noise ratio (PSNR) should be maximal. The frames are assigned with a label of one or zero, where label one denotes the frame with better PSNR (can select for embedding process) and label zero denotes the frame with reduced PSNR (cannot be used for embedding). Consequently, a data library is formed from the obtained results, where each frame of videos is determined with their gray-level co-occurrence matrix (GLCM) features and labels (can embed or not). As in the proposed model, the optimal frame prediction is carried out using deep belief network (DBN) framework; the obtained data are then trained in the model. The optimal frames could be predicted in an efficient manner while testing. The significant contribution of this work concerns the optimization of hidden neurons in the DBN framework, which helps to enhance prediction accuracy. At last, the “watermark embedding process” and “watermark extraction process” are done by which the image could be embedded within the optimal frames.

Application of a Novel Ultra-High Resolution Multi-Detector CT in Quantitative Imaging of Trabecular Microstructure.

To evaluate the performance of a novel ultra-high resolution multi-detector CT scanner (Canon Aquilion Precision UHR CT), capable of visualizing ~150 μm details, in quantitative assessment of bone microarchitecture. Compared to conventional CT, the spatial resolution of UHR CT begins to approach the size of the trabeculae. This might enable measurements of microstructural correlates of osteoporosis, osteoarthritis, and other bone disease. The UHR CT system features a 160-row x-ray detector with 250×250 μm pixels (measured at isocenter) and a custom-designed x-ray source with a 0.4×0.5 mm focal spot. Visualization of high contrast details down to ~150 μm has been achieved on this device, which is now commercially available for clinical use. To evaluate the performance of UHR CT in quantification of bone microstructure, we imaged a variety of human bone samples (including ulna, radius, and vertebrae) embedded in a ~16 cm diameter plastic cylinder and in an anthropomorphic thorax phantom (QRM-Thorax, QRM Gmbh). Helical UHR CT acquisitions (120 kVp tube voltage) were acquired at scan exposures of 375 mAs - 5 mAs. For comparison, the samples were also imaged using a Normal Resolution (NR) mode available on the scanner, involving 500 μm slice thickness, exposure of 50 mAs, and a focal spot of 0.6×1.3 mm. We obtained micro-CT (μCT) of the bone samples at ~28 μm voxel size as a gold-standard reference. Geometric measurements of bone microstructure were performed in 17 regions-of-interests (ROIs) distributed throughout the bones of the phantoms; image registration was used to place the ROIs at corresponding locations in the UHR CT and NR CT. Trabecular thickness Tb.Th, spacing Tb.Sp, and Bone Volume fraction BvTv were obtained. The UHR and NR imaging protocols were compared terms of correlations to μCT and error of trabecular measurements. The effect of dose on trabecular morphometry was also studied for the UHR CT. Furthermore, we evaluated the sensitivity of texture features of trabecular bone (recently proposed as an alternative to geometric indices of microstructure) to imaging protocol. Image texture evaluation was performed using ~150 regions of interest (ROIs) across all bone samples. Three-dimensional Gray Level Co-occurrence Matrix (GLCM) and Gray Level Run Length Matrix (GLRM) features were extracted for each ROI. We analyzed correlation and concordance correlation coefficient (CCC) of the mean ROI values of texture features obtained using the UHR and NR modes. UHR CT reconstructions of bone samples clearly demonstrated improved visualization of the trabeculae compared to NR CT. UHR CT achieved substantially better correlations for all three metrics of bone microstructure, in particular for BvTv (correlation coefficient of 0.91 for UHR CT compared to 0.84 for NR CT) and TbSp (correlation of 0.74 for UHR CT and 0.047 for NR CT). The error obtained with UHR CT was generally smaller than that of NR CT. For TbSp, the mean deviation from μCT (averaged across all bone samples) was only ~0.07 for UHR CT, compared to 0.25 for NR CT. Analysis of reproducibility of texture features of trabecular bone between UHR CT and NR CT revealed fair correlations (>0.7) for the majority of GLCM features, but relatively poor CCC (e.g. 0.02 for Energy and 0.04 for Entropy). The magnitude of texture metrics is particularly affected by the enhanced spatial resolution of UHR CT. The recently introduced UHR CT achieves improved correlation and reduced error in measurements of trabecular bone microstructure compared to conventional resolution CT. Future development of diagnostic strategies based on textural biomarkers derived from UHR CT will need to account for potential sensitivity of texture features to image resolution.

Pulmonary Disease Pattern Recognition on X-Ray Radiography Image Using Artificial Neural Network (ANN) Method

This research aims to recognize the pattern of pulmonary disease on x-ray radiography image using artificial neural network (ANN) method. The images, which were used such as images of healthy pulmonary, pulmonary tuberculosis, and pulmonary tumour. Pattern recognition was using an extraction feature of GLCM (Gray Level Co-occurrence Matrix) and back propagation method. Before being identified, the images were processed by median filter and adaptive histogram equalization. The GLCM features that used were homogeneity, energy, contrast, variance and correlation. The parameters were learning rate and hidden layer. Learning rate was 0.3 and hidden layer was 25. Back propagation training showed 100% accuracy, which all of 44 images were used had been successfully identified. From the result, the healthy pulmonary showed 60% accuracy, 83.3% for pulmonary tuberculosis and 100% for pulmonary tumor. Hence, the overall result showed 81.25% accuracy, which 13 of 16 images had been successfully identified. From these result, extraction feature of GLCM using back propagation method was capable to recognize the pattern of pulmonary disease. However, due to narrow range of the feature, this application may not be used optimally for comparing features in every category of images. Therefore, the further research is needed to determine the best features and parameters of training back propagation.

A two-level fusion for building irregularity detection in post-disaster VHR oblique images

A post-disaster scene is more complicated than a vertical pre-disaster one, since it includes debris-covered areas and the imagery angle may be oblique. Detecting buildings and their irregularities in post-disaster oblique images is a valuable resource in many remote sensing applications, such as building damage assessment, which is a critical and challenging task in the disaster management cycle. We proposed a two-level fusion method, which is fast enough to support save and rescue missions. Firstly, an edge-based knowledge-based approach is designed to extract the vertical building map from temporal pre-disaster data. This approach utilizes Gray-Level Co-Occurrence Matrix (GLCM) features and shadow information. The temporal analysis helps the procedure to find stable objects by reducing the effect of noise in fine-resolution data. The mentioned two-level fusion includes data and decision levels. Spectral and georeferenced bands of pre- and post-disaster samples are fused in the data level. The decision-level refers to fusing the results of two classifiers, Spectral-only and Geo-Spectral classifiers. The locality of the method is preserved by the georeferenced feature. The proposed method is implemented on the Google Earth Engine (GEE) platform, and the evaluation is based on Hurricane Nate (2017) and Hurricane Harvey (2017) oblique images. The proposed method shows a significant reduction in the false-positive error, and provides a high performance in detecting irregularity in facade and rooftop areas.

Effects of variability in radiomics software packages on classifying patients with radiation pneumonitis.

Purpose: While radiomics feature values can differ when extracted using different radiomics software, the effects of these variations when applied to a particular clinical task are currently unknown. The goal of our study was to use various radiomics software packages to classify patients with radiation pneumonitis (RP) and to quantify the variation in classification ability among packages. Approach: A database of serial thoracic computed tomography scans was obtained from 105 patients with esophageal cancer. Patients were treated with radiation therapy (RT), resulting in 20 patients developing RP grade . Regions of interest (ROIs) were randomly placed in the lung volume of the pre-RT scan within high-dose regions ( ), and corresponding ROIs were anatomically matched in the post-RT scan. Three radiomics packages were compared: A1 (in-house), IBEX v1.0 beta, and PyRadiomics v.2.0.0. Radiomics features robust to deformable registration and common among radiomics packages were calculated: four first-order and four gray-level co-occurrence matrix features. Differences in feature values between time points were calculated for each feature, and logistic regression was used in conjunction with analysis of variance to classify patients with and without RP ( ). Classification ability for each package was assessed using receiver operating characteristic (ROC) analysis and compared using the area under the ROC curve (AUC). Results: Of the eight radiomics features, five were significantly correlated with RP status for all three packages, whereas one feature was not significantly correlated with RP for all three packages. The remaining two features differed in whether or not they were significantly associated with RP status among the packages. Seven of the eight features agreed among the packages in whether the AUC value was significantly . Conclusions: Radiomics features extracted using different software packages can result in differences in classification ability.

Prediction of transient tumor enlargement using MRI tumor texture after radiosurgery on vestibular schwannoma.

PurposeVestibular schwannomas (VSs) are uncommon benign brain tumors, generally treated using Gamma Knife radiosurgery (GKRS). However, due to the possible adverse effect of transient tumor enlargement (TTE), large VS tumors are often surgically removed instead of treated radiosurgically. Since microsurgery is highly invasive and results in a significant increased risk of complications, GKRS is generally preferred. Therefore, prediction of TTE for large VS tumors can improve overall VS treatment and enable physicians to select the most optimal treatment strategy on an individual basis. Currently, there are no clinical factors known to be predictive for TTE. In this research, we aim at predicting TTE following GKRS using texture features extracted from MRI scans.MethodsWe analyzed clinical data of patients with VSs treated at our Gamma Knife center. The data was collected prospectively and included patient‐ and treatment‐related characteristics and MRI scans obtained at day of treatment and at follow‐up visits, 6, 12, 24 and 36 months after treatment. The correlations of the patient‐ and treatment‐related characteristics to TTE were investigated using statistical tests. From the treatment scans, we extracted the following MRI image features: first‐order statistics, Minkowski functionals (MFs), and three‐dimensional gray‐level co‐occurrence matrices (GLCMs). These features were applied in a machine learning environment for classification of TTE, using support vector machines.ResultsIn a clinical data set, containing 61 patients presenting obvious non‐TTE and 38 patients presenting obvious TTE, we determined that patient‐ and treatment‐related characteristics do not show any correlation to TTE. Furthermore, first‐order statistical MRI features and MFs did not significantly show prognostic values using support vector machine classification. However, utilizing a set of 4 GLCM features, we achieved a sensitivity of 0.82 and a specificity of 0.69, showing their prognostic value of TTE. Moreover, these results increased for larger tumor volumes obtaining a sensitivity of 0.77 and a specificity of 0.89 for tumors larger than 6 cm3.ConclusionsThe results found in this research clearly show that MRI tumor texture provides information that can be employed for predicting TTE. This can form a basis for individual VS treatment selection, further improving overall treatment results. Particularly in patients with large VSs, where the phenomenon of TTE is most relevant and our predictive model performs best, these findings can be implemented in a clinical workflow such that for each patient, the most optimal treatment strategy can be determined.