Classification of COVID-19 cases from chest CT volumes using hybrid model of 3D CNN and 3D MLP-Mixer

This paper proposes an automated classification method of COVID-19 chest CT volumes using improved 3D MLP-Mixer. Novel coronavirus disease 2019 (COVID-19) spreads over the world, causing a large number of infected patients and deaths. Sudden increase in the number of COVID-19 patients causes a manpower shortage in medical institutions. Computer-aided diagnosis (CAD) system provides quick and quantitative diagnosis results. CAD system for COVID-19 enables efficient diagnosis workflow and contributes to reduce such manpower shortage. In image-based diagnosis of viral pneumonia cases including COVID-19, both local and global image features are important because viral pneumonia cause many ground glass opacities and consolidations in large areas in the lung. This paper proposes an automated classification method of chest CT volumes for COVID-19 diagnosis assistance. MLP-Mixer is a recent method of image classification using Vision Transformer-like architecture. It performs classification using both local and global image features. To classify 3D CT volumes, we developed a hybrid classification model that consists of both a 3D convolutional neural network (CNN) and a 3D version of the MLP-Mixer. Classification accuracy of the proposed method was evaluated using a dataset that contains 1205 CT volumes and obtained 79.5% of classification accuracy. The accuracy was higher than that of conventional 3D CNN models consists of 3D CNN layers and simple MLP layers. © 2023 SPIE.

COVID-19 Identification From Lung CT Scans in a Low-Resource Setting Using a Regularized 3D Convolutional Neural Network

Right at the end of 2019, the world saw an outbreak of a new type of SARS (severe acute respiratory syndrome) disease, SARS-Cov-2, or COVID-19. Even in 2022, around 1 million people worldwide are getting infected with the virus every day. To date, more than 6 million people have died as a result of the virus. To tackle the pandemic, the first step is to successfully detect the virus among the mass population. The most popular method is the RT-PCR test, which, unfortunately, is not always conclusive. The physicians thus suggest lung CT tests for the patients for clinical relevance. But the problem with lung CT scans for the detection of coronavirus is that the COVID-19 infected scan is very similar to community-affected pneumonia (CAP) infected scan, and the results in many cases get wrongly interpreted. In addition, the virus is always mutating into different strains, and the severity and infection pattern slightly change with each mutation. Because of this rapid mutation, a large and balanced dataset of lung CT scans is not always available. In this work, we systematically evaluate the accuracy of a deep 3D convolutional neural network (CNN) on a small-scale and highly imbalanced dataset of lung CT scans (the SPGC COVID 2021 dataset). Our experiments show that it can outperform previous state-of-the-art 3D CNN models with proper regularization, an appropriate number of dense layers, and a weighted loss function. Our research, therefore, suggests an effective solution for identifying COVID-19 in lung CT scans using deep learning for small and highly imbalanced datasets. © 2022 IEEE.

3D CNN-Based Classification of Severity in COVID-19 Using CT Images

With the pandemic worldwide due to COVID-19, several detections and diagnostic methods have been in place. One of the standard modes of detection is computed tomography imaging. With the availability of computing resources and powerful GPUs, the analyses of extensive image data have been possible. Our proposed work initially deals with the classification of CT images as normal and infected images, and later, from the infected data, the images are classified based on their severity. The proposed work uses a 3D convolution neural network model to extract all the relevant features from the CT scan images. The results are also compared with the existing state-of-the-art algorithms. The proposed work is evaluated in accuracy, precision, recall, kappa value, and Intersection over Union. The model achieved an overall accuracy of 94.234% and a kappa value of 0.894. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Two-Stage COVID19 Classification Using BERT Features

We propose an automatic COVID1-19 diagnosis framework from lung CT-scan slice images using double BERT feature extraction. In the first BERT feature extraction, A 3D-CNN is first used to extract CNN internal feature maps. Instead of using the global average pooling, a late BERT temporal pooing is used to aggregate the temporal information in these feature maps, followed by a classification layer. This 3D-CNN-BERT classification network is first trained on sampled fixed number of slice images from every original CT scan volume. In the second stage, the 3D-CNN-BERT embedding features are extracted for every 32 slice images sequentially, and these features are divided into fixed number of segments. Then another BERT network is used to aggregate these features into a single feature followed by another classification layer. The classification results of both stages are combined to generate final outputs. On the validation dataset, we achieve macro F1 score 92.05%;and on the testing dataset, we achieve macro F1 84.43%. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

GTA 3D-DLD: Greedy Training Approach for 3D Deep Learning Diagnosis Based COVID‑19 CT Scan

A numeral of deep learning models has been suggested for COVID-19 examination in computed tomography (CT) scans as an automation tool to help in diagnosis. Although, deep learning models achieved high accuracy, but training approaches are still inefficient to detect injections due to some deep learning models did not meet the requirement of a generalization term in deep learning. Furthermore, other traditional algorithms achieved low detection for 3D CT. Therefore, is high time to develop a deep learning model to diagnose COVID-19 infections in a regularization mode. In this research, greedy learning approach (GLA) is utilized to design and implement the 3D convolutional neural network (3D CNN) model, greedy learning approach is consistings of two stages;the first stage generates many 3D CNN models based on the randomness in the layers, for providing many movements toward solving one problem which is diagnosing COVID-19.Then, the second stage selects an optimal 3D CNN model based on high accuracy of 3D CNNs obtained in the first stage, optimal 3D CNN model is to be significate solution among them. We evaluate the proposed approach on the 3D Mosmed-1110 and 2D SARS-CoV-2 CT Datasets, the best accuracy scores obtained by the present approach are 1.00% and 98.87% respectively on the said datasets in terms of metrics, such as accuracy, precision, recall, and F1. The proposed system also exhibited good generalization and robustness, when it was trained and tested using a portion of data (80%) and (20%). © 2023, International Journal of Intelligent Engineering and Systems. All Rights Reserved.

DECOVID-CT: Lightweight 3D CNN for COVID-19 Infection Prediction

The COVID-19 pandemic has become a critical threat to global health and the economy since its first outbreak in 2019. The standard diagnosis for COVID-19, Reverse Transcription Polymerase Chain Reaction (RT-PCR) is time consuming, and has lower sensitivity compared to CT-scans. Therefore, CT-scans can be used as a complementary method, alongside RT-PCR tests for COVID-19 infection prediction. However, manually reviewing CT scans is time consuming. In this paper, we propose DECOVID-CT, a deep learning model based on 3D convolutional neural network (CNN) for the detection of COVID-19 infection with CT images. The model is trained and tested on the RICORD dataset, a multinational dataset, for higher robustness. Our model achieved an accuracy of 100%, for predicting COVID-19 positive images. © 2022 IEEE.

A General Preprocessing Pipeline for Deep Learning on Radiology Images: A COVID-19 Case Study

During the last years, deep learning has been used intensively in medical domain making considerable progress in the diagnosis of diseases from radiology images. This is mainly due to the availability of proven algorithms on several computer vision tasks and the publicly accessible medical datasets. However, most approaches that apply deep learning techniques to radiology images transform these images into a format that conforms with the inputs of conventional learning algorithms and deal with the dataset as a set of 2D independent slices instead of volumetric images. In this work we deal with the problem of preparing DICOM CT scans as 3D images for a machine learning/deep learning architecture. We propose a general preprocessing pipeline composed of four stages for volumetric images processing followed by a 3D CNN architecture for 3D images classification. The proposed pipeline is evaluated through a case study for COVID-19 detection from chest CT scans. Experiment results demonstrate the effectiveness of the proposed preprocessing operations. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

3D Convolutional Neural Network for Covid Assessment on CT Scans

Due to the rapid spread of the COVID-19 respiratory pathology, an effective diagnosis of positive cases is necessary to stop the contamination. CT scans offer a 3D view of the patient’s thorax and COVID-19 appears as ground glass opacities on these images. This paper describes a deep learning based approach to automatically classify CT scan images as COVID-19 or not COVID-19. We first build a dataset and preprocess this data. Preprocessing includes normalization, resizing and data augmentation. Then, the training step is based on a neural network used for tuberculosis pathology. Training of the dataset is performed using a 3D convolutional neural network. The results of the neural network model on the test set returns an accuracy of 80%. A prototype of the approach is implemented in a form of a web application to assist doctors and speed up the COVID-19 diagnosis. Codes of both the training and the web application are available online for further research. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

A COVID-19 PATIENT SEVERITY STRATIFICATION USING A 3D CONVOLUTIONAL STRATEGY ON CT-SCANS

This work introduces a 3D deep learning methodology to stratify patients according to the severity of lung infection caused by COVID-19 disease on computerized tomography images (CT). A set of volumetric attention maps were also obtained to explain the results and support the diagnostic tasks. The validation of the approach was carried out on a dataset composed of 350 patients, diagnosed by the RT-PCR assay either as negative (control - 175) or positive (COVID-19 - 175). Additionally, the patients were graded (0-25) by two expert radiologists according to the extent of lobar involvement. These gradings were used to define 5 COVID-19 severity categories. The model yields an average 60% accuracy for the multi-severity classification task. Additionally, a set of Mann Whitney U significance tests were conducted to compare the severity groups. Results show that patients in different severity groups have significantly different severity scores (p < 0.01) for all the compared severity groups.

LCOV-NET: A LIGHTWEIGHT NEURAL NETWORK FOR COVID-19 PNEUMONIA LESION SEGMENTATION FROM 3D CT IMAGES

The wide spread of coronavirus disease 2019 (COVID-19) has become a global concern and millions of people have been infected. Chest Computed Tomography (CT) imaging is important for screening and diagnosis of this disease, where segmentation of the lung infections plays a critical role for quantitative assessment of the disease progression. Currently, 3D Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance for automatic medical image segmentation tasks. However, most 3D segmentation CNNs have a large set of parameters and huge floating point operations (FLOPs), causing high command for equipments. In this work, we propose LCOV-Net, a lightweight 3D CNN for accurate segmentation of COVID-19 pneumonia lesions from CT volumes. The core component of LCOV-Net is a lightweight attention-based convolutional block (LACB), which consists of a spatiotemporal separable convolution branch to reduce parameters and a lightweight feature calibration branch to improve the learning ability. We combined our LACB module with 3D U-Net as LCOV-Net, and tested our method on a dataset of CT scans of 130 COVID-19 patients for the infection lesion segmentation. Experimental results show that: (1) our LCOV-Net outperforms existing lightweight networks for 3D segmentation and (2) compared with the widely used 3D U-Net, our LCOV-Net improved the Dice score by around 20.36% and reduced the parameter number by 90.16%, leading to 27.93% speedup. Models and code are available at https://github.com/afeizqf/LCOVNet.

CT-based severity assessment for COVID-19 using weakly supervised non-local CNN.

Evaluating patient criticality is the foremost step in administering appropriate COVID-19 treatment protocols. Learning an Artificial Intelligence (AI) model from clinical data for automatic risk-stratification enables accelerated response to patients displaying critical indicators. Chest CT manifestations including ground-glass opacities and consolidations are a reliable indicator for prognostic studies and show variability with patient condition. To this end, we propose a novel attention framework to estimate COVID-19 severity as a regression score from a weakly annotated CT scan dataset. It takes a non-locality approach that correlates features across different parts and spatial scales of the 3D scan. An explicit guidance mechanism from limited infection labeling drives attention refinement and feature modulation. The resulting encoded representation is further enriched through cross-channel attention. The attention model also infuses global contextual awareness into the deep voxel features by querying the base CT scan to mine relevant features. Consequently, it learns to effectively localize its focus region and chisel out the infection precisely. Experimental validation on the MosMed dataset shows that the proposed architecture has significant potential in augmenting existing methods as it achieved a 0.84 R-squared score and 0.133 mean absolute difference.

Recognition of Peripheral Lung Cancer and Focal Pneumonia on Chest Computed Tomography Images Based on Convolutional Neural Network.

Introduction: Chest computed tomography (CT) is important for the early screening of lung diseases and clinical diagnosis, particularly during the COVID-19 pandemic. We propose a method for classifying peripheral lung cancer and focal pneumonia on chest CT images and undertake 5 window settings to study the effect on the artificial intelligence processing results. Methods: A retrospective collection of CT images from 357 patients with peripheral lung cancer having solitary solid nodule or focal pneumonia with a solitary consolidation was applied. We segmented and aligned the lung parenchyma based on some morphological methods and cropped this region of the lung parenchyma with the minimum 3D bounding box. Using these 3D cropped volumes of all cases, we designed a 3D neural network to classify them into 2 categories. We also compared the classification results of the 3 physicians with different experience levels on the same dataset. Results: We conducted experiments using 5 window settings. After cropping and alignment based on an automatic preprocessing procedure, our neural network achieved an average classification accuracy of 91.596% under a 5-fold cross-validation in the full window, in which the area under the curve (AUC) was 0.946. The classification accuracy and AUC value were 90.48% and 0.957 for the junior physician, 94.96% and 0.989 for the intermediate physician, and 96.92% and 0.980 for the senior physician, respectively. After removing the error prediction, the accuracy improved significantly, reaching 98.79% in the self-defined window2. Conclusion: Using the proposed neural network, in separating peripheral lung cancer and focal pneumonia in chest CT data, we achieved an accuracy competitive to that of a junior physician. Through a data ablation study, the proposed 3D CNN can achieve a slightly higher accuracy compared with senior physicians in the same subset. The self-defined window2 was the best for data training and evaluation.

Attention-based 3D CNN with residual connections for efficient ECG-based COVID-19 detection.

BACKGROUND: The world has been suffering from the COVID-19 pandemic since 2019. More than 5 million people have died. Pneumonia is caused by the COVID-19 virus, which can be diagnosed using chest X-ray and computed tomography (CT) scans. COVID-19 also causes clinical and subclinical cardiovascular injury that may be detected on electrocardiography (ECG), which is easily accessible. METHOD: For ECG-based COVID-19 detection, we developed a novel attention-based 3D convolutional neural network (CNN) model with residual connections (RC). In this paper, the deep learning (DL) approach was developed using 12-lead ECG printouts obtained from 250 normal subjects, 250 patients with COVID-19 and 250 with abnormal heartbeat. For binary classification, the COVID-19 and normal classes were considered; and for multiclass classification, all classes. The ECGs were preprocessed into standard ECG lead segments that were channeled into 12-dimensional volumes as input to the network model. Our developed model comprised of 19 layers with three 3D convolutional, three batch normalization, three rectified linear unit, two dropouts, two additional (for residual connections), one attention, and one fully connected layer. The RC were used to improve gradient flow through the developed network, and attention layer, to connect the second residual connection to the fully connected layer through the batch normalization layer. RESULTS: A publicly available dataset was used in this work. We obtained average accuracies of 99.0% and 92.0% for binary and multiclass classifications, respectively, using ten-fold cross-validation. Our proposed model is ready to be tested with a huge ECG database.

A novel study for automatic two-class COVID-19 diagnosis (between COVID-19 and Healthy, Pneumonia) on X-ray images using texture analysis and 2-D/3-D convolutional neural networks.

The pandemic caused by the COVID-19 virus affects the world widely and heavily. When examining the CT, X-ray, and ultrasound images, radiologists must first determine whether there are signs of COVID-19 in the images. That is, COVID-19/Healthy detection is made. The second determination is the separation of pneumonia caused by the COVID-19 virus and pneumonia caused by a bacteria or virus other than COVID-19. This distinction is key in determining the treatment and isolation procedure to be applied to the patient. In this study, which aims to diagnose COVID-19 early using X-ray images, automatic two-class classification was carried out in four different titles: COVID-19/Healthy, COVID-19 Pneumonia/Bacterial Pneumonia, COVID-19 Pneumonia/Viral Pneumonia, and COVID-19 Pneumonia/Other Pneumonia. For this study, 3405 COVID-19, 2780 Bacterial Pneumonia, 1493 Viral Pneumonia, and 1989 Healthy images obtained by combining eight different data sets with open access were used. In the study, besides using the original X-ray images alone, classification results were obtained by accessing the images obtained using Local Binary Pattern (LBP) and Local Entropy (LE). The classification procedures were repeated for the images that were combined with the original images, LBP, and LE images in various combinations. 2-D CNN (Two-Dimensional Convolutional Neural Networks) and 3-D CNN (Three-Dimensional Convolutional Neural Networks) architectures were used as classifiers within the scope of the study. Mobilenetv2, Resnet101, and Googlenet architectures were used in the study as a 2-D CNN. A 24-layer 3-D CNN architecture has also been designed and used. Our study is the first to analyze the effect of diversification of input data type on classification results of 2-D/3-D CNN architectures. The results obtained within the scope of the study indicate that diversifying X-ray images with tissue analysis methods in the diagnosis of COVID-19 and including CNN input provides significant improvements in the results. Also, it is understood that the 3-D CNN architecture can be an important alternative to achieve a high classification result.

DIAGNOSIS of COVID-19 USING 3D CONVOLUTIONAL NEURAL NETWORKS

To stop the fast-spreading of covid19, there needs to be a significant improvement in the speed with which the diagnosis is performed. Many studies have been done on using deep learning algorithms like convolutional neural networks and many of its variants available in the industry to make the diagnosis faster. However, most of these approaches involve using datasets that are not that compatible with the real world. In this paper, we will be using efficient techniques to address this problem by using CT scans and leveraging most of the features available in CT-scan images to build a model that can classify whether covid19 infects a person or not, given his CT scan as input to the model. As CT scan images are more reliable and can represent the condition of a person in a more detailed way than any other images like X-rays, these can be used for obtaining faster and precise results. © 2021 Little Lion Scientific

Multi-center sparse learning and decision fusion for automatic COVID-19 diagnosis.

The coronavirus disease 2019 (COVID-19) pandemic caused by the novel severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has led to a sharp increase in hospitalized patients with multi-organ disease pneumonia. Early and automatic diagnosis of COVID-19 is essential to slow down the spread of this epidemic and reduce the mortality of patients infected with SARS-CoV-2. In this paper, we propose a joint multi-center sparse learning (MCSL) and decision fusion scheme exploiting chest CT images for automatic COVID-19 diagnosis. Specifically, considering the inconsistency of data in multiple centers, we first convert CT images into histogram of oriented gradient (HOG) images to reduce the structural differences between multi-center data and enhance the generalization performance. We then exploit a 3-dimensional convolutional neural network (3D-CNN) model to learn the useful information between and within 3D HOG image slices and extract multi-center features. Furthermore, we employ the proposed MCSL method that learns the intrinsic structure between multiple centers and within each center, which selects discriminative features to jointly train multi-center classifiers. Finally, we fuse these decisions made by these classifiers. Extensive experiments are performed on chest CT images from five centers to validate the effectiveness of the proposed method. The results demonstrate that the proposed method can improve COVID-19 diagnosis performance and outperform the state-of-the-art methods.

Hybrid-COVID: a novel hybrid 2D/3D CNN based on cross-domain adaptation approach for COVID-19 screening from chest X-ray images.

The novel Coronavirus disease (COVID-19), which first appeared at the end of December 2019, continues to spread rapidly in most countries of the world. Respiratory infections occur primarily in the majority of patients treated with COVID-19. In light of the growing number of COVID-19 cases, the need for diagnostic tools to identify COVID-19 infection at early stages is of vital importance. For decades, chest X-ray (CXR) technologies have proven their ability to accurately detect respiratory diseases. More recently, with the availability of COVID-19 CXR scans, deep learning algorithms have played a critical role in the healthcare arena by allowing radiologists to recognize COVID-19 patients from their CXR images. However, the majority of screening methods for COVID-19 reported in recent studies are based on 2D convolutional neural networks (CNNs). Although 3D CNNs are capable of capturing contextual information compared to their 2D counterparts, their use is limited due to their increased computational cost (i.e. requires much extra memory and much more computing power). In this study, a transfer learning-based hybrid 2D/3D CNN architecture for COVID-19 screening using CXRs has been developed. The proposed architecture consists of the incorporation of a pre-trained deep model (VGG16) and a shallow 3D CNN, combined with a depth-wise separable convolution layer and a spatial pyramid pooling module (SPP). Specifically, the depth-wise separable convolution helps to preserve the useful features while reducing the computational burden of the model. The SPP module is designed to extract multi-level representations from intermediate ones. Experimental results show that the proposed framework can achieve reasonable performances when evaluated on a collected dataset (3 classes to be predicted: COVID-19, Pneumonia, and Normal). Notably, it achieved a sensitivity of 98.33%, a specificity of 98.68% and an overall accuracy of 96.91.