Search

Modern security faces challenges in detecting unauthorized and potentially harmful items in luggage, despite X-ray baggage scanning frameworks and research on efficiently screening highly disguised items. In response to this gap, a groundbreaking Modified Encoder-Decoder-based model has been introduced. This innovative model takes X-ray scan images as input and generates distinct feature representations for both suspicious and non-suspicious baggage materials. A key focus of the model is to address the denoising challenge inherent in X-ray images which reduces the models efficiency. This is achieved through the implementation of a Poisson Noise Reduction method during the preprocessing stage. Following preprocessing, the model effectively segments the non-threat image, identifying potential threats from the denoised input. The model showcases superior performance, as evidenced by high Peak Signal-to-Noise Ratio (PSNR) and low Mean Squared Error (MSE) values, outperforming existing filtering techniques. Rigorous testing on publicly available SIXray and GDXray datasets validates the effectiveness of the proposed methodology. Performance metrics for the SIXray dataset, including mAP, IoU, and DC values of 97.32%, 73.14%, and 85.12%, respectively, underscore the model's efficacy. Notably, the framework attains an impressive accuracy of 99.17% on the SIXray dataset, affirming its robustness in addressing contemporary security challenges. [ABSTRACT FROM AUTHOR]

Coronavirus 2019 causes COVID-19, a worldwide epidemic. It endangers millions globally. Early illness detection improves recovery and control. X-ray image processing is used to categorise and identify COVID-19 in the present study. Preprocessing, feature extraction using local binary pattern (LBP) and edge orient histogram (EOH), and classification utilising K-nearest neighbour (KNN), Navie Bayes, support vector machine (SVM), and transfer learning convolution neural networks (CNNs) are some of the stages that are implemented in the process. Other phases in the process include preprocessing, feature extraction, and preprocessing. LBP+KNN, EOH+KNN, LBP+SVM, EOH +SVM, CNN+LBP, and CNN+EOH are the outputs derived from the combinations of feature extraction operators and classifiers. Other possible outcomes are CNN+EOH and CNN+LBP. A total of 4,000 pictures were used as the basis for conducting an analysis of the performance of six different models. In order to train the models, 10-fold cross-validation was used, and their accuracy was measured accordingly. The evaluation results indicate a high level of accuracy in diagnosis, ranging from 90.2% to 97.56%. The CNN+LBP and CNN+EOH models have demonstrated superior performance compared to other models, achieving average accuracies ranging from 96.66% and 98.54%.. [ABSTRACT FROM AUTHOR]

Coronavirus disease 2019, i.e., COVID-19, an emerging contagious disease with human-to-human transmission, first appeared at the end of year 2019. The sudden demand for disease diagnostic kits prompted researchers to shift their focus toward developing solutions that could assist in identifying COVID-19 using available resources. Therefore, it is imperative to develop a high-accuracy system that makes use of Artificial Intelligence and its tools considering its contribution to computer vision. The time consumed to diagnose test outcomes is to be taken care of as a crucial aspect of an efficient model. To address the global challenges faced by the COVID-19 pandemic, this study proposed two deep learning models developed for automatic COVID-19 detection and distinguish it from pneumonia, another common lung disease. The proposed designs implement layered convolutional neural networks and are trained on a data set of 1824 chest X-rays for binary classification (COVID-19 and normal) and 2736 chest X-rays for ternary classification (COVID-19, normal, and pneumonia). The input images and hyper-parameters in the convolution layers are fine-tuned during the model training phase. The observations show that the proposed models have achieved a better performance as compared to their earlier contemporaries' approaches, resulting in accuracy, precision, recall, and F-score of 98.91%, 98.5%, 98.5%, and 99% for binary-class and 95.99%, 96.3%, 96%, and 96.33% for ternary-class classifiers, respectively. The presented architectures have been built from scratch, thus with the implemented convolutional layered architecture, they were successful in providing more efficient and early diagnosis of the disease. [ABSTRACT FROM AUTHOR]

This study proposes a new deep-learning approach incorporating a superfluity mechanism to categorize knee X-ray images into osteoporosis, osteopenia, and normal classes. The superfluity mechanism suggests the use of two distinct types of blocks. The rationale is that, unlike a conventional serially stacked layer, the superfluity concept involves concatenating multiple layers, enabling features to flow into two branches rather than a single branch. Two knee datasets have been utilized for training, validating, and testing the proposed model. We use transfer learning with two pre-trained models, AlexNet and ResNet50, comparing the results with those of the proposed model. The results indicate that the performance of the pre-trained models, namely AlexNet and ResNet50, was inferior to that of the proposed Superfluity DL architecture. The Superfluity DL model demonstrated the highest accuracy (85.42% for dataset1 and 79.39% for dataset2) among all the pre-trained models. [ABSTRACT FROM AUTHOR]

Abstract This study proposes a new deep-learning approach incorporating a superfluity mechanism to categorize knee X-ray images into osteoporosis, osteopenia, and normal classes. The superfluity mechanism suggests the use of two distinct types of blocks. The rationale is that, unlike a conventional serially stacked layer, the superfluity concept involves concatenating multiple layers, enabling features to flow into two branches rather than a single branch. Two knee datasets have been utilized for training, validating, and testing the proposed model. We use transfer learning with two pre-trained models, AlexNet and ResNet50, comparing the results with those of the proposed model. The results indicate that the performance of the pre-trained models, namely AlexNet and ResNet50, was inferior to that of the proposed Superfluity DL architecture. The Superfluity DL model demonstrated the highest accuracy (85.42% for dataset1 and 79.39% for dataset2) among all the pre-trained models.

Abstract The morphological characteristics of the foot arch and the plantar soft tissue thickness are pivotal in assessing foot health, which is associated with various foot and ankle pathologies. By applying deep learning image segmentation techniques to lateral weight-bearing X-ray images, this study investigates the correlation between foot arch morphology (FAM) and plantar soft tissue thickness (PSTT), examining influences of age and sex. Specifically, we use the DeepLab V3+ network model to accurately delineate the boundaries of the first metatarsal, talus, calcaneus, navicular bones, and overall foot, enabling rapid and automated measurements of FAM and PSTT. A retrospective dataset containing 1497 X-ray images is analyzed to explore associations between FAM, PSTT, and various demographic factors. Our findings contribute novel insights into foot morphology, offering robust tools for clinical assessments and interventions. The enhanced detection and diagnostic capabilities provided by precise data support facilitate population-based studies and the leveraging of big data in clinical settings.

COVID-19 detection using chest X-rays (CXR) has evolved as a significant method for early diagnosis of the pandemic disease. Clinical trials and methods utilize X-ray images with computer and intelligent algorithms to improve detection and classification precision. This article thus proposes a fuzzy-based adaptive convolution neural network (FACNN) model to improve the detection precision by confining the false rates. The feature extraction process between the successive regions is validated using a fuzzy process that classifies labeled and unknown pixels. The membership functions are derived based on high precision features for detection and false rate suppression process. The convolution neural network process is responsible for increasing detection precision through recurrent training based on feature availability. This availability analysis is verified using fuzzy derivatives under local variances. Based on variance-reduced features, the appropriate regions with labeled and unknown features are used for normal or infected classification. Thus, the proposed FACNN improves accuracy, precision, and feature extraction by 14.36%, 8.74%, and 12.35%, respectively. This model reduces the false rate and extraction time by 10.35% and 10.66%, respectively. [ABSTRACT FROM AUTHOR]

X-ray security images face significant challenges due to complex backgrounds, item overlap, and multi-scale target detection. Traditional methods often struggle to accurately identify objects, especially under cluttered conditions. This paper presents an advanced detection model, called YOLOv8n-GEMA, which incorporates several enhancements to address these issues. Firstly, the generalized efficient layer aggregation network (GELAN) module is employed to augment the feature fusion capabilities. Secondly, to tackle the problems of overlap and occlusion in X-ray images, the efficient multi-scale attention (EMA) module is utilized, effectively managing the feature capture and interdependencies among overlapping items, thereby boosting the model's detection capability in such scenarios. Lastly, addressing the diverse sizes of items in X-ray images, the Inner-CIoU loss function uses auxiliary bounding boxes at varying scale ratios for loss calculation, ensuring faster and more effective bounding box predictions. The enhanced YOLOv8 model was tested on the public datasets SIXRay, HiXray, CLCXray, and PIDray, where the improved model's mean average precision (mAP) reached 94.4%, 82.0%, 88.9%, and 85.9%, respectively, showing improvements of 3.6%, 1.6%, 0.9%, and 3.4% over the original YOLOv8. These results demonstrate the effectiveness and universality of the proposed method. Compared to current mainstream X-ray images of dangerous goods detection models, this model significantly reduces the false detection rate of dangerous goods in X-ray security images and achieves substantial improvements in the detection of overlapping and multi-scale targets, realizing higher accuracy in dangerous goods detection. [ABSTRACT FROM AUTHOR]

Aiming at the problems of low contrast, low detection accuracy and easy to miss detection and error detection of X-ray security image color in contraband detection task, based on Faster R-CNN algorithm, K-means clustering algorithm is used to improve the generation method of Anchor. It is proposed to introduce the efficient channel attention mechanism (ECANet) into the ROI pooling layer to highlight the contour, color and other information of contraband. The mAP of the proposed algorithm on the S_DXray dataset reaches 92.06%, and the detection accuracy of the improved network model is improved by 5.06 percentage points. It effectively improves the accuracy of X-ray image contraband detection and the detection ability of small-scale targets, and effectively avoids the phenomenon of false detection and missed detection. [ABSTRACT FROM AUTHOR]

Tuberculosis (TB), a major global health threat caused by mycobacterium tuberculosis, claims lives across all age groups, underscoring the urgent need for accurate diagnostic methods. Traditional TB diagnosis using X-ray images faces challenges in detection accuracy, highlighting a critical problem in medical imaging. Addressing this, our study investigates the use of image processing techniques-specifically, a dataset of 112 TB X-ray images-employing pre-processing, segmentation, edge detection, and feature extraction methods. Central to our method is the adoption of a modified Sobel edge detection technique, named modification and extended magnitude gradient (MEMG), designed to enhance TB identification from X-ray images. The effectiveness of MEMG is rigorously evaluated against the gray-level co-occurrence matrix (GLCM) parameters, contrast, and correlation, where it demonstrably surpasses the standard Sobel detection, amplifying the contrast value by over 50% and achieving a correlation value nearing 1. Consequently, the MEMG method significantly improves the clarity and detail of TB-related anomalies in X-ray images, facilitating more precise TB detection. This study concludes that leveraging the MEMG technique in TB diagnosis presents a substantial advancement over conventional methods, promising a more reliable tool for combating this global health menace. [ABSTRACT FROM AUTHOR]

Visual inspection of defective tires post-production is vital for human safety, as faulty tires can lead to explosions, accidents, and loss of life. With the advancement of technology, transfer learning (TL) plays an influential role in many computer vision applications, including the tire defect detection problem. However, automatic tire defect detection is difficult for two reasons. The first is the presence of complex anisotropic multi-textured rubber layers. Second, there is no standard tire X-ray image dataset to use for defect detection. In this study, a TL-based tire defect detection model is proposed using a new dataset from a global tire company. First, we collected and labeled the dataset consisting of 3366 X-ray images of faulty tires and 20,000 images of qualified tires. Although the dataset covers 15 types of defects arising from different design patterns, our primary focus is on binary classification to detect the presence or absence of defects. This challenging dataset was split into 70, 15, and 15% for training, validation, and testing, respectively. Then, nine common pre-trained models were fine-tuned, trained, and tested on the proposed dataset. These models are Xception, InceptionV3, VGG16, VGG19, ResNet50, ResNet152V2, DenseNet121, InceptionResNetV2, and MobileNetV2. The results show that the fine-tuned VGG19, DenseNet21 and InceptionNet models achieve compatible results with the literature. Moreover, the Xception model outperformed the compared TL models and literature methods in terms of recall, precision, accuracy, and F1 score. Moreover, it achieved on the testing dataset 73.7, 88, 80.2, and 94.75% of recall, precision, F1 score, and accuracy, respectively, and on the validation dataset 73.3, 90.24, 80.9, and 95% of recall, precision, F1 score, and accuracy, respectively. [ABSTRACT FROM AUTHOR]

BACKGROUND: Recently, X-rays have been widely used to detect complex structural workpieces. Due to the uneven thickness of the workpiece and the high dynamic range of the X-ray image itself, the detailed internal structure of the workpiece cannot be clearly displayed. OBJECTIVE: To solve this problem, we propose an image enhancement algorithm based on a multi-scale local edge-preserving filter. METHODS: Firstly, the global brightness of the image is enhanced through logarithmic transformation. Then, to enhance the local contrast, we propose utilizing the gradient decay function based on fuzzy entropy to process the gradient and then incorporate the gradient into the energy function of the local edge-preserving filter (LEP) as a constraint term. Finally, multiple base layers and detail layers are obtained through filtering multi-scale decomposition. All detail layers are enhanced and fused using S-curve mapping to improve contrast further. RESULTS: This method is competitive in both quantitative indices and visual perception quality. CONCLUSIONS: The experimental results demonstrate that the proposed method significantly enhances various complex workpieces and is highly efficient. [ABSTRACT FROM AUTHOR]

In the domain of clinical imaging, the exact and quick identification proof of bone fractures plays a crucial part in a pivotal role in facilitating timely and effective patient care. This research tends to this basic need by harnessing the force of profound learning, explicitly utilizing a convolutional neural network (CNN) model as the foundation of our technique. The essential target of our study was to improve the mechanized recognition of bone fractures in X-ray images, utilizing the capacities of deep learning algorithms. The use of a CNN model permitted us to successfully capture and learn intricate patterns and features within the X-ray images, empowering the framework to make exact fracture detections. The training process included presenting the model to a various dataset, guaranteeing its versatility to an extensive variety of fracture types. The results of our research show the excellent performance of the CNN model in fracture detection, where our model has achieved an average precision of 89.5%, an average recall of 87%, and an overall accuracy of 91%. These metrics assert the vigour of our methodology and highlight the capability of deep learning in medical image analysis. [ABSTRACT FROM AUTHOR]

Since the unexpected upsurge of the severe acute respiratory syndrome coronavirus 2 (COVID-19) in 2019, it has rapidly spread all over the world. This viral pandemic has dramatically affected human health and daily life. Recent advances in artificial intelligence (AI) techniques are considered key enablers to expediting COVID-19 detection issues. In particular, the development of high-performance deep learning (DL) models with high levels of accuracy is a significant step towards a fast and high-precision method for the detection and diagnosis of COVID-19 infected patients. This paper proposes a convolutional neural network (CNN) model for the classification of COVID-19 positive infected and negative/normal patients. This model is applied to a dataset consisting of 3,000 chest X-ray images in 2 classes of diagnoses– COVID-19 and normal. The CNN is implemented via a Keras framework with a hyperparameter tuning technique, and a data augmentation technique is performed to achieve the best accuracy. Experimentally, the confusion matrix, precision-recall curve, and receiver operating characteristic curve (ROCC) are utilized to analyze the performance of the CNN model. Experimental results demonstrate that the CNN provides a high-performance classification of COVID-19 patients with a testing accuracy of 99% and a testing loss rate of 0.034. The Precision, Recall, F1-score, and the area under the ROCC for this model are 99.02%, 98.97%, 99%, and 100%, respectively. This model applied to X-ray images provides a quick and accurate approach to distinguishing between normal negative cases and COVID-19 infected patients, and should aid doctors and radiologists in the screening of COVID-19 patients. [ABSTRACT FROM AUTHOR]

X-ray images typically contain complex background information and abundant small objects, posing significant challenges for object detection in security tasks. Most existing object detection methods rely on complex networks and high computational costs, which poses a challenge to implement lightweight models. This article proposes Fine-YOLO to achieve rapid and accurate detection in the security domain. First, a low-parameter feature aggregation (LPFA) structure is designed for the backbone feature network of YOLOv7 to enhance its ability to learn more information with a lighter structure. Second, a high-density feature aggregation (HDFA) structure is proposed to solve the problem of loss of local details and deep location information caused by the necked feature fusion network in YOLOv7-Tiny-SiLU, connecting cross-level features through max-pooling. Third, the Normalized Wasserstein Distance (NWD) method is employed to alleviate the convergence complexity resulting from the extreme sensitivity of bounding box regression to small objects. The proposed Fine-YOLO model is evaluated on the EDS dataset, achieving a detection accuracy of 58.3% with only 16.1 M parameters. In addition, an auxiliary validation is performed on the NEU-DET dataset, the detection accuracy reaches 73.1%. Experimental results show that Fine-YOLO is not only suitable for security, but can also be extended to other inspection areas. [ABSTRACT FROM AUTHOR]

Bone age assessment is used to diagnose paediatric growth because some types of bone diseases occur in childhood. To overcome these issues, AlexNet-Based Deep Convolutional Neural Network Optimized with the Group Teaching Optimization Algorithm is proposed. First, input images are gathered via RSNA paediatric bone age dataset. These images are preprocessed using Wavelet Packet Transform Cochlear Filter Bank. Then input hand X-ray images' ROI is segmented using Bayesian fuzzy clustering. Then segmented ROI region is fed to ADCNN that accurately predicts BAA. In general, ADCNN does not divulge any optimization techniques adopted for determining the optimal parameters and ensuring accurate classification. Therefore, the GTOA is used to optimize the ADCNN weight parameters. The proposed approach is done in MATLAB and various performance metrics such as accuracy, F-score, sensitivity, precision, specificity, CCC and CC. The BAA-ADCNN-GTOA method provides higher accuracy 23.75%, 17.97%, 31.65% compared with existing methods, like BAA-CNN-RRNN, BAA-RNN-AF-SFO, BAA-U-Net-CTO- WOA, respectively. [ABSTRACT FROM AUTHOR]

BACKGROUND: COVID-19 needs to be diagnosed and staged to be treated accurately. However, prior studies' diagnostic and staging abilities for COVID-19 infection needed to be improved. Therefore, new deep learning-based approaches are required to aid radiologists in detecting and quantifying COVID-19-related lung infections. OBJECTIVE: To develop deep learning-based models to classify and quantify COVID-19-related lung infections. METHODS: Initially, Dual Decoder Attention-based Semantic Segmentation Networks (DDA-SSNets) such as Dual Decoder Attention-UNet (DDA-UNet) and Dual Decoder Attention-SegNet (DDA-SegNet) are proposed to facilitate the dual segmentation tasks such as lung lobes and infection segmentation in chest X-ray (CXR) images. The lung lobe and infection segmentations are mapped to grade the severity of COVID-19 infection in both the lungs of CXRs. Later, a Genetic algorithm-based Deep Convolutional Neural Network classifier with the optimum number of layers, namely GADCNet, is proposed to classify the extracted regions of interest (ROI) from the CXR lung lobes into COVID-19 and non-COVID-19. RESULTS: The DDA-SegNet shows better segmentation with an average BCSSDC of 99.53% and 99.97% for lung lobes and infection segmentations, respectively, compared with DDA-UNet with an average BCSSDC of 99.14% and 99.92%. The proposed DDA-SegNet with GADCNet classifier offered excellent classification results with an average BCCAC of 99.98%, followed by the GADCNet with DDA-UNet with an average BCCAC of 99.92% after extensive testing and analysis. CONCLUSIONS: The results show that the proposed DDA-SegNet has superior performance in the segmentation of lung lobes and COVID-19-infected regions in CXRs, along with improved severity grading compared to the DDA-UNet and improved accuracy of the GADCNet classifier in classifying the CXRs into COVID-19, and non-COVID-19. [ABSTRACT FROM AUTHOR]

Pneumonia is a disease that causes high mortality worldwide in children and adults. Pneumonia is caused by swelling of the lungs, and to ensure that the lungs are swollen, a chest X-ray can be done. The doctor will then analyze the X-ray results. However, doctors sometimes have difficulty confirming pneumonia from the results of chest X-ray observations. Therefore, we propose the combination of SMOTE and several CNN architectures be implemented in a chest X-ray imagebased pneumonia detection system to help the process of diagnosing pneumonia quickly and accurately. The chest X-ray data used in this study were obtained from the Kermany dataset (5216 images). Several stages of pre-processing (grayscaling and normalization) and data augmentation (shifting, zooming, and adjusting the brightness) are carried out before deep learning is carried out. It ensures that the input data for deep learning is not mixed with noise and is according to needs. Then, the output data from the augmentation results are used as input for several CNN deep learning architectures. The augmented data will also utilize SMOTE to overcome data class disparities before entering the CNN algorithm. Based on the test results, the VGG16 architecture shows the best level of performance compared to other architectures. In system testing using SMOTE+CNN Architectures (VGG16, VGG19, Xception, Inception-ResNet v2, and DenseNet 201), the optimum accuracy level reached 93.75%, 89.10%, 91.67%, 86.54% and 91.99% respectively. SMOTE provides a performance increase of up to 4% for all CNN architectures used in predicting pneumonia. [ABSTRACT FROM AUTHOR]

In response to the problems of complex background, multi-scale dangerous goods and severe stacking in X-ray security images, this paper proposes a high-accuracy dangerous goods detection algorithm for X-ray security images based on the improvement of YOLOv7. Firstly, by combining the coordinate attention mechanism, the downsampling structure of the backbone network is improved to enhance the model's target feature localization ability. Secondly, a weighted bidirectional feature pyramid network is used as the feature fusion structure to achieve multi-scale feature weighted fusion and further simplify the network. Then, combined with dynamic snake convolution, a downsampling structure was designed to facilitate the extraction of features at different scales, providing richer feature representations. Finally, drawing inspiration from the idea of group convolution and combining it with Conv2Former, a feature extraction module called a multi-convolution transformer (MCT) was designed to enhance the network's feature extraction ability by combining multi-scale information. The improved YOLOv7 in this article was tested on the public datasets SIXRay, CLCXray, and PIDray. The average detection accuracy (mAP) of the improved model was 96.3%, 79.3%, and 84.7%, respectively, which was 4.7%, 2.7%, and 3.1% higher than YOLOv7. This proves the effectiveness and universality of the method proposed in this article. Compared to the current mainstream X-ray image dangerous goods detection models, this model effectively reduces the false detection rate of dangerous goods in X-ray security inspection images and has achieved significant improvement in the detection of small and multi-scale targets, achieving higher accuracy in dangerous goods detection. [ABSTRACT FROM AUTHOR]

Musculoskeletal diseases affect over 100 million people globally and are a leading cause of severe, prolonged pain, and disability. Recognized as a clinical emergency, prompt and accurate diagnosis of musculoskeletal disorders is crucial, as delayed identification poses the risk of amputation for patients, and in severe cases, can result in life-threatening conditions such as bone cancer. In this paper, a hybrid model HRD (Human-Resnet50-Densenet121) based on deep learning and human participation is proposed to efficiently identify disease features by classifying X-ray images. Feasibility testing of the model was conducted using the MURA dataset, with metrics such as accuracy, recall rate, F1-score, ROC curve, Cohen's kappa, and AUC values employed for evaluation. Experimental results indicate that, in terms of model accuracy, the hybrid model constructed through a combination strategy surpassed the accuracy of any individual model by more than 4%. The model achieved a peak accuracy of 88.81%, a maximum recall rate of 94%, and the highest F1-score value of 87%, all surpassing those of any single model. The hybrid model demonstrates excellent generalization performance and classification accuracy. [ABSTRACT FROM AUTHOR]

COVID-19 is reported as a very infectious which is increasing in rapid speed at present time. In this pandemic World health organization (WHO) is monitoring the situation and providing the preventive measures coordinating the treatment strategies to fight against Covid-19 through out the world. The only way to stop the further spread of this is to detect the disease early. Some works have been started to investigate covid19 using Deep learning algorithm over chestX-ray (CXR) images. In our work we have processed one CNN model which can process CXR images along with the metadata(non imaging data) available with the dataset to classify Covid 19. Resnet 50, Dense net 121, Mobile Net,VGG-16, Inception-V3 and one proposed Convolution Neural Network have been modified to accept the metadata along with CXR image. Some state of the art Deep learning models have been run to classify the covid 19 on the same data set and compared with our best model. Experiments have been done in two phases. In the 1st phase we used CNN models on CXR image only and in the 2nd phase we ran all modified CNN models over the same CXR images with their matadata. The experimental results shows that the output of 2nd phase out performs the output of 1st phase.After that we compared our best model (Proposed CNN) with other state of art models. [ABSTRACT FROM AUTHOR]

Deep learning has profoundly influenced various domains, particularly medical image analysis. Traditional transfer learning approaches in this field rely on models pretrained on domain-specific medical datasets, which limits their generalizability and accessibility. In this study, we propose a novel framework called real-world feature transfer learning, which utilizes backbone models initially trained on large-scale general-purpose datasets such as ImageNet. We evaluate the effectiveness and robustness of this approach compared to models trained from scratch, focusing on the task of classifying pneumonia in X-ray images. Our experiments, which included converting grayscale images to RGB format, demonstrate that real-world-feature transfer learning consistently outperforms conventional training approaches across various performance metrics. This advancement has the potential to accelerate deep learning applications in medical imaging by leveraging the rich feature representations learned from general-purpose pretrained models. The proposed methodology overcomes the limitations of domain-specific pretrained models, thereby enabling accelerated innovation in medical diagnostics and healthcare. From a mathematical perspective, we formalize the concept of real-world feature transfer learning and provide a rigorous mathematical formulation of the problem. Our experimental results provide empirical evidence supporting the effectiveness of this approach, laying the foundation for further theoretical analysis and exploration. This work contributes to the broader understanding of feature transferability across domains and has significant implications for the development of accurate and efficient models for medical image analysis, even in resource-constrained settings. [ABSTRACT FROM AUTHOR]

Purpose: Dental health has been getting increased attention. Timely detection of non-normal teeth (caries, residual root, retainer, teeth filling, etc.) is of great importance for people's health, well-being, and quality of life. This work proposes a rapid detection of non-normal teeth based on improved Mask R-CNN, aiming to achieve comprehensive screening of non-normal teeth on dental X-ray images. Methods: An improved Mask R-CNN based on attention mechanism was used to develop a non-normal teeth detection method trained on a high-quality annotated dataset, which can segment the whole mask of each non-normal tooth on the dental X-ray image immediately. Results: The average precision (AP) of the proposed non-normal teeth detection was 0.795 with an intersection-over-union of 0.5 and max detections (maxDets) of 32, which was higher than that of the typical Mask R-CNN method (AP = 0.750). In addition, validation experiments showed that the evaluation metrics (AP, recall, precision-recall (P-R) curve) of the proposed method were superior to those of the Mask R-CNN method. Furthermore, the experimental results indicated that proposed method exhibited a high sensitivity (95.65%) in detecting secondary caries. The proposed method took about 0.12 s to segment non-normal teeth on one dental X-ray image using the laptop (8G memory, NVIDIA RTX 3060 graphics processing unit), which was much faster than conventional manual methods. Conclusion: The proposed method enhances the accuracy and efficiency of abnormal tooth diagnosis for practitioners, while also facilitating early detection and treatment of dental caries to substantially lower patient costs. Additionally, it can enable rapid and objective evaluation of student performance in dental examinations. [ABSTRACT FROM AUTHOR]

This paper emphasizes a faster digital processing time while presenting an accurate method for identifying spine fractures in X-ray pictures. The study focuses on efficiency by utilizing many methods that include picture segmentation, feature reduction, and image classification. Two important elements are investigated to reduce the classification time: Using feature reduction software and leveraging the capabilities of sophisticated digital processing hardware. The researchers use different algorithms for picture enhancement, including theWiener and Kalman filters, and they look into two background correction techniques. The article presents a technique for extracting textural features and evaluates three picture segmentation algorithms and three fractured spine detection algorithms using transformdomain, PowerDensity Spectrum(PDS), andHigher-Order Statistics (HOS) for feature extraction. With an emphasis on reducing digital processing time, this all-encompassing method helps to create a simplified system for classifying fractured spine fractures. A feature reduction program code has been built to improve the processing speed for picture classification. Overall, the proposed approach shows great potential for significantly reducing classification time in clinical settings where time is critical. In comparison to other transform domains, the texture features' discrete cosine transform (DCT) yielded an exceptional classification rate, and the process of extracting features from the transform domain took less time. More capable hardware can also result in quicker execution times for the feature extraction algorithms. [ABSTRACT FROM AUTHOR]

A deep learning-based model for automatic diagnosis and classification of adolescent idiopathic scoliosis has been constructed. This model mainly included key points detection and Cobb angle measurement. 748 full-length standing spinal X-ray images were retrospectively collected, of which 602 images were used to train and validate the model, and 146 images were used to test the model performance. The results showed that the model had good diagnostic and classification performance, with an accuracy of 94.5%. Compared with experts' measurement, 94.9% of its Cobb angle measurement results were within the clinically acceptable range. The average absolute difference was 2.1°, and the consistency was also excellent (r2≥0.9552, P

During the COVID-19 pandemic, it was crucial for the healthcare sector to detect and classify the virus using X-ray and CT scans. This has underlined the need for advanced Deep Learning and Machine Learning approaches to effectively spot and manage the virus's spread. Indeed, researchers worldwide have dynamically participated in the field by publishing an important number of papers across various databases. In this context, we present a bibliometric analysis focused on the detection and classification of COVID-19 using Deep Learning and Machine Learning techniques, based on X-Ray and CT images. We analyzed published documents of the six prominent databases (IEEE Xplore, ACM, MDPI, PubMed, Springer, and ScienceDirect) during the period between 2019 and November 2023. Our results showed that rising forces in economy and technology, especially India, China, Turkey, and Pakistan, began to compete with the great powers in the field of scientific research, which could be seen from their number of publications. Moreover, researchers contributed to Deep Learning techniques more than the use of Machine Learning techniques or the use of both together and preferred to submit their works to Springer Database. An important result was that more than 57% documents were published as Journal Articles, which was an important portion compared to other publication types (conference papers and book chapters). Moreover, the PubMed journal "Multimedia Tools and Applications" tops the list of journals with a total of 29 published articles.

Abstract Degenerative musculoskeletal disease known as Osteoarthritis (OA) causes serious pain and abnormalities for humans and on detecting at an early stage, timely treatment shall be initiated to the patients at the earliest to overcome this pain. In this research study, X-ray images are captured from the humans and the proposed Gaussian Aquila Optimizer based Dual Convolutional Neural Networks is employed for detecting and classifying the osteoarthritis patients. The new Gaussian Aquila Optimizer (GAO) is devised to include Gaussian mutation at the exploitation stage of Aquila optimizer, which results in attaining the best global optimal value. Novel Dual Convolutional Neural Network (DCNN) is devised to balance the convolutional layers in each convolutional model and the weight and bias parameters of the new DCNN model are optimized using the developed GAO. The novelty of the proposed work lies in evolving a new optimizer, Gaussian Aquila Optimizer for parameter optimization of the devised DCNN model and the new DCNN model is structured to minimize the computational burden incurred in spite of it possessing dual layers but with minimal number of layers. The knee dataset comprises of total 2283 knee images, out of which 1267 are normal knee images and 1016 are the osteoarthritis images with an image of 512 × 512-pixel width and height respectively. The proposed novel GAO-DCNN system attains the classification results of 98.25% of sensitivity, 98.93% of specificity and 98.77% of classification accuracy for abnormal knee case–knee joint images. Experimental simulation results carried out confirms the superiority of the developed hybrid GAO-DCNN over the existing deep learning neural models form previous literature studies.

Abstract Given that defect detection in weld X-ray images is a critical aspect of pressure vessel manufacturing and inspection, accurate differentiation of the type, distribution, number, and area of defects in the images serves as the foundation for judging weld quality, and the segmentation method of defects in digital X-ray images is the core technology for differentiating defects. Based on the publicly available weld seam dataset GDX-ray, this paper proposes a complete technique for fault segmentation in X-ray pictures of pressure vessel welds. The key works are as follows: (1) To address the problem of a lack of defect samples and imbalanced distribution inside GDX-ray, a DA-DCGAN based on a two-channel attention mechanism is devised to increase sample data. (2) A convolutional block attention mechanism is incorporated into the coding layer to boost the accuracy of small-scale defect identification. The proposed MAU-Net defect semantic segmentation network uses multi-scale even convolution to enhance large-scale features. The proposed method can mask electrostatic interference and non-defect-class parts in the actual weld X-ray images, achieve an average segmentation accuracy of 84.75% for the GDX-ray dataset, segment and accurately rate the valid defects with a correct rating rate of 95%, and thus realize practical value in engineering.

The prevalence of knee osteoarthritis (KOA) cases has witnessed a significant increase on a global scale in recent years, emphasizing the need for automated diagnostic computer systems to aid in early‐stage osteoarthritis (OA) diagnosis. The accurate characterization of knee KOA stages through feature extraction poses significant research challenges due to the complexity of identifying relevant attributes. In this study, the development of a KOA diagnostic system is presented, leveraging a combination of Gabor, and Tamura parameters using the Canonical Correlation Analysis algorithm. Two feature selection algorithms, namely Principal Component Analysis and Relief, were employed for KOA classification. Furthermore, various classifiers, including K‐Nearest Neighbors, AdaBoost, Bagging, and Random Forest, were used to assess the proposed feature extraction approach. The diagnostic system was assessed using a dataset comprising 688 x‐ray images sourced from the OA initiative (OAI) dataset, consisting of 344 images from healthy subjects (Grade 0) and 344 images from pathological patients (Grade 2). To mitigate overfitting, a 10‐fold cross‐validation method was utilized. The experimental results indicate that the combination of Tamura and Gabor parameters with the Random Forest classifier achieved remarkable performance in KOA diagnosis, yielding an accuracy of 94.59%, and an area under the curve of 98.3%. Notably, the combined Gabor and Tamura models exhibited superior performance compared to individual models, as well as existing techniques reported in the literature. [ABSTRACT FROM AUTHOR]

Computer-aided weld defect recognition is transforming the field of Non-Destructive Testing by addressing the shortcomings of slow and error-prone manual inspections. This technology provides a reliable solution for detecting changes in pipeline conditions and structural damage. While conventional neural networks fall short in precise fault localization, deep learning-based object detection techniques step in to fill the gap. Addressing a real-industrial problem, particularly visually inspecting an X-ray welding database, without relying on a pre-existing benchmark presents a significant challenge in this field. Additionally, the poor quality of our welding data, which is riddled with small, sticky porosity in each image, poses several issues related to selecting the appropriate deep neural network object detector. This is yet another challenge that needs to be tackled. To direct these challenges, we introduced a novel approach based on the renowned Faster RCNN architecture to develop a model specifically designed for weld defect detection and recognition. This study dives deep into the inner workings of this newly adopted methodology. In our research, we have thoroughly parameterized, trained, tested, and validated this model. Our approach stands out through a comparative analysis with YOLO and DCNN models, highlighting the superiority of our Faster RCNN-based system. By evaluating its robustness and efficiency, our study reveals that the Faster RCNN model outperforms its counterparts in weld defect detection and localization for this specific small and sticky porosity defect type. This stands as a testament to effectively setting a new standard in this area. [ABSTRACT FROM AUTHOR]