Automatic Detection of Lung Ultrasound Artifacts using a Deep Neural Networks approach

The COVID-19 pandemic has challenged many of the healthcare systems around the world. Many patients who have been hospitalized due to this disease develop lung damage. In low and middle-income countries, people living in rural and remote areas have very limited access to adequate health care. Ultrasound is a safe, portable and accessible alternative;however, it has limitations such as being operator-dependent and requiring a trained professional. The use of lung ultrasound volume sweep imaging is a potential solution for this lack of physicians. In order to support this protocol, image processing together with machine learning is a potential methodology for an automatic lung damage screening system. In this paper we present an automatic detection of lung ultrasound artifacts using a Deep Neural Network, identifying clinical relevant artifacts such as pleural and A-lines contained in the ultrasound examination taken as part of the clinical screening in patients with suspected lung damage. The model achieved encouraging preliminary results such as sensitivity of 94%, specificity of 81%, and accuracy of 89% to identify the presence of A-lines. Finally, the present study could result in an alternative solution for an operator-independent lung damage screening in rural areas, leading to the integration of AI-based technology as a complementary tool for healthcare professionals. © 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

Medical Image Diagnosis Using Deep Learning Classifiers for COVID-19

COVID-19 and other diseases must be precisely and swiftly classified to minimize disease spread and avoid overburdening the healthcare system. The main purpose of this study is to develop deep-learning classifiers for normal, viral pneumonia, and COVID-19 disorders using CXR pictures. Deep learning image classification algorithms are used to recognize and categorise image data to detect the presence of illnesses. The raw image must be pre-processed since deep neural networks perform the most important aspect of medical image identification, which includes translating the raw image into an intelligible format. The dataset includes three classifications, including normal and viral pneumonia and COVID-19. To aid in quick diagnosis and the proposed models leverage the performance validation of several models, which are summarised in the form of a recall, Fl-score, precision, accuracy, and AUC, to distinguish COVID-19 from other types of pneumonia. When all the deep learning classifiers and performance parameters were analyzed, the ResNetl0lV2 achieved the highest accuracy of COVID-19 classifications is 97.S2%, ResNetl0lV2 had the greatest accuracy of the normal categorization is 92.04% and the Densenet201 had the greatest accuracy of the pneumonia classification is 99.92%. The suggested deep learning system is an excellent choice for clinical use to aid in the COVID-19, normal, and pneumonia processes for diagnosing infections using CXR scans. Furthermore, the suggested approaches provided a realistic technique to implement in real-world practice, assisting medical professionals in diagnosing illnesses from CXR images. © 2023 IEEE.

CX-R Classification Using DCNN Method

The virus SARS-CoV2 was identified in late 2019. Coronavirus Disease 2019 (COVID-19) is still a threat to global health and safety. Deep Learning (DL) is anticipated to be the most excellent strategy for reliably predicting COVID-19. Convolutional Neural Networks(CNNs) have achieved successful outcomes particularly in categorization and analyzing of medical image data. This work proposes a Deep CNN(DCNN) method for the classification of CX-R(Chest X-Ray) images in prediction of COVID-19. The dataset is preprocessed under many phases with different techniques for creating effective training dataset for the DCNN model to achieve best performance. This is done to deal various complexities like availability of very small sized imbalanced dataset with quality issues. In the first instance, model is trained using the train dataset. Then the model is tested for a separate validate X-ray image dataset and Confusion matrix is displayed. Up to 98.3% Accuracy is obtained, when proposed model was tested using the validate dataset. The Accuracy and Loss graph is plotted for the same. Later, random image prediction is made from prediction dataset which include both COVID and Normal X-rays. Other important performance metrics like F1 score, Recall, Precision for the model is displayed. © 2023 IEEE.

Deep learning model for binary classification of COVID-19 based on Chest X-Ray

COVID-19 is a novel virus infecting the upper respiratory tract and lungs. On a scale of the global pandemic, the number of cases and deaths had been increasing each day. Chest X-ray (CXR) images proved effective in monitoring a variety of lung illnesses, including the COVID-19 disease. In recent years, deep learning (DL) has become one of the most significant topics in the computing world and has been extensively applied in several medical applications. In terms of automatic diagnosis of COVID-19, those approaches had proven to be very effective. In this research, a DL technology based on convolution neural networks (CNN) models had been implemented with less number of layers with tuning parameters that will take less time for training for binary classification of COVID-19 based on CXR images. Experimental results had shown that the proposed model for training had achieved an accuracy of 96.68%, Recall of 94.12%, Precision of 93.49%, Specificity of 97.61%, and F1 Score of 93.8%. Those results had shown the high value of utilizing DL for early COVID-19 diagnosis, which can be utilized as a useful tool for COVID-19 screening. © 2023 IEEE.

A Shuffling Building Block and Augmentation Parameter Tuning Techniques to Handle Small Medical Dataset

The recent COVID-19 outbreak showed us the importance of faster disease diagnosis using medical image processing as it is considered the most reliable and accurate diagnostic tool. In a CNN architecture, performance improves with the increasing number of trainable parameters at the cost of processing time. We have proposed an innovative approach of combining efficient novel architectures like Inception, ResNet, and ResNet-Xt and created a new CNN architecture that benefits Extreme Cardinal dimensions. We have also created four variations of the same base architecture by varying the position of each building block and used X-Ray, Microscopic, MRI, and pathMNIST datasets to train our architecture. For learning curve optimization, we have applied learning rate changing techniques, tuned image augmentation parameters, and chose the best random states value. For a specific dataset, we reduced the validation loss from 0.22 to 0.18 by interchanging the architecture's building block position. Our results indicate that image augmentation parameters can help to decrease the validation loss. We have also shown rearrangement of the building blocks reduces the number of parameters, in our case, from 5,689,008 to 3,876,528. © 2023 IEEE.

Automatic classification of COVID-19 infected patients using convolution neural network models

Coronavirus (COVID-19) has infected millions of people and continues to have a disastrous impact on the economy and health. Timely diagnosis of the COVID-19 infection can help contain the virus and prevent much loss of life. The COVID-19 diagnosis can be achieved by the Reverse Transcript Polymerase Chain Reaction test (RT-PCR) but it has a high false-negative rate and has low sensitivity as compared to Computed Tomography (CT) and X-Ray images. In this study, we have trained six different architectures of the Convolution Neural Network (CNN) model to detect COVID-19. We tried to identify the most efficient CNN model based on accuracy and the number of trainable parameters. The model has been trained on a Chest X-Ray image dataset retrieved from the GitHub platform with 1811 images in the training dataset and 484 images in the validation dataset. The model with the highest accuracy has been trained for a variable number of epochs varying the filter size. It has been demonstrated that architecture 3 can achieve 99% accuracy for 500 epochs with a minimum number of trainable parameters. Using just a simple CNN architecture that can be deployed in any rural healthcare center we can achieve a high level of accuracy for classification with the added advantage of less complexity. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.

Advances in medical image watermarking: a state of the art review.

Watermarking has been considered to be a potent and persuasive gizmo for its application in healthcare setups that work online, especially in the current COVID-19 scenario. The security and protection of medical image data from various manipulations that take place over the internet is a topic of concern that needs to be addressed. A detailed review of security and privacy protection using watermarking has been presented in this paper. Watermarking of medical images helps in the protection of image content, authentication of Electronic Patient Record (EPR), and integrity verification. At first, we discuss the various prerequisites of medical image watermarking systems, followed by the classification of Medical Image Watermarking Techniques (MIWT) that include state-of-the-art. We have classified MIWT's into four broader classes for providing better understanding of medical image watermarking. The existing schemes have been presented along with their cons so that the reader may be able to grasp the shortcomings of the technique in order to develop novel techniques proving the inevitability of the presented review. Further, various evaluation parameters along with potential challenges pertaining to medical image watermarking systems have been discussed to provide a deep insight into this research area.

CT medical image segmentation algorithm based on deep learning technology.

For the problems of blurred edges, uneven background distribution, and many noise interferences in medical image segmentation, we proposed a medical image segmentation algorithm based on deep neural network technology, which adopts a similar U-Net backbone structure and includes two parts: encoding and decoding. Firstly, the images are passed through the encoder path with residual and convolutional structures for image feature information extraction. We added the attention mechanism module to the network jump connection to address the problems of redundant network channel dimensions and low spatial perception of complex lesions. Finally, the medical image segmentation results are obtained using the decoder path with residual and convolutional structures. To verify the validity of the model in this paper, we conducted the corresponding comparative experimental analysis, and the experimental results show that the DICE and IOU of the proposed model are 0.7826, 0.9683, 0.8904, 0.8069, and 0.9462, 0.9537 for DRIVE, ISIC2018 and COVID-19 CT datasets, respectively. The segmentation accuracy is effectively improved for medical images with complex shapes and adhesions between lesions and normal tissues.

Automated COVID-19 screening framework via Deep Convolutional Neural Network with Chest X-ray Medical Images

COVID-19 screening using chest X-rays plays a significant role in the early diagnosis of COVID-19 illness during the ongoing pandemic. Manually identifying this infection from chest X-ray films is a challenging and time-consuming technique due to time restrictions and the competence of radiologists. Also, the manual Covid-19 identification technique is made much more difficult and opaquer by the feature similarity between positive and negative chest X-ray images. Therefore, we propose an automated COVID-19 screening framework that utilizes artificial intelligence techniques with a transfer learning approach for COVID-19 diagnosis using chest X-ray images. Specifically, we employ the transfer learning concept for feature extraction before further processing with modified deep neural networks. Also, Grad-CAM visualization is used for our case study to support the predicted diagnosis. The results of the experiments on the publicly accessible dataset show that the convolutional neural network model, which is simple yet effective, performs significantly better than other deep learning techniques across all metrics, including accuracy, precision, recall, and F-measure. © 2022 IEEE.

The effect of choosing optimizer algorithms to improve computer vision tasks: a comparative study.

Optimization algorithms are used to improve model accuracy. The optimization process undergoes multiple cycles until convergence. A variety of optimization strategies have been developed to overcome the obstacles involved in the learning process. Some of these strategies have been considered in this study to learn more about their complexities. It is crucial to analyse and summarise optimization techniques methodically from a machine learning standpoint since this can provide direction for future work in both machine learning and optimization. The approaches under consideration include the Stochastic Gradient Descent (SGD), Stochastic Optimization Descent with Momentum, Rung Kutta, Adaptive Learning Rate, Root Mean Square Propagation, Adaptive Moment Estimation, Deep Ensembles, Feedback Alignment, Direct Feedback Alignment, Adfactor, AMSGrad, and Gravity. prove the ability of each optimizer applied to machine learning models. Firstly, tests on a skin cancer using the ISIC standard dataset for skin cancer detection were applied using three common optimizers (Adaptive Moment, SGD, and Root Mean Square Propagation) to explore the effect of the algorithms on the skin images. The optimal training results from the analysis indicate that the performance values are enhanced using the Adam optimizer, which achieved 97.30% accuracy. The second dataset is COVIDx CT images, and the results achieved are 99.07% accuracy based on the Adam optimizer. The result indicated that the utilisation of optimizers such as SGD and Adam improved the accuracy in training, testing, and validation stages.

Explainability of deep learning models in medical image classification

The ability to explain the reasons for one's decisions to others is an important aspect of being human intelligence. We will look at the explainability aspects of the deep learning models, which are most frequently used in medical image processing tasks. The Explainability of machine learning models in medicine is essential for understanding how the particular ML model works and how it solves the problems it was designed for. The work presented in this paper focuses on the classification of lung CT scans for the detection of COVID-19 patients. We used CNN and DenseNet models for the classification and explored the application of selected visual explainability techniques to provide insight into how the model works when processing the images. © 2022 IEEE.

DCACorrCapsNet: A deep channel‐attention correlative capsule network for COVID‐19 detection based on multi‐source medical images

The raging trend of COVID‐19 in the world has become more and more serious since 2019, causing large‐scale human deaths and affecting production and life. Generally speaking, the methods of detecting COVID‐19 mainly include the evaluation of human disease characterization, clinical examination and medical imaging. Among them, CT and X‐ray screening is conducive to doctors and patients' families to observe and diagnose the severity and development of the COVID‐19 more intuitively. Manual diagnosis of medical images leads to low the efficiency, and long‐term tired gaze will decline the diagnosis accuracy. Therefore, a fully automated method is needed to assist processing and analysing medical images. Deep learning methods can rapidly help differentiate COVID‐19 from other pneumonia‐related diseases or healthy subjects. However, due to the limited labelled images and the monotony of models and data, the learning results are biased, resulting in inaccurate auxiliary diagnosis. To address these issues, a hybrid model: deep channel‐attention correlative capsule network, for channel‐attention based spatial feature extraction, correlative feature extraction, and fused feature classification is proposed. Experiments are validated on X‐ray and CT image datasets, and the results outperform a large number of existing state‐of‐the‐art studies. [ABSTRACT FROM AUTHOR] Copyright of IET Image Processing (Wiley-Blackwell) is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

COVID-19 Detection Based on 6-Layered Explainable Customized Convolutional Neural Network

This paper presents a 6-layer customized convolutional neural network model (6L-CNN) to rapidly screen out patients with COVID-19 infection in chest CT images. This model can effectively detect whether the target CT image contains images of pneumonia lesions. In this method, 6L-CNN was trained as a binary classifier using the dataset containing CT images of the lung with and without pneumonia as a sample. The results show that the model improves the accuracy of screening out COVID-19 patients. Compared to other methods, the performance is better. In addition, the method can be extended to other similar clinical conditions. © 2023 Tech Science Press. All rights reserved.

Predicting, Analyzing and Communicating Outcomes of COVID-19 Hospitalizations with Medical Images and Clinical Data

We propose PACO, a visual analytics framework to support the prediction, analysis, and communication of COVID-19 hospitalization outcomes. Although several real-world data sets about COVID-19 are openly available, most of the current research focuses on the detection of the disease. Until now, no previous work exists on combining insights from medical image data with knowledge extracted from clinical data, predicting the likelihood of an intensive care unit (ICU) visit, ventilation, or decease. Moreover, available literature has not yet focused on communicating such results to the broader society. To support the prediction, analysis and communication of the outcomes of COVID-19 hospitalizations on the basis of a publicly available data set comprising both electronic health data and medical image data [SSP∗21], we conduct the following three steps: (1) automated segmentation of the available X-ray images and processing of clinical data, (2) development of a model for the prediction of disease outcomes and a comparison to state-of-the-art prediction scores for both data sources, i.e., medical images and clinical data, and (3) the communication of outcomes to two different groups (i.e., clinical experts and the general population) through interactive dashboards. Preliminary results indicate that the prediction, analysis and communication of hospitalization outcomes is a significant topic in the context of COVID-19 prevention. © 2022 The Author(s) © 2022 The Eurographics Association.

A Deep Learning Approach for Automated COVID-19 Detection

Nowadays, COVID-19 is a life-threatening virus lor human beings, and the reason behind it is its attackon the respiratory system. A large number of cases of infection were reported with minor tono symptoms. So, detection of the disease at an earlier stage can decrease the death rate in the patients. Chest X-Rays scans can be used primarily for analyzing the infection. X-ray technology is chosen over CT scans because its equipment is readily available, results can be obtained quickly, and the process is quite affordable in terms of cost. This paper proposed a solution using a deep learning approach to detect COVID-19 infection in human lungs using Chest X-Ray scans. Here, we have used CLAHE (Contrast Limited Adaptive Histogram Equalization) to enhance the contrast of X-ray images and then Convolutional Neural Network on CLAHE processed images to improve the accuracy of the overall model. Further, these scans are classified using machine learning classifiers among COVID-19 infected and normal. The proposed model is trained and validated on a publicly available COVID-19 X-ray dataset containing 15917 X-ray Images. Confusion matrices and ROC curves have been generated to analyze the model's efficiency. Training and validation graphs are developed to calculate the other parameters like validation accuracy and training Accuracy. The model's accuracy is 99.8%, which is better than its existing state-of-the-art approaches. These results show that this model is promising for physicians to classify the chest X-Rays scans of infected patients with COVID-19. © 2023 J.J. Strossmayer University of Osijek , Faculty of Electrical Engineering, Computer Science and Information Technology. All rights reserved.

Lung CT image segmentation algorithm based on improved U-net structure

Accurate segmentation of medical images can help doctors diagnose and treat diseases. In the face of the complex COVID-19 image, this paper proposes an improved U-net network segmentation model, which uses the residual network structure to deepen the network level, and adds the attention module to integrate different receptive field, global, local and spatial features to enhance the detail segmentation effect of the network. For the COVID-19 CT data set, the F1-Score, Accuracy, SE, SP and Precision of the U-Net network are 0.9176, 0.9578, 0.9669, 0.9487 and 0.8574 respectively. Compared with U-Net, our model proposed in this paper increased by 6.43%, 3.36%, 0.85%, 4.78% and 13.11% on F1-Score, Accuracy, SE, SP and Precision, respectively. The automatic and effective segmentation of COVID-19 lung CT image is realized. © 2022 IEEE.

Adversarial Machine Learning Protection Using the Example of Evasion Attacks on Medical Images

This work considers evasion attacks on machine learning (ML) systems that use medical images in their analysis. Their systematization and a practical assessment of feasibility are carried out. Existing protection techniques against ML evasion attacks are presented and analyzed. The features of medical images are given and the formulation of the problem of evasion attack protection for these images based on several protective methods is provided. The authors have identified, implemented, and tested the most relevant protection methods on practical examples: an analysis of images of patients with COVID-19.

MediNet: transfer learning approach with MediNet medical visual database.

The rapid development of machine learning has increased interest in the use of deep learning methods in medical research. Deep learning in the medical field is used in disease detection and classification problems in the clinical decision-making process. Large amounts of labeled datasets are often required to train deep neural networks; however, in the medical field, the lack of a sufficient number of images in datasets and the difficulties encountered during data collection are among the main problems. In this study, we propose MediNet, a new 10-class visual dataset consisting of Rontgen (X-ray), Computed Tomography (CT), Magnetic Resonance Imaging (MRI), Ultrasound, and Histopathological images such as calcaneal normal, calcaneal tumor, colon benign colon adenocarcinoma, brain normal, brain tumor, breast benign, breast malignant, chest normal, chest pneumonia. AlexNet, VGG19-BN, Inception V3, DenseNet 121, ResNet 101, EfficientNet B0, Nested-LSTM + CNN, and proposed RdiNet deep learning algorithms are used in the transfer learning for pre-training and classification application. Transfer learning aims to apply previously learned knowledge in a new task. Seven algorithms were trained with the MediNet dataset, and the models obtained from these algorithms, namely feature vectors, were recorded. Pre-training models were used for classification studies on chest X-ray images, diabetic retinopathy, and Covid-19 datasets with the transfer learning technique. In performance measurement, an accuracy of 94.84% was obtained in the traditional classification study for the InceptionV3 model in the classification study performed on the Chest X-Ray Images dataset, and the accuracy was increased 98.71% after the transfer learning technique was applied. In the Covid-19 dataset, the classification success of the DenseNet121 model before pre-trained was 88%, while the performance after the transfer application with MediNet was 92%. In the Diabetic retinopathy dataset, the classification success of the Nested-LSTM + CNN model before pre-trained was 79.35%, while the classification success was 81.52% after the transfer application with MediNet. The comparison of results obtained from experimental studies observed that the proposed method produced more successful results.

Deep Learning Techniques to Diagnose Lung Cancer.

Medical imaging tools are essential in early-stage lung cancer diagnostics and the monitoring of lung cancer during treatment. Various medical imaging modalities, such as chest X-ray, magnetic resonance imaging, positron emission tomography, computed tomography, and molecular imaging techniques, have been extensively studied for lung cancer detection. These techniques have some limitations, including not classifying cancer images automatically, which is unsuitable for patients with other pathologies. It is urgently necessary to develop a sensitive and accurate approach to the early diagnosis of lung cancer. Deep learning is one of the fastest-growing topics in medical imaging, with rapidly emerging applications spanning medical image-based and textural data modalities. With the help of deep learning-based medical imaging tools, clinicians can detect and classify lung nodules more accurately and quickly. This paper presents the recent development of deep learning-based imaging techniques for early lung cancer detection.