Mixup-Inf-Net: A data augmentation algorithm for segmentation of new coronary pneumonia infections

In 2020, the global spread of Coronavirus Disease 2019 exposed entire world to a severe health crisis. This has limited fast and accurate screening of suspected cases due to equipment shortages and and harsh testing environments. The current diagnosis of suspected cases has benefited greatly from the use of radiographic brain imaging, also including X-ray and scintigraphy, as a crucial addition to screening tests for new coronary pneumonia disease. However, it is impractical to gather enormous volumes of data quickly, which makes it difficult for depth models to be trained. To solve these problems, we obtained a new dataset by data augmentation Mixup method for the used chest CT slices. It uses lung infection segmentation (Inf-Net [1]) in a deep network and adds a learning framework with semi-supervised to form a Mixup-Inf-Net semi-supervised learning framework model to identify COVID-19 infection area from chest CT slices. The system depends primarily on unlabeled data and merely a minimal amount of annotated data is required;therefore, the unlabeled data generated by Mixup provides good assistance. Our framework can be used to improve improve learning and performance. The SemiSeg dataset and the actual 3D CT images that we produced are used in a variety of tests, and the analysis shows that Mixup-Inf-Net semi-supervised outperforms most SOTA segmentation models learning framework model in this study, which also enhances segmentation performance. © 2023 SPIE.

Semi-Supervised Modified-UNet for Lung Infection Image Segmentation

Automatic lung infection segmentation in computed tomography (CT) scans can offer great assistance in radiological diagnosis by improving accuracy and reducing time required for diagnosis. The biggest challenges for deep learning (DL) models in segmenting infection region are the high variances in infection characteristics, fuzzy boundaries between infected and normal tissues, and the troubles in getting large number of annotated data for training. To resolve such issues, we propose a Modified U-Net (Mod-UNet) model with minor architectural changes and significant modifications in the training process of vanilla 2D UNet. As part of these modifications, we updated the loss function, optimization function, and regularization methods, added a learning rate scheduler and applied advanced data augmentation techniques. Segmentation results on two Covid-19 Lung CT segmentation datasets show that the performance of Mod-UNet is considerably better than the baseline U-Net. Furthermore, to mitigate the issue of lack of annotated data, the Mod-UNet is used in a semi-supervised framework (Semi-Mod-UNet) which works on a random sampling approach to progressively enlarge the training dataset from a large pool of unannotated CT slices. Exhaustive experiments on the two Covid-19 CT segmentation datasets and on a real lung CT volume show that the Mod-UNet and Semi-Mod-UNet significantly outperform other state-of-theart approaches in automated lung infection segmentation. IEEE

Performance, Trust, or both? COVID-19 Diagnosis and Prognosis using Deep Ensemble Transfer Learning on X-ray Imagesg±

The COVID-19 pandemic still affects most parts of the world today. Despite a lot of research on diagnosis, prognosis, and treatment, a big challenge today is the limited number of expert radiologists who provide diagnosis and prognosis on X-Ray images. Thus, to make the diagnosis of COVID-19 accessible and quicker, several researchers have proposed deep-learning-based Artificial Intelligence (AI) models. While most of these proposed machine and deep learning models work in theory, they may not find acceptance among the medical community for clinical use due to weak statistical validation. For this article, radiologists' views were considered to understand the correlation between the theoretical findings and real-life observations. The article explores Convolutional Neural Network (CNN) classification models to build a four-class viz. "COVID-19", "Lung Opacity", "Pneumonia", and "Normal"classifiers, which also provide the uncertainty measure associated with each class. The authors also employ various pre-processing techniques to enhance the X-Ray images for specific features. To address the issues of over-fitting while training, as well as to address the class imbalance problem in our dataset, we use Monte Carlo dropout and Focal Loss respectively. Finally, we provide a comparative analysis of the following classification models - ResNet-18, VGG-19, ResNet-152, MobileNet-V2, Inception-V3, and EfficientNet-V2, where we match the state-of-the-art results on the Open Benchmark Chest X-ray datasets, with a sensitivity of 0.9954, specificity of 0.9886, the precision of 0.9880, F1-score of 0.9851, accuracy of 0.9816, and receiver operating characteristic (ROC) of the area under the curve (AUC) of 0.9781 (ROC-AUC score). © 2022 ACM.

Research on Chest X-Ray Image Diagnosis of Covid-19 Based on Improved ResNet

With the outbreak of covid-19 in 2020, timely and effective diagnosis and treatment of each covid-19 patient is particularly important. This paper combines the advantages of deep learning in image recognition, takes RESNET as the basic network framework, and carries out the experiment of improving the residual structure on this basis. It is tested on the open source new coronal chest radiograph data set, and the accuracy rate is 82.3%. Through a series of experiments, the training model has the advantages of good generalization, high accuracy and fast convergence. This paper proves the feasibility of the improved residual neural network in the diagnosis of covid-19. © 2023 SPIE.

HarDNet and Dual-Code Attention Mechanism based model for medical images segmentation

During the formation of medical images, they are easily disturbed by factors such as acquisition devices and tissue backgrounds, causing problems such as blurred image backgrounds and difficulty in differentiation. In this paper, we combine the HarDNet module and the multi-coding attention mechanism module to optimize the two stages of encoding and decoding to improve the model segmentation performance. In the encoding stage, the HarDNet module extracts medical image feature information to improve the segmentation network operation speed. In the decoding stage, the multi-coding attention module is used to extract both the position feature information and channel feature information of the image to improve the model segmentation effect. Finally, to improve the segmentation accuracy of small targets, the use of Cross Entropy and Dice combination function is proposed as the loss function of this algorithm. The algorithm has experimented on three different types of medical datasets, Kvasir-SEG, ISIC2018, and COVID-19CT. The values of JS were 0.7189, 0.7702, 0.9895, ACC were 0.8964, 0.9491, 0.9965, SENS were 0.7634, 0.8204, 0.9976, PRE were 0.9214, 0.9504, 0.9931. The experimental results showed that the model proposed in this paper achieved excellent segmentation results in all the above evaluation indexes, which can effectively assist doctors to diagnose related diseases quickly and improve the speed of diagnosis and patients’quality of life. Author

U-Net based Semantic Segmentation for Touchless Fingerprint Technology: A Reflective Review

Touch-based fingerprints are widely used in today's world;even with all the success, the touch-based nature of these is a threat, especially in this COVID-19 period. A solution to the same is the introduction of Touchless Fingerprint Technology. The workflow of a touchless system varies vastly from its touch-based counterpart in terms of acquisition, pre-processing, image enhancement, and fingerprint verification. One significant difference is the methods used to segment desired fingerprint regions. This literature focuses on pixel-level classification or semantic segmentation using U-Net, a key yet challenging task. A plethora of semantic segmentation methods have been applied in this field. In this literature, a spectrum of efforts in the field of semantic segmentation using U-Net is investigated along with the components that are integral while training and testing a model, like optimizers, loss functions, and metrics used for evaluation and enumeration of results obtained. © 2022 IEEE.

Multilevel Thresholding of Grayscale Complex Crop Images using Minimum Cross Entropy

Crop image segmentation plays a key step in the field of agriculture. The crop images present near the environs have complex backgrounds and their grayscale histogram is mostly multimodal. Hence, multilevel segmentation of grayscale crop images may be helpful for better analysis. This paper proposed multilevel thresholding of grayscale crop images incorporated with minimum cross entropy as an objective function. The time complexity of this technique increases with the threshold levels. Hence, the coronavirus herd immunity optimizer (CHIO) has been amalgamated with the objective function. This technique improves the image's accuracy. The CHIO is a humanbased algorithm that separates the foreground and background efficiently with multiple thresholds value. The simulation has been performed on grayscale crop images. It is. compared with bacterial foraging algorithm (BFO), and beta differential algorithm (BDE) to validate the accuracy. The results validates that the proposed method outperforms BFO and BDE for grayscale crop images in terms of fidelity parameters. The qualitative and quantitative results evidence the proficiency of suggested method. © 2023 IEEE.

Comparative Analysis of Laboratory and Radiation Methods of Studies with the Degree of Severity of Patients with COVID-19

The study is devoted to a comparative analysis and retrospective evaluation of laboratory and instrumental data with the severity of lung tissue damage in COVID-19 of patients with COVID-19. An improvement was made in the methodology for interpreting and analyzing dynamic changes associated with COVID-19 on CT images of the lungs. The technique includes the following steps: pre-processing, segmentation with color coding, calculation and evaluation of signs to highlight areas with probable pathology (including combined evaluation of signs). Analysis and interpretation is carried out on the emerging database of patients. At the same time the following indicators are distinguished: the results of the analysis of CT images of the lungs in dynamics;the results of the analysis of clinical and laboratory data (severity course of the disease, temperature, saturation, etc.). The results of laboratory studies are analyzed with an emphasis on the values of the main indicator - interleukin-6. This indicator is a marker of significant and serious changes characterizing the severity of the patient's condition. © 2023 IEEE.

Multi-Attentional U-Net for Medical Image Segmentation

Deep learning (DL) approaches for image segmentation have been gaining state-of-the-art performance in recent years. Particularly, in deep learning, U-Net model has been successfully used in the field of image segmentation. However, traditional U-Net methods extract features, aggregate remote information, and reconstruct images by stacking convolution, pooling, and up sampling blocks. The traditional approach is very inefficient due of the stacked local operators. In this paper, we propose the multi-attentional U-Net that is equipped with non-local blocks based self-attention, channel-attention, and spatial-attention for image segmentation. These blocks can be inserted into U-Net to flexibly aggregate information on the plane and spatial scales. We perform and evaluate the multi-attentional U-Net model on three benchmark data sets, which are COVID-19 segmentation, skin cancer segmentation, thyroid nodules segmentation. Results show that our proposed models achieve better performances with faster computation and fewer parameters. The multi-attention U-Net can improve the medical image segmentation results. © 2022 IEEE.

COVID-19 Detection on X-Ray Image Using Deep Learning

COVID-19 is one of the threats that came out of nowhere and literally shook the entire world. Various prediction techniques have been invented in a very short time. This study also develops a Deep Learning (DL) model which can predict the presence of COVID-19 and pneumonia by analyzing the X-ray images of human lungs. From Kaggle, a collection of X-ray images of the lungs is collected. Then, this dataset is preprocessed using two alternative methods. Some of the techniques include image enhancement and picture resizing. The two deep-learning models are then trained using the preprocessed dataset. A few more examples of DL algorithms include MobileNet and Inception-V3. The best model is then selected by validating the learned deep-learning models. As the epochs count increases during training and validation, the accuracy value for both models increases. The value of the loss increases as the number of epochs decreases. During the fourteenth validation period, the model generates a loss value of 0.32 for the MobileNet technique. During the first few training epochs, accuracy is lower, and by the fifteenth, it is close to 0.9. The Inception-V3 method produces a loss value of 0.1452 at the eleventh validation epoch, which is the lowest value. The greatest accuracy value of 0.9697 is obtained after the twelfth cycle of validation. The model that performs better and has lower loss values is then put through one last test. Inception-V3 is therefore selected as the top method for COVID-19 detection. The Inception-V3 system properly predicted each of the normal images and the COVID-19 images in the final test. Regarding pneumonia, it correctly predicted just one image out of 20 that are so small as to be disregarded. When a patient cannot afford to find a doctor for consultation, the DL model created in this work can be utilized as a preliminary test for COVID-19. By including the model created in this study as a backend processor for a website or software application, the study's findings can be updated. © 2023 IEEE.

A Deep Learning-Based Preventive Measures of COVID-19 in a crowd using Reinforcement Model over GAN for Enhanced efficiency

The fast human-to-human spread of COVID-19 has caused significant lifestyle changes for many individuals. At the end of January 2020, the pandemic began, and many nations responded with varying degrees of testing, sanitation, lockdown, and quarantine centers. New normals of testing, sanitization, social separation, and lockdown are being implemented, and people are gradually returning to work and other daily routines. The COVID-19 infected population is monitored by testing individuals regularly. But it's a resource-heavy endeavor to test everyone without good reason. An optimum strategy is required to efficiently identify persons who are most likely to test positive for COVID-19. Sanitation is utilized for both persons and public spaces to eliminate germs. However, the disruption of governmental operations and economic development makes the use of lockdown and quarantine centers a resource-intensive endeavor. Conversely, it degrades the standard of living across a society. Furthermore, keeping people inside their houses or quarantine centers for an unlimited amount of time would not allow the government to care for everyone. These variables impact virus propagation, human health and happiness, available resources, and the economy's health, making their management resource-intensive. counting and density estimation are both attempts to create clever and efficient algorithms that can interpret the data provided by images to carry out Efficiency. GANs have been proven to have promising applications in overcoming the data dearth problem in COVID-19 lung image analysis. The Convolutional Neural Network (CNN) models built for the diagnosis of COVID-19 have benefited from the GAN-generated data used to refine their training. Moreover, GANs have helped improve the performance of CNNs by super-resolving pictures and performing segmentation. This work highlights the Reinforcement deep learning model over the fundamental constraints of the possible transformation of GANs-based approaches. This work proposes the model be developed with a new intelligent approach using RL to quantify these different types of testing considered for social distancing, face mask detection, limiting the gathering, and locking the location using the Q Learning technique. Different RL algorithms are implemented, and agents are equipped with these algorithms so that they may interact with the environment and learn the optimum method for doing so. © 2023 IEEE.

Deep Learning for Detection and Prediction of Covid-19 Virus on CT-Scan Image Dataset

As we all know, COVID-19 appears to be having a terrible impact on world health and well-being. Furthermore, at its peak, the COVID-19 cases worldwide reached a huge number i.e., in millions. The objective of the present work is to develop a model that detects COVID-19 utilizing CT-Scan Image Dataset and DL Techniques. As the number of verified cases rises, it becomes more critical to monitor and precisely categorize healthy and infected people. RT-PCR testing is the most used approach for the detection of Covid-19. However, several investigations have found that it has a low sensitivity in the early stages. Computer tomography (CT) is also used to detect image-morphological patterns of COVID-19-related chest lesions. The RT-PCR technique for diagnosing COVID has some drawbacks. For starters, test kits are insufficiently available, necessitating greater testing time and the sensitivity of testing varies. Therefore, employing CT scan pictures to screen COVID-19 is essential. The results showed that CT scan pictures might efficiently identify COVID-19, saving more lives. A Convolutional Neural Network (CNN) is a sort of Artificial Neural Network that is commonly used for image/object detection with class. An Input layer, Hidden layers, and an Output layer are common components of a neural network (NN). CNN is inspired by the brain's architecture. Artificial neurons or nodes in CNNs, like neurons in the brain, take inputs, process them, and deliver the result as output. Illness severity can be detected and calculated for future scopes and research. Another challenge encountered when dealing with severity infection detection and extending the existing work by using frameworks in order to increase accuracy. The proposed ECNN technique outperformed than CNN in terms of accuracy (95.35), execution time, and performance. This study could be extended or improved in the future by directing severity identification on the CT-Scan image dataset. © 2023 IEEE.

An Improved Computer Vision based Face Mask Detection and Alerting System

A global healthcare crisis has been declared as a result of the covid-19 nandemic's extensive snread. The coronavirus spreads mostly by the release of droplets from an infected person's irritated nose and throat. The risk of spreading disease is highest in public gathering places. Wearing a facial mask in public is one of the greatest ways, according to the World Health Organization, to avoid getting an infectious disease. This research work proposes an approach to human face mask detection using TensorFlow and OpenCV. Whether or not a character is wearing a mask is indicated by an enclosing field drawn around their head. An alert email will be sent to a person whose face is in the database if they make a call without a mask worn. © 2023 IEEE.

GAN-based Algorithm for Efficient Image Inpainting

Global pandemic due to the spread of COVID-19 has post challenges in a new dimension on facial recognition, where people start to wear masks. Under such condition, the authors consider utilizing machine learning in image inpainting to tackle the problem, by complete the possible face that is originally covered in mask. In particular, autoencoder has great potential on retaining important, general features of the image as well as the generative power of the generative adversarial network (GAN). The authors implement a combination of the two models, context encoders and explain how it combines the power of the two models and train the model with 50,000 images of influencers faces and yields a solid result that still contains space for improvements. Furthermore, the authors discuss some shortcomings with the model, their possible improvements, as well as some area of study for future investigation for applicative perspective, as well as directions to further enhance and refine the model. © 2023 SPIE.

OutCLIP, A New Multi-Outfit CLIP Based Triplet Network

Choosing a proper outfit is one of the problems we deal with every day. Today, people tend to use online websites for shopping, and the COVID-19 situation forced this condition more than before. In this research, we proposed a new architecture for multi-fashion item retrieval from a website database. We deployed a CLIP transformer model instead of convolutional neural networks in a triplet network. We also added a long short-term memory network (LSTM) to automatically extract and code the image features to generate descriptive text for each input image. Our OutCLIP model succeeded in doing its task with 83% precision and 85% recall accuracy in multi-item retrieval. This model can be trained and used in fashion retrieval problems and improve the former proposed models. Considering the descriptive text and the image together gives the model a better understanding of the concept and improves its generalization. © 2023 IEEE.

Efficient intelligent compression and recognition system-based vision computing for computed tomography COVID images

Computed tomography (CT) image-based medical recognition is extensively used for COVID recognition as it improves recognition and scanning rate. A method for intelligent compression and recognition system-based vision computing for CT COVID (ICRS-VC-COVID) was developed. The proposed system first preprocesses lung CT COVID images. Segmentation is then used to split the image into two regions: nonregion of interest (NROI) with fractal lossy compression and region of interest with context tree weighting lossless. Subsequently, a fast discrete curvelet transform (FDCT) is applied. Finally, vector quantization is implemented through the encoder, channel, and decoder. Two experiments were conducted to test the proposed ICRS-VC-COVID. The first evaluated the segmentation compression, FDCT, wavelet transform, and discrete curvelet transform (DCT). The second evaluated the FDCT, wavelet transform, and DCT with segmentation. It demonstrates a significant improvement in performance parameters, such as mean square error, peak signal-to-noise ratio, and compression ratio. At similar computational complexity, the proposed ICRS-VC-COVID is superior to some existing techniques. Moreover, at the same bit rate, it significantly improves the quality of the image. Thus, the proposed method can enable lung CT COVID images to be applied for disease recognition with low computational power and space. © The Authors. Published by SPIE under a Creative Commons Attribution 4.0 International License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI. [DOI: 10.1117/1.JEI.32.2.021404] © 2023 SPIE. All rights reserved.

COVID-19 X-RAY IMAGE DETECTION ALGORITHM BASED ON DEEP LEARNING

In order to enhance the ability to diagnose and distinguish COVID-19 from ordinary pneumonia, and to assist medical staff in chest X-ray detection of pneumonia patients, this paper proposes a COVID-19 X-ray image detection algorithm based on deep learning network. First of all, a model of deep learning network is set up based on VGG - 16, and then, the network structure and parameter optimization is adjusted, which makes the network model can be applied to COVID - 19 x ray imaging detection task. In the end, through adjusting the image size of the original data set, the input data meets the requirements of the deep learning network. Experimental results show that the proposed algorithm can effectively learn the characteristics of the COVID-19 X-ray image data set and accurately detect three states of COVID-19, common viral pneumonia and non-pneumonia, with a very high detection accuracy of 95.8%. © 2023 SPIE.

COVID-LiteNet: A lightweight CNN based network for COVID-19 detection using X-ray images

To restrict the virus's transmission in the pandemic and lessen the strain on the healthcare industry, computer-assisted diagnostics for the accurate and speedy diagnosis of coronavirus illness (COVID-19) has become a prerequisite. Compared to other types of imaging and detection, chest X-ray imaging (CXR) provides several advantages. Healthcare practitioners may profit from any technology instrument providing quick and accurate COVID-19 infection detection. COVID-LiteNet is a technique suggested in this paper that combines white balance with Contrast Limited Adaptive Histogram Equalization (CLAHE) and a convolutional neural network (CNN). White balance is employed as an image pre-processing step in this approach, followed by CLAHE, to improve the visibility of CXR images, and CNN is trained using sparse categorical cross-entropy for image classification tasks and gives the smaller parameters file size, i.e., 2.24 MB. The suggested COVID-LiteNet technique produced better results than vanilla CNN with no pre-processing. The proposed approach outperformed several state-of-the-art methods with a binary classification accuracy of 98.44 percent and a multi-class classification accuracy of 97.50 percent. COVID-LiteNet, the suggested technique, outperformed the competition on various performance parameters. COVID-LiteNet may help radiologists discover COVID-19 patients from CXR pictures by providing thorough model interpretations, cutting diagnostic time significantly. © 2023 IEEE.

Mask Wear Detection Algorithm Based on YOLOv5m

Wearing a mask during the COVID-19 epidemic can effectively prevent the spread of the virus. In view of the problems of small target size, crowd blocking each other and dense arrangement of targets in crowded places, a target detection algorithm based on the improved YOLOv5m model is proposed to achieve efficient detection of whether a mask is worn or not. This paper introduces four attention mechanisms in the feature extraction network based on the YOLOv5m model to suppress irrelevant information, enhance the information representation of the feature map, and improve the detection capability of the model for small-scale targets. The experimental results showed that the introduction of the SE module increased the mAP value of the original network by 9.3 percentage points, the most significant increase among the four attention mechanisms. And then a dual-scale feature fusion network is used in the Neck layer, giving different weights to the feature layers to convey more effective feature information. In the image pre-processing, the Mosaic method was used for data enhancement, and the CIoU loss function was used for coordinate frame positioning in the prediction layer. Experiments on the improved YOLOv5m algorithm demonstrate that the mean recognition accuracy of the method improves by 10.7 percentage points over the original method while maintaining the original model size and detection speed, and better solves the problems of small scale, dense arrangement and mutual occlusion of targets in mask wearing detection tasks in crowded places. © 2023 IEEE.

Croup disease classification using VGG19 and ResNet50 transfer learning method

Detection of any disease in the early stage can save a life. There are many medical imaging modalities like MRI, FMRI, ultrasound, CT, and X-ray used in the detection of disease. In the last decades, neural network-based methods are effective in detecting and classifying the disease based on abnormalities present in the medical images. Acute laryngotracheobronchitis (croup) is one of the common diseases seen in children among the 0.5-3 years age group which infects the respiratory system that can cause the larynx, trachea, and bronchi. Prior detection can lower the risk of spreading and can be treated accurately by a pediatrician. Commonly this infection can be diagnosed though physical examination. But due to the similarity of Covid-19 symptoms urges the physicians to get accurate detection of this disease using X-ray and CT images of the infant's chest and throat. The proposed work aims to develop a croup diagnose system (CDS) which identify the Croup infection through post anterior (PA) view of pediatric X-ray using deep learning algorithm. We used the well-known transfer learning algorithm VGG19 and ResNet50. Data augmentation being adapted for reducing the overfitting and to improve the quantity of image samples. We show that the proposed transfer learning based CDS method can be used to classify the X-ray images into two classes namely, croup and normal. The experiment results confirm that VGG19 performs better than ResNet50 with promising classification accuracy (90.91%.). The results show that the proposed CDS models can be used for more pediatric medical image classification problem. © 2024 World Scientific Publishing Company.