Gray Level Run Length Research Articles

Effects of non-stationary blur on texture biomarkers of bone using Ultra-High Resolution CT.

To advance the development of radiomic models of bone quality using the recently introduced Ultra-High Resolution CT (UHR CT), we investigate inter-scan reproducibility of trabecular bone texture features to spatially-variant azimuthal and radial blurs associated with focal spot elongation and gantry rotation. The UHR CT system features 250×250 μm detector pixels and an x-ray source with a 0.4×0.5 mm focal spot. Visualization of details down to ~150 μm has been reported for this device. A cadaveric femur was imaged on UHR CT at three radial locations within the field-of-view: 0 cm (isocenter), 9 cm from the isocenter, and 18 cm from the isocenter; we expect the non-stationary blurs to worsen with increasing radial displacement. Gray level cooccurrence (GLCM) and gray level run length (GLRLM) texture features were extracted from 237 trabecular regions of interest (ROIs, 5 cm diameter) placed at corresponding locations in the femoral head in scans obtained at the different shifts. We evaluated concordance correlation coefficient (CCC) between texture features at 0 cm (reference) and at 9 cm and 18 cm. We also investigated whether the spatially-variant blurs affect K-means clustering of trabecular bone ROIs based on their texture features. The average CCCs (against the 0 cm reference) for GLCM and GLRM features were ~0.7 at 9 cm. At 18 cm, the average CCCs were reduced to ~0.17 for GLCM and ~0.26 for GLRM. The non-stationary blurs are incorporated in radiomic features of cancellous bone, leading to inconsistencies in clustering of trabecular ROIs between different radial locations: an intersection-over-union overlap of corresponding (most similar) clusters between 0 cm and 9 cm shift was >70%, but dropped to <60% for the majority of corresponding clusters between 0 cm and 18 cm shift. Non-stationary CT system blurs reduce inter-scan reproducibility of texture features of trabecular bone in UHR CT, especially for locations >15 cm from the isocenter. Radiomic models of bone quality derived from UHR CT measurements at isocenter might need to be revised before application in peripheral body sites such as the hips.

Radiomics-based sialadenitis staging in contrast-enhanced computed tomography and ultrasonography: a preliminary rat model study

The aim of this study was to measure the ability of radiomics analysis to diagnose different stages of sialadenitis, compare the diagnostic accuracy of computed tomography (CT) and ultrasonography (US), and suggest radiomics features selected through 3 machine learning algorithms that would be helpful in discriminating between stages of sialadenitis with both imaging systems. Wistar rats were treated to induce acute and chronic sialadenitis in the left and right submandibular glands, respectively. Contrast-enhanced CT and US of the glands were performed, followed by extirpation and histopathologic confirmation. Radiomics feature values of the glands were obtained from all images. Based on 3 feature selection methods, an optimal feature set was defined after a comparison of the receiver operating characteristic area under the curve (AUC) of each combination of 3 deep learning algorithms and 3 classification models. The attribute features for the CT model were 2 gray-level run length matrices and 2 gray-level zone length matrices. In the US model, there were 2 gray-level co-occurrence matrices and 2 gray-level zone length matrices. The most accurate diagnostic models of CT and US yielded outstanding (AUC=1.000) and excellent (AUC=0.879) discrimination, respectively. The radiomics diagnostic model using gray-level zone length matrices-based features conferred clinically outstanding discriminating ability among stages of sialadenitis using CT and excellent discrimination with US in almost all combinations of machine learning feature selections and classification models.

ColpoClassifier: A Hybrid Framework for Classification of the Cervigrams

Colposcopy plays a vital role in detecting cervical cancer. Artificial intelligence-based methods have been implemented in the literature for the classification of colposcopy images. However, there is a need for a more effective method that can accurately classify cervigrams. In this paper, ColpoClassifier, a hybrid framework for the classification of cervigrams, is proposed, which consists of feature extraction followed by classification. This paper uses a Gray-level co-occurrence matrix (GLCM), a Gray-level run length matrix (GLRLM), and a histogram of gradients (HOG) for feature extraction. These features are combined to form a feature fusion vector of the form GLCM + GLRLM + HOG. The different machine learning classifiers are used for classification by using individual feature vectors as well as feature fusion vectors. The dataset used in this paper is compiled by downloading images from the WHO website. Two variants of this dataset are created, Dataset-I contains images of the aceto-whitening effect, green filter, iodine application, and raw cervigram while Dataset-II only contains images of the aceto-whitening effect. This paper presents the classification performance on all kinds of images with the individual as well as hybrid feature fusion vector and concludes that hybrid feature fusion vectors on aceto-whitening images have given the best results.

Prediction of Coronary Artery Disease Using Machine Learning Techniques with Iris Analysis

Coronary Artery Disease (CAD) occurs when the coronary vessels become hardened and narrowed, limiting blood flow to the heart muscles. It is the most common type of heart disease and has the highest mortality rate. Early diagnosis of CAD can prevent the disease from progressing and can make treatment easier. Optimal treatment, in addition to the early detection of CAD, can improve the prognosis for these patients. This study proposes a new method for non-invasive diagnosis of CAD using iris images. In this study, iridology, a method of analyzing the iris to diagnose health conditions, was combined with image processing techniques to detect the disease in a total of 198 volunteers, 94 with CAD and 104 without. The iris was transformed into a rectangular format using the integral differential operator and the rubber sheet methods, and the heart region was cropped according to the iris map. Features were extracted using wavelet transform, first-order statistical analysis, a Gray-Level Co-Occurrence Matrix (GLCM), and a Gray Level Run Length Matrix (GLRLM). The model's performance was evaluated based on accuracy, sensitivity, specificity, precision, score, mean, and Area Under the Curve (AUC) metrics. The proposed model has a 93% accuracy rate for predicting CAD using the Support Vector Machine (SVM) classifier. With the proposed method, coronary artery disease can be preliminarily diagnosed by iris analysis without needing electrocardiography, echocardiography, and effort tests. Additionally, the proposed method can be easily used to support telediagnosis applications for coronary artery disease in integrated telemedicine systems.

Role of textural analysis parameters derived from FDG PET/CT in differentiating hepatocellular carcinoma and hepatic metastases.

Texture and radiomic analysis characterize the tumor's phenotype and evaluate its microenvironment in quantitative terms. The aim of this study was to investigate the role of textural features of 18F-FDG PET/computed tomography (CT) images in differentiating hepatocellular carcinoma (HCC) and hepatic metastasis in patients with suspected liver tumors. This is a retrospective, single-center study of 30 patients who underwent FDG PET/CT for the characterization of liver lesions or for staging a suspected liver tumor. The histological diagnosis of either primary or metastatic tumor was obtained from CT-guided biopsy, ultrasound-guided biopsy, or surgical removal of a liver lesion. The PET/CT images were then processed in commercially available textural analysis software. Region of interest was drawn over the primary tumor with a 40% threshold and was processed further to derive 42 textural and radiomic parameters. These parameters were then compared between HCC group and hepatic metastases group. Receiver-operating characteristic (ROC) curves were used to identify cutoff values for textural features with a P value <0.05 for statistical significance. A retrospective study of 30 patients with suspected liver tumors was done. After undergoing PET/CT, the histological diagnosis of these lesions was confirmed. Among these 30 patients, 15 patients had HCC, and 15 patients had hepatic metastases from various primary sites. Seven textural analysis parameters were significant in differentiating HCC from liver metastasis. Cutoff values were calculated for these parameters according to the ROC curves, standardized uptake value (SUV) Skewness (0.705), SUV Kurtosis (3.65), SUV Excess Kurtosis (0.653), gray-level zone length matrix_long zone emphasis (349.2), gray-level zone length matrix_long zone low gray-level emphasis (1.6), gray-level run length matrix_long run emphasis (1.38) and gray-level co-occurrence matrix_Homogeneity (0.406). Textural analysis parameters could successfully differentiate HCC and hepatic metastasis non-invasively. Larger multi-center studies are needed for better clinical prognostication of these parameters.

Optimized Deep CNN with Deviation Relevance-based LBP for Skin Cancer Detection: Hybrid Metaheuristic Enabled Feature Selection

Segmentation of skin lesions is a significant and demanding task in dermoscopy images. This paper proposes a new skin cancer recognition scheme, with: “Pre-processing, Segmentation, Feature extraction, Optimal Feature Selection and Classification”. Here, pre-processing is done with certain processes. The pre-processed images are segmented via the “Otsu Thresholding model”. The third phase is feature extraction, where Deviation Relevance-based “Local Binary Pattern (DRLBP), Gray-Level Co-Occurrence Matrix (GLCM) features and Gray Level Run-Length Matrix (GLRM) features” are extracted. From these extracted features, the optimal features are chosen via Particle Updated WOA (PU-WOA) model. Subsequently, classification occurs via Optimized DCNN and NN to classify the skin lesion. To make the classification more precise, the DCNN is optimized by the introduced algorithm. The result has shown a higher accuracy of 0.998737, when compared with other extant models like IPSO, IWOA, PSO+CNN, WOA+CNN and CNN schemes.

Role of Optimal Features Selection with Machine Learning Algorithms for Chest X-ray Image Analysis.

The objective of the present study is to classify chest X-ray (CXR) images into COVID-positive and normal categories with the optimal number of features extracted from the images. The successful optimal feature selection algorithm that can represent images and the classification algorithm with good classification ability has been determined as the result of experiments. This study presented a framework for the automatic detection of COVID-19 from the CXR images. To enhance small details, textures, and contrast of the images, contrast limited adaptive histogram equalization was used. Features were extracted from the first-order statistics, Gray-Level Co-occurrence Matrix, Gray-Level Run Length Matrix, local binary pattern, Law's Texture Energy Measures, Discrete Wavelet Transform, and Zernikes' Moments using an image feature extraction tool "pyFeats. For the feature selection, three nature-inspired optimization algorithms, Grey Wolf Optimization, Particle Swarm Optimization (PSO), and Genetic Algorithm, were used. For classification, Random Forest classifier, K-Nearest Neighbour classifier, support vector machine (SVM) classifier, and light gradient boosting model classifier were used. For all the feature selection methods, the SVM classifier gives the most accurate and precise result compared to other classification models. Furthermore, in feature selection methods, PSO gives the best result as compared to other methods for feature selection. Using the combination of the SVM classifier with the PSO method, it was observed that the accuracy, precision, recall, and F1-score were 100%. The result of the study indicates that with optimal features with the best choice of the classifier algorithm, the most accurate computer-aided diagnosis of CXR can be achieved. The approach presented in this study with optimal features may be utilized as a complementary tool to assist the radiologist in the early diagnosis of disease and making a more accurate decision.

Comparative assessment of Pest damage identification of coconut plant using damage texture and color analysis.

Coconut cultivation is a promising agricultural activity. But to keep the coconut plants pest-free, the detection of various pest damage in coconut plants is of utmost importance for the cultivators. The processes that the cultivators use to detect pest damage in coconut plants are conventional methods, experts' views, or some laboratory techniques. But these procedures are not adequate in the detection of coconut damage identification. In this study, 16 different color and texture features are reported for 1265 coconut pest damage images by extracting the color and texture features of the damage images in the color and grey domain after the damage segmentation using the thresholding technique. The Gray Level Co-occurrence Matrix (GLCM) and Gray Level Run Length Matrix (GLRLM) techniques are applied to extract the texture features of the damages and two Artificial Neural Network (ANN) architectures are reported to classify the extracted data features of the damages into 5 different classes such as Eriophyid_Mite, Rhinoceros_Beetle, Red_Palm_Weevil, Rugose_Spiraling_White_fly, and Rugose_in_Mature with an average testing accuracy of almost 100% respectively. To compare the results with the other machine learning techniques, the Support Vector Machine(SVM), Decision Tree (DT), and Naïve Bayes (NB) are also introduced for damage identification where the SVM methods also report almost 100% accuracy on the fuse features of GLCM and GLRLM. The results of the ANN and SVM are compared by finding the confusion matrix, precision, recall, and f-1 score of the ANN model with the DT and NB classifier. The ANN and SVM outperform in all matrices and they can be used as the base model for further study of coconut pest damage identification using deep learning techniques.

Cone-beam computed tomography texture analysis can help differentiate odontogenic and non-odontogenic maxillary sinusitis.

This study aimed to assess texture analysis (TA) of cone-beam computed tomography (CBCT) images as a quantitative tool for the differential diagnosis of odontogenic and non-odontogenic maxillary sinusitis (OS and NOS, respectively). CBCT images of 40 patients diagnosed with OS (N=20) and NOS (N=20) were evaluated. The gray level co-occurrence (GLCM) matrix parameters, and gray level run length matrix texture (GLRLM) parameters were extracted using manually placed regions of interest on lesion images. Seven texture parameters were calculated using GLCM and 4 parameters using GLRLM. The Mann-Whitney test was used for comparisons between the groups, and the Levene test was performed to confirm the homogeneity of variance (α=5%). The results showed statistically significant differences (P<0.05) between the OS and NOS patients regarding 3 TA parameters. NOS patients presented higher values for contrast, while OS patients presented higher values for correlation and inverse difference moment. Greater textural homogeneity was observed in the OS patients than in the NOS patients, with statistically significant differences in standard deviations between the groups for correlation, sum of squares, sum of entropy, and entropy. TA enabled quantitative differentiation between OS and NOS on CBCT images by using the parameters of contrast, correlation, and inverse difference moment.

Recognition of Corrosion State of Water Pipe Inner Wall Based on SMA-SVM under RF Feature Selection

To solve the problem of low detection accuracy of water supply pipeline internal wall damage, a random forest algorithm with simplified features and a slime mold optimization support vector machine detection method was proposed. Firstly, the color statistical characteristics, gray level co-occurrence matrix, and gray level run length matrix features of the pipeline image are extracted for multi-feature fusion. The contribution of the fused features is analyzed using the feature simplified random forest algorithm, and the feature set with the strongest feature expression ability is selected for classification and recognition. The global search ability of the slime mold optimization algorithm is used to find the optimal kernel function parameters and penalty factors of the support vector machine model. Finally, the optimal parameters are applied to support the vector machine model for classification prediction. The experimental results show that the recognition accuracy of the classification model proposed in this paper reaches 94.710% on the data sets of different corrosion forms on the inner wall of the pipeline. Compared with the traditional Support Vector Machines (SVM) classification model, the SVM model based on differential pollination optimization, the SVM model based on particle swarm optimization, and the back propagation (BP) neural network classification model, it is improved by 4.786%, 3.023%, 4.030%, and 0.503% respectively.

Computer-aided Diagnosis applied to MRI images of Brain Tumor using Spatial Fuzzy Level Set and ANN Classifier

The most vital organs in the human body are the brain, heart, and lungs. Because the brain controls and coordinates the operations of all other organs, normal brain function is vital. Brain tumour is a mass of tissues which interrupts the normal functioning of the brain, if left untreated will lead to the death of the subject. The classification of multiclass brain tumours using spatial fuzzy based level sets and artificial neural network (ANN) techniques is proposed in this paper. In the proposed method, images are preprocessed using Median Filtering technique, the boundaries of the Brain Tumor are obtained using Spatial Fuzzy based Level Set method, features are extracted using Gabor Wavelet and Gray-Level Run Length Matrix (GLRLM) methods. Finally ANN technique is used for the classification of the image into Normal or Benign Tumor or Malignant Tumor. The proposed method was implemented in the MATLAB working platform and achieved classification accuracy of 94%, which is significant compared to state-of-the-art classification techniques. Thus, the proposed method assist in differentiating between benign and malignant brain tumours, enabling doctors to provide adequate treatment.

Correlation of image textures of a polarization feature parameter and the microstructures of liver fibrosis tissues

Mueller matrix imaging is emerging for the quantitative characterization of pathological microstructures and is especially sensitive to fibrous structures. Liver fibrosis is a characteristic of many types of chronic liver diseases. The clinical diagnosis of liver fibrosis requires time-consuming multiple staining processes that specifically target on fibrous structures. The staining proficiency of technicians and the subjective visualization of pathologists may bring inconsistency to clinical diagnosis. Mueller matrix imaging can reduce the multiple staining processes and provide quantitative diagnostic indicators to characterize liver fibrosis tissues. In this study, a fiber-sensitive polarization feature parameter (PFP) was derived through the forward sequential feature selection (SFS) and linear discriminant analysis (LDA) to target on the identification of fibrous structures. Then, the Pearson correlation coefficients and the statistical T-tests between the fiber-sensitive PFP image textures and the liver fibrosis tissues were calculated. The results show the gray level run length matrix (GLRLM)-based run entropy that measures the heterogeneity of the PFP image was most correlated to the changes of liver fibrosis tissues at four stages with a Pearson correlation of 0.6919. The results also indicate the highest Pearson correlation of 0.9996 was achieved through the linear regression predictions of the combination of the PFP image textures. This study demonstrates the potential of deriving a fiber-sensitive PFP to reduce the multiple staining process and provide textures-based quantitative diagnostic indicators for the staging of liver fibrosis.

Radiomics in bone pathology of the jaws.

To define which are and how the radiomics features of jawbone pathologies are extracted for diagnosis, predicting prognosis and therapeutic response. A comprehensive literature search was conducted using eight databases and gray literature. Two independent observers rated these articles according to exclusion and inclusion criteria. 23 papers were included to assess the radiomics features related to jawbone pathologies. Included studies were evaluated by using JBI Critical Appraisal Checklist for Analytical Cross-Sectional Studies. Agnostic features were mined from periapical, dental panoramic radiographs, cone beam CT, CT and MRI images of six different jawbone alterations. The most frequent features mined were texture-, shape- and intensity-based features. Only 13 studies described the machine learning step, and the best results were obtained with Support Vector Machine and random forest classifier. For osteoporosis diagnosis and classification, filtering, shape-based and Tamura texture features showed the best performance. For temporomandibular joint pathology, gray-level co-occurrence matrix (GLCM), gray level run length matrix (GLRLM), Gray Level Size Zone Matrix (GLSZM), first-order statistics analysis and shape-based analysis showed the best results. Considering odontogenic and non-odontogenic cysts and tumors, contourlet and SPHARM features, first-order statistical features, GLRLM, GLCM had better indexes. For odontogenic cysts and granulomas, first-order statistical analysis showed better classification results. GLCM was the most frequent feature, followed by first-order statistics, and GLRLM features. No study reported predicting response, prognosis or therapeutic response, but instead diseases diagnosis or classification. Although the lack of standardization in the radiomics workflow of the included studies, texture analysis showed potential to contribute to radiologists' reports, decreasing the subjectivity and leading to personalized healthcare.

Combining Radiomics Features with Immune Response Biomarkers to Build a XGBoost Model to Predict Radiation Pneumonitis (RP) in Patients with Primary Lung Cancer

<h3>Purpose/Objective(s)</h3> Patients are heterogenous in their responses to radiation lung damage. It has been reported mostly from western people that the computed tomography (CT) radiomics features have a potential to identify patients at high risk for radiation pneumonitis (RP) in Western people. The purpose of this study was to 1) validate the significance of radiomics features on RP prediction, 2) exam the differences in systemic level of immune checkpoint indoleamine 2,3-dioxygenase (IDO) in patients with RP and without RP, and 3) explore the performance of the extreme gradient boosting (XGBoost) of combining above factors, on grade 2 and above RP in Chinese patients with primary lung cancer. <h3>Materials/Methods</h3> Planning CT scans and blood of baseline and end of treatment from 43 patients treated for primary lung cancer with radiotherapy were collected. Grade 2 and above RP was defined as cough or short of breath need medication treatment during or at the end of radiotherapy. Radiomics features were extracted from lung-GTV volume in planning CT using python package open-source software. Serum kynurenine, tryptophan and kynurenine: tryptophan ratio, which is IDO systemic activity related biomarkers (IDO biomarker) were measured at pre-RT and end of RT. The relation between features [radiomics features and IDO biomarker] and RP. Finally, the radiomics features with p value smaller than 0.1 were used for modeling. Patients were randomly split into 80% for training and 20% for validation. Model was built with XGBoost in train dataset and was tested in independent test dataset. The model predictive ability was assessed using area under the receiver operating characteristic curve (AUC). <h3>Results</h3> Seven out of 43 (16.3%) patients presented grade 2 and above RP. A total of 109 radiomics features were extracted. A total of 31 features, including 6 first-order, 4 gray level co-occurrence matrix (GLCM), 5 gray level dependence matrix (GLDM), 5 gray level run length matrix (GLRLM), 3 gray level size zone matrix (GLSZM) and 8 shape features, were significantly different (p value ≤ 0.05) between patients with RP and without RP. The IDO biomarkers at pre-RT and end of RT seemed to be non-significant (p value: 0.46-0.81). 43 radiomics features with p values smaller than 0.1 were used for model building. AUC of in the training dataset was 0.86 [95% CI 0.75-1] and of test dataset was 0.75 [95% 0.5-1]. A model of combined IDO biomarkers and radiomics features to build model, The predictive AUC of the training dataset was 0.9 [0.75-1] and of test dataset was 0.75 [0.5-1]. AUC slightly improved on training set. <h3>Conclusion</h3> This study at some degree validated the significance of radiomics features extracted from planning CT on predicting grade 2 and above RP in primary lung cancer in Chinese patients which has not been reported previously. IDO biomarkers did seem help, but the model built with XGBoost approach improved the predictive ability. Study with larger number of patients and ideally from multicenters are needed to validate this finding.

Local Homogeneity of PET Images Visualizes Peri-Irradiation CD8 T Cell Exhaustion

<h3>Purpose/Objective(s)</h3> The functional states of CD8⁺ T cells are associated with response to immune checkpoint inhibitors (ICI) and might become a potential biomarker indicating the timing of ICI. CD8⁺ T cells undergoing exhaustion (Tex) exhibit progressive loss of effector functions as well as metabolic insufficiency, such as suppressed glycolysis and restricted glucose uptake. We assumed that metabolic characteristics of Tex might be reflected by PET radiomic features, which could be used to noninvasively visualize the peri-irradiation dynamics of Tex and predict the optimal timing of ICI integration. Here, we aim to investigate the dynamics of Tex after ablative irradiation and develop an ¹⁸F-FDG PET/CT radiomic approach to assess tumor infiltrating Tex basing on non-small cell lung cancer (NSCLC) xenograft experiments. <h3>Materials/Methods</h3> C57BL/6 mice were inoculated with 1M Lewis Lung Carcinoma (LLC) cells subcutaneously on the right flank. On day 10 post-tumor inoculation, 20Gy was delivered to the tumors in a single fraction. For the control (D0) and those irradiated (D3, D7, D14 and D21 post-irradiation), mice received micro PET-CT scans and were sacrificed immediately after scanning, with tumors and spleens collected. The abundance of tumor-infiltrating immune cell subsets were estimated by deconvoluting the tumor microarray data with CIBERSORTx. ICI-responsive early Tex (CD8⁺PD-1^intTcf-1⁺) and ICI-nonresponsive terminal Tex (CD8⁺PD-1^hiTIM-3⁺TOX⁺) were identified by flow cytometry. Tumors on PET/CT images were manually contoured, and radiomic features were extracted by a compact proton therapy machine. Robust features which passed Test-retest analysis will undergo further selection. Least absolute shrinkage and selection operator (LASSO) logistic regression was used to select radiomic features significantly correlated with the infiltration of early or terminal Tex. <h3>Results</h3> After ablative irradiation, the tumor CD8⁺ T cell infiltration increased from D3 through the peak on D14, and then declined sharply to a below-baseline level on D21. However, dysfunctional terminal Tex significantly predominated CD8⁺ T cells from D7 to D14 (69.44%∼ 76.35%), indicating a potential window for ICI treatment between D3-D7 post-irradiation. 40 (out of 57) CT and 9 (out of 61) PET radiomic features of good robustness were brought into LASSO regression. Gray Level Co-occurrence Matrix (GLCM)-inverse variance and Gray Level Run Length Matrix (GLRLM)-long run emphasis on PET images were found to be inversely correlated with the abundance of terminal Tex, showing more heterogeneous local distribution of FDG uptake correlated with higher T exhaustion. <h3>Conclusion</h3> The dynamics of Tex help identify the proper timing to combine ICI with irradiation. Local homogeneity of PET images may provide a noninvasive approach to visualize peri-irradiation T cell exhaustion, and exhibit the potential to estimate ICI timing among more radiation dose-fractionation schedules in future study.

Utilization of Radiomics to Predict Radiation Associated Cardiovascular Morbidity in Lung SBRT

<h3>Purpose/Objective(s)</h3> SBRT for early lung cancers is now considered standard of care for some patients, but there is increasing evidence linking long-term cardiac toxicity with cardiovascular dose. While the dose constraints for aortic radiation exposure are still unclear, there is accumulating data that higher aortic doses can be associated with mortality. Our study explores the link between central thoracic radiation and early radiomic changes, determining if these radiomic changes are associated with relevant cardiovascular toxicity. This information will allow us to identify the most relevant dosing information for a variety of central thoracic organs in predicting cardiovascular toxicity from SBRT to lung. <h3>Materials/Methods</h3> We analyzed 27 patients who received SBRT to lung tumors with curative intent. Pretreatment and post treatment contrast enhanced diagnostic CT scans were accessed. The following structures were manually contoured by a medical student and reviewed by an MD: aorta, vena cava, pulmonary artery, heart, L atrium, R atrium, L ventricle, R Ventricle, and septum. For this analysis, the aorta was divided in to 10 equal sections along the inferior/superior direction. 1) 168 radiomic features were extracted for each section of the aorta wall for all 27 patients. (Mean value /standard deviation >10) between patients was used as a criterion to determine the useful and stable features. 2) dose dependent aortic wall volumes for 26 pre and post (up to 4.5 years post) treatment contrast enhanced CT scans were evaluated for the radiomic feature changes with dose. <h3>Results</h3> 1) Only 13 radiomic features were deemed stable according to our radiomic feature analysis between patients across all 10 sections of the aortic wall. These include 4 Gray-Level Co-occurrence Matrix (GLCM) features, 1 Gray Level Dependence Matrix (GLDM) feature, 5 Gray-Level Run-Length Matrix (GLRLM) features, and 3 Gray Level Size Zone Matrix (GLSZM) feature. 2) Early results indicate that no statistically significant radiomic changes of these 13 parameters were observed post SBRT to lung up to 4.5 years even with a dose of 55 Gy to the aorta. These observations were confirmed by the patient's clinical status. <h3>Conclusion</h3> Preliminary analysis suggests that radiomic features for contrast enhanced CTs could be used to evaluate the absence of radiation damage to cardiovascular structures.

An efficient classification of cirrhosis liver disease using hybrid convolutional neural network-capsule network

Liver cirrhosis is the diffuse and advanced phase of liver disease. Several morphological methods are used for imaging modalities. But, these modalities are biased and lack in higher detection accuracy. Hence, this work introduces automated cirrhosis liver disease classification using an optimized hybrid deep learning model. In this work, Magnetic Resonance Image (MRI) is considered for the process. Initially, an Extended Guided Filter (EGF) is used for eliminating the noise from input MRI images. Binomial thresholding is used to segment the tumor from the image. Then, Feature Extraction (FE) phase is carried out by Grey Level Co-occurrence Matrix (GLCM) and Gray level Run-length Matrix (GRLM). Finally, a hybrid of two Deep Learning (DL) algorithms Convolutional Neural Network and Capsule Network (HCNN-CN) are integrated to classify the Cirrhosis liver disease. Moreover, for fine tuning the parameters of the neural network, an optimization approach Adaptive Emperor Penguin Optimization (AEPO) is used. The proposed HCNN-CN-AEPO is compared over several approaches and depicted accuracy and sensitivity value of 0.993 and 0.986 on the real time dataset. The experimental results proved that the proposed HCNN-CN-AEPO can exactly diagnose the tumour.

A Novel System for Precise Grading of Glioma.

Gliomas are the most common type of primary brain tumors and one of the highest causes of mortality worldwide. Accurate grading of gliomas is of immense importance to administer proper treatment plans. In this paper, we develop a comprehensive non-invasive multimodal magnetic resonance (MR)-based computer-aided diagnostic (CAD) system to precisely differentiate between different grades of gliomas (Grades: I, II, III, and IV). A total of 99 patients with gliomas (M = 49, F = 50, age range = 1–79 years) were included after providing their informed consent to participate in this study. The proposed imaging-based glioma grading (GG-CAD) system utilizes three different MR imaging modalities, namely; contrast-enhanced T1-MR, T2-MR known as fluid-attenuated inversion-recovery (FLAIR), and diffusion-weighted (DW-MR) to extract the following imaging features: (i) morphological features based on constructing the histogram of oriented gradients (HOG) and estimating the glioma volume, (ii) first and second orders textural features by constructing histogram, gray-level run length matrix (GLRLM), and gray-level co-occurrence matrix (GLCM), (iii) functional features by estimating voxel-wise apparent diffusion coefficients (ADC) and contrast-enhancement slope. These features are then integrated together and processed using a Gini impurity-based selection approach to find the optimal set of significant features. The reduced significant features are then fed to a multi-layer perceptron artificial neural networks (MLP-ANN) classification model to obtain the final diagnosis of a glioma tumor as Grade I, II, III, or IV. The GG-CAD system was evaluated on the enrolled 99 gliomas (Grade I = 13, Grade II = 22, Grade III = 22, and Grade IV = 42) using a leave-one-subject-out (LOSO) and k-fold stratified (with k = 5 and 10) cross-validation approach. The GG-CAD achieved 0.96 ± 0.02 quadratic-weighted Cohen’s kappa and 95.8% ± 1.9% overall diagnostic accuracy at LOSO and an outstanding diagnostic performance at k = 10 and 5. Alternative classifiers, including RFs and SVM produced inferior results compared to the proposed MLP-ANN GG-CAD system. These findings demonstrate the feasibility of the proposed CAD system as a novel tool to objectively characterize gliomas using the comprehensive extracted and selected imaging features. The developed GG-CAD system holds promise to be used as a non-invasive diagnostic tool for Precise Grading of Glioma.

Influence of Image Processing on Radiomic Features From Magnetic Resonance Imaging.

Before implementing radiomics in routine clinical practice, comprehensive knowledge about the repeatability and reproducibility of radiomic features is required. The aim of this study was to systematically investigate the influence of image processing parameters on radiomic features from magnetic resonance imaging (MRI) in terms of feature values as well as test-retest repeatability. Utilizing a phantom consisting of 4 onions, 4 limes, 4 kiwifruits, and 4 apples, we acquired a test-retest dataset featuring 3 of the most commonly used MRI sequences on a 3 T scanner, namely, a T1-weighted, a T2-weighted, and a fluid-attenuated inversion recovery sequence, each at high and low resolution. After semiautomatic image segmentation, image processing with systematic variation of image processing parameters was performed, including spatial resampling, intensity discretization, and intensity rescaling. For each respective image processing setting, a total of 45 radiomic features were extracted, corresponding to the following 7 matrices/feature classes: conventional indices, histogram matrix, shape matrix, gray-level zone length matrix, gray-level run length matrix, neighboring gray-level dependence matrix, and gray-level cooccurrence matrix. Systematic differences of individual features between different resampling steps were assessed using 1-way analysis of variance with Tukey-type post hoc comparisons to adjust for multiple testing. Test-retest repeatability of radiomic features was measured using the concordance correlation coefficient, dynamic range, and intraclass correlation coefficient. Image processing influenced radiological feature values. Regardless of the acquired sequence and feature class, significant differences ( P < 0.05) in feature values were found when the size of the resampled voxels was too large, that is, bigger than 3 mm. Almost all higher-order features depended strongly on intensity discretization. The effects of intensity rescaling were negligible except for some features derived from T1-weighted sequences. For all sequences, the percentage of repeatable features (concordance correlation coefficient and dynamic range ≥ 0.9) varied considerably depending on the image processing settings. The optimal image processing setting to achieve the highest percentage of stable features varied per sequence. Irrespective of image processing, the fluid-attenuated inversion recovery sequence in high-resolution overall yielded the highest number of stable features in comparison with the other sequences (89% vs 64%-78% for the respective optimal image processing settings). Across all sequences, the most repeatable features were generally obtained for a spatial resampling close to the originally acquired voxel size and an intensity discretization to at least 32 bins. Variation of image processing parameters has a significant impact on the values of radiomic features as well as their repeatability. Furthermore, the optimal image processing parameters differ for each MRI sequence. Therefore, it is recommended that these processing parameters be determined in corresponding test-retest scans before clinical application. Extensive repeatability, reproducibility, and validation studies as well as standardization are required before quantitative image analysis and radiomics can be reliably translated into routine clinical care.

Optimization assisted framework for thyroid detection and classification: A new ensemble technique

Ultrasound (US) is an inexpensive and non-invasive technique for capturing the image of the thyroid gland and nearby tissue. The classification and detection of thyroid disorders is still in its infant stage. This study aims to present a new thyroid diagnosis approach, which consists of three phases like “(i) feature extraction, (ii) feature dimensionality reduction, and (iii) classification”. Initially, the thyroid images as well as its related data are given as input. From the input image, the features such as“ Grey Level Co-occurrence Matrix(GLCM), Grey level Run Length Matrix(GLRM), proposed Local Binary Pattern(LBP), and Local Tetra Patterns (LTrP)” are extracted. Meanwhile, from the input data, the higher-order statistical features like skewness, kurtosis, entropy, as well as moment get retrieved. Consequently, the Linear Discriminant Analysis (LDA) based dimensionality reduction is processed to resolve the problem of “curse of dimensionality”. Finally, the classification is carried out via two phases: Image features are classified using an ensemble classifier that includes Support Vector Machine (SVM)& Neural Network(NN) models. The data features are subjected to Recurrent Neural Network(RNN) based classification, which is optimized by an Adaptive Elephant Herding Algorithm (AEHO) via tuning the optimal weight. At last, the performance of the adopted scheme is compared to the extant models in terms of various measures. Especially, the mean value of the suggested RNN + AEHO model is 4.35%, 3.54%, 6.07%, 3.8%, 1.69%, 2.85%, 2.07%, 2.54%, 0.13%, 0.035%, and 8.53% better than the existing CNN, NB, RF, KNN, Levenberg, RNN + EHO, RNN + FF, RNN + WOA, WF-CS, FU-SLnO and HFBO methods respectively.