Gray Level Co-occurrence Matrix Features Research Articles

A Malware Detection Scheme via Smart Memory Forensics for Windows Devices

With the introduction of 4G/5G Internet and the increase in the number of users, the malicious cyberattacks on computing devices have been increased making them vulnerable to external threats. High availability windows servers are designed to ensure delivery of consistent services such as business activities and e-services to their customers without any interruption. At the same time, a cyberattack on any of the clustered computer can put servers and customer devices in danger. A memory dump mechanism can capture the contents of memory in the event of a system or device crash such as corrupted files, damaged hardware, or irregular CPU power consumption. In this paper, we present a smart memory forensics scheme to recognize malicious attacks over high availability servers by capturing the memory dump of suspicious processes in the form of RGB visual images. Second, the local and global properties of malware images are captured using local binary patterns (LBP) and gray-level co-occurrence matrices (GLCM). A state-of-the-art t-distributed stochastic neighbor embedding scheme (t-SNE) is applied to reduce data dimensionality and improve the detection time of unknown malwares and their variants. An optimized CNN model is designed to predict malicious files harming servers or user devices. Throughout this study, we employed public data set of 4294 malicious samples covering malware variants and benign executables. A baseline is prepared to compare the performance of proposed model with state-of-the-art malware detection methods. The combined LBP + GLCM feature extraction along with t-SNE dimensionality reduction scheme further improved the detection accuracy by 98%, whereas the detection time is also increased by 73x. The overall performance shows that memory forensics is more effective for malware detection in terms accuracy and response time.

Optimized textural features for mass classification in digital mammography using a weighted average gravitational search algorithm

Early detection of breast cancer cells can be predicted through a precise feature extraction technique that can produce efficient features. The application of Gabor filters, gray level co-occurrence matrices (GLCM) and other textural feature extraction techniques have proven to achieve promising results but were often characterized by a high false-positive rate (FPR) and false-negative rate (FNR) with high computational complexities. This study optimized textural features for mass classification in digital mammography using the weighted average gravitational search algorithm (WA-GSA). The Gabor and GLCM features were fused and optimized using WA-GSA to overcome the weakness of the textural feature techniques. With support vector machine (SVM) used as the classifier, the proposed algorithm was compared with commonly applied techniques. Experimental results show that the SVM with WA-GSA features achieved FPR, FNR and accuracy of 1.60%, 9.68% and 95.71% at 271.83 s, respectively. Meanwhile, SVM with Gabor features achieved FPR, FNR and accuracy of 3.21%, 12.90% and 93.57% at 2351.29 s, respectively, while SVM with GLCM features achieved FPR, FNR and accuracy of 4.28%, 18.28% and 91.07% at 384.54 s, respectively. The obtained results show the prevalence of the proposed algorithm, WA-GSA, in the classification of breast cancer tumor detection.

Obscurant Segmentation in Long Wave Infrared Images Using GLCM Textures.

The benefits of autonomous image segmentation are readily apparent in many applications and garners interest from stakeholders in many fields. The wide range of benefits encompass applications ranging from medical diagnosis, where the shape of the grouped pixels increases diagnosis accuracy, to autonomous vehicles where the grouping of pixels defines roadways, traffic signs, other vehicles, etc. It even proves beneficial in many phases of machine learning, where the resulting segmentation can be used as inputs to the network or as labels for training. The majority of the available image segmentation algorithmic development and results focus on visible image modalities. Therefore, in this treatment, the authors present the results of a study designed to identify and improve current semantic methods for infrared scene segmentation. Specifically, the goal is to propose a novel approach to provide tile-based segmentation of occlusion clouds in Long Wave Infrared images. This work complements the collection of well-known semantic segmentation algorithms applicable to thermal images but requires a vast dataset to provide accurate performance. We document performance in applications where the distinction between dust cloud tiles and clear tiles enables conditional processing. Therefore, the authors propose a Gray Level Co-Occurrence Matrix (GLCM) based method for infrared image segmentation. The main idea of our approach is that GLCM features are extracted from local tiles in the image and used to train a binary classifier to provide indication of tile occlusions. Our method introduces a new texture analysis scheme that is more suitable for image segmentation than the solitary Gabor segmentation or Markov Random Field (MRF) scheme. Our experimental results show that our algorithm performs well in terms of accuracy and a better inter-region homogeneity than the pixel-based infrared image segmentation algorithms.

Light field quality assessment based on aggregation learning of multiple visual features.

Light field imaging is a way to represent human vision from a computational perspective. It contains more visual information than traditional imaging systems. As a basic problem of light field imaging, light field quality assessment has received extensive attention in recent years. In this study, we explore the characteristics of light field data for different visual domains (spatial, angular, coupled, projection, and depth), study the multiple visual features of a light field, and propose a non-reference light field quality assessment method based on aggregation learning of multiple visual features. The proposed method has four key modules: multi-visual representation of a light field, feature extraction, feature aggregation, and quality assessment. It first extracts the natural scene statistics (NSS) features from the central view image in the spatial domain. It extracts gray-level co-occurrence matrix (GLCM) features both in the angular domain and in the spatial-angular coupled domain. Then, it extracts the rotation-invariant uniform local binary pattern (LBP) features of depth map in the depth domain, and the statistical characteristics of the local entropy (SDLE) features of refocused images in the projection domain. Finally, the multiple visual features are aggregated to form a visual feature vector for the light field. A prediction model is trained by support vector machines (SVM) to establish a light field quality assessment method based on aggregation learning of multiple visual features.

Improving the Land Cover Mapping Accuracy of the Sentinel-2 Imagery on Google Earth Engine

Accurate land cover information is necessary for successful monitoring, planning and management of the land cover features. Thanks to free-access satellite images, studies have focused on the creation of more accurate thematic maps, which have been used as a base data in many applications. The cloud-based Google Earth Engine (GEE) service makes it easier to access, store and process these satellite images. This study aims to improve the accuracy of a land cover map produced with the Sentinel-2 satellite image. For this purpose, as the very first step, study site was classified using only traditional bands of the Sentinel-2 data. To improve the classification accuracy, Sentinel-1 Synthetic Aperture Radar (SAR) data, Advanced Land Observing Satellite (ALOS) World 3D data, various spectral indices and gray-level co-occurrence matrix (GLCM) features were added to the traditional bands of the Sentinel-2 data, leading to a multi-source classification process. In this study, where the city center of Trabzon was selected as the study area, the accuracy of the land cover map produced using the Random Forest (RF) classification algorithm was increased from 83.51% to 92.78% with the auxiliary data used.

Hybrid Techniques for Diagnosis with WSIs for Early Detection of Cervical Cancer Based on Fusion Features

Cervical cancer is a global health problem that threatens the lives of women. Liquid-based cytology (LBC) is one of the most used techniques for diagnosing cervical cancer; converting from vitreous slides to whole-slide images (WSIs) allows images to be evaluated by artificial intelligence techniques. Because of the lack of cytologists and cytology devices, it is major to promote automated systems that receive and diagnose huge amounts of images quickly and accurately, which are useful in hospitals and clinical laboratories. This study aims to extract features in a hybrid method to obtain representative features to achieve promising results. Three proposed approaches have been applied with different methods and materials as follows: The first approach is a hybrid method called VGG-16 with SVM and GoogLeNet with SVM. The second approach is to classify the cervical abnormal cell images by ANN classifier with hybrid features extracted by the VGG-16 and GoogLeNet. A third approach is to classify the images of abnormal cervical cells by an ANN classifier with features extracted by the VGG-16 and GoogLeNet and combine them with hand-crafted features, which are extracted using Fuzzy Color Histogram (FCH), Gray Level Co-occurrence Matrix (GLCM) and Local Binary Pattern (LBP) algorithms. Based on the mixed features of CNN with features of FCH, GLCM, and LBP (hand-crafted), the ANN classifier reached the best results for diagnosing abnormal cells of the cervix. The ANN network achieved with the hybrid features of VGG-16 and hand-crafted an accuracy of 99.4%, specificity of 100%, sensitivity of 99.35%, AUC of 99.89% and precision of 99.42%.

Cloud Computing-Based Framework for Breast Tumor Image Classification Using Fusion of AlexNet and GLCM Texture Features with Ensemble Multi-Kernel Support Vector Machine (MK-SVM).

Breast cancer is common among women all over the world. Early identification of breast cancer lowers death rates. However, it is difficult to determine whether these are cancerous or noncancerous lesions due to their inconsistencies in image appearance. Machine learning techniques are widely employed in imaging analysis as a diagnostic method for breast cancer classification. However, patients cannot take advantage of remote areas as these systems are unavailable on clouds. Thus, breast cancer detection for remote patients is indispensable, which can only be possible through cloud computing. The user is allowed to feed images into the cloud system, which is further investigated through the computer aided diagnosis (CAD) system. Such systems could also be used to track patients, older adults, especially with disabilities, particularly in remote areas of developing countries that do not have medical facilities and paramedic staff. In the proposed CAD system, a fusion of AlexNet architecture and GLCM (gray-level cooccurrence matrix) features are used to extract distinguishable texture features from breast tissues. Finally, to attain higher precision, an ensemble of MK-SVM is used. For testing purposes, the proposed model is applied to the MIAS dataset, a commonly used breast image database, and achieved 96.26% accuracy.

Segmentation algorithm for overlap recognition of seedling lettuce and weeds based on SVM and image blocking

For the problem of a low recognition rate and shape feature failure caused by overlapping seedlings and weeds during the development of an intelligent lettuce weeding robot, a method to identify seedling lettuce and weeds based on an image block and support vector machine (SVM) is proposed, which realizes their precise identification and boundary segmentation. The a* channel is used to grayscale the collected image. The Otsu and morphological methods are selected to extract all the green targets in the image. The connected component analysis method is applied to label the green targets with regions of interest (ROIs), and those with pixel areas larger than the area threshold are normalized to 256 × 256 pixels. The image blocking technique is introduced to separately aliquot the normalized ROI, with block sizes of 16 × 16, 32 × 32, and 64 × 64 pixels. On this basis, the image sub-blocks are manually labeled, block by block, to extract three texture features: histogram of oriented gradient (HOG), local binary pattern (LBP), and gray-level co-occurrence matrix (GLCM). With the accuracy of fivefold cross-validation as the optimization objective, a genetic algorithm (GA) is used to optimize the SVM penalty and kernel parameters of 21 groups of research objects (one block size has three texture features, which are arbitrarily combined to form seven research objects, with a total of three block sizes). We compare the recognition performance of the SVM, RF, KNN, and GA-SVM classifiers in a single feature and a combination of fusion strategies through comparative analysis. When the block size is 32 × 32 pixels, the fusion of LBP and GLCM features under the GA-SVM classifier has the highest accuracy, and the optimal SVM model for the identification of lettuce and weeds in the seedling stage is obtained. For the misidentified image sub-blocks in optimization model recognition, an image block reconstruction method based on the comparison of the center point and eight-neighbor label value is proposed, and this is combined with the proportion of image blocks of two labels for comprehensive judgment. The center point label value is reconstructed to the improve recognition accuracy. Experimental results show that the average precision, recall, and F1 score of the proposed method are 0.9473, 0.9529, and 0.9498, respectively, and those of images without overlapping leaves can all reach 1, thus providing a theoretical basis for crop recognition and segmentation.

Rapid and Accurate Diagnosis of COVID-19 Cases from Chest X-ray Images through an Optimized Features Extraction Approach

The mutants of novel coronavirus (COVID-19 or SARS-Cov-2) are spreading with different variants across the globe, affecting human health and the economy. Rapid detection and providing timely treatment for the COVID-19 infected is the greater challenge. For fast and cost-effective detection, artificial intelligence (AI) can perform a key role in enhancing chest X-ray images and classifying them as infected/non-infected. However, AI needs huge datasets to train and detect the COVID-19 infection, which may impact the overall system speed. Therefore, Deep Neural Network (DNN) is preferred over standard AI models to speed up the classification with a set of features from the datasets. Further, to have accurate feature extraction, an algorithm that combines Zernike Moment Feature (ZMF) and Gray Level Co-occurrence Matrix Feature (GF) is proposed and implemented. The proposed algorithm uses 36 Zernike Moment features with variance and contrast textures. This helps to detect the COVID-19 infection accurately. Finally, the Region Blocking (RB) approach with an optimum sub-image size (32 × 32) is employed to improve the processing speed up to 2.6 times per image. The performance of this implementation presents an accuracy (A) of 93.4%, sensitivity (Se) of 72.4%, specificity (Sp) of 95%, precision (Pr) of 74.9% and F1-score (F1) of 72.3%. These metrics illustrate that the proposed model can identify the COVID-19 infection with a lesser dataset and improved accuracy up to 1.3 times than state-of-the-art existing models.

Tool Wear Monitoring Using Improved Dragonfly Optimization Algorithm and Deep Belief Network

In recent decades, tool wear monitoring has played a crucial role in the improvement of industrial production quality and efficiency. In the machining process, it is important to predict both tool cost and life, and to reduce the equipment downtime. The conventional methods need enormous quantities of human resources and expert skills to achieve precise tool wear information. To automatically identify the tool wear types, deep learning models are extensively used in the existing studies. In this manuscript, a new model is proposed for the effective classification of both serviceable and worn cutting edges. Initially, a dataset is chosen for experimental analysis that includes 254 images of edge profile cutting heads; then, circular Hough transform, canny edge detector, and standard Hough transform are used to segment 577 cutting edge images, where 276 images are disposable and 301 are functional. Furthermore, feature extraction is carried out on the segmented images utilizing Local Binary Pattern (LBPs) and Speeded up Robust Features (SURF), Harris Corner Detection (HCD), Histogram of Oriented Gradients (HOG), and Grey-Level Co-occurrence Matrix (GLCM) feature descriptors for extracting the texture feature vectors. Next, the dimension of the extracted features is reduced by an Improved Dragonfly Optimization Algorithm (IDOA) that lowers the computational complexity and running time of the Deep Belief Network (DBN), while classifying the serviceable and worn cutting edges. The experimental evaluations showed that the IDOA-DBN model attained 98.83% accuracy on the patch configuration of full edge division, which is superior to the existing deep learning models.

Application of Virtual Reality Technology in Adolescent Mental Health Science Education

The 21st century is a time of rapid advances in science and technology, and scientific knowledge and literacy are highly relevant to the development of the country. Science education is the main means of learning scientific and cultural knowledge, and its teaching quality determines the formation of national scientific literacy. In addition, information technology teaching assistants are one of the main research areas in the field of educational technology, and they have long attracted the attention of researchers in the field of education. Based on these facts, this research introduces virtual reality technology into science education to make a favorable influence on the psychological well-being of young people, through color feature extraction, gray-level cooccurrence matrix feature extraction, Marching Cubes algorithm, and image synthesis technology to be scientifically and effectively combined with science education, and the popularization rate of students receiving science education has increased by 26.9%. As a result, the mental health of students was improved, and the number of students with subhealth mentality decreased by 16.9%. Adolescence is a transitional period for adolescents from immaturity to maturity. Adolescents are prone to fall into depression, anxiety, rebellion, autism, and other emotions, which will have a damaging impact on the growth of adolescents’ mental health. The use of virtual reality technology in science education has opened up a new field of virtual teaching and learning. This pattern of education will make a huge influence on the future growth of education and the creation of teaching concepts.

Identification of Acne Vulgaris Type in Facial Acne Images Using GLCM Feature Extraction and Extreme Learning Machine Algorithm

Acne vulgaris or acne is a common inflammatory pilosebaceous condition that affects up to 90% of teenagers, begins during adolescent years, and often persists into adulthood. Acne vulgaris, especially on the face, has a major impact on the emotional, social and psychological health of patients. In treating acne, it is necessary to identify the exact type of acne. The manual method is considered less effective, so it is proposed an automatic method using a computer, which uses image processing techniques. This research was conducted to identify the types of acne on facial acne images. The methods used are K-Means Clustering for segmentation, Gray Level Co-occurrence Matrix (GLCM) for feature extraction, and Extreme Learning Machine (ELM) for classification. The dataset is 100 images and consists of 3 classes, namely Nodules, Papules and Pustules. Testing is done in two stages, namely testing 2 classes (Nodules and Papules), followed by testing 3 classes (Nodules, Papules and Pustules). Testing of 2 classes produces the highest accuracy of 95,24% and testing of 3 classes produces the highest accuracy of 80%.

Feature Ranking Importance from Multimodal Radiomic Texture Features using Machine Learning Paradigm: A Biomarker to Predict the Lung Cancer

The machine learning based techniques for detection of lungs cancer can assist the clinicians in assessing the risk of pulmonary nodules being malignant. We are developing non-invasive methods to accurately distinguish the non-small cell cancer carcinoma (NSCLC) from small cell cancer carcinoma (SCLC) brain metastases. In this study, we extracted multimodal radiomic features including texture and statistical Haralick texture, gray level co-occurrence matrix (GLCM) features, Gray level size-zone matrix (GLSZM) features, Gray-level run-length matrix (GLRLM) features. We also applied image enhancement contrast stretching and gamma correction to further improve the classification performance. We then ranked these features in order to investigate that which features category is more important to accurately distinguish the lung cancer subtypes. We employed robust machine learning techniques. We evaluated the performance based on top ranked 03 and 05 features and last ranked 05 and 02 features based on the receiver operating curve (ROC). The highest classification performance in terms of accuracy and AUC was obtained with all Haralick texture features using SVM polynomial with accuracy (99.89%) and AUC (0.9984). The classification performance with contrast stretching [0.02, 0.08; 0.05, 0.95] and gamma correction with gamma = 0.5 yielded highest accuracy of 100% and AUC of 1.00. The top three ranked features using image enhancement methods also yielded accuracy more than 95% which indicates that these top ranked features contributed higher in accuracy classifying the lung cancer subtypes. The results revealed that proposed model with multimodal features, image enhancement techniques and features ranking methods improved the classification performance which can be used for better diagnostic aid to improve the decision making to treat the patients suffering from SCLC and NSCLC.

SCDC-Net: Skin Cancer Detection and Classification using Deep Q Neural Network with Hybrid Features

Skin cancer is one of the most severe malignancies that may affect individuals of all ages. It can affect people of all races and ethnicities. Thus, early detection and treatment of skin cancer have the potential to save millions of lives. Because of the high degree of similarity between skin lesions, conventional machine learning approaches failed to provide the highest possible detection and classification accuracy in the skin cancer detection and classification (SCDC) system. To achieve the robust performance, this work is presented a SCDC-Net by employing deep learning, transfer learning models with hybrid features. Initially, UG-Net based transfer learning model is developed by combining generative adversarial networks (GAN) and U-Net. Here, UG-Net is used to remove hair from skin lesions and also preprocess enhances lesion. In addition, Hybrid U-Net (HU-Net) is used to localize the disease effected area of skin cancer. Further, various hybrid features are extracted from the segmented output by employing the gray-level cooccurrence matrix (GLCM) based texture characteristics, the discrete wavelet transform (DWT)-based low-level features, and the computation of image statistics for the texture, low-level, and colour features, respectively. In order to ensure the highest possible performance of the system, a deep q neural network (DQNN) was constructed for the classification of skin cancer using GLCM, DWT, and statistical colour features. The simulation results shows that the proposed method resulted in superior subjective and objective performance as compared to state of art approaches on ISIC-2019 public challenge dataset.

The impact of inter-observer variation in delineation on robustness of radiomics features in non-small cell lung cancer

Artificial intelligence and radiomics have the potential to revolutionise cancer prognostication and personalised treatment. Manual outlining of the tumour volume for extraction of radiomics features (RF) is a subjective process. This study investigates robustness of RF to inter-observer variation (IOV) in contouring in lung cancer. We utilised two public imaging datasets: ‘NSCLC-Radiomics’ and ‘NSCLC-Radiomics-Interobserver1’ (‘Interobserver’). For ‘NSCLC-Radiomics’, we created an additional set of manual contours for 92 patients, and for ‘Interobserver’, there were five manual and five semi-automated contours available for 20 patients. Dice coefficients (DC) were calculated for contours. 1113 RF were extracted including shape, first order and texture features. Intraclass correlation coefficient (ICC) was computed to assess robustness of RF to IOV. Cox regression analysis for overall survival (OS) was performed with a previously published radiomics signature. The median DC ranged from 0.81 (‘NSCLC-Radiomics’) to 0.85 (‘Interobserver’—semi-automated). The median ICC for the ‘NSCLC-Radiomics’, ‘Interobserver’ (manual) and ‘Interobserver’ (semi-automated) were 0.90, 0.88 and 0.93 respectively. The ICC varied by feature type and was lower for first order and gray level co-occurrence matrix (GLCM) features. Shape features had a lower median ICC in the ‘NSCLC-Radiomics’ dataset compared to the ‘Interobserver’ dataset. Survival analysis showed similar separation of curves for three of four RF apart from ‘original_shape_Compactness2’, a feature with low ICC (0.61). The majority of RF are robust to IOV, with first order, GLCM and shape features being the least robust. Semi-automated contouring improves feature stability. Decreased robustness of a feature is significant as it may impact upon the features’ prognostic capability.

Breast Cancer Histopathological Image Recognition Based on Pyramid Gray Level Co-Occurrence Matrix and Incremental Broad Learning

In order to recognize breast cancer histopathological images, this article proposed a combined model consisting of a pyramid gray level co-occurrence matrix (PGLCM) feature extraction model and an incremental broad learning (IBL) classification model. The PGLCM model is designed to extract the fusion features of breast cancer histopathological images, which can reflect the multiresolution useful information of the images and facilitate the improvement of the classification effect in the later stage. The IBL model is used to improve the classification accuracy by increasing the number of network enhancement nodes horizontally. Unlike deep neural networks, the IBL model compresses the training and testing time cost greatly by making full use of its single-hidden-layer structure. To our knowledge, it is the first attempt for the IBL model to be introduced into the breast cancer histopathological image recognition task. The experimental results in four magnifications of the BreaKHis dataset show that the accuracy of binary classification and eight-class classification outperforms the existing algorithms. The accuracy of binary classification reaches 91.45%, 90.17%, 90.90% and 90.73%, indicating the effectiveness of the established combined model and demonstrating the advantages in breast cancer histopathological image recognition.

Clustering based lung lobe segmentation and optimization based lung cancer classification using CT images

A serious condition with a high death and morbidity rate worldwide is lung cancer. To increase the likelihood that a person will survive, early diagnosis is urgently required. Various existing approaches are modeled to detect lung cancer, but low visibility of tumor region and the negative rates of images still result a complex task to recognize infected regions. Also, the traditional methods failed to enhance the accuracy of the lung cancer classification. Hence, this research developed a method named Shuffled Social Sky Optimizer-based Multi-Object Rectified Attention Network (SSSO-based MORAN) to effectively classify lung cancer disease. The proposed SSSO algorithm is the integration of the Shuffled Shepherd Optimization Algorithm (SSOA) and social ski-driver (SSD) algorithm, respectively. The input computed tomography (CT) image is supplied to the pre-processing phase, where the Gaussian filtering is employed to pre-process the image, and thereby the Region of Interest (ROI) is acquired from the input image. Then, the lung lobes are segmented using the proposed Deep Renyi entropy fuzzy clustering (DREFC). With the segmented lung lobes, the nodule region is identified from the lung image, and the process of cancer classification is done based on features. The features considered for the lung cancer classification are Local Gabor XOR Pattern (LGXP), Gray-Level Co-occurrence Matrix (GLCM) features, Global Binary Pattern (GBP), Tetrolet transform, and statistical features. The proposed algorithm effectively showed higher performance of accuracy, Mean Absolute Error (MAE), sensitivity, and specificity of 0.896, 0.104, 0.8969, and 0.845, respectively.

A Machine Vision Approach for Classification of Skin Cancer Using Hybrid Texture Features.

The main purpose of this study is to observe the importance of machine vision (MV) approach for the identification of five types of skin cancers, namely, actinic-keratosis, benign, solar-lentigo, malignant, and nevus. The 1000 (200 × 5) benchmark image datasets of skin cancers are collected from the International Skin Imaging Collaboration (ISIC). The acquired ISIC image datasets were transformed into texture feature dataset that was a combination of first-order histogram and gray level co-occurrence matrix (GLCM) features. For the skin cancer image, a total of 137,400 (229 × 3 x 200) texture features were acquired on three nonover-lapping regions of interest (ROIs). Principal component analysis (PCA) clustering approach was employed for reducing the dimension of feature dataset. Each image acquired twenty most discriminate features based on two different approaches of statistical features such as average correlation coefficient plus probability of error (ACC + POE) and Fisher (Fis). Furthermore, a correlation-based feature selection (CFS) approach was employed for feature reduction, and optimized 12 features were acquired. Furthermore, a classification algorithm naive bayes (NB), Bayes Net (BN), LMT Tree, and multilayer perception (MLP) using 10 K-fold cross-validation approach were employed on optimized feature datasets and the overall accuracy achieved by MLP is 97.1333%.

Deep and Hybrid Learning Technique for Early Detection of Tuberculosis Based on X-ray Images Using Feature Fusion

Tuberculosis (TB) is a fatal disease in developing countries, with the infection spreading through direct contact or the air. Despite its seriousness, the early detection of tuberculosis by means of reliable techniques can save the patients’ lives. A chest X-ray is a recommended screening technique for locating pulmonary abnormalities. However, analyzing the X-ray images to detect abnormalities requires highly experienced radiologists. Therefore, artificial intelligence techniques come into play to help radiologists to perform an accurate diagnosis at the early stages of TB disease. Hence, this study focuses on applying two AI techniques, CNN and ANN. Furthermore, this study proposes two different approaches with two systems each to diagnose tuberculosis from two datasets. The first approach hybridizes two CNN models, which are Res-Net-50 and GoogLeNet techniques. Prior to the classification stage, the approach applies the principal component analysis (PCA) algorithm to reduce the features’ dimensionality, aiming to extract the deep features. Then, the SVM algorithm is used for classifying features with high accuracy. This hybrid approach achieved superior results in diagnosing tuberculosis based on X-ray images from both datasets. In contrast, the second approach applies artificial neural networks (ANN) based on the fused features extracted by ResNet-50 and GoogleNet models and combines them with the features extracted by the gray level co-occurrence matrix (GLCM), discrete wavelet transform (DWT) and local binary pattern (LBP) algorithms. ANN achieved superior results for the two tuberculosis datasets. When using the first dataset, the ANN, with ResNet-50, GLCM, DWT and LBP features, achieved an accuracy of 99.2%, a sensitivity of 99.23%, a specificity of 99.41%, and an AUC of 99.78%. Meanwhile, with the second dataset, ANN, with the features of ResNet-50, GLCM, DWT and LBP, reached an accuracy of 99.8%, a sensitivity of 99.54%, a specificity of 99.68%, and an AUC of 99.82%. Thus, the proposed methods help doctors and radiologists to diagnose tuberculosis early and increase chances of survival.

Detection of liver abnormalities—A new paradigm in medical image processing and classification techniques

AbstractThe liver is the body's most essential organ, and all human activities are interrelated with normal liver function. Any malfunction of the liver may lead to fatal diseases; therefore, early detection of liver abnormalities is essential. Modern medical imaging techniques combined with engineering procedures are reducing human suffering caused by liver disease. This study uses multiple classifiers to detect liver cirrhosis in ultrasonic images. The ultrasound images were obtained from The Cancer Imaging Archive database. A gray‐level co‐occurrence matrix (GLCM) and statistical approaches are used to extract features from normal and liver‐cirrhosis images. The extracted GLCM features are normalized and classified using nonlinear regression, linear regression, logistic regression, Bayesian Linear Discriminant Classifiers (BLDC), Gaussian Mixture Model (GMM), Firefly, Cuckoo search, Particle Swarm Optimization (PSO), Elephant search, Dragon Fly, Firefly GMM, Cuckoo search GMM, PSO GMM, Elephant search GMM, and Dragon Fly GMM classifiers. Benchmark metrics, such as sensitivity, specificity, accuracy, precision, negative predictive value, false‐negative rate, balanced accuracy, F1 score, Mathew correlation coefficient, F measure, error rate, Jaccard metric, and classifier success index, are assessed to identify the best‐performing classifier. The GMM classifier outperformed other classifiers for statistical features, and it achieved the highest accuracy (98.39%) and lowest error rate (1.61%). Moreover, the Dragon Fly GMM classifier achieved 90.69% for the GLCM feature used to classify liver cirrhosis.