First-order Statistics Research Articles

Direct simulations and subgrid modeling of turbulent channel flows asymmetrically heated from both walls

Thermal large-eddy simulations (T-LES) and a direct numerical simulation are carried out in a bi-periodical channel with hot and cold wall temperatures of, respectively, 900 and 1300 K. The mean fluid temperature is lowered below the cold wall temperature thanks to a heat source, resulting in a both walls heating of the fluid. The hot and cold wall friction Reynolds numbers are, respectively, 640 and 1000. These conditions are representative of the working conditions of gas-pressurized solar receiver of solar power tower. The low Mach number Navier–Stokes equations are solved. The coupling between the dynamic and the temperature effects is considered. In the T-LES, both the momentum convection and the density–velocity correlation subgrid terms are modeled. Functional models, structural models, and mixed models are considered. A tensorial version of the anisotropic minimum-dissipation (AMD) model is also investigated. The Quick and the second-order-centered schemes are tested for the discretization of the mass convection term. First, an overview of the results of 17 T-LES on first- and second-order statistics is proposed. It permits selecting 6 of these simulations for a detailed analysis consisting in the investigation of profiles of mean quantities and turbulent correlations. Particular attention is given to the wall heat fluxes because they are a critical point for the design and the optimization of solar receivers. Overall, the first-order statistics are better predicted than the second-order's. The tensorial AMD model takes advantage of the classical AMD model properties and better reproduces the anisotropy of the flow thanks to its formulation. The tensorial AMD model produces the most reliable and efficient results among the considered models.

Potential role of CT-radiomics of epicardial adipose tissue in the prognosis of atrial fibrillation catheter ablation outcome

Abstract Funding Acknowledgements Type of funding sources: Public Institution(s). Main funding source(s): None Previous studies have shown that an increase of epicardial adipose tissue (EAT) volume is an independent risk factor of atrial fibrillation (AF) occurrence. However, there is no reliable data about the relationship between EAT and AF recurrence after catheter ablation (CA). Also, there are no studies of the possibility of using of CT radiomics of EAT, in particular of the quantitative assessment of EAT textural changes, for prognosis of CA outcomes in patients with AF. Thus, the aim of the present study was to estimate the association of CT-radiomics features of EAT with probability of AF recurrence after catheter ablation. Materials and Methods The prospective research included 46 patients (42 males and 4 females, mean age 42.4 ± 9.36) with drug-refractory lone AF referred for catheter ablation (CA). Before CA all patients underwent multislice CT-angiography for preoperative evaluation of cardiac and vessels anatomy and volumes. Images were acquired using a 64-detector CT scanner (GE Discovery NM/CT 570c, GE Healthcare, Milwaukee, WI, USA). Imaging parameters included a gantry rotation time of 400 ms, tube voltage of 120 mA, slice thickness 1.25 mm. For evaluation of EAT only native images (contrast-free scans) without ECG synchronization were analyzed. Epicardial adipose tissue segmentation was performed by 3D-Sliser software and the SliserRadiomics module (version 4.10.2). From CT images we quantified EAT volume and 93 radiomic features, including subgroups of first-order statistics, GLCM, GLDM, GLRLM, GLSZM and NGTDM parameters. All patients were followed-up prospectively for 12 months after the CA. A blanking period of 3 months was applied. The criteria of AF recurrence were AF episodes of more than 30 sec duration. Results. Recurrence of AF was registered in 26 patients. After the end of the follow-up, we divided study population on those with (Group 1) and without (Group 2) AF recurrence. EAT volume and attenuation values for Group 1 were 176.6 ± 56.9 sm3 and -77.47 ± 2.2 HU respectively; for Group 2 were 174.05 ± 73.3 sm3 and -78.42 ± 3.3 HU respectively, with no significant differences (p < 0.05). In the same time, 16 of 93 CT radiomics EAT parameters were significantly different between Group 1 and Group 2 and were significantly associated with AF recurrence after CA according to univariable logistic analyses. Multivariate regression analysis demonstrated that only Gray Level Non-Uniformity Normalized (GLNUN of GLSZM) parameter was an independent predictor of AF recurrence (Odds ratio 1.0022, 95%Cl 1.0006 to 1.0038, p = 0.0013); ROC-curve analysis data showed that GLNUN > 1227.2 indicates high probability of AF recurrence during 12 months (sensitivity 84.2 %, specificity 70.8 %, AUC:0.765; p = 0.001). Conclusion radiomic biomarkers of EAT have a potential to serve as a predictors of AF recurrence after CA.

Prediction of plant-level tomato biomass and yield using machine learning with unmanned aerial vehicle imagery

BackgroundThe objective of this study is twofold. First, ascertain the important variables that predict tomato yields from plant height (PH) and vegetation index (VI) maps. The maps were derived from images taken by unmanned aerial vehicles (UAVs). Second, examine the accuracy of predictions of tomato fresh shoot masses (SM), fruit weights (FW), and the number of fruits (FN) from multiple machine learning algorithms using selected variable sets. To realize our objective, ultra-high-resolution RGB and multispectral images were collected by a UAV on ten days in 2020’s tomato growing season. From these images, 756 total variables, including first- (e.g., average, standard deviation, skewness, range, and maximum) and second-order (e.g., gray-level co-occurrence matrix features and growth rates of PH and VIs) statistics for each plant, were extracted. Several selection algorithms (i.e., Boruta, DALEX, genetic algorithm, least absolute shrinkage and selection operator, and recursive feature elimination) were used to select the variable sets useful for predicting SM, FW, and FN. Random forests, ridge regressions, and support vector machines were used to predict the yield using the top five selected variable sets.ResultsFirst-order statistics of PH and VIs collected during the early to mid-fruit formation periods, about one month prior to harvest, were important variables for predicting SM. Similar to the case for SM, variables collected approximately one month prior to harvest were important for predicting FW and FN. Furthermore, variables related to PH were unimportant for prediction. Compared with predictions obtained using only first-order statistics, those obtained using the second-order statistics of VIs were more accurate for FW and FN. The prediction accuracy of SM, FW, and FN by models constructed from all variables (rRMSE = 8.8–28.1%) was better than that from first-order statistics (rRMSE = 10.0–50.1%).ConclusionsIn addition to basic statistics (e.g., average and standard deviation), we derived second-order statistics of PH and VIs at the plant level using the ultra-high resolution UAV images. Our findings indicated that our variable selection method reduced the number variables needed for tomato yield prediction, improving the efficiency of phenotypic data collection and assisting with the selection of high-yield lines within breeding programs.

Predictive Radiomic Models for the Chemotherapy Response in Non-Small-Cell Lung Cancer based on Computerized-Tomography Images.

The heterogeneity and complexity of non-small cell lung cancer (NSCLC) tumors mean that NSCLC patients at the same stage can have different chemotherapy prognoses. Accurate predictive models could recognize NSCLC patients likely to respond to chemotherapy so that they can be given personalized and effective treatment. We propose to identify predictive imaging biomarkers from pre-treatment CT images and construct a radiomic model that can predict the chemotherapy response in NSCLC. This single-center cohort study included 280 NSCLC patients who received first-line chemotherapy treatment. Non-contrast CT images were taken before and after the chemotherapy, and clinical information were collected. Based on the Response Evaluation Criteria in Solid Tumors and clinical criteria, the responses were classified into two categories: response (n = 145) and progression (n = 135), then all data were divided into two cohorts: training cohort (224 patients) and independent test cohort (56 patients). In total, 1629 features characterizing the tumor phenotype were extracted from a cube containing the tumor lesion cropped from the pre-chemotherapy CT images. After dimensionality reduction, predictive models of the chemotherapy response of NSCLC with different feature selection methods and different machine-learning classifiers (support vector machine, random forest, and logistic regression) were constructed. For the independent test cohort, the predictive model based on a random-forest classifier with 20 radiomic features achieved the best performance, with an accuracy of 85.7% and an area under the receiver operating characteristic curve of 0.941 (95% confidence interval, 0.898–0.982). Of the 20 selected features, four were first-order statistics of image intensity and the others were texture features. For nine features, there were significant differences between the response and progression groups (p < 0.001). In the response group, three features, indicating heterogeneity, were overrepresented and one feature indicating homogeneity was underrepresented. The proposed radiomic model with pre-chemotherapy CT features can predict the chemotherapy response of patients with non-small cell lung cancer. This radiomic model can help to stratify patients with NSCLC, thereby offering the prospect of better treatment.

Development and Validation of a Magnetic Resonance Imaging-Based Machine Learning Model for TMJ Pathologies.

The purpose of this study was to propose a machine learning model and assess its ability to classify TMJ pathologies on magnetic resonance (MR) images. This retrospective cohort study included 214 TMJs from 107 patients with TMJ signs and symptoms. A radiomics platform was used to extract (Huiying Medical Technology Co., Ltd., China) imaging features of TMJ pathologies, condylar bone changes, and disc displacements. Thereafter, different machine learning (ML) algorithms and logistic regression were implemented on radiomic features for feature selection, classification, and prediction. The following radiomic features included first-order statistics, shape, texture, gray-level cooccurrence matrix (GLCM), gray-level run length matrix (GLRLM), and gray-level size zone matrix (GLSZM). Six classifiers, including logistic regression (LR), random forest (RF), decision tree (DT), k-nearest neighbors (KNN), XGBoost, and support vector machine (SVM) were used for model building which could predict the TMJ pathologies. The performance of models was evaluated by sensitivity, specificity, and ROC curve. KNN and RF classifiers were found to be the most optimal machine learning model for the prediction of TMJ pathologies. The AUC, sensitivity, and specificity for the training set were 0.89 and 1, while those for the testing set were 0.77 and 0.74, respectively, for condylar changes and disc displacement, respectively. For TMJ condylar bone changes Large-Area High-Gray-Level Emphasis, Gray-Level Nonuniformity, Long-Run Emphasis Long-Run High-Gray-Level Emphasis, Flatness, and Volume features, while for TMJ disc displacements Average Intensity, Sum Average, Spherical Disproportion, and Entropy features, were selected. This study has proposed a machine learning model by KNN and RF analysis on TMJ MR images, which can be used to classify condylar changes and TMJ disc displacements.

SPH Viscous Flow Around a Circular Cylinder: Impact of Viscous Formulation and Background Pressure

Two-dimensional dynamics of the wake in transitional flow around a circular cylinder is studied using weakly compressible smoothed particle hydrodynamics scheme up to 10 cylinder diameters downstream at a Reynolds number of 4000. The main objectives of this study are to evaluate the capability of SPH-LES and artificial viscosity in capturing flow activity as well as to test the performance of these formulations and background pressure coupling against the so-called tensile instability and to understand the effect of this instability in terms of mean integral quantities, first-order statistics and frequency spectra. It is observed that the effect of viscous formulation on flow dynamics becomes significant between four-and-seven diameters downstream of the cylinder. Background pressure coupling shifts the onset of transition about two diameters upstream by creating stiffer density field; however, it results in more energetic smaller scale activity.

Accurate Diagnosis of Diabetic Retinopathy and Glaucoma Using Retinal Fundus Images Based on Hybrid Features and Genetic Algorithm

Diabetic retinopathy (DR) and glaucoma can both be incurable if they are not detected early enough. Therefore, ophthalmologists worldwide are striving to detect them by personally screening retinal fundus images. However, this procedure is not only tedious, subjective, and labor-intensive, but also error-prone. Worse yet, it may not even be attainable in some countries where ophthalmologists are in short supply. A practical solution to this complicated problem is a computer-aided diagnosis (CAD) system—the objective of this work. We propose an accurate system to detect at once any of the two diseases from retinal fundus images. The accuracy stems from two factors. First, we calculate a large set of hybrid features belonging to three groups: first-order statistics (FOS), higher-order statistics (HOS), and histogram of oriented gradient (HOG). Then, these features are skillfully reduced using a genetic algorithm scheme that selects only the most relevant and significant of them. Finally, the selected features are fed to a classifier to detect one of three classes: DR, glaucoma, or normal. Four classifiers are tested for this job: decision tree (DT), naive Bayes (NB), k-nearest neighbor (kNN), and linear discriminant analysis (LDA). The experimental work, conducted on three publicly available datasets, two of them merged into one, shows impressive performance in terms of four standard classification metrics, each computed using k-fold crossvalidation for added credibility. The highest accuracy has been provided by DT—96.67% for DR, 100% for glaucoma, and 96.67% for normal.

Effect of the yaw angle and spanning length on flow characteristics around a near-wall cylindrical structure

Three-dimensional direct numerical simulation is carried out to investigate the effects of the yaw angle and spanning length on the vortex structures and hydrodynamics of flow crossing a near-wall cylindrical structure. Two yaw angles (α = 0°, 45°), and three spanning length ratios (L* = 25, 50, 100) are investigated at Re = 500. Under the normal cylinder condition (α = 0°), a parallel vortex shedding pattern is observed in the wake. The vortex formation lengths are identical for all L*, whereas the spanwise correlation of the vortex shedding declines with the increasing L*, indicating the intensified three-dimensionality. A single dominant peak is found in the lift frequency spectra for each L* case. Under the yawed condition (α = 45°), the flow characteristics are fundamentally changed with negatively-yawed linear vortex shedding tubes being observed in the wake. Different from the normal cases, the vortex formation length for L* = 25 is larger than that of L* = 50 and 100, while the oblique angle of the vortex tube decreases with the increasing L*. It is shown that, at α = 45°, the three-dimensional flow features are fully developed when L* ≥ 50. The lift frequency spectra show multiple peaks while the magnitudes of the secondary peaks are significantly reduced by extending the spanning length. By comparing the results between α = 0° and α = 45°, it is found the Independence Principle (IP) is applicable for predicting the first-order statistics of the hydrodynamic forces and vortex shedding frequency, but fails in predicting the second-order force statistics. The effects of the yaw angle on the pressure and shear stress distributions of the bottom wall are also discussed.

Parallax‐based second‐order mixed attention for stereo image super‐resolution

Stereo image pairs can effectively enhance the performance of super-resolution (SR) since both intra-view and cross-view information can be used. However, exploiting cross-view information accurately is extremely challenging. Most recent methods use the attention mechanism to get stereo correspondence. But these methods ignore the high-frequency information since they only utilise first-order statistics, which leads to reducing the discriminative ability of the network. To address this issue, in this work, a parallax-based second-order mixed attention stereo SR network (PSMASSRnet) is proposed to integrate the cross-view information from a stereo image pair for SR. Specifically, a novel parallax-based second-order mixed attention module (PSMAM) is developed to combine second-order channel features and spatial features to obtain more discriminative representations. Furthermore, a dense cross-atrous spatial pyramid pooling (ASPP) module is also presented, which can effectively explore the local and the multi-scale features with different dilation rates to extract more discriminative features with fewer parameters and less execution. The extensive experiments on the KITTI2012, KITTI2015 and Middlebury datasets have demonstrated the superiority of the proposed PSMASSRnet over the state-of-the-art methods in the aspects of both the quantitative metrics and the visual quality.

COVID-19 discrimination framework for X-ray images by considering radiomics, selective information, feature ranking, and a novel hybrid classifier

In medical imaging procedures for the detection of coronavirus, apart from medical tests, approval of diagnosis has special significance. Imaging procedures are also useful for detecting the damage caused by COVID-19. Chest X-ray imaging is frequently used to diagnose COVID-19 and different pneumonias. This paper presents a task-specific framework to detect coronavirus in X-ray images. Binary classification of three different labels (healthy, bacterial pneumonia, and COVID-19) was performed on two differentiated data sets in which corona is stated as positive. First-order statistics, gray level co-occurrence matrix, gray level run length matrix, and gray level size zone matrix were analyzed to form fifteen sub-data sets and to ascertain the necessary radiomics. Two normalization methods are compared to make the data meaningful. Furthermore, five feature ranking approaches (Bhattacharyya, entropy, Roc, t-test, and Wilcoxon) are mentioned to provide necessary information to a state-of-the-art classifier based on Gauss-map-based chaotic particle swarm optimization and neural networks. The proposed framework was designed according to the analyses about radiomics, normalization approaches, and filter-based feature ranking methods. In experiments, seven metrics were evaluated to objectively determine the results: accuracy, area under the receiver operating characteristic (ROC) curve, sensitivity, specificity, g-mean, precision, and f-measure. The proposed framework showed promising scores on two X-ray-based data sets, especially with the accuracy and area under the ROC curve rates exceeding 99% for the classification of coronavirus vs. others.

Current progress and quality of radiomic studies for predicting EGFR mutation in patients with non-small cell lung cancer using PET/CT images: a systematic review.

To assess the methodological quality of radiomic studies based on positron emission tomography/computed tomography (PET/CT) images predicting epidermal growth factor receptor (EGFR) mutation status in patients with non-small cell lung cancer (NSCLC). We systematically searched for eligible studies in the PubMed and Web of Science datasets using the terms "radiomics", "PET/CT", "NSCLC", and "EGFR". The included studies were screened by two reviewers independently. The quality of the radiomic workflow of studies was assessed using the Radiomics Quality Score (RQS). Interclass correlation coefficient (ICC) was used to determine inter rater agreement for the RQS. An overview of the methodologies used in steps of the radiomics workflow and current results are presented. Six studies were included with sample sizes of 973 ranging from 115 to 248 patients. Methodologies in the radiomic workflow varied greatly. The first-order statistics were the most reproducible features. The RQS scores varied from 13.9 to 47.2%. All studies were scored below 50% due to defects on multiple segmentations, phantom study on all scanners, imaging at multiple time points, cut-off analyses, calibration statistics, prospective study, potential clinical utility, and cost-effectiveness analysis. The ICC results for majority of RQS items were excellent. The ICC for summed RQS was 0.986 [95% confidence interval (CI): 0.898-0.998]. The PET/CT-based radiomics signature could serve as a diagnostic indicator of EGFR mutation status in NSCLC patients. However, the current conclusions should be interpreted with care due to the suboptimal quality of the studies. Consensus for standardization of PET/CT-based radiomic workflow for EGFR mutation status in NSCLC patients is warranted to further improve research. Radiomics can offer clinicians better insight into the prediction of EGFR mutation status in NSCLC patients, whereas the quality of relative studies should be improved before application to the clinical setting.

Acoustic Seafloor Classification Using the Weyl Transform of Multibeam Echosounder Backscatter Mosaic

The use of multibeam echosounder systems (MBES) for detailed seafloor mapping is increasing at a fast pace. Due to their design, enabling continuous high-density measurements and the coregistration of seafloor’s depth and reflectivity, MBES has become a fundamental instrument in the advancing field of acoustic seafloor classification (ASC). With these data becoming available, recent seafloor mapping research focuses on the interpretation of the hydroacoustic data and automated predictive modeling of seafloor composition. While a methodological consensus on which seafloor sediment classification algorithm and routine does not exist in the scientific community, it is expected that progress will occur through the refinement of each stage of the ASC pipeline: ranging from the data acquisition to the modeling phase. This research focuses on the stage of the feature extraction; the stage wherein the spatial variables used for the classification are, in this case, derived from the MBES backscatter data. This contribution explored the sediment classification potential of a textural feature based on the recently introduced Weyl transform of 300 kHz MBES backscatter imagery acquired over a nearshore study site in Belgian Waters. The goodness of the Weyl transform textural feature for seafloor sediment classification was assessed in terms of cluster separation of Folk’s sedimentological categories (4-class scheme). Class separation potential was quantified at multiple spatial scales by cluster silhouette coefficients. Weyl features derived from MBES backscatter data were found to exhibit superior thematic class separation compared to other well-established textural features, namely: (1) First-order Statistics, (2) Gray Level Co-occurrence Matrices (GLCM), (3) Wavelet Transform and (4) Local Binary Pattern (LBP). Finally, by employing a Random Forest (RF) categorical classifier, the value of the proposed textural feature for seafloor sediment mapping was confirmed in terms of global and by-class classification accuracies, highest for models based on the backscatter Weyl features. Further tests on different backscatter datasets and sediment classification schemes are required to further elucidate the use of the Weyl transform of MBES backscatter imagery in the context of seafloor mapping.

Auxiliary task guided mean and covariance alignment network for adversarial domain adaptation

Adversarial domain adaptation (ADA) learns representations with strong transferability by eliminating the discrepancy between the probability distributions of the source and the target domains. Conventional ADA methods usually employ the Wasserstein distance as a discrepancy measure and train the classifier only from the source domain data. We show that such methods actually only consider first-order statistics in the latent feature space and the discriminability of the learned representations is not fully explored. In this paper, we propose a novel method called auxiliary task guided mean and covariance alignment network (AT-MCAN) for unsupervised domain adaptation. To take the second-order statistics differences into consideration, AT-MCAN introduces a covariance-aware divergence metric to align the distributions of two domains. To enhance the discriminability of the features, AT-MCAN introduces an auxiliary clustering task to the target domain so that the classifier can employ the data from both domains. We provide both theoretical analysis on the generalization bound and empirical evaluations on standard benchmarks to show the effectiveness of our proposed AT-MCAN.

Investigation of Informal Settlement Indicators in a Densely Populated Area Using Very High Spatial Resolution Satellite Imagery

Automation of informal settlements detection using satellite imagery remains a challenging task in urban remote sensing. This is due to the fact that informal settlements vary in shape, size and spatial arrangement from one region to the other in some cases within a city. This paper investigated the methodology to detect informal settlements in a densely populated township by assessing informal settlement indicators observed from very high spatial resolution satellite imagery. We assessed twelve informal settlement indicators to determine the most effective indicators to distinguish between informal and informal classes. These indicators included the spectral indices first and second-order statistical measurements. In addition to the commonly used informal settlement indicators, we assessed the effectiveness of built-up area and iron cover. The GLCM textural measures performed poorly in separating informal and formal settlements compared to first-order statistics measurement and spectral indices. The built-up area index, coastal blue index and the first-order statistics mean measurements produced higher separability distance of informal and formal settlements. The iron index performed better in separating the two settlement types than the commonly used GLCM measure and NDVI. The proposed ruleset that uses the three features with the highest separability distance achieved producer and user accuracies of informal settlements of 95% and 82%, respectively. The results of this study will contribute towards developing methodologies to automatically detect informal settlements.

Feasibility of the Quantitative Assessment Method for CT Quality Control in Phantom Image Evaluation

Computed tomography (CT) quality control (QC) is regularly performed with standard phantoms, to bar faulty equipment from medical use. Its accuracy may be improved by replacing qualitative methods based on good visual distinction with pixel value-based quantitative methods. We hypothesized that statistical texture analysis (TA) that covers the entire phantom image would be a more appropriate tool. Therefore, our study devised a novel QC method based on the TA for contrast resolution (CR) and spatial resolution (SR) and proposed new, quantitative CT QC criteria. TA of CR and SR images on an American Association of Physicists in Medicine (AAPM) CT Performance Phantom were performed with nine CT scanner models. Six texture descriptors derived from first-order statistics of grayscale image histograms were analyzed. Principal component analysis was used to reveal descriptors with high utility. For CR evaluation, contrast and softness were the most accurate descriptors. For SR evaluation, contrast, softness, and skewness were the most useful descriptors. We propose the following ranges: contrast for CR, 29.5 ± 15%, for SR, 29 ± 10%; softness for CR, &lt;0.015, for SR, &lt;0.014; and skewness for SR, &gt;−1.85. Our novel TA method may improve the assessment of CR and SR of AAPM phantom images.

Artificial Intelligence Techniques for Prostate Cancer Detection through Dual-Channel Tissue Feature Engineering.

Simple SummaryArtificial intelligence techniques were used for the detection of prostate cancer through tissue feature engineering. A radiomic method was used to extract the important features or information from histopathology tissue images to perform binary classification (i.e., benign vs. malignant). This method can identify a histological pattern that is invisible to the human eye, which helps researchers to predict and detect prostate cancer. We used different performance metrics to evaluate the results of the classification. In the future, it is expected that a method like radiomic will provide a consistent contribution to analyze histopathology tissue images and differentiate between cancerous and noncancerous tumors.The optimal diagnostic and treatment strategies for prostate cancer (PCa) are constantly changing. Given the importance of accurate diagnosis, texture analysis of stained prostate tissues is important for automatic PCa detection. We used artificial intelligence (AI) techniques to classify dual-channel tissue features extracted from Hematoxylin and Eosin (H&E) tissue images, respectively. Tissue feature engineering was performed to extract first-order statistic (FOS)-based textural features from each stained channel, and cancer classification between benign and malignant was carried out based on important features. Recursive feature elimination (RFE) and one-way analysis of variance (ANOVA) methods were used to identify significant features, which provided the best five features out of the extracted six features. The AI techniques used in this study for binary classification (benign vs. malignant and low-grade vs. high-grade) were support vector machine (SVM), logistic regression (LR), bagging tree, boosting tree, and dual-channel bidirectional long short-term memory (DC-BiLSTM) network. Further, a comparative analysis was carried out between the AI algorithms. Two different datasets were used for PCa classification. Out of these, the first dataset (private) was used for training and testing the AI models and the second dataset (public) was used only for testing to evaluate model performance. The automatic AI classification system performed well and showed satisfactory results according to the hypothesis of this study.

IDH-Based Radiogenomic Characterization of Glioma Using Local Ternary Pattern Descriptor Integrated with Radiographic Features and Random Forest Classifier

Mutations in family of Isocitrate Dehydrogenase (IDH) gene occur early in oncogenesis, especially with glioma brain tumor. Molecular diagnostic of glioma using machine learning has grabbed attention to some extent from last couple of years. The development of molecular-level predictive approach carries great potential in radiogenomic field. But more focused efforts need to be put to develop such approaches. This study aims to develop an integrative genomic diagnostic method to assess the significant utility of textures combined with other radiographic and clinical features for IDH classification of glioma into IDH mutant and IDH wild type. Random forest classifier is used for classification of combined set of clinical features and radiographic features extracted from axial T2-weighted Magnetic Resonance Imaging (MRI) images of low- and high-grade glioma. Such radiogenomic analysis is performed on The Cancer Genome Atlas (TCGA) data of 74 patients of IDH mutant and 104 patients of IDH wild type. Texture features are extracted using uniform, rotation invariant Local Ternary Pattern (LTP) method. Other features such as shape, first-order statistics, image contrast-based, clinical data like age, histologic grade are combined with LTP features for IDH discrimination. Proposed random forest-assisted model achieved an accuracy of 85.89% with multivariate analysis of integrated set of feature descriptors using Glioblastoma and Low-Grade Glioma dataset available with The Cancer Imaging Archive (TCIA). Such an integrated feature analysis using LTP textures and other descriptors can effectively predict molecular class of glioma as IDH mutant and wild type.

A Systematic Review of PET Textural Analysis and Radiomics in Cancer.

Background: Although many works have supported the utility of PET radiomics, several authors have raised concerns over the robustness and replicability of the results. This study aimed to perform a systematic review on the topic of PET radiomics and the used methodologies. Methods: PubMed was searched up to 15 October 2020. Original research articles based on human data specifying at least one tumor type and PET image were included, excluding those that apply only first-order statistics and those including fewer than 20 patients. Each publication, cancer type, objective and several methodological parameters (number of patients and features, validation approach, among other things) were extracted. Results: A total of 290 studies were included. Lung (28%) and head and neck (24%) were the most studied cancers. The most common objective was prognosis/treatment response (46%), followed by diagnosis/staging (21%), tumor characterization (18%) and technical evaluations (15%). The average number of patients included was 114 (median = 71; range 20–1419), and the average number of high-order features calculated per study was 31 (median = 26, range 1–286). Conclusions: PET radiomics is a promising field, but the number of patients in most publications is insufficient, and very few papers perform in-depth validations. The role of standardization initiatives will be crucial in the upcoming years.

Machine Learning–based Differentiation of Benign and Premalignant Colorectal Polyps Detected with CT Colonography in an Asymptomatic Screening Population: A Proof-of-Concept Study

Background CT colonography does not enable definite differentiation between benign and premalignant colorectal polyps. Purpose To perform machine learning-based differentiation of benign and premalignant colorectal polyps detected with CT colonography in an average-risk asymptomatic colorectal cancer screening sample with external validation using radiomics. Materials and Methods In this secondary analysis of a prospective trial, colorectal polyps of all size categories and morphologies were manually segmented on CT colonographic images and were classified as benign (hyperplastic polyp or regular mucosa) or premalignant (adenoma) according to the histopathologic reference standard. Quantitative image features characterizing shape (n = 14), gray level histogram statistics (n = 18), and image texture (n = 68) were extracted from segmentations after applying 22 image filters, resulting in 1906 feature-filter combinations. Based on these features, a random forest classification algorithm was trained to predict the individual polyp character. Diagnostic performance was validated in an external test set. Results The random forest model was fitted using a training set consisting of 107 colorectal polyps in 63 patients (mean age, 63 years ± 8 [standard deviation]; 40 men) comprising 169 segmentations on CT colonographic images. The external test set included 77 polyps in 59 patients comprising 118 segmentations. Random forest analysis yielded an area under the receiver operating characteristic curve of 0.91 (95% CI: 0.85, 0.96), a sensitivity of 82% (65 of 79) (95% CI: 74%, 91%), and a specificity of 85% (33 of 39) (95% CI: 72%, 95%) in the external test set. In two subgroup analyses of the external test set, the area under the receiver operating characteristic curve was 0.87 in the size category of 6-9 mm and 0.90 in the size category of 10 mm or larger. The most important image feature for decision making (relative importance of 3.7%) was quantifying first-order gray level histogram statistics. Conclusion In this proof-of-concept study, machine learning-based image analysis enabled noninvasive differentiation of benign and premalignant colorectal polyps with CT colonography. © RSNA, 2021 Online supplemental material is available for this article.

Statistical features from frame aggregation and differences for human gait recognition

Human gait recognition, an alternate biometric technique, received significant attention in the last decade. As many gait recognition applications require real-time response, the primary concern is to design efficient and straightforward gait features for human recognition. In this work, two novel gait features are proposed. Both features are designed by exploring the dynamic variations of different body parts during a gait cycle. The first feature set is based on one-against-all gait frame differences for person identification. This novel approach divides each frame in a gait cycle to blocks, compute the block sum, and then find the difference of respective block sum between the first frame and the rest. The second feature set is defined on the first-order statistics of the normalized sum of the frames in a cycle. Two other existing features- Centroid of Silhouette frames and feature values defined on Change Energy Images are also considered. Feature level fusion is realized by considering the different combinations of the four types of features. Experiments carried out with the CASIA Gait Dataset B demonstrated the proposal’s merit with high recognition accuracy. The outcome of the investigations is promising when compared to recent contributions.