Gray Level Co-occurrence Matrix Features Research Articles

Analysis of mango fruit surface temperature using thermal imaging and deep learning

Abstract Thermal imaging has the potential to measure the object’s surface temperature. This study investigated the thermal behavior of mango fruit stored in a refrigerated environment. Thermal images of the fruit were collected with sufficient quality by supplying hot air to the acquisition environment. Grey-Level Co-occurrence Matrix (GLCM) features of mango images were determined to distinguish the subtle and noticeable changes. The thermal images were analyzed to find the temperature difference between the different regions of the fruit. The temperature of the bruise boundary (T bd ) was higher than the bruised center (T C ) throughout the storage period. In addition, an enhanced deep-learning model was used to predict the damaged mango. Over 10 days, 3500 thermal images were obtained from the 400 mangoes. In that, 80 % of the images were used for training, 10 % for testing, and 10 % for validation. The model achieved a classification accuracy of 99.6 %.

The Deep Learning ResNet101 and Ensemble XGBoost Algorithm with Hyperparameters Optimization Accurately Predict the Lung Cancer

ABSTRACT Lung cancer is the most common and second leading cause of cancer with lowest survival rate due to lack of efficient diagnostic tools. Currently, researchers are devising artificial intelligence based tools to improve the diagnostic capabilities. The machine learning (ML) requires hand-crafted features to train the algorithms. To extract most relevant features is still a challenging task in the field image processing. We first extracted the texture gray level co-occurrence matrix features. We fed these features to traditional ML algorithms such as k-nearest neighbor (KNN) and support vector machine (SVM). The SVM yielded an accuracy of 83.0%, whereas KNN produced an accuracy of 97.0%. We then optimized and employed the ensemble extreme boosting (XGBoost) algorithm, which improved the detection performance with precision, recall, and accuracy of 100%. We also optimized and employed the deep learning ResNet101 to distinguish the small cell cancer from non-small cell lung cancer and obtained the 100% performance with these evaluation performance measures. The results revealed that proposed approach is more robust than traditional ML algorithms. Based on these results, the proposed methodology can be very helpful in the early detection and treatment of lung cancer for better diagnosis system.

Rural land cover mapping using short-term Sentinel-2 temporal composites and machine learning

Multispectral sensors have been invaluable for land cover mapping. Nonetheless, cloud cover is frequent in many parts in the tropics, meaning that relying on single-date multispectral data can be problematic. The limited number of variables, i.e., only two, in conventional dual-polarized synthetic aperture radar data usually drives low classification accuracies. Researchers have explored an augmentation strategy that uses textural features, such as Haralick’s Gray Level Co-occurrence Matrix and/or decomposition features. However, this also does not produce an acceptable outcome. Another approach involves short-term temporal stacking. This masks out atmospheric disturbance and means every pixel has a single value representing the object. Our research explored this last approach to identify woody vegetation in a rural area of Indonesia from Sentinel-2 data. Ten machine learning algorithms were explored to investigate limitations and opportunities. We investigated algorithms capable of reporting variable importance to indicate crucial spectral bands. This study indicated that highly important spectra include red edge and short-wave infrared bands and to a lesser extent, the red band. Part of these bands were confirmed by the variable importance. The spectral similarity between bands 8 and 8A could be seen as a drawback when both bands are employed. Variable importance indicated a negative impact due to this similarity, suggesting that only one should be used in the classification. Overall, classification accuracy was generally high (over 96%), except in the case of the benchmark, i.e., classification and regression trees. Highest accuracy (97.6%) was provided by C5.0 model, although the difference from random forests (RFs) was negligible. The RF was favored as it produced a better estimate of timber plantations. A few algorithms were unable to separate woody vegetation types, including the popular support vector machine. Successful separation was mainly achieved by ensemble tree learners, such as RFs and the variants of extreme gradient boosting.

Content-Based remote sensing image retrieval method using adaptive tetrolet transform based GLCM features

This paper proposed a novel texture feature extraction technique for radar remote sensing image retrieval application using adaptive tetrolet transform and Gray level co-occurrence matrix. Tetrolets have provided fine texture information in the radar image. Tetrominoes have been employed on each decomposed radar image and best pattern of tetrominoes has been chosen which represents the better radar image geometry at each decomposition level. All three high pass components of the decomposed radar image at each level and low pass component at the last level are considered as input values for Gray level co-occurrence matrix (GLCM), where GLCM provides the spatial relationship among the pixel values of decomposed components in different directions at certain distances. The GLCMs of decomposed components are computed in (1). (0, π/2, π, 3π/2), (2). (π/4, 3π/4, 5π/4, 7π/4) (3). (0, π/4, π/2, 3π/4, π, 3π/2, 5π/4, 7π/4) directions individually and subsequently a texture feature descriptor is constructed by computing statistical parameters from the corresponding GLCMs. The retrieval performance is validated on two standard radar remote sensing image databases: 20-class satellite remote sensing dataset and 21-class land-cover dataset. The average metrices i.e., precision, recall and F-score are 61.43%, 12.29% and 20.47% for 20-class satellite remote sensing dataset while 21-class land-cover dataset have achieved 67.75%, 9.03% and 15.94% average metrices. The retrieved results show the better accuracy as compared to the other related state of arts radar remote sensing image retrieval methods.

Avoid non-diagnostic EUS-FNA: a DNN model as a possible gatekeeper to distinguish pancreatic lesions prone to inconclusive biopsy.

This work aimed to explore the utility of CT radiomics with machine learning for distinguishing the pancreatic lesions prone to non-diagnostic ultrasound-guided fine-needle aspiration (EUS-FNA). 498 patients with pancreatic EUS-FNA were retrospectively reviewed [Development cohort: 147 pancreatic ductal adenocarcinoma (PDAC); Validation cohort: 37 PDAC]. Pancreatic lesions not PDAC were also tested exploratively. Radiomics extracted from contrast-enhanced CT was integrated with deep neural networks (DNN) after dimension reduction. The receiver operating characteristic (ROC) curve, and decision curve analysis (DCA) were performed for model evaluation. And, the explainability of the DNN model was analyzed by integrated gradients. The DNN model was effective in distinguishing PDAC lesions prone to non-diagnostic EUS-FNA (Development cohort: AUC = 0.821, 95% CI: 0.742-0.900; Validation cohort: AUC = 0.745, 95% CI: 0.534-0.956). In all cohorts, the DNN model showed better utility than the logistic model based on traditional lesion characteristics with NRI >0 (p < 0.05). And, the DNN model had net benefits of 21.6% at the risk threshold of 0.60 in the validation cohort. As for the model explainability, gray-level co-occurrence matrix (GLCM) features contributed the most averagely and the first-order features were the most important in the sum attribution. The CT radiomics-based DNN model can be a useful auxiliary tool for distinguishing the pancreatic lesions prone to nondiagnostic EUS-FNA and provide alerts for endoscopists preoperatively to reduce unnecessary EUS-FNA. This is the first investigation into the utility of CT radiomics-based machine learning in avoiding non-diagnostic EUS-FNA for patients with pancreatic masses and providing potential pre-operative assistance for endoscopists.

Classification of COVID-19 from X-ray Images using GLCM Features and Machine Learning

As the world continues to battle the devastating effects of the COVID-19 pandemic, it has become increasingly crucial to screen patients for contamination accurately and effectively. One of the primary screening methods is chest radiography, utilizing radiological imaging to detect the presence of the virus in the lungs. This study presents a cutting-edge solution to classify COVID-19 infections in chest X-ray images by utilizing the Gray-Level Co-occurrence Matrix (GLCM) and machine learning algorithms. The proposed method analyzes each X-ray image using the GLCM to extract 22 statistical texture features and then trains two machine learning classifiers - K-Nearest Neighbor and Support Vector Machine - on these features. The method was tested on the COVID-19 Radiography Database and was compared to a state-of-the-art method, delivering highly efficient results with impressive sensitivity, accuracy, precision, F1-score, specificity, and Matthew's correlation coefficient. The proposed approach offers a promising new way to classify COVID-19 infections in chest X-ray images and has the potential to play a crucial role in the ongoing fight against the pandemic.

Distinguishing Parkinson's Disease with GLCM Features from the Hankelization of EEG Signals.

This study proposes a novel method that uses electroencephalography (EEG) signals to classify Parkinson's Disease (PD) and demographically matched healthy control groups. The method utilizes the reduced beta activity and amplitude decrease in EEG signals that are associated with PD. The study involved 61 PD patients and 61 demographically matched controls groups, and EEG signals were recorded in various conditions (eyes closed, eyes open, eyes both open and closed, on-drug, off-drug) from three publicly available EEG data sources (New Mexico, Iowa, and Turku). The preprocessed EEG signals were classified using features obtained from gray-level co-occurrence matrix (GLCM) features through the Hankelization of EEG signals. The performance of classifiers with these novel features was evaluated using extensive cross-validations (CV) and leave-one-out cross-validation (LOOCV) schemes. This method under 10 × 10 fold CV, the method was able to differentiate PD groups from healthy control groups using a support vector machine (SVM) with an accuracy of 92.4 ± 0.01, 85.7 ± 0.02, and 77.1 ± 0.06 for New Mexico, Iowa, and Turku datasets, respectively. After a head-to-head comparison with state-of-the-art methods, this study showed an increase in the classification of PD and controls.

A novel machine learning-based feature extraction method for classifying intracranial hemorrhage computed tomography images

One of the most serious forms of brain stroke is intracranial hemorrhage (ICH). When an artery bursts, the brain and the tissue around the artery start bleeding. This study proposes a joint feature selection strategy to classify computed tomography (CT) images of intracranial hemorrhage. The joint feature set is composed of transform and texture features. Joint features are constructed from a combination of grey level co-occurrence matrix (GLCM) features, discrete wavelet features (DWT), and discrete cosine features (DCT). Brain hemorrhage CT image classification uses ensemble-based machine learning (ML) techniques. On the training dataset, a Synthetic Minority Over-Sampling Technique (SMOTE) is applied to treat the problem of oversampling by adding fresh data. Additionally, the sequential forward feature selection technique is used to obtain feature subsets. The classification accuracy is further examined for varied feature vector sizes. Confusion matrix, precision, and recall in categorization are employed as performance evaluation measurements. The ML-based ensemble classifiers can produce highly accurate results with the aid of the proposed novel feature extraction mechanism. When taking into consideration a crucial feature set consisting of six features, it can be seen that Random Forest obtained the greatest accuracy, which is 87.22%.

A Study of Dimensionality Reduction in GLCM Feature-Based Classification of Machined Surface Images

AbstractThe surfaces produced by the machining process are sensitive to the type of machining process and the conditions under which it is performed. Thus, surface texture identification is crucial in quality assurance, as it acts as a feedback to the machining process. Machined surface identification using image processing and machine learning (ML)-based techniques is gaining much importance due to industrial automation. This investigation addresses the development of ML models using gray-level co-occurrence matrices (GLCM) features to classify the machined (turned, ground and shaped) surfaces. The influence of distance-based dimensionality reduction techniques (DRT) viz., Fisher's criterion, Separation index and Bhattacharya distance on the performance of the ML-based image classifiers is explored. The GLCM features extracted from the machined surface images are used as inputs to ML classifiers. A threshold criterion function (TCF) is used to select the sensitive features in the DRT. Among all the classifiers, the (Random Forest) RAF model could produce a better classification accuracy as high as 95.3%. Also, analysis results show that the proposed dimensionality reduction methodology with TCF effectively identifies the most sensitive features. A maximum dimensionality reduction of 62% is achieved. The proposed methodology showed a 7.2% improvement in classification accuracy over the techniques reported in the previous study. Thus, developed ML models successfully classify the machined surface images with a minimum time and computational burden on the computer.

A Novel Approach for Brain Tumor Classification Using an Ensemble of Deep and Hand-Crafted Features.

One of the most severe types of cancer caused by the uncontrollable proliferation of brain cells inside the skull is brain tumors. Hence, a fast and accurate tumor detection method is critical for the patient's health. Many automated artificial intelligence (AI) methods have recently been developed to diagnose tumors. These approaches, however, result in poor performance; hence, there is a need for an efficient technique to perform precise diagnoses. This paper suggests a novel approach for brain tumor detection via an ensemble of deep and hand-crafted feature vectors (FV). The novel FV is an ensemble of hand-crafted features based on the GLCM (gray level co-occurrence matrix) and in-depth features based on VGG16. The novel FV contains robust features compared to independent vectors, which improve the suggested method's discriminating capabilities. The proposed FV is then classified using SVM or support vector machines and the k-nearest neighbor classifier (KNN). The framework achieved the highest accuracy of 99% on the ensemble FV. The results indicate the reliability and efficacy of the proposed methodology; hence, radiologists can use it to detect brain tumors through MRI (magnetic resonance imaging). The results show the robustness of the proposed method and can be deployed in the real environment to detect brain tumors from MRI images accurately. In addition, the performance of our model was validated via cross-tabulated data.

The classification of wheat yellow rust disease based on a combination of textural and deep features.

Yellow rust is a devastating disease that causes significant losses in wheat production worldwide and significantly affects wheat quality. It can be controlled by cultivating resistant cultivars, applying fungicides, and appropriate agricultural practices. The degree of precautions depends on the extent of the disease. Therefore, it is critical to detect the disease as early as possible. The disease causes deformations in the wheat leaf texture that reveals the severity of the disease. The gray-level co-occurrence matrix(GLCM) is a conventional texture feature descriptor extracted from gray-level images. However, numerous studies in the literature attempt to incorporate texture color with GLCM features to reveal hidden patterns that exist in color channels. On the other hand, recent advances in image analysis have led to the extraction of data-representative features so-called deep features. In particular, convolutional neural networks (CNNs) have the remarkable capability of recognizing patterns and show promising results for image classification when fed with image texture. Herein, the feasibility of using a combination of textural features and deep features to determine the severity of yellow rust disease in wheat was investigated. Textural features include both gray-level and color-level information. Also, pre-trained DenseNet was employed for deep features. The dataset, so-called Yellow-Rust-19, composed of wheat leaf images, was employed. Different classification models were developed using different color spaces such as RGB, HSV, and L*a*b, and two classification methods such as SVM and KNN. The combined model named CNN-CGLCM_HSV, where HSV and SVM were employed, with an accuracy of 92.4% outperformed the other models.

Synthetic Aperture Radar Remote Sensing for Crop Classification

This Study proposes the approach for crop classification using the Grey Level Co-occurrence Matrix feature of Synthetic Aperture Radar (SAR) images. The method utilizes the SAR Images acquired by Sentinel 1A SAR Data and extract textural features using GLCM. In this study, we investigate the potential of Grey Level Co-occurrence Matrix (GLCM)-based texture information for horticulture crop classification with SAR images in Kharif and cloud weather condition. A study on Synthetic Aperture Radar (SAR) satellite imagery was conducted in Chhattisgarh with the objective to evaluate the potential of different texture parameters among crop. The SAR data were pre-processed for textural analysis having entire angle and equal distance quantization. The results were categorized among different parameters showing significant variation for horticulture crops for Contrast, Dissimilarity, Homogeneity, ASM, Energy, Entropy and GLCM Mean. The statistical analysis was done for fruit crop along with major kharif crop of study area. The results shows that mean backscatter value was lowest for banana (99.12 dB) and highest for Mango (198.26 dB) regarding contrast textural property in VH Channel whereas mean backscatter value in VH Channel w.r.t to energy was maximum for banana (0.60 dB) followed by papaya (0.49 dB) and guava (0.45 dB) and least for mango (0.44 dB). The mean backscatter value for GLCM mean textural property in VH channel was shown maximum by banana (51.24 dB) followed by papaya (41.96 dB) and mango (32.98 dB). These results indicate the usefulness of texture information for classification of SAR images, particularly when acquisition of optical images is difficult in Kharif and cloud weather condition for crop classification. Thus GLCM feature of SAR Data proven to be significant for the classification of horticulture crops.

Gray-Level Co-occurrence Matrix Analysis of Nuclear Textural Patterns in Laryngeal Squamous Cell Carcinoma: Focus on Artificial Intelligence Methods.

Gray-level co-occurrence matrix (GLCM) and discrete wavelet transform (DWT) analyses are two contemporary computational methods that can identify discrete changes in cell and tissue textural features. Previous research has indicated that these methods may be applicable in the pathology for identification and classification of various types of cancers. In this study, we present findings that squamous epithelial cells in laryngeal carcinoma, which appear morphologically intact during conventional pathohistological evaluation, have distinct nuclear GLCM and DWT features. The average values of nuclear GLCM indicators of these cells, such as angular second moment, inverse difference moment, and textural contrast, substantially differ when compared to those in noncancerous tissue. In this work, we also propose machine learning models based on random forests and support vector machine that can be successfully trained to separate the cells using GLCM and DWT quantifiers as input data. We show that, based on a limited cell sample, these models have relatively good classification accuracy and discriminatory power, which makes them suitable candidates for future development of AI-based sensors potentially applicable in laryngeal carcinoma diagnostic protocols.

Multifeature Fusion Classification Method for Adaptive Endoscopic Ultrasonography Tumor Image.

Endoscopic ultrasonography (EUS) has been found to be of great advantage in the diagnosis of digestive tract submucosal tumors. However, EUS-based diagnosis is limited by variability in subjective interpretation on the part of doctors. Tumor classification of ultrasound images with the computer-aided diagnosis system can significantly improve the diagnostic efficiency and accuracy of doctors. In this study, we proposed a multifeature fusion classification method for adaptive EUS tumor images. First, for different ultrasound tumor images, we selected the region of interest based on prior information to facilitate the estimation in the subsequent works. Second, we proposed a method based on image gray histogram feature extraction with principal component analysis dimensionality reduction, which learns the gray distribution of different tumor images effectively. Third, we fused the reduced grayscale features with the improved local binary pattern features and gray-level co-occurrence matrix features, and then used the multiclassification support vector machine. Finally, in the experiment, we selected the 431 ultrasound images of 109 patients in the hospital and compared the experimental effects of different features and different classifiers. The results revealed that the proposed method performed best, with the highest accuracy of 96.18% and an area under the curve of 99%. It is evident that the method proposed in this study can efficiently contribute to the classification of EUS tumor images.

PD22-06 RADIOMIC ASSESSMENT OF CLEAR CELL RENAL CELL CARCINOMA TUMOR IMMUNE MICROENVIRONMENT

You have accessJournal of UrologyCME1 Apr 2023PD22-06 RADIOMIC ASSESSMENT OF CLEAR CELL RENAL CELL CARCINOMA TUMOR IMMUNE MICROENVIRONMENT Alexander Shieh, Steven Cen, Bino Varghese, Darryl Hwang, Xiaomeng Lei, Kirthika Gurumurthy, Imran Siddiqi, Manju Aron, Inderbir Gill, W. Dean Wallace, and Vinay Duddalwar Alexander ShiehAlexander Shieh More articles by this author , Steven CenSteven Cen More articles by this author , Bino VargheseBino Varghese More articles by this author , Darryl HwangDarryl Hwang More articles by this author , Xiaomeng LeiXiaomeng Lei More articles by this author , Kirthika GurumurthyKirthika Gurumurthy More articles by this author , Imran SiddiqiImran Siddiqi More articles by this author , Manju AronManju Aron More articles by this author , Inderbir GillInderbir Gill More articles by this author , W. Dean WallaceW. Dean Wallace More articles by this author , and Vinay DuddalwarVinay Duddalwar More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003295.06AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Understanding individual tumor immune microenvironment (TIME) in clear cell renal cell carcinoma (ccRCC) patients may predict prognosis and response to therapy. However, tissue-based TIME such as multiplex immunohistochemistry (mIHC) may be expensive and inaccessible to patients. In this work, we explore the concept of using radiomic features extracted from computer tomography (CT) imaging to correlate the TIME measurements from mIHC analysis. CT imaging has long been the standard for evaluation of ccRCCs and has the potential to provide dynamic and non-invasive approximations of the tissue-based mIHC biomarkers. METHODS: We targeted two biomarkers that were grounded by clinical outcome research: tumor PD-L1 expression and tumor PD-1+CD8+ to CD8+ T cell ratio. Nephrectomy specimens from 52 patients underwent mIHC staining in this study. Expert pathologists extracted a total of 582 regions of interest (ROIs). Tissue segmentation and cell phenotype identification were performed using the PhenoChart and the inForm software. Overall, more than 1.9 million cells were identified. The tumor on contrast-enhanced CT volumes of these 52 patients were manually segmented, and 1,708 radiomic features representing 13 different texture classes were extracted by our radiomics pipeline. We used Random Forest, AdaBoost and ElasticNet to classify each tumor, represented by the radiomic features, as either expressing high or low levels of these markers on the mIHC slices. RESULTS: The radiomic features can correlate increased tumor epithelium PD-L1 expression > 5% and > 10%, and increased intratumoral CD8+PD1+ to CD8 T cell ratio > 37%. The threshold used were based on prior prognostic clinical studies. The best-performing method AdaBoost achieved AUROC scores of 0.75 (95% CI, 0.58 to 0.93), 0.85 (95% CI, 0.73 to 0.97) and 0.71 (95% CI, 0.56 to 0.87), respectively. Variables of importance analysis showed that gray level co-occurrence matrix (GLCM) features are important for PD-L1 level prediction, and discrete cosine transform (DCT) features are important for PD1+CD8+ to CD8 T cell ratio prediction. CONCLUSIONS: We demonstrated the feasibility of using CT radiomic features to correlate mIHC-based TIME signatures of ccRCC, including increased tumor PD-L1 expression and PD-1+CD8+ T cells. Our study is limited by smaller sample size and a patient population in earlier stages of ccRCC. Future investigation with larger patient population and more diverse immune markers from mIHC data is warranted. Source of Funding: N/A © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e666 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information Alexander Shieh More articles by this author Steven Cen More articles by this author Bino Varghese More articles by this author Darryl Hwang More articles by this author Xiaomeng Lei More articles by this author Kirthika Gurumurthy More articles by this author Imran Siddiqi More articles by this author Manju Aron More articles by this author Inderbir Gill More articles by this author W. Dean Wallace More articles by this author Vinay Duddalwar More articles by this author Expand All Advertisement PDF downloadLoading ...

Hybrid deep-spatio textural feature model for medicinal plant disease classification

The high-pace rise in the demands of medicinal plants towards pharmaceutical significances as well as the different ayurvedic or herbal remedials have forced agro-industries However, rising plant disease cases have limited the cumulative growth and hence both volumetric production as well as quality of medicine. In this paper a first of its kind evolutionary computing driven ROI-specific hybrid deep-spatio temporal textural feature learning model is developed for medicinal plant disease detection (HDST-MPD). To alleviate any possible class-imbalance problem, HDST-MPD model at first applied firefly heuristic driven fuzzy C-means clustering to retrieve ROI-specific RGB regions. Subsequently, to exploit maximum possible deep spatiotemporal textural features, it applied gray-level co-occurrence matrix (GLCM) and AlexNet transferable network. Here, the use of multiple GLCM features helped in exploiting textural feature distribution, while AlexNet deep model yielded high-dimensional features. These deep-spatio temporal textural feature (deep-STTF) features were fused together to yield a composite vector, which was trained over random forest ensemble to perform two-class classification to classify each sample medicinal image as normal or diseased. Depth performance assessment confirmed that the proposed model yields accuracy of 98.97%, precision 99.42%, recall 98.89%, F-measure 99.15%, and equal error rate of 1.03%, signifying its robustness towards real-time medicinal plant disease detection and classification.

Automated diagnosis of Retinopathy of prematurity from retinal images of preterm infants using hybrid deep learning techniques

SignificanceRetinopathy of prematurity (ROP) is a retinal disease in premature infants, which, when left untreated, can cause permanent blindness. Due to high variability and interobserver inconsistency in the diagnosis of ROP, there is a significant need to develop an automated system for the prediction of ROP. Although several methods have been used in automated diagnosis in ROP, no dedicated models have been described with adequate performance. Objectivesi) To develop a hybrid deep learning network for the prediction of ROP that can be used in the mass screening of infants. ii) To compare the performance of the proposed hybrid model with the Machine Learning classifiers and pre-trained CNN model. MethodsThe hybrid network is trained with 3200 and tested with 800 infant fundus images. Modified MultiResUNet and matched filter with first-order Gaussian derivative are used to segment the retinal vessels from the fundus images. The Gray level co-occurrence matrix (GLCM) and contour features of segmented images are extracted and selected using an embedded feature selection method. The selected features are evaluated using permutation importance and classified using the Random Forest classifier. ResultsThe proposed hybrid model predicts ROP with an accuracy of 94.5%, sensitivity of 94%, and specificity of 93%, surpassing the machine learning classifiers and the pre-trained models with reduced parameters and being computationally inexpensive. ConclusionsThe proposed hybrid model improves the quality of infant care by providing additional diagnostic assistance to clinicians. It also enhances the accessibility to remote healthcare centers for large-scale automated screening systems.

Identification of reproducible radiomic features from on-board volumetric images: A multi-institutional phantom study.

Radiomics analysis using on-board volumetric images has attracted research attention as a method for predicting prognosis during treatment; however, the lack of standardization is still one of the main concerns. This study investigated the factors that influence the reproducibility of radiomic features extracted from on-board volumetric images using an anthropomorphic radiomics phantom. Furthermore, a phantom experiment was conducted with different treatment machines from multiple institutions as external validation to identify reproducible radiomic features. The phantom was designed to be 35 × 20 × 20cm with eight types of heterogeneous spheres (⌀=1, 2, and 3cm). On-board volumetric images were acquired using 15 treatment machines from eight institutions. Of these, kilovoltage cone-beam computed tomography (kV-CBCT) image data acquired from four treatment machines at one institution were used as an internal evaluation dataset to explore the reproducibility of radiomic features. The remaining image data, including kV-CBCT, megavoltage-CBCT (MV-CBCT), and megavoltage computed tomography (MV-CT) provided by seven different institutions (11 treatment machines), were used as an external validation dataset. A total of 1,302 radiomic features, including 18 first-order, 75 texture, 465 (i.e., 93 × 5) Laplacian of Gaussian (LoG) filter-based, and 744 (i.e., 93 × 8) wavelet filter-based features, were extracted within the spheres. The intraclass correlation coefficient (ICC) was calculated to explore feature repeatability and reproducibility using an internal evaluation dataset. Subsequently, the coefficient of variation (COV) was calculated to validate the feature variability of external institutions. An absolute ICC exceeding 0.85 or COV under 5% was considered indicative of a highly reproducible feature. For internal evaluation, ICC analysis showed that the median percentage of radiomic features with high repeatability was 95.2%. The ICC analysis indicated that the median percentages of highly reproducible features for inter-tube current, reconstruction algorithm, and treatment machine were decreased by 20.8%, 29.2%, and 33.3%, respectively. For external validation, the COV analysis showed that the median percentage of reproducible features was 31.5%. A total of 16 features, including nine LoG filter-based and seven wavelet filter-based features, were indicated as highly reproducible features. The gray-level run-length matrix (GLRLM) was classified as containing the most frequent features (N=8), followed by the gray-level dependence matrix (N=7) and gray-level co-occurrence matrix (N=1) features. We developed the standard phantom for radiomics analysis of kV-CBCT, MV-CBCT, and MV-CT images. With this phantom, we revealed that the differences in the treatment machine and image reconstruction algorithm reduce the reproducibility of radiomic features from on-board volumetric images. Specifically, the most reproducible features for external validation were LoG or wavelet filter-based GLRLM features. However, the acceptability of the identified features should be examined in advance at each institution before applying the findings to prognosis prediction.

Matching method for mutated veneer sheet images using gray-level co-occurrence matrix features

This paper studies the tracking of wooden veneer sheets by matching their respective wet and dry colour images. The tracking of veneer sheets has proved to be a challenging task due to random mutations during processing in terms of color changes, the emergence of defects, and, occasionally, lost pieces of the veneer surface. The proposed matching procedure involves image segmentation with five different sizes, followed by segment-wise extraction of Gray Level Co-occurrence Matrix (GLCM) textural feature arrays, and their similarity comparisons respectively. A voting mechanism is introduced that allocates the correct match based on the majority. An optional shifting procedure is applied to match candidates with missing areas. The method is demonstrated and benchmarked using a real-world dataset sourced from the industry, comprising 2579 high-quality images of spruce veneer pairs obtained from peeling and drying. In comparison to earlier studies that employed randomized 50 pair sampling on the same dataset, our approach yields a matching accuracy of 99.41%, outperforming the previously reported 84.93%. These findings have relevance for researchers in wood image analytics and carry practical implications for large-scale, automated veneer production facilities seeking innovative ways to optimize their raw material usage.

An Optimum Classifier Model with Fuzzy C-Means for Fire Detection Technology

Flames recognition methodology is most important for completely diminishing the flame losses in different fired environmental conditions. However, there is delayed detection and lower accuracy in the various common detection methods. Thus, optimum image/video fire detection technology is proposed in this paper based on a support vector machine (SVM) with the fuzzy c-mean, discrete wavelet transform (DWT), and gray level co-occurrence matrices (GLCM) feature extraction for the detection of fires. This algorithm has been tested on various fire and non-fire images for classification accuracy. A performance evaluation of the proposed classifier algorithm and existing algorithms is compared, showing that the accuracy and other metrics of the proposed classifier algorithm are higher than other algorithms. Furthermore, simulation results show that the proposed classifier model is improved the forecast detection accuracy of fires.