3D Texture Features Research Articles

Label-free identification of human coronary atherosclerotic plaque based on a three-dimensional quantitative assessment of multiphoton microscopy images.

The rupture of coronary atherosclerotic plaque (CAP) and the resulting intracoronary thrombosis account for most acute coronary syndromes. Thus, the early identification and risk assessment of CAP is crucial for timely medical intervention. In this study, we propose a quantitative and label-free method for human CAP identification using multiphoton microscopy (MPM) and three-dimensional (3D) image analysis techniques. By detecting the intrinsic MPM signals, the microstructures of collagen and elastin fibers within normal and CAP-lesioned human coronary artery walls were imaged. Using a 3D gray level co-occurrence matrix method and 3D weighted vector summation algorithm, quantitative indicators that characterize the spatial texture and orientation features of the fibers were extracted. We demonstrate that these indicators show superior accuracy and repeatability over 2D texture features in CAP discrimination. Furthermore, by combining the 3D microstructural indicators, a support vector machine model that classifies CAP from the normal arterial wall with an accuracy of >97% was established. In conjunction with advances in multiphoton endoscopy, the proposed method shows great potential in providing a quantitative, label-free, and real-time tool for the early identification and risk assessment of CAP in the future.

3D Texture Feature Extraction and Classification Using GLCM and LBP-Based Descriptors

Lately, 3D imaging techniques have achieved a lot of progress due to recent developments in 3D sensor technologies. This leads to a great interest regarding 3D image feature extraction and classification techniques. As pointed out in literature, one of the most important and discriminative features in images is the textural content. Within this context, we propose a texture feature extraction technique for volumetric images with improved discrimination power. The method could be used in textured volumetric data classification tasks. To achieve this, we fuse two complementary pieces of information, feature vectors derived from Local Binary Patterns (LBP) and the Gray-Level Co-occurrence Matrix-based methods. They provide information regarding the image pattern and the contrast, homogeneity and local anisotropy in the volumetric data, respectively. The performance of the proposed technique was evaluated on a public dataset consisting of volumetric textured images affected by several transformations. The classifiers used are the Support Vector Machine, k-Nearest Neighbours and Random Forest. Our method outperforms other handcrafted 3D or 2D texture feature extraction methods and typical deep-learning networks. The proposed technique improves the discrimination power and achieves promising results even if the number of images per class is relatively small.

Pore texture analysis in automated 3D breast ultrasound images for implanted lightweight hernia mesh identification: a preliminary study

BackgroundPrecise visualization of meshes and their position would greatly aid in mesh shrinkage evaluation, hernia recurrence risk assessment, and the preoperative planning of salvage repair. Lightweight (LW) meshes are able to preserve abdominal wall compliance by generating less post-implantation fibrosis and rigidity. However, conventional 3D imaging techniques such as computed tomography (CT) and magnetic resonance imaging (MRI) cannot visualize the LW meshes. Patients sometimes have to undergo a second-look operation for visualizing the mesh implants. The goal of this work is to investigate the potential advantages of Automated 3D breast ultrasound (ABUS) pore texture analysis for implanted LW hernia mesh identification.MethodsIn vitro, the appearances of four different flat meshes in both ABUS and 2D hand-held ultrasound (HHUS) images were evaluated and compared. In vivo, pore texture patterns of 87 hernia regions were analyzed both in ABUS images and their corresponding HHUS images.ResultsIn vitro studies, the imaging results of ABUS for implanted LW meshes are much more visualized and effective in comparison to HHUS. In vivo, the inter-class distance of 40 texture features was calculated. The texture features of 2D sectional plans (axial and sagittal plane) have no significant contribution to implanted LW mesh identification. Significant contribution was observed in coronal plane. However, since the mesh may have spatial variation such as shrinkage after implantation surgery, the inter-class distance of 3D coronal plane pore texture features are bigger than 2D coronal plane, so the contribution of 3D coronal plane pore texture features are more valuable than 2D coronal plane for implanted LW mesh identification. The use of 3D pore texture features significantly improved the robustness of the identification method in distinguishing between LW mesh and fascia.ConclusionsAn innovative new ABUS provides additional pore texture visualization, by separating the LW mesh from the fascia tissues. Therefore, ABUS has the potential to provides more accurate features to characterize pore texture patterns, and ultimately provide more accurate measures for implanted LW mesh identification.

Rethinking Shape From Shading for Spoofing Detection

Spoofing attacks are critical threats to modern face recognition systems, and most common countermeasures exploit 2D texture features as they are easy to extract and deploy. 3D shape-based methods can substantially improve spoofing prevention, but extracting the 3D shape of the face often requires complex hardware such as a 3D scanner and expensive computation. Motivated by the classical shape-from-shading model, we propose to obtain 3D facial features that can be used to recognize the presence of an actual 3D face, without explicit shape reconstruction. Such shading-based 3D features are extracted highly efficiently from a pair of images captured under different illumination, e.g., two images captured with and without flash. Thus the proposed method provides a rich 3D geometrical representation at negligible computational cost and minimal to none additional hardware. A theoretical analysis is provided to support why such simple 3D features can effectively describe the presence of an actual 3D shape while avoiding complicated calibration steps or hardware setup. Experimental validation shows that the proposed method can produce state-of-the-art spoofing prevention and enhance existing texture-based solutions.

Texture analysis of T2-weighted MRI predicts SDH mutation in paraganglioma.

Texture analysis can quantify sophisticated imaging characteristics. We hypothesized that 2D textures computed with T2-weighted and post-contrast T1-weighted MRI can predict succinate dehydrogenase (SDH) mutation status in head and neck paragangliomas. Our retrospective study included 21 patients (1 to 4 tumors/patient) with 24 pathologically proven paragangliomas in the head and neck. Fourteen lesions (58%) were SDH mutation-positive. All patients underwent T2-weighted and post-contrast T1-weighted MRI sequences. Three 2D texture features of dependence non-uniformity normalized (DNN), small dependence high gray level emphasis (SDHGLE), and small dependence low gray level emphasis (SDLGLE) were calculated. Computed textures between SDH mutants and non-mutants were compared using Mann-Whitney U test. Area under the receiver operating characteristic (AUROC) curve was used to quantify the predictive power of each texture. Only T2-based SDLGLE was statistically significant (p = 0.048), and AUROC was 0.71. Diagnostic accuracy was 70.8%. 2D texture parameter of T2-based SDLGLE predicts SDH mutation in head and neck paragangliomas. This noninvasive technique can potentially facilitate further genetic workup.

Sensitivity analysis of FDG PET tumor voxel cluster radiomics and dosimetry for predicting mid-chemoradiation regional response of locally advanced lung cancer

We investigated the sensitivity of regional tumor response prediction to variability in voxel clustering techniques, imaging features, and machine learning algorithms in 25 patients with locally advanced non-small cell lung cancer (LA-NSCLC) enrolled on the FLARE-RT clinical trial. Metabolic tumor volumes (MTV) from pre-chemoradiation (PETpre) and mid-chemoradiation fluorodeoxyglucose-positron emission tomography (FDG PET) images (PETmid) were subdivided into K-means or hierarchical voxel clusters by standardized uptake values (SUV) and 3D-positions. MTV cluster separability was evaluated by CH index, and morphologic changes were captured by Dice similarity and centroid Euclidean distance. PETpre conventional features included SUVmean, MTV/MTV cluster size, and mean radiation dose. PETpre radiomics consisted of 41 intensity histogram and 3D texture features (PET Oncology Radiomics Test Suite) extracted from MTV or MTV clusters. Machine learning models (multiple linear regression, support vector regression, logistic regression, support vector machines) of conventional features or radiomic features were constructed to predict PETmid response. Leave-one-out-cross-validated root-mean-squared-error (RMSE) for continuous response regression (ΔSUVmean) and area-under-receiver-operating-characteristic-curve (AUC) for binary response classification were calculated. K-means MTV 2-clusters (MTVhi, MTVlo) achieved maximum CH index separability (Friedman p < 0.001). Between PETpre and PETmid, MTV cluster pairs overlapped (Dice 0.70–0.87) and migrated 0.6–1.1 cm. PETmid ΔSUVmean response prediction was superior in MTV and MTVlo (RMSE = 0.17–0.21) compared to MTVhi (RMSE = 0.42–0.52, Friedman p < 0.001). PETmid ΔSUVmean response class prediction performance trended higher in MTVlo (AUC = 0.83–0.88) compared to MTVhi (AUC = 0.44–0.58, Friedman p = 0.052). Models were more sensitive to MTV/MTV cluster regions (Friedman p = 0.026) than feature sets/algorithms (Wilcoxon signed-rank p = 0.36). Top-ranked radiomic features included GLZSM-LZHGE (large-zone-high-SUV), GTSDM-CP (cluster-prominence), GTSDM-CS (cluster-shade) and NGTDM-CNT (contrast). Top-ranked features were consistent between MTVhi and MTVlo cluster pairs but varied between MTVhi-MTVlo clusters, reflecting distinct regional radiomic phenotypes. Variability in tumor voxel cluster response prediction can inform robust radiomic target definition for risk-adaptive chemoradiation in patients with LA-NSCLC.FLARE-RT trial: NCT02773238.

Glioblastomas and brain metastases differentiation following an MRI texture analysis-based radiomics approach

PurposeTo evaluate the potential of 2D texture features extracted from magnetic resonance (MR) images for differentiating brain metastasis (BM) and glioblastomas (GBM) following a radiomics approach. MethodsThis retrospective study included 50 patients with BM and 50 with GBM who underwent T1-weighted MRI between December 2010 and January 2017. Eighty-eight rotation-invariant texture features were computed for each segmented lesion using six texture analysis methods. These features were also extracted from the four images obtained after applying the discrete wavelet transform (88 features × 4 images). Three feature selection methods and five predictive models were evaluated. A 5-fold cross-validation scheme was used to randomly split the study group into training (80 patients) and testing (20 patients), repeating the process ten times. Classification was evaluated computing the average area under the receiver operating characteristic curve. Sensibility, specificity and accuracy were also computed. The whole process was tested quantizing the images with different gray-level values to evaluate their influence in the final results. ResultsHighest classification accuracy was obtained using the original images quantized with 128 gray-levels and a feature selection method based on the p-value. The best overall performance was achieved using a support vector machine model with a subset of 32 features (AUC = 0.896 ± 0.067, sensitivity of 82% and specificity of 80%). Naïve Bayes and k-nearest neighbors models showed also valuable results (AUC ≈ 0.8) with a lower number of features (<13), thus suggesting that these models may be more generalizable when using external validations. ConclusionThe proposed radiomics MRI approach is able to discriminate between GBM and BM with high accuracy employing a set of 2D texture features, thus helping in the diagnosis of brain lesions in a fast and non-invasive way.

CT texture analysis of acetabular subchondral bone can discriminate between normal and cam-positive hips.

The purpose of this study was to determine if the CT texture profile of acetabular subchondral bone differs between normal, asymptomatic cam-positive, and symptomatic cam-FAI hips. In addition, the utility of texture analysis to discriminate between the three hip statuses was explored using a machine learning approach. IRB-approved, case-control study analyzing CT images in subjects with and without cam morphology from August 2010 to December 2013. Sixty-eight subjects were included: 19 normal controls, 26 asymptomatic cam, and 23 symptomatic cam-FAI. Acetabular subchondral bone was contoured on the sagittal oblique CT images using ImageJ ®. 3D histogram texture features (mean, variance, skewness, kurtosis, and percentiles) were evaluated using MaZda software. Groupwise differences were investigated using Kruskal-Wallis tests and Mann-Whitney U tests. Gradient-boosted decision trees were created and trained to discriminate between control and cam-positive hips. Both asymptomatic and symptomatic cam-FAI hips demonstrated significantly higher values of texture variance (p = 0.0007, p < 0.0001), 90th percentile (p = 0.007, p = 0.006), and 99th percentile (p = 0.009, p = 0.009), but significantly lower values of skewness (p = 0.0001, p = 0.0013) and kurtosis (p = 0.0001, p = 0.0001) compared to normal controls. There were no differences in texture profile between asymptomatic cam and symptomatic cam-FAI hips. Machine learning models demonstrated high classification accuracy for discriminating control hips from asymptomatic cam-positive (82%) and symptomatic cam-FAI (86%) hips. Texture analysis can discriminate between normal and cam-positive hips using conventional descriptive statistics, regression modeling, and machine learning algorithms. It has the potential to become an important tool in compositional analysis of hip subchondral trabecular bone in the context of FAI, and possibly serve as a biomarker of joint degeneration. • The CT texture profile of acetabular subchondral bone is significantly different between normal and cam-positive hips. • Texture analysis can detect changes in subchondral bone in asymptomatic cam-positive hips that are equal to that of symptomatic cam-FAI hips. • Texture analysis has the potential to become an important tool in compositional analysis of hip subchondral bone in the context of FAI and may serve as a biomarker in the study of joint physiology and biomechanics.

Adaptive Steganography using 3D Color Texture Feature

Human vision framework is commonly an emotional recognition which differs according to people. Intricacy of a picture assumes huge job while verifying information in to it. In this paper another steganography approach is introduced which uses joined 3D Color Texture Feature (CTF) to distinguish complex districts of picture for information stowing away so visual assault to identify shrouded message turns out to be very testing. Recurrence area is utilized to shroud the information in these chose complex areas by means of Discrete Cosine Transform (DCT). These sorts of zones are initially boisterous and separating additional data is difficult. Each picture has diverse multifaceted nature levels and spatial districts, and since information covering up is legitimately reliant on it, so the steganography framework ends up versatile. The outcome demonstrates that proposed versatile strategy gives secure message stowing away while keeping up subtlety quality and high implanting limit. Last spread pictures keeps up PSNR estimation of over 50. Inserting limit is around multiple times higher in contrast with comparative calculation which uses Gray Level Co-event Matrices (GLCM) highlight to recognize complex districts of pictures for information covering up.

Prognostic Value of Texture Analysis Based on Pretreatment DWI-Weighted MRI for Esophageal Squamous Cell Carcinoma Patients Treated With Concurrent Chemo-Radiotherapy.

Purpose: The purpose of the research was to assess the prognostic value of three-dimensional (3D) texture features based on diffusion-weighted magnetic resonance imaging (DWI) for esophageal squamous cell carcinoma (ESCC) patients undergoing concurrent chemo-radiotherapy (CRT).Methods: We prospectively enrolled 82 patients with ESCC into a cohort study. Two DWI sequences (b = 0 and b = 600 s/mm2) were acquired along with axial T2WI and T1WI before CRT. Two groups of features were examined: (1) clinical and demographic features (e.g., TNM stage, age and sex) and (2) changes in spatial texture characteristics of the apparent diffusion coefficient (ADC), which characterizes gray intensity changes in tumor areas, spatial pattern and distribution, and related changes caused by CRT. Reproducible feature sets without redundancy were statistically filtered and validated. The prognostic values associated with overall survival (OS) for each parameter were studied using Kaplan-Meier and Cox regression models for univariate and multivariate analyses, respectively.Results: Both univariate and multivariate Cox model analyses showed that the energy of intensity histogram texture (IHIST_energy), radiation dose, mean of the contrast in distance 1 of 26 directions (m_contrast_1), extreme difference of the homogeneity in distance 2 of 26 directions (Diff_homogeneity_2), mean of the inverse variance in distance 2 of 26 directions (m_lnversevariance_2), high-intensity small zone emphasis (HISE), and low-intensity large zone emphasis (LILE) were significantly associated with survival. The results showed that 6 texture parameters extracted from the ADC images before treatment could distinguish among high-, medium-, and low-risk groups (log-rank χ2 = 9.7; P = 0.00773). The biased C-index value was 0.715 (95% CI: 0.708 to 0.732) based on bootstrapping validation.Conclusions: The ADC 3D texture feature can be used as a useful biomarker to predict the survival of ESCC patients undergoing CRT. Combining ADC 3D texture features with conventional prognostic factors can generate reliable survival prediction models.

409P - 3D based texture analysis serving as potential diagnostic factor in discriminating primary central nervous system lymphoma from metastatic brain tumours: A preliminary study

BackgroundThe purpose of current study is to discriminate primary central nervous system lymphoma from metastatic brain tumors with 3D texture features. MethodsA total number of 120 patients involved this study, 58 with PCNSL and 62 with MBTs. Texture features were retrieved from histogram matrix and GLCM matrix. Mann Whitney U tests were performed to detect if texture feature were significantly different between two type of tumors. Binary logistic regressions were conducted to detect if they could be taken as independent predictors, based on which integrated model was built. ROC curves of each parameter were generated to evaluate the ability in discrimination. ResultsThree texture features (histo-Kurtosis, GLCM-Contrast and GLCM-Dissimilarity from post contrast T1WI) were independent predictors in discrimination, whose AUC were 0.632, 0.742 and 0.706 respectively. The integrated model represented better diagnostic value than any single features. ROC curve suggested the AUC of model was 0.832, representing practical clinical value. ConclusionsTexture analysis has potential in the differentiation between primary central nervous system lymphoma from metastatic brain tumors. Moreover, combination of single texture shows more promising and effective ability in discrimination. Legal entity responsible for the studyXuelei Ma. FundingHas not received any funding. DisclosureAll authors have declared no conflicts of interest.

Fully automatic 3D reconstruction of the placenta and its peripheral vasculature in intrauterine fetal MRI.

Recent advances in fetal magnetic resonance imaging (MRI) open the door to improved detection and characterization of fetal and placental abnormalities. Since interpreting MRI data can be complex and ambiguous, there is a need for robust computational methods able to quantify placental anatomy (including its vasculature) and function. In this work, we propose a novel fully-automated method to segment the placenta and its peripheral blood vessels from fetal MRI. First, a super-resolution reconstruction of the uterus is generated by combining axial, sagittal and coronal views. The placenta is then segmented using 3D Gabor filters, texture features and Support Vector Machines. A uterus edge-based instance selection is proposed to identify the support vectors defining the placenta boundary. Subsequently, peripheral blood vessels are extracted through a curvature-based corner detector. Our approach is validated on a rich set of 44 control and pathological cases: singleton and (normal / monochorionic) twin pregnancies between 25-37 weeks of gestation. Dice coefficients of 0.82 ± 0.02 and 0.81 ± 0.08 are achieved for placenta and its vasculature segmentation, respectively. A comparative analysis with state of the art convolutional neural networks (CNN), namely, 3D U-Net, V-Net, DeepMedic, Holistic3D Net, HighRes3D Net and Dense V-Net is also conducted for placenta localization, with our method outperforming all CNN approaches. Results suggest that our methodology can aid the diagnosis and surgical planning of severe fetal disorders.

Opportunistic osteoporosis screening in multi-detector CT images via local classification of textures

SummaryOur study proposed an automatic pipeline for opportunistic osteoporosis screening using 3D texture features and regional vBMD using multi-detector CT images. A combination of different local and global texture features outperformed the global vBMD and showed high discriminative power to identify patients with vertebral fractures.IntroductionMany patients at risk for osteoporosis undergo computed tomography (CT) scans, usable for opportunistic (non-dedicated) screening. We compared the performance of global volumetric bone mineral density (vBMD) with a random forest classifier based on regional vBMD and 3D texture features to separate patients with and without osteoporotic fractures.MethodsIn total, 154 patients (mean age 64 ± 8.5, male; n = 103) were included in this retrospective single-center analysis, who underwent contrast-enhanced CT for other reasons than osteoporosis screening. Patients were dichotomized regarding prevalent vertebral osteoporotic fractures (noFX, n = 101; FX, n = 53). Vertebral bodies were automatically segmented, and trabecular vBMD was calculated with a dedicated phantom. For 3D texture analysis, we extracted gray-level co-occurrence matrix Haralick features (HAR), histogram of gradients (HoG), local binary patterns (LBP), and wavelets (WL). Fractured vertebrae were excluded for texture-feature and vBMD data extraction. The performance to identify patients with prevalent osteoporotic vertebral fractures was evaluated in a fourfold cross-validation.ResultsThe random forest classifier showed a high discriminatory power (AUC = 0.88). Parameters of all vertebral levels significantly contributed to this classification. Importantly, the AUC of the proposed algorithm was significantly higher than that of volumetric global BMD alone (AUC = 0.64).ConclusionThe presented classifier combining 3D texture features and regional vBMD including the complete thoracolumbar spine showed high discriminatory power to identify patients with vertebral fractures and had a better diagnostic performance than vBMD alone.

A new method for classification of Alzheimer's disease combined with structural magnetic resonance imaging texture features

In this paper, a new method for the classification of Alzheimer's disease (AD) using multi-feature combination of structural magnetic resonance imaging is proposed. Firstly, hippocampal segmentation and cortical thickness and volume measurement were performed using FreeSurfer software. Then, histogram, gradient, length of gray level co-occurrence matrix and run-length matrix were used to extract the three-dimensional (3D) texture features of the hippocampus, and the parameters with significant differences between AD, MCI and NC groups were selected for correlation study with MMSE score. Finally, AD, MCI and NC are classified and identified by the extreme learning machine. The results show that texture features can provide better classification results than volume features on both left and right sides. The feature parameters with complementary texture, volume and cortical thickness had higher classification recognition rate, and the classification accuracy of the right side (100%) was higher than that of the left side (91.667%). The results showed that 3D texture analysis could reflect the pathological changes of hippocampal structures of AD and MCI patients, and combined with multi-feature analysis, it could better reflect the essential differences between AD and MCI cognitive impairment, which was more conducive to clinical differential diagnosis.

False positive reduction in pulmonary nodule classification using 3D texture and edge feature in CT images.

Pulmonary nodule detection can significantly influence the early diagnosis of lung cancer while is confused by false positives. In this study, we focus on the false positive reduction and present a method for accurate and rapid detection of pulmonary nodule from suspective regions with 3D texture and edge feature. This work mainly consists of four modules. Firstly, small pulmonary nodule candidates are preprocessed by a reconstruction approach for enhancing 3D image feature. Secondly, a texture feature descriptor is proposed, named cross-scale local binary patterns (CS-LBP), to extract spatial texture information. Thirdly, we design a 3D edge feature descriptor named orthogonal edge orientation histogram (ORT-EOH) to obtain spatial edge information. Finally, hierarchical support vector machines (H-SVMs) is used to classify suspective regions as either nodules or non-nodules with joint CS-LBP and ORT-EOH feature vector. For the solitary solid nodule, ground-glass opacity, juxta-vascular nodule and juxta-pleural nodule, average sensitivity, average specificity and average accuracy of our method are 95.69%, 96.95% and 96.04%, respectively. The elapsed time in training and testing stage are 321.76s and 5.69s. Our proposed method has the best performance compared with other state-of-the-art methods and is shown the improved precision of pulmonary nodule detection with computationaly low cost.

Glioblastoma and primary central nervous system lymphoma: Preoperative differentiation by using MRI-based 3D texture analysis

ObjectivesTo investigate the diagnostic value of magnetic resonance imaging (MRI)-based 3D texture and shape features in the differentiation of glioblastoma (GBM) and primary central nervous system lymphoma (PCNSL). Patients and methodsA total of eighty-two patients, including sixty patients with GBM and twenty-two patients with PCNSL were followed up retrospectively from January 2012 to September 2017. MRI-based 3D texture and shape analysis were performed to evaluate the detectable differences between the two malignancies. The performance of machine-learning models was assessed. The Mann-Whitney U test and receiver operating characteristic (ROC) analysis were performed, and the corresponding sensitivity, specificity, accuracy, and area under the curve (AUC) were calculated.Ultimately, 60 GBM patients (33 males, 27 females; mean age 51.55 ± 13.58 years, range 8–74 years) and 22 PCNSL patients (14 males, 8 females; mean age 55.18 ± 12.19 years, range 32–78 years) were included in this study. All the PCNSLs were of the diffuse large B-cell type, and all patients were immunocompetent. ResultsThe variables Firstorder_Skewness, Firstorder_Kurtosis, and Ngtdm_Busyness, representing features extracted from contrast-enhanced T1-weighted images, showed high discriminatory power. Firstorder_ Skewness was the best selected predictor for classification (AUC = 0.86), followed by Ngtdm_Busyness (AUC = 0.83) and Firstorder_Kurtosis (AUC = 0.80). The sensitivities and specificities ranged from 70.0% to 83.3% and from 71.4% to 90.5%, respectively. Among three classification models, the naive Bayes classifier was superior overall, with a high AUC (0.90) and the best specificity (0.91). The support vector machine models provided the best sensitivity and accuracy (0.92 and 0.88, respectively). ConclusionsMRI-based 3D texture analysis has potential utility for preoperative discrimination of GBM and PCNSL.

Classifying brain metastases by their primary site of origin using a radiomics approach based on texture analysis: a feasibility study.

To examine the capability of MRI texture analysis to differentiate the primary site of origin of brain metastases following a radiomics approach. Sixty-seven untreated brain metastases (BM) were found in 3D T1-weighted MRI of 38 patients with cancer: 27 from lung cancer, 23 from melanoma and 17 from breast cancer. These lesions were segmented in 2D and 3D to compare the discriminative power of 2D and 3D texture features. The images were quantized using different number of gray-levels to test the influence of quantization. Forty-three rotation-invariant texture features were examined. Feature selection and random forest classification were implemented within a nested cross-validation structure. Classification was evaluated with the area under receiver operating characteristic curve (AUC) considering two strategies: multiclass and one-versus-one. In the multiclass approach, 3D texture features were more discriminative than 2D features. The best results were achieved for images quantized with 32 gray-levels (AUC = 0.873 ± 0.064) using the top four features provided by the feature selection method based on the p-value. In the one-versus-one approach, high accuracy was obtained when differentiating lung cancer BM from breast cancer BM (four features, AUC = 0.963 ± 0.054) and melanoma BM (eight features, AUC = 0.936 ± 0.070) using the optimal dataset (3D features, 32 gray-levels). Classification of breast cancer and melanoma BM was unsatisfactory (AUC = 0.607 ± 0.180). Volumetric MRI texture features can be useful to differentiate brain metastases from different primary cancers after quantizing the images with the proper number of gray-levels. • Texture analysis is a promising source of biomarkers for classifying brain neoplasms. • MRI texture features of brain metastases could help identifying the primary cancer. • Volumetric texture features are more discriminative than traditional 2D texture features.

A hybrid CNN feature model for pulmonary nodule malignancy risk differentiation.

The malignancy risk differentiation of pulmonary nodule is one of the most challenge tasks of computer-aided diagnosis (CADx). Most recently reported CADx methods or schemes based on texture and shape estimation have shown relatively satisfactory on differentiating the risk level of malignancy among the nodules detected in lung cancer screening. However, the existing CADx schemes tend to detect and analyze characteristics of pulmonary nodules from a statistical perspective according to local features only. Enlightened by the currently prevailing learning ability of convolutional neural network (CNN), which simulates human neural network for target recognition and our previously research on texture features, we present a hybrid model that takes into consideration of both global and local features for pulmonary nodule differentiation using the largest public database founded by the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI). By comparing three types of CNN models in which two of them were newly proposed by us, we observed that the multi-channel CNN model yielded the best discrimination in capacity of differentiating malignancy risk of the nodules based on the projection of distributions of extracted features. Moreover, CADx scheme using the new multi-channel CNN model outperformed our previously developed CADx scheme using the 3D texture feature analysis method, which increased the computed area under a receiver operating characteristic curve (AUC) from 0.9441 to 0.9702.

Exploiting morphology and texture of 3D tumor models in DTI for differentiating glioblastoma multiforme from solitary metastasis

Ambiguous imaging appearance of Glioblastoma Multiforme (GBM) and solitary Metastasis (MET) is a challenge to conventional Magnetic Resonance Imaging (MRI) based diagnosis, leading to exploitation of advanced MRI techniques, such as Diffusion Tensor Imaging (DTI). In this study, 3D tumor models are generated by a DTI clustering segmentation technique, providing up to 16 brain tissue diffusivities, complemented by T1 post-contrast imaging, resulting in the identification of tumor core, whose surface is refined by a Morphological Morphing interpolation technique. The 3D models are analyzed in terms of their surface and internal signal variations characteristics towards identification of discriminant features for differentiation between GBMs and METs, utilizing a case sample composed of 10 GBMs and 10 METs. Morphology analysis of tumor core surface is assessed by 5 local curvature features. Texture analysis considers 11 first and 16 second order 3D textural features. From the 16 second order features, 11 are based on Gray Level Co-Occurrence Matrices (GLCM) and 5 on Gray Level Run Length Matrices (GLRLM), calculated from DTI isotropic and anisotropic parametric maps, corresponding to 3D tumor core segmented from the clustering technique. Also, 3 different image quantization levels (QL) were tested for both GLCM and GLRLM analysis, while 1–4 pixel displacements (D) in case of GLCM analysis. Case sample distributions of morphology and texture features were analyzed using the Mann-Whitney U test, with a cut-off value of 0.05 to identify discriminant features. The discriminatory performance of the derived features was analyzed with Receiver Operating Characteristic (ROC) curve analysis. Results highlight the value of all 5 local curvature descriptors to capture differences between the boundary of GBMs and METs. Histogram analysis of isotropy maps revealed statistical significant differences for median value and kurtosis, while 7 out of the 11 GLCM features were capable of discriminating heterogeneity of anisotropic diffusion properties of GBMs and METs, at QL = 6 and D = 2. Finally, all 5 GLRLM features extracted from diffusion isotropy maps seem to discriminate structural properties of GBMs and METs, at QL = 5. Results demonstrate the potential of surface morphology and texture analysis of 3D tumor imaging appearance in pre-treatment brain MRI tumor differentiation.

An expression recognition algorithm based on convolution neural network and RGB-D Images

Aiming at the problem of recognition effect is not stable when 2D facial expression recognition in the complex illumination and posture changes. A facial expression recognition algorithm based on RGB-D dynamic sequence analysis is proposed. The algorithm uses LBP features which are robust to illumination, and adds depth information to study the facial expression recognition. The algorithm firstly extracts 3D texture features of preprocessed RGB-D facial expression sequence, and then uses the CNN to train the dataset. At the same time, in order to verify the performance of the algorithm, a comprehensive facial expression library including 2D image, video and 3D depth information is constructed with the help of Intel RealSense technology. The experimental results show that the proposed algorithm has some advantages over other RGB-D facial expression recognition algorithms in training time and recognition rate, and has certain reference value for future research in facial expression recognition.