Detection of COVID-19 Using Transfer Learning and Grad-CAM Visualization on Indigenously Collected X-ray Dataset

Enhancing surgical decision-making in NEC with ResNet18: a deep learning approach to predict the need for surgery through x-ray image analysis

Background

Necrotizing enterocolitis (NEC) is a severe neonatal intestinal disease, often occurring in preterm infants following the administration of hyperosmolar formula. It is one of the leading causes of neonatal mortality in the NICU, and currently, there are no clear standards for surgical intervention, which typically depends on the joint discretion of surgeons and neonatologists. In recent years, deep learning has been extensively applied in areas such as image segmentation, fracture and pneumonia classification, drug development, and pathological diagnosis.

Objective

Investigating deep learning applications using bedside x-rays to help optimizing surgical decision-making in neonatal NEC.

Methods

Through a retrospective analysis of anteroposterior bedside chest and abdominal x-rays from 263 infants diagnosed with NEC between January 2015 and April 2023, including a surgery group (94 cases) and a non-surgery group (169 cases), the infants were divided into a training set and a validation set in a 7:3 ratio. Models were built based on Resnet18, Densenet121, and SimpleViT to predict whether NEC patients required surgical intervention. Finally, the model's performance was tested using an additional 40 cases, including both surgical and non-surgical NEC cases, as a test group. To enhance the interpretability of the models, the study employed 2D-Grad-CAM technology to describe the models' focus on significant areas within the x-ray images.

Results

Resnet18 demonstrated outstanding performance in binary diagnostic capability, achieving an accuracy of 0.919 with its precise lesion imaging and interpretability particularly highlighted. Its precision, specificity, sensitivity, and F1 score were significantly high, proving its advantages in optimizing surgical decision-making for neonatal NEC.

Conclusion

The Resnet18 deep learning model, constructed using bedside chest and abdominal imaging, effectively assists clinical physicians in determining whether infants with NEC require surgical intervention.

A Hybrid Deep Learning CNN model for COVID-19 detection from chest X-rays

Coronavirus disease (COVID-2019) is emerging in Wuhan, China in 2019. It has spread throughout the world since the year 2020. Millions of people were affected and caused death to them till now. To avoid the spreading of COVID-2019, various precautions and restrictions have been taken by all nations. At the same time, infected persons are needed to identify and isolate, and medical treatment should be provided to them. Due to a deficient number of Reverse Transcription Polymerase Chain Reaction (RT-PCR) tests, a Chest X-ray image is becoming an effective technique for diagnosing COVID-19. In this work, the Hybrid Deep Learning CNN model is proposed for the diagnosis COVID-19 using chest X-rays. The proposed model consists of a heading model and a base model. The base model utilizes two pre-trained deep learning structures such as VGG16 and VGG19. The feature dimensions from these pre-trained models are reduced by incorporating different pooling layers, such as max and average. In the heading part, dense layers of size three with different activation functions are also added. A dropout layer is supplemented to avoid overfitting. The experimental analyses are conducted to identify the efficacy of the proposed hybrid deep learning with existing transfer learning architectures such as VGG16, VGG19, EfficientNetB0 and ResNet50 using a COVID-19 radiology database. Various classification techniques, such as K-Nearest Neighbor (KNN), Naive Bayes, Random Forest, Support Vector Machine (SVM), and Neural Network, were also used for the performance comparison of the proposed model. The hybrid deep learning model with average pooling layers, along with SVM-linear and neural networks, both achieved an accuracy of 92%.These proposed models can be employed to assist radiologists and physicians in avoiding misdiagnosis rates and to validate the positive COVID-19 infected cases.

RVCNet: A hybrid deep neural network framework for the diagnosis of lung diseases

Early evaluation and diagnosis can significantly reduce the life-threatening nature of lung diseases. Computer-aided diagnostic systems (CADs) can help radiologists make more precise diagnoses and reduce misinterpretations in lung disease diagnosis. Existing literature indicates that more research is needed to correctly classify lung diseases in the presence of multiple classes for different radiographic imaging datasets. As a result, this paper proposes RVCNet, a hybrid deep neural network framework for predicting lung diseases from an X-ray dataset of multiple classes. This framework is developed based on the ideas of three deep learning techniques: ResNet101V2, VGG19, and a basic CNN model. In the feature extraction phase of this new hybrid architecture, hyperparameter fine-tuning is used. Additional layers, such as batch normalization, dropout, and a few dense layers, are applied in the classification phase. The proposed method is applied to a dataset of COVID-19, non-COVID lung infections, viral pneumonia, and normal patients' X-ray images. The experiments take into account 2262 training and 252 testing images. Results show that with the Nadam optimizer, the proposed algorithm has an overall classification accuracy, AUC, precision, recall, and F1-score of 91.27%, 92.31%, 90.48%, 98.30%, and 94.23%, respectively. Finally, these results are compared with some recent deep-learning models. For this four-class dataset, the proposed RVCNet has a classification accuracy of 91.27%, which is better than ResNet101V2, VGG19, VGG19 over CNN, and other stand-alone models. Finally, the application of the GRAD-CAM approach clearly interprets the classification of images by the RVCNet framework.

A Real Time Method for Distinguishing COVID-19 Utilizing 2D-CNN and Transfer Learning

Rapid identification of COVID-19 can assist in making decisions for effective treatment and epidemic prevention. The PCR-based test is expert-dependent, is time-consuming, and has limited sensitivity. By inspecting Chest R-ray (CXR) images, COVID-19, pneumonia, and other lung infections can be detected in real time. The current, state-of-the-art literature suggests that deep learning (DL) is highly advantageous in automatic disease classification utilizing the CXR images. The goal of this study is to develop models by employing DL models for identifying COVID-19 and other lung disorders more efficiently. For this study, a dataset of 18,564 CXR images with seven disease categories was created from multiple publicly available sources. Four DL architectures including the proposed CNN model and pretrained VGG-16, VGG-19, and Inception-v3 models were applied to identify healthy and six lung diseases (fibrosis, lung opacity, viral pneumonia, bacterial pneumonia, COVID-19, and tuberculosis). Accuracy, precision, recall, f1 score, area under the curve (AUC), and testing time were used to evaluate the performance of these four models. The results demonstrated that the proposed CNN model outperformed all other DL models employed for a seven-class classification with an accuracy of 93.15% and average values for precision, recall, f1-score, and AUC of 0.9343, 0.9443, 0.9386, and 0.9939. The CNN model equally performed well when other multiclass classifications including normal and COVID-19 as the common classes were considered, yielding accuracy values of 98%, 97.49%, 97.81%, 96%, and 96.75% for two, three, four, five, and six classes, respectively. The proposed model can also identify COVID-19 with shorter training and testing times compared to other transfer learning models.

Design and Analysis of a Deep Learning Ensemble Framework Model for the Detection of COVID-19 and Pneumonia Using Large-Scale CT Scan and X-ray Image Datasets

Recently, various methods have been developed to identify COVID-19 cases, such as PCR testing and non-contact procedures such as chest X-rays and computed tomography (CT) scans. Deep learning (DL) and artificial intelligence (AI) are critical tools for early and accurate detection of COVID-19. This research explores the different DL techniques for identifying COVID-19 and pneumonia on medical CT and radiography images using ResNet152, VGG16, ResNet50, and DenseNet121. The ResNet framework uses CT scan images with accuracy and precision. This research automates optimum model architecture and training parameters. Transfer learning approaches are also employed to solve content gaps and shorten training duration. An upgraded VGG16 deep transfer learning architecture is applied to perform multi-class classification for X-ray imaging tasks. Enhanced VGG16 has been proven to recognize three types of radiographic images with 99% accuracy, typical for COVID-19 and pneumonia. The validity and performance metrics of the proposed model were validated using publicly available X-ray and CT scan data sets. The suggested model outperforms competing approaches in diagnosing COVID-19 and pneumonia. The primary outcomes of this research result in an average F-score (95%, 97%). In the event of healthy viral infections, this research is more efficient than existing methodologies for coronavirus detection. The created model is appropriate for recognition and classification pre-training. The suggested model outperforms traditional strategies for multi-class categorization of various illnesses.

RADIC:A tool for diagnosing COVID-19 from chest CT and X-ray scans using deep learning and quad-radiomics

Deep learning (DL) algorithms have demonstrated a high ability to perform speedy and accurate COVID-19 diagnosis utilizing computed tomography (CT) and X-Ray scans. The spatial information in these images was used to train DL models in the majority of relevant studies. However, training these models with images generated by radiomics approaches could enhance diagnostic accuracy. Furthermore, combining information from several radiomics approaches with time-frequency representations of the COVID-19 patterns can increase performance even further. This study introduces "RADIC", an automated tool that uses three DL models that are trained using radiomics-generated images to detect COVID-19. First, four radiomics approaches are used to analyze the original CT and X-ray images. Next, each of the three DL models is trained on a different set of radiomics, X-ray, and CT images. Then, for each DL model, deep features are obtained, and their dimensions are decreased using the Fast Walsh Hadamard Transform, yielding a time-frequency representation of the COVID-19 patterns. The tool then uses the discrete cosine transform to combine these deep features. Four classification models are then used to achieve classification. In order to validate the performance of RADIC, two benchmark datasets (CT and X-Ray) for COVID-19 are employed. The final accuracy attained using RADIC is 99.4% and 99% for the first and second datasets respectively. To prove the competing ability of RADIC, its performance is compared with related studies in the literature. The results reflect that RADIC achieve superior performance compared to other studies. The results of the proposed tool prove that a DL model can be trained more effectively with images generated by radiomics techniques than the original X-Ray and CT images. Besides, the incorporation of deep features extracted from DL models trained with multiple radiomics approaches will improve diagnostic accuracy.

A fuzzy fine-tuned model for COVID-19 diagnosis

The COVID-19 disease pandemic spread rapidly worldwide and caused extensive human death and financial losses. Therefore, finding accurate, accessible, and inexpensive methods for diagnosing the disease has challenged researchers. To automate the process of diagnosing COVID-19 disease through images, several strategies based on deep learning, such as transfer learning and ensemble learning, have been presented. However, these techniques cannot deal with noises and their propagation in different layers. In addition, many of the datasets already being used are imbalanced, and most techniques have used binary classification, COVID-19, from normal cases. To address these issues, we use the blind/referenceless image spatial quality evaluator to filter out inappropriate data in the dataset. In order to increase the volume and diversity of the data, we merge two datasets. This combination of two datasets allows multi-class classification between the three states of normal, COVID-19, and types of pneumonia, including bacterial and viral types. A weighted multi-class cross-entropy is used to reduce the effect of data imbalance. In addition, a fuzzy fine-tuned Xception model is applied to reduce the noise propagation in different layers. Quantitative analysis shows that our proposed model achieves 96.60% accuracy on the merged test set, which is more accurate than previously mentioned state-of-the-art methods.

Artificial intelligence-assisted multistrategy image enhancement of chest X-rays for COVID-19 classification

Background

The coronavirus disease 2019 (COVID-19) led to a dramatic increase in the number of cases of patients with pneumonia worldwide. In this study, we aimed to develop an AI-assisted multistrategy image enhancement technique for chest X-ray (CXR) images to improve the accuracy of COVID-19 classification.

Methods

Our new classification strategy consisted of 3 parts. First, the improved U-Net model with a variational encoder segmented the lung region in the CXR images processed by histogram equalization. Second, the residual net (ResNet) model with multidilated-rate convolution layers was used to suppress the bone signals in the 217 lung-only CXR images. A total of 80% of the available data were allocated for training and validation. The other 20% of the remaining data were used for testing. The enhanced CXR images containing only soft tissue information were obtained. Third, the neural network model with a residual cascade was used for the super-resolution reconstruction of low-resolution bone-suppressed CXR images. The training and testing data consisted of 1,200 and 100 CXR images, respectively. To evaluate the new strategy, improved visual geometry group (VGG)-16 and ResNet-18 models were used for the COVID-19 classification task of 2,767 CXR images. The accuracy of the multistrategy enhanced CXR images was verified through comparative experiments with various enhancement images. In terms of quantitative verification, 8-fold cross-validation was performed on the bone suppression model. In terms of evaluating the COVID-19 classification, the CXR images obtained by the improved method were used to train 2 classification models.

Results

Compared with other methods, the CXR images obtained based on the proposed model had better performance in the metrics of peak signal-to-noise ratio and root mean square error. The super-resolution CXR images of bone suppression obtained based on the neural network model were also anatomically close to the real CXR images. Compared with the initial CXR images, the classification accuracy rates of the internal and external testing data on the VGG-16 model increased by 5.09% and 12.81%, respectively, while the values increased by 3.51% and 18.20%, respectively, for the ResNet-18 model. The numerical results were better than those of the single-enhancement, double-enhancement, and no-enhancement CXR images.

Conclusions

The multistrategy enhanced CXR images can help to classify COVID-19 more accurately than the other existing methods.

EVAE-Net: An Ensemble Variational Autoencoder Deep Learning Network for COVID-19 Classification Based on Chest X-ray Images

The COVID-19 pandemic has had a significant impact on many lives and the economies of many countries since late December 2019. Early detection with high accuracy is essential to help break the chain of transmission. Several radiological methodologies, such as CT scan and chest X-ray, have been employed in diagnosing and monitoring COVID-19 disease. Still, these methodologies are time-consuming and require trial and error. Machine learning techniques are currently being applied by several studies to deal with COVID-19. This study exploits the latent embeddings of variational autoencoders combined with ensemble techniques to propose three effective EVAE-Net models to detect COVID-19 disease. Two encoders are trained on chest X-ray images to generate two feature maps. The feature maps are concatenated and passed to either a combined or individual reparameterization phase to generate latent embeddings by sampling from a distribution. The latent embeddings are concatenated and passed to a classification head for classification. The COVID-19 Radiography Dataset from Kaggle is the source of chest X-ray images. The performances of the three models are evaluated. The proposed model shows satisfactory performance, with the best model achieving 99.19% and 98.66% accuracy on four classes and three classes, respectively.

COVID-19 Diagnosis and Classification Using Radiological Imaging and Deep Learning Techniques: A Comparative Study

In December 2019, the novel coronavirus disease 2019 (COVID-19) appeared. Being highly contagious and with no effective treatment available, the only solution was to detect and isolate infected patients to further break the chain of infection. The shortage of test kits and other drawbacks of lab tests motivated researchers to build an automated diagnosis system using chest X-rays and CT scanning. The reviewed works in this study use AI coupled with the radiological image processing of raw chest X-rays and CT images to train various CNN models. They use transfer learning and numerous types of binary and multi-class classifications. The models are trained and validated on several datasets, the attributes of which are also discussed. The obtained results of various algorithms are later compared using performance metrics such as accuracy, F1 score, and AUC. Major challenges faced in this research domain are the limited availability of COVID image data and the high accuracy of the prediction of the severity of patients using deep learning compared to well-known methods of COVID-19 detection such as PCR tests. These automated detection systems using CXR technology are reliable enough to help radiologists in the initial screening and in the immediate diagnosis of infected individuals. They are preferred because of their low cost, availability, and fast results.

Chest X-ray Classification for the Detection of COVID-19 Using Deep Learning Techniques

Recent technological developments pave the path for deep learning-based techniques to be used in almost every domain of life. The precision of deep learning techniques make it possible for these to be used in the medical field for the classification and detection of various diseases. Recently, the coronavirus (COVID-19) pandemic has put a lot of pressure on the health system all around the world. The diagnosis of COVID-19 is possible by PCR testing and medical imagining. Since COVID-19 is highly contagious, diagnosis using chest X-ray is considered safe in various situations. In this study, a deep learning-based technique is proposed to classify COVID-19 infection from other non-COVID-19 infections. To classify COVID-19, three different pre-trained models named EfficientNetB1, NasNetMobile and MobileNetV2 are used. The augmented dataset is used for training deep learning models while two different training strategies have been used for classification. In this study, not only are the deep learning model fine-tuned but also the hyperparameters are fine-tuned, which significantly improves the performance of the fine-tuned deep learning models. Moreover, the classification head is regularized to improve the performance. For the evaluation of the proposed techniques, several performance parameters are used to gauge the performance. EfficientNetB1 with regularized classification head outperforms the other models. The proposed technique successfully classifies four classes that include COVID-19, viral pneumonia, lung opacity, and normal, with an accuracy of 96.13%. The proposed technique shows superiority in terms of accuracy when compared with recent techniques present in the literature.

Gaze Tracking Based on Concatenating Spatial-Temporal Features

Based on experimental observations, there is a correlation between time and consecutive gaze positions in visual behaviors. Previous studies on gaze point estimation usually use images as the input for model trainings without taking into account the sequence relationship between image data. In addition to the spatial features, the temporal features are considered to improve the accuracy in this paper by using videos instead of images as the input data. To be able to capture spatial and temporal features at the same time, the convolutional neural network (CNN) and long short-term memory (LSTM) network are introduced to build a training model. In this way, CNN is used to extract the spatial features, and LSTM correlates temporal features. This paper presents a CNN Concatenating LSTM network (CCLN) that concatenates spatial and temporal features to improve the performance of gaze estimation in the case of time-series videos as the input training data. In addition, the proposed model can be optimized by exploring the numbers of LSTM layers, the influence of batch normalization (BN) and global average pooling layer (GAP) on CCLN. It is generally believed that larger amounts of training data will lead to better models. To provide data for training and prediction, we propose a method for constructing datasets of video for gaze point estimation. The issues are studied, including the effectiveness of different commonly used general models and the impact of transfer learning. Through exhaustive evaluation, it has been proved that the proposed method achieves a better prediction accuracy than the existing CNN-based methods. Finally, 93.1% of the best model and 92.6% of the general model MobileNet are obtained.

Data-Driven Analytics Leveraging Artificial Intelligence in the Era of COVID-19: An Insightful Review of Recent Developments

This paper presents the role of artificial intelligence (AI) and other latest technologies that were employed to fight the recent pandemic (i.e., novel coronavirus disease-2019 (COVID-19)). These technologies assisted the early detection/diagnosis, trends analysis, intervention planning, healthcare burden forecasting, comorbidity analysis, and mitigation and control, to name a few. The key-enablers of these technologies was data that was obtained from heterogeneous sources (i.e., social networks (SN), internet of (medical) things (IoT/IoMT), cellular networks, transport usage, epidemiological investigations, and other digital/sensing platforms). To this end, we provide an insightful overview of the role of data-driven analytics leveraging AI in the era of COVID-19. Specifically, we discuss major services that AI can provide in the context of COVID-19 pandemic based on six grounds, (i) AI role in seven different epidemic containment strategies (a.k.a non-pharmaceutical interventions (NPIs)), (ii) AI role in data life cycle phases employed to control pandemic via digital solutions, (iii) AI role in performing analytics on heterogeneous types of data stemming from the COVID-19 pandemic, (iv) AI role in the healthcare sector in the context of COVID-19 pandemic, (v) general-purpose applications of AI in COVID-19 era, and (vi) AI role in drug design and repurposing (e.g., iteratively aligning protein spikes and applying three/four-fold symmetry to yield a low-resolution candidate template) against COVID-19. Further, we discuss the challenges involved in applying AI to the available data and privacy issues that can arise from personal data transitioning into cyberspace. We also provide a concise overview of other latest technologies that were increasingly applied to limit the spread of the ongoing pandemic. Finally, we discuss the avenues of future research in the respective area. This insightful review aims to highlight existing AI-based technological developments and future research dynamics in this area.

Noninvasive Detection of Respiratory Disorder Due to COVID-19 at the Early Stages in Saudi Arabia

The Kingdom of Saudi Arabia has suffered from COVID-19 disease as part of the global pandemic due to severe acute respiratory syndrome coronavirus 2. The economy of Saudi Arabia also suffered a heavy impact. Several measures were taken to help mitigate its impact and stimulate the economy. In this context, we present a safe and secure WiFi-sensing-based COVID-19 monitoring system exploiting commercially available low-cost wireless devices that can be deployed in different indoor settings within Saudi Arabia. We extracted different activities of daily living and respiratory rates from ubiquitous WiFi signals in terms of channel state information (CSI) and secured them from unauthorized access through permutation and diffusion with multiple substitution boxes using chaos theory. The experiments were performed on healthy participants. We used the variances of the amplitude information of the CSI data and evaluated their security using several security parameters such as the correlation coefficient, mean-squared error (MSE), peak-signal-to-noise ratio (PSNR), entropy, number of pixel change rate (NPCR), and unified average change intensity (UACI). These security metrics, for example, lower correlation and higher entropy, indicate stronger security of the proposed encryption method. Moreover, the NPCR and UACI values were higher than 99% and 30, respectively, which also confirmed the security strength of the encrypted information.

Neonatal Jaundice Diagnosis Using a Smartphone Camera Based on Eye, Skin, and Fused Features with Transfer Learning

Neonatal jaundice is a common condition worldwide. Failure of timely diagnosis and treatment can lead to death or brain injury. Current diagnostic approaches include a painful and time-consuming invasive blood test and non-invasive tests using costly transcutaneous bilirubinometers. Since periodic monitoring is crucial, multiple efforts have been made to develop non-invasive diagnostic tools using a smartphone camera. However, existing works rely either on skin or eye images using statistical or traditional machine learning methods. In this paper, we adopt a deep transfer learning approach based on eye, skin, and fused images. We also trained well-known traditional machine learning models, including multi-layer perceptron (MLP), support vector machine (SVM), decision tree (DT), and random forest (RF), and compared their performance with that of the transfer learning model. We collected our dataset using a smartphone camera. Moreover, unlike most of the existing contributions, we report accuracy, precision, recall, f-score, and area under the curve (AUC) for all the experiments and analyzed their significance statistically. Our results indicate that the transfer learning model performed the best with skin images, while traditional models achieved the best performance with eyes and fused features. Further, we found that the transfer learning model with skin features performed comparably to the MLP model with eye features.