Image Texture Analysis Research Articles

A Prognostic Model Integrating PET-Derived Quantitative Parameters and Image Texture Analyses Using Radiomics in a Large Prospective Phase III Trial, GOYA

A Prognostic Model Integrating PET-Derived Quantitative Parameters and Image Texture Analyses Using Radiomics in a Large Prospective Phase III Trial, GOYA

The potential of machine learning to predict postoperative pancreatic fistula based on preoperative, non-contrast-enhanced CT: A proof-of-principle study

BackgroundPostoperative pancreatic fistula remains an unsolved challenge after pancreatoduodenectomy. Important in this regard is the presence of a soft pancreatic texture which is a major risk factor. Advances in machine learning and texture analysis of medical images allow identification of features of parenchyma that are invisible to the human eye. The aim of this study was to investigate the potential of machine learning to predict postoperative pancreatic fistula based on preoperative, non-contrast-enhanced computed tomography. MethodsWe screened a prospectively assessed database including all patients undergoing pancreatoduodenectomy at a tertiary center from 2008 until 2018 for patients based on the occurrence of postoperative pancreatic fistula. In total, 110 patients were included, consisting of 55 patients who developed a postoperative pancreatic fistula and 55 without postoperative pancreatic fistula. For machine learning-based texture analysis preoperative, non-contrast-enhanced computed tomography axial images were used. Machine learning results were tested using 10-fold cross validation. Previously validated clinical fistula risk scores (original and alternative fistula risk scores) served as reference tests. ResultsBoth the original and the alternative fistula risk scores showed good discrimination between patients without and with postoperative pancreatic fistula (area under the curve 0.76 and 0.72, respectively). Machine learning-based texture analysis showed potential to detect histologic fibrosis (area under the curve 0.84, sensitivity 75%; specificity 92%), histologic lipomatosis (area under the curve 0.82, sensitivity 78%; specificity 89%), and intraoperative pancreatic hardness (area under the curve 0.70, sensitivity 78%; specificity 74%). The features of the machine learning-based texture analysis were most accurate in predicting the occurrence of postoperative pancreatic fistula (area under the curve 0.95, sensitivity of 96%; specificity 98%) after pancreatoduodenectomy. ConclusionThis proof-of-principle study suggests the ability of machine learning in recognizing important features of pancreatic texture associated with an increased risk of postoperative pancreatic fistula based on preoperative computed tomography.

Evaluation of Texture Analysis for the Differential Diagnosis of Mass-Forming Pancreatitis From Pancreatic Ductal Adenocarcinoma on Contrast-Enhanced CT Images.

Purpose: To investigate the potential of computed tomography (CT) imaging features and texture analysis to differentiate between mass-forming pancreatitis (MFP) and pancreatic ductal adenocarcinoma (PDAC).Materials and Methods: Thirty patients with pathologically proved MFP and 79 patients with PDAC were included in this study. Clinical data and CT imaging features of the two lesions were evaluated. Texture features were extracted from arterial and portal phase CT images using commercially available software (AnalysisKit). Multivariate logistic regression analyses were used to identify relevant CT imaging and texture parameters to discriminate MFP from PDAC. Receiver operating characteristic curves were performed to determine the diagnostic performance of predictions.Results: MFP showed a larger size compared to PDAC (p = 0.009). Cystic degeneration, pancreatic ductal dilatation, vascular invasion, and pancreatic sinistral portal hypertension were more frequent and duct penetrating sign was less frequent in PDAC compared to MFP. Arterial CT attenuation, arterial, and portal enhancement ratios of MFP were higher than PDAC (p < 0.05). In multivariate analysis, arterial CT attenuation and pancreatic duct penetrating sign were independent predictors. Texture features in arterial phase including SurfaceArea, Percentile40, InverseDifferenceMoment_angle90_offset4, LongRunEmphasis_angle45_offset4, and uniformity were independent predictors. Texture features in portal phase including LongRunEmphasis_angle135_offset7, VoxelValueSum, LongRunEmphasis_angle135_offset4, and GLCMEntropy_angle45_offset1 were independent predictors. Areas under the curve of imaging feature-based, texture feature-based in arterial and portal phases, and the combined models were 0.84, 0.96, 0.93, and 0.98, respectively.Conclusions: CT texture analysis demonstrates great potential to differentiate MFP from PDAC.

Reliability of 2D Magnetic Resonance Imaging Texture Analysis in Cerebral Gliomas: Influence of Slice Selection Bias on Reproducibility of Radiomic Features

Reliability of 2D Magnetic Resonance Imaging Texture Analysis in Cerebral Gliomas: Influence of Slice Selection Bias on Reproducibility of Radiomic Features

PET-MR Imaging and MR Texture Analysis in the Diagnosis of Pancreatic Cysts: A Prospective Preliminary Study

Our aim was to evaluate the capability of textural and metabolic parameters measured at pretreatment 18F-fluorodeoxyglucose Positron emission tomography (PET)-MR in differentiating malignant from benign pancreatic cystic lesions. Forty consecutive patients were prospectively enrolled in this study. They underwent simultaneous PET-MR for the diagnosis of pancreatic cysts. Thirty texture parameters were extracted from manually contoured axial T2-weighted imaging with fat suppression (T2FS) and apparent diffusion coefficient images, respectively. Maximal and mean standardized uptake values (SUVmax and SUVmean, respectively) of pancreatic cysts were measured at PET-MR imaging. The Mann-Whitney test was used to compare both textural and metabolic parameters between benign and malignant group. FDG uptake was significantly higher in patients with malignant pancreatic cysts (SUVmaxp = 0.002, SUVmeanp < 0.001). Malignant cysts showed significantly lower standard deviation for spatial scaling factor at 3-6mm on T2FS images and lower skewness for spatial scaling factor at 2-4mm on apparent diffusion coefficient images (p < 0.01). SUVmean had the highest Area under the curve of 0.892 on receiver-operating characteristic analysis with a sensitivity, specificity, and accuracy of 88.9%, 87.1%, and 87.6%, respectively. When metabolic and textural features were combined into a single diagnostic model, the AUC increased to 0.961, with a sensitivity, specificity, and accuracy of 88.9%, 96.8%, and 95.0%, respectively. Our study implied that PET-MR showed no obvious advantages over traditional PET-related imaging in differentiating malignant from benign pancreatic cystic lesions. Diagnostic model based on the combination of metabolic and textural parameters showed satisfactory performance.

Texture Analysis of T1-Weighted Contrast-Enhanced Magnetic Resonance Imaging Potentially Predicts Outcomes of Patients with Non–Wingless-Type/Non–Sonic Hedgehog Medulloblastoma

To investigate whether tumor texture features derived from preoperative T1-weighted magnetic resonance imaging (MRI) are associated with overall survival (OS) of patients with non-wingless-type (WNT)/non-sonic hedgehog (SHH) medulloblastoma. We retrospectively reviewed 38 patients with non-WNT/non-SHH (encompassing group 3 and group 4) medulloblastoma treated with surgery in our institution from 2013 to 2016. All patients were followed-up for at least 2 years or until death. Primary tumor traditional parameters were evaluated, and texture features were extracted from preoperative T1-weighted MRI, including 4 features from the histogram matrix and 6 textures from the gray-level co-occurrence matrix (GLCM). Texture features were dichotomized into 2 subgroups based on their optimal cutoff values obtained from receiver operating characteristics curve analysis. Two-year OS was compared between the dichotomized subgroups using the Kaplan-Meier analysis and log-rank test. Multivariate Cox regression analysis was performed to determine independent prognostic factors. The therapy regimen was the only basic characteristic significantly related to 2-year OS (P=0.015). Two features of the GLCM were shown to be significantly associated with 24-month OS. Multivariate Cox regression analysis revealed that GLCM homogeneity (adjusted hazard ratio, 0.145; P= 0.013) was an independent prognostic predictor for patients. Texture analysis on T1-weighted contrast-enhanced MRI potentially serves as a prognostic predictor of survival for patients with non-WNT/non-SHH medulloblastoma.

Quantification of perceptual coarseness of metallic coatings containing aluminum flakes using texture analysis and visual assessment methods

The industrial need for controlling the quality of metallic coatings for producing efficient and high-quality products makes it necessary to conduct an appearance quantification process. In this study, it had been attempted to present an appropriate algorithm to analyze the coarseness property of the metallic coatings using the image processing technique and texture analysis methods to achieve acceptable correlation with visual perception. For this purpose, we examined metallic silver and metallic blue coatings containing eight grades of aluminum flakes with different size distributions from fine to coarse cases. After capturing the images of samples using a scanner, they were studied using different texture analysis methods including autocorrelation function, distance-dependent edge frequency, gray level co-occurrence matrix (GLCM), Fourier transform and wavelet transform. Visual assessments were performed using a comparative judgment method. The precisions of the applied analysis methods were evaluated based on the correlation between their results and the visual assessment data. According to the obtained data, the autocorrelation function with R-squares of 0.88 and 0.9 for the metallic silver and metallic blue coatings, and also wavelet transform in the vertical channel with R-squares of 0.86 and 0.89 for the same mentioned coatings, respectively, had the best performance in comparison to visual perception. Consequently, it was possible to precisely quantify the coarseness perception of metallic coating using autocorrelation function and the wavelet transform as two feasible texture analysis methods. Moreover, the presence of the blue absorption pigment in the formulation had no significant effect on the performance of these two methods.

Application of an expert system of X- ray micro computed tomography imaging for identification of Sitophilus oryzae infestation in stored rice grains.

The plausibility of image texture analysis to assess X-ray images of S. oryzae-infested rice after variable storage days (fresh, 45, 90, 135, 180 and 225 days) was investigated using an X-ray micro computed tomography instrument. Subsequently, image acquisition, pre-processing, and the extraction of the image textural features was done using volume graphics VGL 2.2 software. Morphological features (radius, diameter, volume, compactness, sphericity, defect volume, and voids) were extracted from the x, y, and z views of the rice grain and used as inputs for principal component analysis (PCA). Clear grouping was observed between the fresh, 45 and 225-day-oldS. oryzae-infested rice grains with a classification accuracy of 88.34%. The voids (884 248.53 μm3 ) and defect volume distribution (137 428.04 μm3 ) were found to be the maximum in 225-day-old samples. The similarity or the distance indices values between fresh and 255-day-old S. oryzae-infested rice samples were found to be 35 038.08, which resulted in clear discrimination between different storage days in S. oryzae-infested rice grains. This work contributes to the potential use of image texture analysis to aid in distinguishing S. oryzae-infested rice grains from fresh rice grains. © 2019 Society of Chemical Industry.

Quantification of multiphoton and fluorescence images of reproductive tissues from a mouse ovarian cancer model shows promise for early disease detection.

.Ovarian cancer is the deadliest gynecologic cancer due predominantly to late diagnosis. Early detection of ovarian cancer can increase 5-year survival rates from 40% up to 92%, yet no reliable early detection techniques exist. Multiphoton microscopy (MPM) is a relatively new imaging technique sensitive to endogenous fluorophores, which has tremendous potential for clinical diagnosis, though it is limited in its application to the ovaries. Wide-field fluorescence imaging (WFI) has been proposed as a complementary technique to MPM, as it offers high-resolution imagery of the entire organ and can be tailored to target specific biomarkers that are not captured by MPM imaging. We applied texture analysis to MPM images of a mouse model of ovarian cancer. We also conducted WFI targeting the folate receptor and matrix metalloproteinases. We find that texture analysis of MPM images of the ovary can differentiate between genotypes, which is a proxy for disease, with high statistical significance (). The wide-field fluorescence signal also changes significantly between genotypes (). We use the features to classify multiple tissue groups to over 80% accuracy. These results suggest that MPM and WFI are promising techniques for the early detection of ovarian cancer.

Magnetic Resonance Imaging Texture Analysis Predicts Recurrence in Patients With Nasopharyngeal Carcinoma

BackgroundThe personalization of oncologic treatment using radiomic signatures is mounting in nasopharyngeal carcinoma (NPC). We ascertain the predictive ability of 3D volumetric magnetic resonance imaging (MRI) texture features on NPC disease recurrence. MethodsA retrospective study of 58 patients with NPC undergoing primary curative-intent treatment was performed. Forty-two image texture features were extracted from pre-treatment MRI in addition to clinical factors. A multivariate logistic regression was used to model the texture features. A receiver operating characteristic curve on 100 bootstrap samples was used to maximize generalizability to out-of-sample data. A Cox proportional model was used to predict disease recurrence in the final model. ResultsA total of 58 patients were included in the study. MRI texture features predicted disease recurrence with an area under the curve (AUC), sensitivity, and specificity of 0.79, 0.73, and 0.71, respectively. Loco-regional recurrence was predicted with AUC, sensitivity, and specificity of 0.82, 0.73 and 0.74 respectively while prediction for distant metastasis had an AUC, sensitivity, and specificity of 0.92, 0.79 and 0.84, respectively. Texture features on MRI had a hazard ratio of 4.37 (95% confidence interval 1.72–20.2) for disease recurrence when adjusting for age, sex, smoking, and TNM staging. ConclusionTexture features on MRI are independent predictors of NPC recurrence in patients undergoing curative-intent treatment.

Differential Diagnosis of Nonhypervascular Pancreatic Neuroendocrine Neoplasms From Pancreatic Ductal Adenocarcinomas, Based on Computed Tomography Radiological Features and Texture Analysis

To determine computed tomography (CT) radiological features and texture features that are rewarding in differentiating nonhypervascular pancreatic neuroendocrine neoplasms (PNENs) from pancreatic ductal adenocarcinomas (PDACs). We compared patients to pathologically proven nonhypervascular PNENs and age-matched controls with pathologically proven PDACs in a 1:2 ratio. Preoperative CT images in the arterial phase (AP) and portal vein phase (PVP) were obtained. Two radiologists independently reviewed the morphological characteristics of each tumor. Three-dimensional regions of interest (ROIs), drawn using ITK-SNAP software, were input into AK software (Artificial Intelligent Kit, GE) to extract texture features from AP and PVP images. Differences between PNENs and PDACs were analyzed with the chi-squared test, least absolute shrinkage and selection operator, kappa statistics, and uni- and multivariate logistic regression analyses. In total, 40 nonhypervascular PNENs and 80 PDACs were evaluated. Maximum diameter on axial section, margin, calcification, vascularity in the tumor, and tumor heterogeneity were significantly different between PDACs and nonhypervascular PNENs. Multivariate analysis showed well-defined tumor margin (odds ratio: 21.0) and presence of calcification (odds ratio: 4.4) were significant predictors of nonhypervascular PNENs. The area under the receiver operating characteristic curve of the radiological feature model, AP texture model, and PVP texture model were 0.780, 0.855, and 0.929, respectively, based on logistic regression. A well-defined margin and calcification in the tumor were helpful in discriminating nonhypervascular PNENs from PDACs. Texture analysis of contrast-enhanced CT images could be beneficial in differentially diagnosing nonhypervascular PNENs and PDACs.

Texture Analysis of Standard Magnetic Resonance Images to Predict Response to Gamma Knife Radiosurgery in Vestibular Schwannomas

To search for texture features of routine magnetic resonance imaging to predict tumor volume reduction and transient versus permanent tumor progression of vestibular schwannomas treated by Gamma Knife stereotactic radiosurgery. Included were 23 patients with vestibular schwannomas treated in our center and followed over a period of 23.7-80.3 months (mean 42.7). Magnetic resonance imaging was performed on a 3-Tesla scanner and included T1-weighted images with and without contrast enhancement, T2-weighted, and fluid-attenuated inversion recovery images. Volumetric results were followed longitudinally over time and correlated to texture features as mean, minimum, maximum, standard deviation, skewness, and kurtosis of normalized signals taken from regions of interest covering the total tumor volume. In total, 14 tumors showed early progression during the first 5-18 months (2 cases permanent, 12 cases transient), whereas 9 tumors regressed immediately after SRS. Kurtosis of T2-weighted image intensity values turned out to predict progression best with a sensitivity and specificity of 71% and 78%. From all texture feature parameters, only the minimum of the normalized T2-weighted image intensity values correlated significantly to the final reduction of tumor volume per month (correlation coefficient=-0.634, P < 0.05, corrected for false discovery rate). Texture feature analysis helps to predict permanent versus transient enlargement and final volume reduction of schwannomas after SRS. Thus, alternative treatment strategies might be considered, mainly in large tumors, where further clinical deterioration cannot be excluded. To confirm these results, a prospective study including more cases and a longer follow-up period is necessary.

Image Texture Analysis - A Survey

In this paper, different image texture analysis methods are discussed along with soft bio metric traits using various existing approaches. This adds to an outlook for future work in building integrated range of classifiers based on application side requirements. Texture is a measurable Characteristic having more reliability in case of security relevant applications. At the preliminary stage the judging quality of input image for any of the system is also an essential attribute. At the same time the basic blocks that makes the system for image texture analysis is also been tried to cover. Image texture analysis is currently the most focused topic for many of the researchers. The survey deals some of the significant techniques exist in image texture analysis.

Accuracy of magnetic resonance imaging texture analysis in differentiating low-grade from high-grade gliomas: systematic review and meta-analysis

ObjectivesTexture analysis (TA) is a method used for quantifying the spatial distributions of intensities in images using scanning software. MRI TA could be applied to grade gliomas. This meta-analysis was...

Design of rotation, illumination, and scale invariant Gabor texture descriptor for image texture analysis and retrieval

ABSTRACT Automatic classification in medical image processing with new problems to computer-aided detection methods is attributed to the dynamics of the image acquisition conditions. Such problems request that automatic outlines can provide robust descriptions of images irrespective of camera rotation, zoom, and illumination gradients. In order to attain better retrieval, a new HIRSG feature descriptor is intended that is self-determining of illumination, sale, and rotation differences. The proposed hybrid method is developed by implementing autocorrelation Gabor filter responses on the high frequency DWT coefficients. The proposed methodology is compared with the existing methods to show the system effectiveness.

Deep Learning for Alzheimer's Disease Classification using Texture Features.

We propose a classification method for Alzheimer's disease (AD) based on the texture of the hippocampus, which is the organ that is most affected by the onset of AD. We obtained magnetic resonance images (MRIs) of Alzheimer's patients from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. This dataset consists of image data for AD, mild cognitive impairment (MCI), and normal controls (NCs), classified according to the cognitive condition. In this study, the research methods included image processing, texture analyses, and deep learning. Firstly, images were acquired for texture analyses, which were then re-spaced, registered, and cropped with Gabor filters applied to the resulting image data. In the texture analyses, we applied the 3-dimensional (3D) gray-level co-occurrence (GLCM) method to evaluate the textural features of the image, and used Fisher's coefficient to select the appropriate features for classification. In the last stage, we implemented a deep learning multi-layer perceptron (MLP) model, which we divided into three types, namely, AD-MCI, AD-NC, and MCI-NC. We used this model to assess the accuracy of the proposed method. The classification accuracy of the proposed deep learning model was confirmed in the cases of AD-MCI (72.5%), ADNC (85%), and MCI-NC (75%). We also evaluated the results obtained using a confusion matrix, support vector machine (SVM), and K-nearest neighbor (KNN) classifier and analyzed the results to objectively verify our model. We obtained the highest accuracy of 85% in the AD-NC. The proposed model was at least 6-19% more accurate than the SVM and KNN classifiers, respectively. Hence, this study confirms the validity and superiority of the proposed method, which can be used as a diagnostic tool for early Alzheimer's diagnosis.

Textural Analysis of Liver Tumor using Watershed Segmentation based on Statistical and Geometrical features

The liver diseases can define as the tumor or disorder that can affect the liver and causes deformation in its shape. The early detection and diagnose of the tumor using CT medical images, helps the detector to specify the tumor perfectly. This search aims to detect and classify the liver tumor depending on the use of a computer (image processing and textural analysis) helps in getting an accurate diagnosis. The methods which are used in this search depend on creating a binary mask used to separate the liver from the origins of the other in the CT images. The threshold has been used as an early segmentation. A Process, the watershed process is used as a classification technique to isolate the tumor which is cancer and cyst.&#x0D; The test images are taking five for cancer case and five for the cyst, the geometrical and statistical features are calculated for both cases to identify the identity for each case. The statistical features are obtained from the gray level co-occurrence matrix which is contrast, homogeneity, correlation and energy. The geometrical features are the area of the tumor, the circumference and irregularity. The irregularity tends to lose one of the cyst cases than for cancer because of its shape in more regular than cancer.

ANALISIS TEKSTUR PADA CITRA IRIS MATA MENGGUNAKAN ALGORITMA GRAY LEVEL CO-OCCURENCY MATRIX

According to data from the ministry of health, with the high intensity of use the gadget nowadays, therefore the number of people with eye disease is increasing. To overcome increase suffers of eye disease, it takes need early detection for who suffers potentially eye disease so that handling and prevention of blindness from eye disease effect can be immediately. The process detection of eye disease can be see in iris, there are several disease can be seen in iris among there are diabetic retinopathy and glaucoma. This research present texture analysis for iris images, the method is used GLCM (Gray Level Co-occurency Matrix) which is implemented using Matlab, and using 5 parameters namely contrast, correlation, energy, homogeneity and entropy. Process analysis texture is developed with preprocessing technique, the result of texture in images data iris can be recognized and produce the dataset of result from feature extraction with GLCM (Gray Level Co-occurency Matrix).

Diseño de un sistema de reconocimiento de patrones en imágenes termográficas y de huella plantar para la identificación de pie plano en niños con edades entre cinco y seis años

The following paper presents the main results of exploratory research-oriented to the design and implementation of a pattern recognition system for flatfoot identification in children between 5 and 6 years. Patterns were determined from texture analysis of foot thermographic images, and from contour analysis of footprint images. For each case, an artificial neuronal network was trained, with base in a back-propagation algorithm. In each trial, 70 % of data were used for training, and 30 % for validation. For experiments done, success rates greater than 80 % were achieved. The best results were reached with contour patterns reduced by principal components analysis, PCA, in a binary system, with a success rate of 90.84 % in cross-validation. Results are a contribution to the study of diagnostic techniques for flatfoot treatment through the use of technologic tools.

Texture analysis in 177Lu SPECT phantom images: Statistical assessment of uniformity requirements using texture features.

The purpose of this study was to apply texture analysis (TA) to evaluate the uniformity of SPECT images reconstructed with the 3D Ordered Subsets Expectation Maximization (3D-OSEM) algorithm. For this purpose, a cylindrical homogeneous phantom filled with 177Lu was used and a total of 24 spherical volumes of interest (VOIs) were considered inside the phantom. The location of the VOIs was chosen in order to define two different configurations, i.e. gravity and radial configuration. The former configuration was used to investigate the uniformity of distribution of 177Lu inside the phantom, while the latter configuration was used to investigate the lack of uniformity from center towards edge of the images. For each VOI, the trend of different texture features considered as a function of 3D-OSEM updates was investigated in order to evaluate the influence of reconstruction parameters. TA was performed using CGITA software. The equality of the average texture feature trends in both spatial configurations was assumed as the null hypothesis and was tested by functional analysis of variance (fANOVA). With regard to the gravity configuration, no texture feature rejected the null hypothesis when the number of subsets increased. For the radial configuration, the statistical analysis revealed that, depending on the 3D-OSEM parameters used, a few texture features were capable of detecting the non-uniformity of 177Lu distribution inside the phantom moving from the center of the image towards its edge. Finally, cross-correlation coefficients were calculated to better identify the features that could play an important role in assessing quality assurance procedures performed on SPECT systems.