Inverse Difference Moment Research Articles

High-Precision Detection of Defects of Tire Texture Through X-ray Imaging Based on Local Inverse Difference Moment Features.

Automatic defect detection is an important and challenging issue in the tire industrial quality control. As is well known, the production quality of tire is directly related to the vehicle running safety and passenger security. However, it is difficult to inspect the inner structure of tire on the surface. This paper proposes a high-precision detection of defects of tire texture image obtained by X-ray image sensor for tire non-destructive inspection. In this paper, the feature distribution generated by local inverse difference moment (LIDM) features is proposed to be an effective representation of tire X-ray texture image. Further, the defect feature map (DFM) may be constructed by computing the Hausdorff distance between the LIDM feature distributions of original tire image and each sliding image patch. Moreover, DFM may be enhanced to improve the robustness of defect detection algorithm by a background suppression. Finally, an effective defect detection algorithm is proposed to achieve the pixel-level detection of defects with high precision over the enhanced DFM. In addition, the defect detection algorithm is not only robust to the noise in the background, but also has a more powerful capability of handling different shapes of defects. To validate the performance of our proposed method, two kinds of experiments about the defect feature map and defect detection are conducted to demonstrate its good performance. Moreover, a series of comparative analyses demonstrate that the proposed algorithm can accurately detect the defects and outperforms other algorithms in terms of various quantitative metrics.

MR texture analysis: potential imaging biomarker for predicting the chemotherapeutic response of patients with colorectal liver metastases.

The purpose of the study was to determine whether the pre-treated MR texture features of colorectal liver metastases (CRLMs) are predictive of therapeutic response after chemotherapy. The study included twenty-six consecutive patients (a total of 193 liver metastasis) with unrespectable CRLMs at our institution from August 2014 to February 2016. Lesions were categorized into either responding group or non-responding group according to changes in size. Texture analysis was quantified on T2-weightedimages by two radiologists with consensus on regions of interest which were manually drawn on the largest cross-sectional area of the lesions. Five histogram features (mean, variance, skewness, kurtosis, and entropy1) and five gray level co-occurrence matrix features (GLCM; angular second moment (ASM), entropy2, contrast, correlation, and inverse difference moment (IDM)) were extracted. The texture parameters were statistically analyzed to identify the differences between the two groups, and the potential predictive parameters to differentiate the responding group from the non-responding group were subsequently tested using multivariable logistic regression analysis. A total of 107 responding and 86 non-responding lesions were evaluated. A higher variance, entropy1, contrast, entropy2 and a lower ASM, correlation, IDM were independently (P < 0.05) associated with a good response to chemotherapy with the areas under the ROC curves (AUCs) of 0.602-0.784. Variance (P < 0.001) and ASM (P = 0.001) remained potential predictive values to discriminate responding lesions from non-responding lesions when tested using multivariable logistic regression analysis. The highest AUC of the predictors from the association of variance and ASM was 0.814. MR texture features on pre-treated T2 images have the potential to predict the therapeutic response of colorectal liver metastases.

Sistem Klasifikasi Tingkat Keparahan Retinopati Diabetik Menggunakan Support Vector Machine

Diabetic retinopathy is a vision disorder disease that can cause damage to the retina of the eye that will have a direct impact on the disruption of vision of the patient. The diabetic retinopathy phase is classified into four types (normal, mild NPDR, moderate NPDR (Non-Proliferative Diabetic Retinopathy), and severe NPDR). Retinal of eye data of diabetic retinopathy patients treated from the MESSIDOR database. By applying image processing, the retinal image of the eye in extraction using the area features extraction from the detection of exudate, blood vessels, microaneurysms, and texture feature extraction Gray Level Co-occurrence Matrix. The extracted results classified using the Support Vector Machine method with the Radial Basis Function (RBF) kernel. Classification evaluated with these parameters: Accuracy, specificity, and sensitivity.The results of classification show the best value using 6 statistical features ie, contrast, homogeneity, correlation, energy, entropy and inverse difference moment in the direction of 45 degrees with the RBF kernel. The result of classification research system on 240 data training and 60 data testing yields an average accuracy is 95.93%, the value of specificity is 97.29%, and a sensitivity rating is 91.07%. From the research result, using RBF kernel get the best accuracy result than using kernel polynomial or kernel linear.

URBAN SHANTY TOWN RECOGNITION BASED ON HIGH-RESOLUTION REMOTE SENSING IMAGES AND NATIONAL GEOGRAPHICAL MONITORING FEATURES – A CASE STUDY OF NANNING CITY

Abstract. Urban shanty towns are communities that has contiguous old and dilapidated houses with more than 2000 square meters built-up area or more than 50 households. This study makes attempts to extract shanty towns in Nanning City using the product of Census and TripleSat satellite images. With 0.8-meter high-resolution remote sensing images, five texture characteristics (energy, contrast, maximum probability, and inverse difference moment) of shanty towns are trained and analyzed through GLCM. In this study, samples of shanty town are well classified with 98.2 % producer accuracy of unsupervised classification and 73.2 % supervised classification correctness. Low-rise and mid-rise residential blocks in Nanning City are classified into 4 different types by using k-means clustering and nearest neighbour classification respectively. This study initially establish texture feature descriptions of different types of residential areas, especially low-rise and mid-rise buildings, which would help city administrator evaluate residential blocks and reconstruction shanty towns.

Value of Magnetic Resonance Imaging Texture Feature Analysis in the Differential Diagnosis between Pancreatic Serous Cystadenoma and Mucinous Cystadenoma

Objective To investigate the difference of tumor textures presented on T1-weighted image(T1WI) and T2-weighted image(T2WI) between pancreatic serous cystadenoma and mucinous cystadenoma. Methods Subjects including 24 patients with serous cystadenoma and 20 patients with mucinous cystadenoma who were treated in Hainan Branch of Chinese PLA General Hospital were enrolled in this study.The texture analysis was performed on T1WI and T2WI,and the texture parameters included angular second moment,contrast,correlation,inverse difference moment(IDM),and entropy.Independent sample t-test and Mann-Whitney U test were performed for the between-group comparison,the regression model was established by Binary Logistic regression analysis,and receiver operating characteristics curve(ROC) was drawn.Results The contrast and IDM of T1WI and the contrast,correlation,and IDM of T2WI showed significant differences between serous cystadenoma and mucinous cystadenoma(T1WI:Pangular second momont=0.714,Pcontrast=0.003,Pcorrelation=0.069,PIDM=0.004,Pentropy=0.818;T2WI:Pangular second momont=0.122,Pcontrast=0.000,Pcorrelation=0.000,PIDM=0.024,and Pentropy=0.081).The area under the ROC curve was 0.736-0.846 for the positive texture variables,and the area under the ROC curve was 0.879 for the variables in the model of Logistic regression.Binary Logistic regression analysis demonstrated that the contrast was a specific imaging variable for the differential diagnosis between serous cystadenoma and mucinous cystadenoma.Conclusion The texture analysis of T1WI and T2WI may be a simple and effective tool in the differential diagnosis between pancreatic serous cystadenoma and mucinous cystadenoma.

Role of quantitative computed tomography texture analysis in the prediction of adherent perinephric fat.

To assess the performance of computed tomography (CT) texture analysis to predict the presence of adherent perinephric fat (APF). Seventy patients with small renal tumors treated with robot-assisted partial nephrectomy were included. Patients were divided into two groups according to the presence of APF. We extracted 15 image features from unenhanced CT and contrast-enhanced CT corresponding to first-order and second-order Haralick textural features. Predictors of APF were evaluated by univariable and multivariable analysis. Receiver operating characteristic (ROC) analysis was performed and the area under the ROC curve (AUC) to predict APF was calculated for the independent predictors. APF was observed in 26 patients (37%). We identified entropy (p = 0.01), sum entropy (p = 0.02) and difference entropy (p = 0.05) as significant independent predictors of APF. In the portal phase, we identified correlation (p = 0.03), inverse difference moment (p = 0.01), sum entropy (p = 0.02), entropy (p = 0.01), difference variance (p = 0.04) and difference entropy (p = 0.02) as significant independent predictors of APF. Combining these parameters yielded to an ROC-AUC of 0.82 (95% CI 0.65-0.86). Results from this preliminary study suggest that CT texture analysis might be a promising quantitative imaging tool that helps urologist to identify APF.

Radiomics analysis of pulmonary nodules in low-dose CT for early detection of lung cancer.

To develop a radiomics prediction model to improve pulmonary nodule (PN) classification in low-dose CT. To compare the model with the American College of Radiology (ACR) Lung CT Screening Reporting and Data System (Lung-RADS) for early detection of lung cancer. We examined a set of 72 PNs (31 benign and 41 malignant) from the Lung Image Database Consortium image collection (LIDC-IDRI). One hundred three CT radiomic features were extracted from each PN. Before the model building process, distinctive features were identified using a hierarchical clustering method. We then constructed a prediction model by using a support vector machine (SVM) classifier coupled with a least absolute shrinkage and selection operator (LASSO). A tenfold cross-validation (CV) was repeated ten times (10 × 10-fold CV) to evaluate the accuracy of the SVM-LASSO model. Finally, the best model from the 10 × 10-fold CV was further evaluated using 20 × 5- and 50 × 2-fold CVs. The best SVM-LASSO model consisted of only two features: the bounding box anterior-posterior dimension (BB_AP) and the standard deviation of inverse difference moment (SD_IDM). The BB_AP measured the extension of a PN in the anterior-posterior direction and was highly correlated (r = 0.94) with the PN size. The SD_IDM was a texture feature that measured the directional variation of the local homogeneity feature IDM. Univariate analysis showed that both features were statistically significant and discriminative (P = 0.00013 and 0.000038, respectively). PNs with larger BB_AP or smaller SD_IDM were more likely malignant. The 10 × 10-fold CV of the best SVM model using the two features achieved an accuracy of 84.6% and 0.89 AUC. By comparison, Lung-RADS achieved an accuracy of 72.2% and 0.77 AUC using four features (size, type, calcification, and spiculation). The prediction improvement of SVM-LASSO comparing to Lung-RADS was statistically significant (McNemar's test P = 0.026). Lung-RADS misclassified 19 cases because it was mainly based on PN size, whereas the SVM-LASSO model correctly classified 10 of these cases by combining a size (BB_AP) feature and a texture (SD_IDM) feature. The performance of the SVM-LASSO model was stable when leaving more patients out with five- and twofold CVs (accuracy 84.1% and 81.6%, respectively). We developed an SVM-LASSO model to predict malignancy of PNs with two CT radiomic features. We demonstrated that the model achieved an accuracy of 84.6%, which was 12.4% higher than Lung-RADS.

Interactive segmentation of texture image based on active contour model with local inverse difference moment feature

Texture image segmentation is a challenging problem in image processing field due to wide variability of characterizing textures and a lack of proper contour information. In this paper, an effective presentation is found with which different textures can be represented with some corresponding distributions generated by feature values of local inverse difference moment (LIDM). By the analysis of local statistical information in gray level co-occurrence matrix (GLCM), we found that similar textures can be characterized with similar distributions. In this way, an interactive segmentation method is presented to achieve the segmentation of texture image based on GLCM with an optimizing model. Our scheme can be narrated separately as follows, firstly, a proper Gaussian kernel is selected to discriminate two classes of textures by analyzing LIDM feature distributions, which are obtained from two different local regions marked manually in the initial texture image. Secondly, the LIDM feature map can be constructed by computing LIDM feature values of image patches with the proper Gaussian kernel, and the center of these image patches may traverse the whole image domain. Finally, the texture image segmentation is implemented based on an improved optimizing model with local binary fitting and local extremum regularizing. In order to validate the performance of our proposed method, two kinds of experiments about discriminative feature map construction and texture image segmentation are carried out to demonstrate its well performance, and more experiments on real texture images are also conducted.

Abstract P4-02-04: Quantitative MRI features analysis for differentiation of triple negative and HER2 positive subtypes of breast cancer

Abstract Objective: The aim of this study was to evaluate ability of quantitative analysis of MRI features to distinguish triple negative (TN) and HER2 positive (HER2+) subtypes of breast cancer, which have different biological characteristics, exhibiting different growth patterns and response to treatment. Materials and Method: Breast cancer patients, who had MRI exam of the breast in our institution at the time of staging for breast carcinoma and who subsequently had surgery (segmentectomy or mastectomy) from January 1, 2008 through December 31, 2015 were identified. All lesions were evaluated by radiologists in accordance with the BI-RADS lexicon. The patient's age, breast cancer histology, multifocality/multicentricity (MF/MC), lesion size, axillary lymphadenopathy (LAN), MRI morphologic and enhancement characteristics were documented. Quantitative MRI feature analysis was performed using shape, texture, and histogram based features. Machine-learning-based (Xgboost) models were used to predict subtypes, and Leave-one-out cross-validation (LOOCV) was used to avoid model overfitting. Statistical significance was determined using the Student's t-test. Results: Total of 105 patients, 51 patients with TN and 54 patients with HER2+ breast cancer were included in analysis. Mean age for TN was 50 (range 29-79)) years old and for HER2+ was 49 (range 25-70) years old. Axillary LAN and MF/MC disease was seen more commonly in HER2+ patients when compared to TN patients, but didn't reach statistical significance (13 vs 7, p=0.9; and 31 vs 20, p=0.06, respectively). Mass rim enhancement was associated with TN subtype and irregular mass enhancement was associated with HER2+ subtype of breast cancer (p&amp;lt;0.05). Quantitative analysis showed that six out of the top 10 ranked MRI features: surface to volume ratio, difference variance, difference entropy, inverse difference moment, 75 percentile in histogram and sum average, were significantly different between these 2 subtypes with p&amp;lt;0.05. When the significant features were incorporated to distinguish TN and HER+ subtypes, use of the top 2 features achieved the best accuracy on LOOCV of 0.69. Conclusion: The quantitative MRI features show promise in distinguishing TN and HER2+ breast cancer subtypes reflecting their underlying biological characteristics and may be used as predictive quantitative biological markers. Further studies in a larger cohort evaluating associations with treatment response are underway. FeatureIndexP-valueSurface to volume ratioShape30.005Difference VarianceGLCM110.005Difference EntropyGLCM100.009Inverse Difference MomentGLCM50.01875 percentile in histogramHistogram50.043Sum AverageGLCM60.044Median in histogramHistogram 30.08025 percentile in histogramHistogram 40.095VolumeShape10.104Max in histogramHistogram 10.105 Citation Format: Rauch GM, Li H, Zhu H, Adrada BE, Santiago L, Candelaria RP, Wang H, Leung J, Thompson A, Litton J, Wu Y, Lim B, Moulder S, Mittendorf EA, Yang W. Quantitative MRI features analysis for differentiation of triple negative and HER2 positive subtypes of breast cancer [abstract]. In: Proceedings of the 2017 San Antonio Breast Cancer Symposium; 2017 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2018;78(4 Suppl):Abstract nr P4-02-04.

Response evaluation of giant-cell tumor of bone treated by denosumab: Histogram and texture analysis of CT images

This study aimed to compare computed tomography (CT) features, including tumor size and textural and histogram measurements, of giant-cell tumors of bone (GCTBs) before and after denosumab treatment and determine their applicability in monitoring GCTB response to denosumab treatment. This retrospective study included eight patients (male, 3; female, 5; mean age, 33.4 years) diagnosed with GCTB, who had received treatment by denosumab and had undergone pre- and post-treatment non-contrast CT between January 2010 and December 2016. This study was approved by the institutional review board. Pre- and post-treatment size, histogram, and textural parameters of GCTBs were compared by the Wilcoxon signed-rank test. Pathological findings of five patients who underwent surgery after denosumab treatment were evaluated for assessment of treatment response. Relative to the baseline values, the tumor size had decreased, while the mean attenuation, standard deviation, entropy (all, P=0.017), and skewness (P=0.036) of the GCTBs had significantly increased post-treatment. Although the difference was statistically insignificant, the tumors also exhibited increased kurtosis, contrast, and inverse difference moment (P=0.123, 0.327, and 0.575, respectively) post-treatment. Histologic findings revealed new bone formation and complete depletion or decrease in the number of osteoclast-like giant cells. The histogram and textural parameters of GCTBs changed significantly after denosumab treatment. Knowledge of the tendency towards increased mean attenuation and heterogeneity but increased local homogeneity in post-treatment CT histogram and textural features of GCTBs might aid in treatment planning and tumor response evaluation during denosumab treatment.

The Effects of Betaine on the Nuclear Fractal Dimension, Chromatin Texture, and Proliferative Activity in Hepatocytes in Mouse Model of Nonalcoholic Fatty Liver Disease.

The effects of betaine on hepatocytes chromatin architecture changes were examined by using fractal and gray-level co-occurrence matrix (GLCM) analysis in methionine/choline-deficient (MCD) diet-induced, nonalcoholic fatty liver disease (NAFLD). Male C57BL/6 mice were divided into groups: (1) Control: standard diet; (2) BET: standard diet and betaine supplementation through drinking water (solution 1.5%); (3) MCD group: MCD diet for 6 weeks; (4) MCD+BET: fed with MCD diet + betaine for 6 weeks. Liver tissue was collected for histopathology, immunohistochemistry, and determination of fractal dimension and GLCM parameters. MCD diet induced diffuse micro- and macrovesicular steatosis accompanied with increased Ki67-positive hepatocyte nuclei. Steatosis and Ki67 immunopositivity were less prominent in the MCD+BET group compared with the MCD group. Angular second moment (ASM) and inverse difference moment (IDM) (textural homogeneity markers) were significantly increased in the MCD+BET group versus the MCD group (p<0.001), even though no difference between the MCD and the control group was evident. Heterogeneity parameters, contrast, and correlation were significantly increased in the MCD group versus the control (p<0.001). On the other hand, betaine treatment significantly reduced correlation, contrast, and entropy compared with the MCD group (p<0.001). Betaine attenuated MCD diet-induced NAFLD by reducing fat accumulation and inhibiting hepatocyte proliferation. Betaine supplementation increased nuclear homogeneity and chromatin complexity with reduction of entropy, contrast, and correlation.

Magnetic Resonance Image Texture Analysis of the Periaqueductal Gray Matter in Episodic Migraine Patients without T2-Visible Lesions.

ObjectiveThe periaqueductal gray matter (PAG), a small midbrain structure, presents dysfunction in migraine. However, the precise neurological mechanism is still not well understood. Herein, the aim of this study was to investigate the texture characteristics of altered PAG in episodic migraine (EM) patients based on high resolution brain structural magnetic resonance (MR) images.Materials and MethodsThe brain structural MR images were obtained from 18 normal controls (NC), 18 EM patients and 16 chronic migraine (CM) patients using a 3T MR system. A PAG template was created using the International Consortium Brain Mapping 152 gray matter model, and the individual PAG segment was developed by applying the deformation field from the structural image segment to the PAG template. A grey level co-occurrence matrix was used to calculate the texture parameters including the angular second moment (ASM), contrast, correlation, inverse difference moment (IDM) and entropy.ResultsThere was a significant difference for ASM, IDM and entropy in the EM group (998.629 ± 0.162 × 10−3, 999.311 ± 0.073 × 10−3, 916.354 ± 0.947 × 10−5) compared to that found in the NC group (998.760 ± 0.110 × 10−3, 999.358 ± 0.037 × 10−3 and 841.198 ± 0.575 × 10−5) (p < 0.05). The entropy was significantly lower among the patients with CM (864.116 ± 0.571 × 10−5) than that found among patients with EM (p < 0.05). The area under the receiver operating characteristic curve was 0.776 and 0.750 for ASM and entropy in the distinction of the EM from NC groups, respectively. ASM was negatively related to disease duration (DD) and the Migraine Disability Assessment Scale (MIDAS) scores in the EM group, and entropy was positively related to DD and MIDAS in the EM group (p < 0.05).ConclusionThe present study identified altered MR image texture characteristics of the PAG in EM. The identified texture characteristics could be considered as imaging biomarkers for EM.

Chlorophyll Content Detection of Field Maize Using RGB-NIR Camera

In order to rapidly detect the chlorophyll content in the field, the RGB-NIR camera was used to collect the multi-spectral image of maize canopy. The SPAD value was measured at the same time to indicate the chlorophyll content. The multi-spectral images were processed. Considering the features of multi-spectral images, after image median filtering and segmentation to remove the background effect by field soil, dry straw and weeds, 15 image parameters were extracted including the average grey value of each channel (AR, AG, AB and ANIR), the vegetation indices (ANDVI, ANDGI, ARVI, ADVI), vegetation coverage index (VCI), hue average(AH) and image texture parameters (energy (AASM), moment of inertia (ACON), correlation (ACOR), entropy (AEN) and inverse difference moment (AL)). The sensitive parameters were selected by correlation coefficient analysis and RF method. There were 4 and 8 parameters, respectively. After modeling, the LS-SVM model built by RF selected parameters showed better detection accuracy with Rc2=0.87 and Rv2=0.74. It could be used for rapid and non-destructive detection of the chlorophyll content for field maize.

Apparent diffusion coefficient map based radiomics model in differentiating benign from malignant entity in breast imaging-reporting and data system 4 breast lesions

Objective To investigate the diagnostic values of radiomics model based on ADC map in differentiating benign from malignant lesions in suspicious breast findings with MRI breast imaging reporting and data system (BI-RADS) category 4. Methods Eighty eight patients (36 benign and 52 malignant) with diagnosis of MRI BI-RADS 4 in our hospital from December 2014 to December 2015 were retrospectively enrolled in this study. All the patients were proved by pathology and examined by sequence of T1WI, T2WI, DWI and dynamic contrast enhanced magnetic resonance imaging (DCE-MRI), and then were further sub-categorized into BI-RADS 4A, BI-RADS 4B, or BI-RADS 4C based on DCE-MRI sequence. Thus positive predictive value (PPV) of each sub-category were calculated and ROC were used to describe its efficiency in differential diagnosis. Radiomics features based on ADC map were generated automatically from Analysis-Kinetics (GE Healthcare). Sixty three of the 88 cases randomized-selected by computer were used to establish forecasting models and other 25 cases for validation. Kruskal-Wallis test and Spearman were introduced to reduce radiomics features that were highly correlated with others. Logistic linear regression (LLR) model was constructed based on the selected features by 'glm’ function in R software and then verified by 10-fold cross validation (repeat 10 times). ROC was curved to determine the diagnostic accuracy of the model. Results The PPV of BI-RADS 4A,4B,4C were 16.7% (2/12) ,59.6% (28/47) ,75.9% (22/29) respectively. Area under curve (AUC) of ROC was 0.650, sensitivity and specificity were 76.9% and 45.9% respectively. Three hundred and ninety six radiomics features were extracted automatically by software and 5 features (size zone variability, difference entropy, zone percentage, intensity variability and inverse difference moment) were left after redundancy reduction step. Cross-validation showed the accuracy of Logistic regression model was 80.0% (20/25), AUC was 0.790, sensitivity and specificity were 81.3% and 77.8% when cut-off was 0.45. Conclusion The radiomics model could provide important reference for differentiation between benign and malignant lesions in suspicious BI-RADS 4 findings. Key words: Breast neoplasms; Magnetic resonance imaging; Radiomics

AUTOMATIC FEATURE EXTRACTION FOR BREAST DENSITY SEGMENTATION AND CLASSIFICATION

Objective: Cancer is the uncontrollable multiplication of cells in human body. The expansion of cancerous cells in the breast area of the women is identified as breast cancer. It is mostly identified among women aged above 40. With the current advancement in the medical field, various automatic tests are available for the identification of cancerous tissues. The cancerous cells are spotted by taking the photo imprint in the form of X-ray comprising the breast area of the woman. Such images are called mammograms. Segmentation of mammograms is the primary step toward diagnosis. It involves the pre-processing of the image to identify the region of interest (ROI). Later, features are extracted from the image which involves the learned features that may be statistical and textural features [7]. When these features are used as input to the simple classifier, it helps us to predict the risk of cancer. The support vector machine (SVM) classifier was proved to produce a better accuracy percentage with the features extracted.Methods: The mammograms are subjected to a pre-processing stage, where the images are processed to identify the ROI. Next, the features are extracted from these images to identify the statistical [9] and textural features. Finally, these features are used as input to the simple classifier, it helps us to predict the risk of cancer.Results: The SVM classifier was proved to produce the maximum accuracy of about 88.67% considering 13 features including both statistical and textural features. The features taken for the study are mean, inverse difference moment, energy, entropy, root mean square, correlation, homogeneity, variance, skewness, range, contrast, kurtosis, and smoothness.Conclusion: Computer-aided diagnosis is one of the most common methods of detection of cancer with mammograms, and it involves minor human intervention. The dataset of mammograms was analyzed and found that SVM provided the highest accuracy of 88.67%. A wide range of the study is progressing in the field of cancer as this disease causes a high threat of human life in this era.

Alteration of gray matter texture features over the whole brain in medication-overuse headache using a 3-dimentional texture analysis

BackgroundImaging studies have provided valuable information in understanding the headache neuromechanism for medication-overuse headache (MOH), and the aim of this study is to investigate altered texture features of MR structural images over the whole brain in MOH using a 3-dimentional texture analysis.MethodsBrain three-dimensional T1-weighted structural images were obtained from 44 MOH patients and 32 normal controls (NC). The imaging processing included two steps: gray matter (gray images) segment and a 3-dimensional texture features mapping. Voxel-based gray-level co-occurrence matrix (VGLCM) was performed to measure the texture parameters mapping including Contrast, Correlation, Energy, Entropy and inverse difference moment (IDM).ResultsThe texture parameters of increased Contrast and Entropy, decreased Energy and IDM were identified in cerebellar vermis of MOH patients compared to NCs. Increased Contrast and decreased Energy were found in left cerebellum. Increased Correlation located in left dorsolateral periaqueductal gray (L-dlPAG), right parahippocampal gyrus (R-PHG), and left middle frontal gyrus (L-MFG) and decreased Correlation located in right superior parietal lobule(R-SPL). Disease duration was positively correlated with Contrast of vermis and negatively correlated with Correlation of R-SPL.HAMD score was negatively correlated with Correlation of R-PHG. MoCA score was positively correlated with Correlation of R-SPL.ConclusionThe altered textures in gray matter related to pain discrimination and modulation, affective and cognitive processing were helpful in understanding the pathogenesis of MOH. Texture analysis using VGLCM is a sensitive and efficient method to detect subtle gray matter changes in MOH.

Postnatal Developmental Changes in Fractal Complexity of Giemsa-Stained Chromatin in Mice Spleen Follicular Cells.

Although there are numerous recent works focusing on fractal properties of DNA and chromatin, many issues regarding changes in chromatin fractality during physiological aging remain unclear. In this study, we present results indicating that in mice, there is an age-related reduction of chromatin fractal complexity in a population of spleen follicular cells (SFCs). Spleen tissue was obtained from 16 mice and fixated in Carnoy solution. The youngest animal was newborn, and each animal was exactly 1 month older than the previous. We performed fractal analysis of SFC chromatin structure, stained using Giemsa technique. Fractal analysis was done in a plugin algorithm of ImageJ software. We also performed gray-level co-occurrence matrix (GLCM) analysis of all chromatin structures with the calculation of parameters such as angular second moment and inverse difference moment. Giemsa-stained SFC chromatin exhibited an age-dependent reduction of fractal dimension with statistically significant (p<0.01) linear trend. Moreover, there was a statistically significant increase of SFC chromatin lacunarity. The chromatin GLCM parameters did not significantly change. To our knowledge, this is the first study to perform fractal and GLCM analyses of SFC chromatin and to investigate potential changes of fractal parameters during postnatal development.

Textural features of dynamic contrast-enhanced MRI derived model-free and model-based parameter maps in glioma grading.

Presurgical glioma grading by dynamic contrast-enhanced MRI (DCE-MRI) has unresolved issues. The aim of this study was to investigate the ability of textural features derived from pharmacokinetic model-based or model-free parameter maps of DCE-MRI in discriminating between different grades of gliomas, and their correlation with pathological index. Retrospective. Forty-two adults with brain gliomas. 3.0T, including conventional anatomic sequences and DCE-MRI sequences (variable flip angle T1-weighted imaging and three-dimensional gradient echo volumetric imaging). Regions of interest on the cross-sectional images with maximal tumor lesion. Five commonly used textural features, including Energy, Entropy, Inertia, Correlation, and Inverse Difference Moment (IDM), were generated. All textural features of model-free parameters (initial area under curve [IAUC], maximal signal intensity [Max SI], maximal up-slope [Max Slope]) could effectively differentiate between grade II (n = 15), grade III (n = 13), and grade IV (n = 14) gliomas (P < 0.05). Two textural features, Entropy and IDM, of four DCE-MRI parameters, including Max SI, Max Slope (model-free parameters), vp (Extended Tofts), and vp (Patlak) could differentiate grade III and IV gliomas (P < 0.01) in four measurements. Both Entropy and IDM of Patlak-based Ktrans and vp could differentiate grade II (n = 15) from III (n = 13) gliomas (P < 0.01) in four measurements. No textural features of any DCE-MRI parameter maps could discriminate between subtypes of grade II and III gliomas (P < 0.05). Both Entropy and IDM of Extended Tofts- and Patlak-based vp showed highest area under curve in discriminating between grade III and IV gliomas. However, intraclass correlation coefficient (ICC) of these features revealed relatively lower inter-observer agreement. No significant correlation was found between microvascular density and textural features, compared with a moderate correlation found between cellular proliferation index and those features. Textural features of DCE-MRI parameter maps displayed a good ability in glioma grading. 3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018;47:1099-1111.

Texture Feature Analysis for Different Resolution Level of Kidney Ultrasound Images

Image feature extraction is a technique to identify the characteristic of the image. The objective of this work is to discover the texture features that best describe a tissue characteristic of a healthy kidney from ultrasound (US) image. Three ultrasound machines that have different specifications are used in order to get a different quality (different resolution) of the image. Initially, the acquired images are pre-processed to de-noise the speckle to ensure the image preserve the pixels in a region of interest (ROI) for further extraction. Gaussian Low- pass Filter is chosen as the filtering method in this work. 150 of enhanced images then are segmented by creating a foreground and background of image where the mask is created to eliminate some unwanted intensity values. Statistical based texture features method is used namely Intensity Histogram (IH), Gray-Level Co-Occurance Matrix (GLCM) and Gray-level run-length matrix (GLRLM).This method is depends on the spatial distribution of intensity values or gray levels in the kidney region. By using One-Way ANOVA in SPSS, the result indicated that three features (Contrast, Difference Variance and Inverse Difference Moment Normalized) from GLCM are not statistically significant; this concludes that these three features describe a healthy kidney characteristics regardless of the ultrasound image quality.

Evaluation of Early Kidney Damage Caused by Brain Death Using Real-Time Ultrasound Elastography in a Bama Pig Model

The aim of this study was to investigate the value of real-time tissue elastography (RTE) in the evaluation of early graft damage resulting from brain death. We performed RTE before and 0, 3, 6 and 9 h after brain death in a Bama pig model. Eleven RTE parameters were compared among time groups, and their correlations with electron microscopic findings were analyzed. Receiver operating characteristic curve analysis was used to find the RTE parameter cutoff values. The mean relative strain value within the region of interest (MEAN), standard deviation of the relative strain value within the region of interest (SD), percentage area of low strain within the region of interest (%AREA), complexity of low-strain area within the region of interest (COMP), kurtosis (KURT), skewness (SKEW), contrast (CONT) and entropy (ENT) and inverse difference moment (IDM) differed statistically significantly between groups (p < 0.05). Electron microscopy of kidney tissue revealed that irreversible damage gradually occurred with longer brain death duration and was marked at 9 h (p < 0.05). These findings correlated best with MEAN (r = 0.632, p ＜ 0.05). Receiver operating characteristic curve analysis of RTE parameters identified a cutoff value of 63.43 for MEAN for optimal diagnostic performance. RTE allows non-invasive, preliminary evaluation of early renal graft damage resulting from brain death.