COVID-19 Classification Using Medical Image Synthesis by Generative Adversarial Networks

Recent progress in COVID-19 detection techniques involve deep learning models. The patient’s image data like Chest X-Ray Images, CT-scan data help the physician for analyzing whether the patient is COVID-19 positive or negative. However, huge data size is essential for improving the classification accuracy of deep learning model. Data Augmentation (DA) is a promising solution to generate synthetic samples of data. Sampling is a traditional data augmentation technique to generate synthetic samples. Recently, Generative Adversarial Networks (GAN) have declared in generating high quality synthetic data from acutal small data to treat imbalance issue. This work proposed a method called GAN based Deep 2D-CNN (G-DCNN) for COVID-19 recognition. In this study, GAN has been used for synthesizing Chest X-Ray and CT-scan images followed by Deep 2D-CNN with the goal of detecting COVID-19.

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

Chest X-ray image quality is crucial for accurate medical diagnosis, yet acquired images are often degraded by noise, which can obscure important anatomical details. This work presents a deep learning–based denoising framework for chest X-ray images using a customized U-Net-like architecture combined with adversarial learning. Normal chest X-ray images from the Kaggle Chest X-ray Pneumonia dataset are preprocessed, resized, and synthetically corrupted with Gaussian noise to generate paired noisy and clean training samples. The proposed generator network, termed SharpXRLikeUNet, integrates Laplacian filtering to enhance edge preservation during denoising. Initially, the model is trained using a composite loss function consisting of L1 loss, structural similarity index measure (SSIM) loss, and perceptual loss derived from a pretrained VGG16 network. To further improve visual realism, a generative adversarial network (GAN) framework is employed by introducing a patch-based discriminator, and an adversarial loss component is incorporated into the generator objective. Experimental results demonstrate effective noise reduction while preserving fine structural details in chest X-ray images. The trained models are saved, and the generator is exported to ONNX format to support efficient deployment and cross-platform inference.

目的 基于计算机的胸腔X线影像疾病检测和分类目前存在误诊率高，准确率低的问题。本文在视觉Transformer（vision Transformer，ViT）预训练模型的基础上，通过迁移学习方法，实现胸腔X线影像辅助诊断，提高诊断准确率和效率。方法 选用带有卷积神经网络（convolutional neural network，CNN）的ViT模型，其在超大规模自然图像数据集中进行了预训练；通过微调模型结构，使用预训练的ViT模型参数初始化主干网络，并迁移至胸腔X线影像数据集中再次训练，实现疾病多标签分类。结果 在IU X-Ray数据集中对ViT迁移学习前、后模型平均AUC（area under ROC curve）得分进行对比分析实验。结果表明，预训练ViT模型平均AUC得分为0.774，与不使用迁移学习相比提升了0.208。并针对模型结构和数据预处理进行了消融实验，对ViT中的注意力机制进行可视化，进一步验证了模型有效性。最后使用Chest X-Ray14和CheXpert数据集训练微调后的ViT模型，平均AUC得分为0.839和0.806，与对比方法相比分别有0.014～0.031的提升。结论 与其他方法相比，ViT模型胸腔X线影像的多标签分类精确度更高，且迁移学习可以在降低训练成本的同时提升ViT模型的分类性能和泛化性。消融实验与模型可视化表明，包含CNN结构的ViT模型能重点关注有意义的区域，高效获取胸腔X线影像的视觉特征。;Objective The chest X-ray-relevant screening and diagnostic method is essential for radiology nowadays. Most of chest X-ray images interpretation is still restricted by clinical experience and challenged for misdiagnose and missed diagnoses. To detect and identify one or more potential diseases in images automatically，it is beneficial for improving diagnostic efficiency and accuracy using computer-based technique. Compared to natural images，multiple lesions are challenged to be detected and distinguished accurately in a single image because abnormal areas have a small proportion and complex representations in chest X-ray images. Current convolutional neural network（CNN）based deep learning models have been widely used in the context of medical imaging. The structure of the CNN convolution kernel has sensitive to local detail information，and it is possible to extract richer image features. However，the convolution kernel cannot be used to get global information，and the features-extracted are restricted of redundant information like its relevance of background， muscles，and bones. The model’s performance in multi-label classification tasks are affected to a certain extent. At present，the vision Transformer（ViT）model has achieved its priorities in computer vision-related tasks. The ViT can be used to capture information simultaneously and effectively for multiple regions of the entire image. However，it is required to use large-scale dataset training to achieve good performance. Due to some factors like patient privacy and manual annotate costs，the size of the chest X-ray image data set has been limited. To reduce the model's dependence on data scale and improve the performance of multi-label classification，we develop the CNN-based ViT pre-training model in terms of the transfer learning method for diagnosis-assisted of chest X-ray image and multi-label classification. Method The CNN-based ViT model is pre-trained on a huge scale ground truth dataset，and it is used to obtain the initial parameters of the model. The model structure is fine-tuned according to the features of chest X-ray dataset. A 1×1 convolution layer is used to convert the chest X-ray images channels between 1 to 3. The number of output nodes of the linear layer in the classifier is balanced from 1 000 to the number of chest X-ray classification labels，and the Sigmoid is used as an activation function. The parameters of the backbone network are initialized in terms of the pre-trained ViT model parameters，and it is trained in the chest X-ray dataset after that to complete multi-label classification. The experiment is configured of Python3. 7 and PyTorch1. 8 to construct the model and RTX3090 GPU for training. Stochastic gradient descent（SGD）optimizer，binary cross-entropy（BCE）loss function，an initial learning rate of 1E-3，the cosine annealing learning rate decay are used. For training，each image is scaled to a size of 512×512 pixels，and a 224×224 pixels area and it is then cropped in random as the model input，and data augmentation is performed randomly by some of the flipping，perspective transformation， shearing，translation，zooming，and changing brightness. For testing，the chest X-ray image is scaled to 256×256 pixels and center crop a 224×224 area to input the trained model. Result The experiment is performed on the IU X-Ray，which is a small-scale chest X-ray dataset. This model is evaluated in quantitative using the average of area under ROC curve （AUC）scores across all classification labels. The results show that the average AUC score of the pre-trained ViT model is 0. 774. The accuracy and training efficiency of the non-pre-trained ViT model is dropped significantly. The average AUC score is reached to 0. 566 only，which is 0. 208 lower. In addition，the attention mechanism heat map is generated based on the ViT model，which can strengthen the interpretability of the model. A series of ablation experiments are carried out for data augmentation，model structure，and batch size design. The fine-tuned ViT model is trained on the Chest-Ray14 and CheXpert dataset as well. The average AUC score is reached to 0. 839 and 0. 806，which is optimized by 0. 014 and 0. 031. Conclusion A pre-trained ViT model is used for the multi-label classification of chest X-ray images via transfer learning. The experimental results illustrate that the ViT has its stronger multi-label classification performance in chest Xray images，and its attention mechanism is beneficial for lesions precision-focused like the interior of the chest cavity and the heart. Transfer learning is potential to improve the classification performance and model generalization of the ViT in small-scale datasets，and the training cost is reduced greatly. Ablation experiments demonstrate that the incorporated model of CNN and Transformer has its priority beyond single-structure model. Data enhancement and the batch size cutting can improve the performance of the model，but smaller scale of batch is still interlinked to longer training span. To improve the model's ability，we predict that future research direction can be focused on the extraction for complex disease and highlevel semantic information，such as their small lesions，disease location，and severity.

Classification of COVID-19 chest X-Ray and CT images using a type of dynamic CNN modification method

The identification of COVID-19 using chest X-ray (CXR) images plays a critical role in managing the pandemic by providing a rapid, non-invasive, and accessible diagnostic tool. This study evaluates the impact of different image preprocessing techniques on the performance of deep learning models for COVID-19 classification based on COVID-19 Radiography Database, which includes 10,192 normal CXR images, 6012 lung opacity (non-COVID lung infection) images, and 1345 viral pneumonia images. Along with the images, corresponding lung masks are also included to aid in the segmentation and analysis of lung regions. Specifically, three convolutional neural network (CNN) models were developed, each using a distinct preprocessing method: Contrast Limited Adaptive Histogram Equalization (CLAHE), traditional histogram equalization, and no preprocessing. The results revealed that while the CLAHE-enhanced model achieved the highest training accuracy (93.26%) and demonstrated superior stability during training, it showed lower performance in the validation phase, with validation accuracy of 91.31%. In contrast, the model with no preprocessing, which exhibited slightly lower training accuracy (92.98%), outperformed the CLAHE model during validation, achieving the highest validation accuracy of 91.50% and the lowest validation loss. The histogram equalization model demonstrated performance similar to that of CLAHE but with slightly higher validation loss and accuracy compared to the unprocessed model. These findings suggest that while CLAHE excels in enhancing image details during training, it may lead to overfitting and reduced generalization ability. In contrast, the model without preprocessing showed the best generalization and stability, indicating that preprocessing techniques should be chosen carefully to balance feature enhancement with the need for generalization in real-world applications. This study underscores the importance of selecting appropriate image preprocessing techniques to enhance deep learning models' performance in medical image classification, particularly for COVID-19 detection. Histogram Equalization The results contribute to ongoing efforts to optimize diagnostic tools using AI and image processing.

IEViT: An enhanced vision transformer architecture for chest X-ray image classification

Pneumonia, a severe lung infection caused by various viruses, presents significant challenges in diagnosis and treatment due to its similarities with other respiratory conditions. Additionally, the need to protect patient privacy complicates the sharing of sensitive clinical data. This study introduces FLPneXAINet, an effective framework that combines federated learning (FL) with deep learning (DL) and explainable AI (XAI) to securely and accurately predict pneumonia using chest X-ray (CXR) images. We utilized a benchmark dataset from Kaggle, comprising 8,402 CXR images (3,904 normal and 4,498 pneumonia). The dataset was preprocessed and augmented using a cycle-consistent generative adversarial (CycleGAN) network to increase the volume of training data. Three pre-trained DL models named VGG16, NASNetMobile, and MobileNet were employed to extract features from the augmented dataset. Further, four ensemble DL (EDL) models were used to enhance feature extraction. Feature optimization was performed using recursive feature elimination (RFE), analysis of variance (ANOVA), and random forest (RF) to select the most relevant features. These optimized features were then inputted into machine learning (ML) models, including K-nearest neighbor (KNN), naive bayes (NB), support vector machine (SVM), and RF, for pneumonia prediction. The performance of the models was evaluated in a FL environment, with the EDL network achieving the best results: accuracy 97.61%, F1 score 98.36%, recall 98.13%, and precision 98.59%. The framework's predictions were further validated using two XAI techniques-Local Interpretable Model-Agnostic Explanations (LIME) and Grad-CAM. FLPneXAINet offers a robust solution for healthcare professionals to accurately diagnose pneumonia, ensuring timely treatment while safeguarding patient privacy.

Coronavirus disease-19 (COVID-19) has rapidly spread all over the world. It is found that the low sensitivity of reverse transcription-polymerase chain reaction (RT-PCR) examinations during the early stage of COVID-19 disease. Thus, efficient models are desirable for early-stage testing of COVID-19 infected patients. Chest X-ray (CXR) images of COVID-19 infected patients have shown some bilateral changes. In this paper, deep transfer learning and a deep forest-based model are proposed to diagnose COVID-19 infection from CXR images. Initially, features of X-ray images are extracted using the well-known deep transfer learning model (i.e., ResNet101), which does not require tuning many parameters compared to the deep convolutional neural network (CNN). After that, the deep forest model is utilised to predict COVID-19 infected patients. The deep forest is based upon ensemble learning and requires a small number of hyper-parameters. Additionally, the proposed model is trained on a multi-class dataset that contains four different classes as COVID-19 (+), pneumonia, tuberculosis, and healthy patients. The comparisons are drawn among the proposed deep transfer learning and deep forest-based models, the competitive models. The obtained results show that the proposed model effectively diagnoses COVID-19 infection with an accuracy of 99.4%.

In this presentation, we quantify the uncertainty of deep neural networks (DNNs) for the task of Chest X-Ray (CXR) image classification. We investigate uncertainties of several commonly used DNN architectures including ResNet, ResNeXt, DenseNet and SENet. We propose an uncertainty based strategy and analyze the impact of this strategy on the classifier performance. Results show that utilizing uncertainty information may improve DNN performance for some metrics and observations.

Reasons for healthcare workers becoming infected with novel coronavirus disease 2019 (COVID-19) in China

BackgroundThis study was conducted to alleviate a common difficulty in chest X-ray image diagnosis: The attention region in a convolutional neural network (CNN) does not often match the doctor’s point of focus. The method presented herein, which guides the area of attention in CNN to a medically plausible region, can thereby improve diagnostic capabilities.MethodsThe model is based on an attention branch network, which has excellent interpretability of the classification model. This model has an additional new operation branch that guides the attention region to the lung field and heart in chest X-ray images. We also used three chest X-ray image datasets (Teikyo, Tokushima, and ChestX-ray14) to evaluate the CNN attention area of interest in these fields. Additionally, after devising a quantitative method of evaluating improvement of a CNN’s region of interest, we applied it to evaluation of the proposed model.ResultsOperation branch networks maintain or improve the area under the curve to a greater degree than conventional CNNs do. Furthermore, the network better emphasizes reasonable anatomical parts in chest X-ray images.ConclusionsThe proposed network better emphasizes the reasonable anatomical parts in chest X-ray images. This method can enhance capabilities for image interpretation based on judgment.

PurposeTo develop generative adversarial networks (GANs) that synthesize realistic anterior segment optical coherence tomography (AS-OCT) images and evaluate deep learning (DL) models that are trained on real and synthetic datasets for detecting angle closure.MethodsThe GAN architecture was adopted and trained on the dataset with AS-OCT images collected from the Joint Shantou International Eye Center of Shantou University and the Chinese University of Hong Kong, synthesizing open- and closed-angle AS-OCT images. A visual Turing test with two glaucoma specialists was performed to assess the image quality of real and synthetic images. DL models, trained on either real or synthetic datasets, were developed. Using the clinicians’ grading of the AS-OCT images as the reference standard, we compared the diagnostic performance of open-angle vs. closed-angle detection of DL models and the AS-OCT parameter, defined as a trabecular-iris space area 750 µm anterior to the scleral spur (TISA750), in a small independent validation dataset.ResultsThe GAN training included 28,643 AS-OCT anterior chamber angle (ACA) images. The real and synthetic datasets for DL model training have an equal distribution of open- and closed-angle images (all with 10,000 images each). The independent validation dataset included 238 open-angle and 243 closed-angle AS-OCT ACA images. The image quality of real versus synthetic AS-OCT images was similar, as assessed by the two glaucoma specialists, except for the scleral spur visibility. For the independent validation dataset, both DL models achieved higher areas under the curve compared with TISA750. Two DL models had areas under the curve of 0.97 (95% confidence interval, 0.96–0.99) and 0.94 (95% confidence interval, 0.92–0.96).ConclusionsThe GAN synthetic AS-OCT images appeared to be of good quality, according to the glaucoma specialists. The DL models, trained on all-synthetic AS-OCT images, can achieve high diagnostic performance.Translational RelevanceThe GANs can generate realistic AS-OCT images, which can also be used to train DL models.

The COVID-19 pandemic has created havoc on the lives of many people and their health all over the world. It has been increasing very rapidly, one must find an effective model/method to detect COVID-19 in order to help the Health Care System. Chest X-ray is one of the reliable diagnostic technologies, which helps in the identification of COVID-19. Despite the fact that there are numerous deep learning methodologies for identifying COVID -19, these methodologies are useless if they only detect one type of illness while ignoring the others. This study proposed a Hybrid Classification model based on CNN (Convolutional Neural Network) for more efficient detection of COVID-19 from Chest X-Rays. Using CNN, this study differentiates COVID-19 affected chest X-Ray images from normal chest X-Ray images and eight additional chest disorders (Cardiomegaly, Atelectasis, Infiltration, Effusion, Nodule, Pneumonia, Mass, Pneumothorax). The Hybrid Classification Model contains two classifiers, Classifier-1 and Classifier-2. In Classifier-1, it contains the information about Normal Chest X-rays images and chest X-ray images that have been affected by COVID-19 and whereas in the Classifier-2, it contains the information about other 8 chest diseases. For getting highest accuracy of Classifier-1 and Classifier-2 models, this research work utilizes several models i.e., ResNet50, InceptionResNetV2, VGG16, DensNet121 and Mobile Net. Based on all these models, this research work considers ResNet50 for Classifier-1, and DensNet121 for Classifier-2, Because these two models had given the highest accuracy compared to other models.

Amid the COVID-19 pandemic, extensive research has focused on deep learning methodologies for accurately diagnosing the virus from chest X-ray images. Various models, including Convolutional Neural Networks (CNNs) and pre-trained models, have achieved accuracies ranging from 85.20% to 99.66%. However, the proposed Fine-Tuned ResNet50 model consistently outperforms others with an impressive accuracy of 98.20%. By leveraging on transfer learning and careful architectural design the proposed model demonstrates superior performance compared to previous studies using DarkNet, ResNet50, and pre-trained models. Graphical comparisons highlight its competitive edge, emphasizing its effectiveness in COVID-19 classification tasks. The ResNet50 architecture, known for its deep residual layers and skip connections, facilitates robust feature extraction and classification, especially in medical imaging. Data pre-processing techniques, like noise reduction and contrast enhancement, ensure input data quality and reliability, enhancing the model's predictive abilities. Training results reveal the model's steady accuracy improvement and loss reduction over 20 epochs, aligning closely with validation metrics. Evaluation on a test set of COVID-19 chest X-ray images confirms exceptional accuracy (98.20%), precision (99.00%), recall (98.82%), and F1-score (98.91%), highlighting its proficiency in identifying COVID-19 cases while minimizing false positives and negatives. Comparative analyses against prior studies further validate its superior performance, establishing the Fine-Tuned ResNet50 model as a reliable tool for COVID-19 diagnosis. Future research should focus on exploring ensemble learning techniques, interpretability methods, and stakeholder collaboration to ensure safe AI deployment in clinical settings. Moreover, larger and diverse datasets are crucial for validating model performance and improving generalization, ultimately enhancing patient care and public health outcomes in the mitigating COVID-19 and future pandemics.