Performance Analysis for COVID-19 Diagnosis Using Custom and State-of-the-Art Deep Learning Models

RETRACTED ARTICLE: MTR-SDL: a soft computing based multi-tier rank model for shoulder X-ray classification

Deep neural networks (DNN) effectiveness are contingent upon access to quality-labelled training datasets since label mistakes (label noise) in training datasets may significantly impair the accuracy of models trained on clean test data. The primary impediments to developing and using DNN models in the healthcare sector include the lack of sufficient label data. Labeling data by a domain expert are a costly and time-consuming task. To overcome this limitation, the proposed Multi-Tier Rank-based Semi-supervised deep learning (MTR-SDL) for Shoulder X-Ray Classification uses the small labelled dataset to generate a labelled dataset from unable dataset to obtain performance equivalent to approaches trained on the enormous dataset. The motivation behind the suggested model MTR-SDL approach is analogous to how physicians deal with unknown or suspicious patients in everyday life. Practitioners handle these questionable circumstances with the support of professional colleagues. Before initiating treatment, some patients consult with a range of skilled doctors. Patients are treated according to the most suitable professional diagnosis (vote count). In this article, we have proposed a new ensemble learning technique called "Rank based Ensemble Selection with machine learning models" (MTR-SDL) approach. In this technique, multiple machine learning models are trained on a labeled dataset, and their accuracy is ranked. A dynamic ensemble voting approach is then used to tag samples for each base model in the ensemble. The combination of these tags is used to generate a final tag for an unlabeled dataset. Our suggested MTR-SDL model has attained the best accuracy and specificity, sensitivity, precision, Matthew's correlation coefficient, false discovery rate, false positive rate, f1 score, negative predictive value, and false negative rate negative 92.776%, 97.376%, 86.932%, 96.192%, 85.644%, 3.808%, 2.624%, 91.072%, 90.85%, and 13.068% for unseen dataset, respectively. This approach has the potential to improve the performance of ensemble models by leveraging the strengths of multiple base models and selecting the most informative samples for each model. This study results in an improved Semi-supervised deep learning model that is more effective and precise.

Combating the COVID-19 infodemic using Prompt-Based curriculum learning

The COVID-19 pandemic has been accompanied by a proliferation of online misinformation and disinformation about the virus. Combating this 'infodemic' has been identified as one of the top priorities of the World Health Organization, because false and misleading information can lead to a range of negative consequences, including the spread of false remedies, conspiracy theories, and xenophobia. This paper aims to combat the COVID-19 infodemic on multiple fronts, including determining the credibility of information, identifying its potential harm to society, and the necessity of intervention by relevant organizations. We present a prompt-based curriculum learning method to achieve this goal. The proposed method could overcome the challenges of data sparsity and class imbalance issues. Using online social media texts as input, the proposed model can verify content from multiple perspectives by answering a series of questions concerning the text's reliability. Experiments revealed the effectiveness of prompt tuning and curriculum learning in assessing the reliability of COVID-19-related text. The proposed method outperforms typical text classification methods, including fastText and BERT. In addition, the proposed method is robust to the hyperparameter settings, making it more applicable with limited infrastructure resources.

A novel framework based on deep learning for COVID-19 diagnosis from X-ray images

Background

The coronavirus infection has endangered human health because of the high speed of the outbreak. A rapid and accurate diagnosis of the infection is essential to avoid further spread. Due to the cost of diagnostic kits and the availability of radiology equipment in most parts of the world, the COVID-19 detection method using X-ray images is still used in underprivileged countries. However, they are challenging due to being prone to human error, time-consuming, and demanding. The success of deep learning (DL) in automatic COVID-19 diagnosis systems has necessitated a detection system using these techniques. The most critical challenge in using deep learning techniques in diagnosing COVID-19 is accuracy because it plays an essential role in controlling the spread of the disease.

Methods

This article presents a new framework for detecting COVID-19 using X-ray images. The model uses a modified version of DenseNet-121 for the network layer, an image data loader to separate images in batches, a loss function to reduce the prediction error, and a weighted random sampler to balance the training phase. Finally, an optimizer changes the attributes of the neural networks.

Results

Extensive experiments using different types of pneumonia expresses satisfactory diagnosis performance with an accuracy of 99.81%.

Conclusion

This work aims to design a new deep neural network for highly accurate online recognition of medical images. The evaluation results show that the proposed framework can be considered an auxiliary device to help radiologists accurately confirm initial screening.

Boosting automatic COVID-19 detection performance with self-supervised learning and batch knowledge ensembling

PROBLEM

Detecting COVID-19 from chest X-ray (CXR) images has become one of the fastest and easiest methods for detecting COVID-19. However, the existing methods usually use supervised transfer learning from natural images as a pretraining process. These methods do not consider the unique features of COVID-19 and the similar features between COVID-19 and other pneumonia.

AIM

In this paper, we want to design a novel high-accuracy COVID-19 detection method that uses CXR images, which can consider the unique features of COVID-19 and the similar features between COVID-19 and other pneumonia.

METHODS

Our method consists of two phases. One is self-supervised learning-based pertaining; the other is batch knowledge ensembling-based fine-tuning. Self-supervised learning-based pretraining can learn distinguished representations from CXR images without manually annotated labels. On the other hand, batch knowledge ensembling-based fine-tuning can utilize category knowledge of images in a batch according to their visual feature similarities to improve detection performance. Unlike our previous implementation, we introduce batch knowledge ensembling into the fine-tuning phase, reducing the memory used in self-supervised learning and improving COVID-19 detection accuracy.

RESULTS

On two public COVID-19 CXR datasets, namely, a large dataset and an unbalanced dataset, our method exhibited promising COVID-19 detection performance. Our method maintains high detection accuracy even when annotated CXR training images are reduced significantly (e.g., using only 10% of the original dataset). In addition, our method is insensitive to changes in hyperparameters.

CONCLUSION

The proposed method outperforms other state-of-the-art COVID-19 detection methods in different settings. Our method can reduce the workloads of healthcare providers and radiologists.

Classification of spinal curvature types using radiography images: deep learning versus classical methods

Scoliosis is a spinal abnormality that has two types of curves (C-shaped or S-shaped). The vertebrae of the spine reach an equilibrium at different times, which makes it challenging to detect the type of curves. In addition, it may be challenging to detect curvatures due to observer bias and image quality. This paper aims to evaluate spinal deformity by automatically classifying the type of spine curvature. Automatic spinal curvature classification is performed using SVM and KNN algorithms, and pre-trained Xception and MobileNetV2 networks with SVM as the final activation function to avoid vanishing gradient. Different feature extraction methods should be used to investigate the SVM and KNN machine learning methods in detecting the curvature type. Features are extracted through the representation of radiographic images. These representations are of two groups: (i) Low-level image representation techniques such as texture features and (ii) local patch-based representations such as Bag of Words (BoW). Such features are utilized by various algorithms for classification by SVM and KNN. The feature extraction process is automated in pre-trained deep networks. In this study, 1000 anterior-posterior (AP) radiographic images of the spine were collected as a private dataset from Shafa Hospital, Tehran, Iran. The transfer learning was used due to the relatively small private dataset of anterior-posterior radiology images of the spine. Based on the results of these experiments, pre-trained deep networks were found to be approximately 10% more accurate than classical methods in classifying whether the spinal curvature is C-shaped or S-shaped. As a result of automatic feature extraction, it has been found that the pre-trained Xception and mobilenetV2 networks with SVM as the final activation function for controlling the vanishing gradient perform better than the classical machine learning methods of classification of spinal curvature types.

COVID-19 CT ground-glass opacity segmentation based on attention mechanism threshold

The ground glass opacity (GGO) of the lung is one of the essential features of COVID-19. The GGO in computed tomography (CT) images has various features and low-intensity contrast between the GGO and edge structures. These problems pose significant challenges for segmenting the GGO. To tackle these problems, we propose a new threshold method for accurate segmentation of GGO. Specifically, we offer a framework for adjusting the threshold parameters according to the image contrast. Three functions include Attention mechanism threshold, Contour equalization, and Lung segmentation (ACL). The lung is divided into three areas using the attention mechanism threshold. Further, the segmentation parameters of the attention mechanism thresholds of the three parts are adaptively adjusted according to the image contrast. Only the segmentation regions restricted by the lung segmentation results are retained. Extensive experiments on four COVID datasets show that ACL can segment GGO images at low contrast well. Compared with the state-of-the-art methods, the similarity Dice of the ACL segmentation results is improved by 8.9%, the average symmetry surface distance ASD is reduced by 23%, and the required computational power F L O P s are only 0.09% of those of deep learning models. For GGO segmentation, ACL is more lightweight, and the accuracy is higher. Code will be released at https://github.com/Lqs-github/ACL.

Classification of COVID-19 from community-acquired pneumonia: Boosting the performance with capsule network and maximum intensity projection image of CT scans

BACKGROUND

The coronavirus disease 2019 (COVID-19) and community-acquired pneumonia (CAP) present a high degree of similarity in chest computed tomography (CT) images. Therefore, a procedure for accurately and automatically distinguishing between them is crucial.

METHODS

A deep learning method for distinguishing COVID-19 from CAP is developed using maximum intensity projection (MIP) images from CT scans. LinkNet is employed for lung segmentation of chest CT images. MIP images are produced by superposing the maximum gray of intrapulmonary CT values. The MIP images are input into a capsule network for patient-level pred iction and diagnosis of COVID-19. The network is trained using 333 CT scans (168 COVID-19/165 CAP) and validated on three external datasets containing 3581 CT scans (2110 COVID-19/1471 CAP).

RESULTS

LinkNet achieves the highest Dice coefficient of 0.983 for lung segmentation. For the classification of COVID-19 and CAP, the capsule network with the DenseNet-121 feature extractor outperforms ResNet-50 and Inception-V3, achieving an accuracy of 0.970 on the training dataset. Without MIP or the capsule network, the accuracy decreases to 0.857 and 0.818, respectively. Accuracy scores of 0.961, 0.997, and 0.949 are achieved on the external validation datasets. The proposed method has higher or comparable sensitivity compared with ten state-of-the-art methods.

CONCLUSIONS

The proposed method illustrates the feasibility of applying MIP images from CT scans to distinguish COVID-19 from CAP using capsule networks. MIP images provide conspicuous benefits when exploiting deep learning to detect COVID-19 lesions from CT scans and the capsule network improves COVID-19 diagnosis.

Validation of a Deep Learning Model for Detecting Chest Pathologies from Digital Chest Radiographs

Purpose: Manual interpretation of chest radiographs is a challenging task and is prone to errors. An automated system capable of categorizing chest radiographs based on the pathologies identified could aid in the timely and efficient diagnosis of chest pathologies. Method: For this retrospective study, 4476 chest radiographs were collected between January and April 2021 from two tertiary care hospitals. Three expert radiologists established the ground truth, and all radiographs were analyzed using a deep-learning AI model to detect suspicious ROIs in the lungs, pleura, and cardiac regions. Three test readers (different from the radiologists who established the ground truth) independently reviewed all radiographs in two sessions (unaided and AI-aided mode) with a washout period of one month. Results: The model demonstrated an aggregate AUROC of 91.2% and a sensitivity of 88.4% in detecting suspicious ROIs in the lungs, pleura, and cardiac regions. These results outperform unaided human readers, who achieved an aggregate AUROC of 84.2% and sensitivity of 74.5% for the same task. When using AI, the aided readers obtained an aggregate AUROC of 87.9% and a sensitivity of 85.1%. The average time taken by the test readers to read a chest radiograph decreased by 21% (p < 0.01) when using AI. Conclusion: The model outperformed all three human readers and demonstrated high AUROC and sensitivity across two independent datasets. When compared to unaided interpretations, AI-aided interpretations were associated with significant improvements in reader performance and chest radiograph interpretation time.

COVID-19 and pneumonia diagnosis from chest X-ray images using convolutional neural networks

X-ray is a useful imaging modality widely utilized for diagnosing COVID-19 virus that infected a high number of people all around the world. The manual examination of these X-ray images may cause problems especially when there is lack of medical staff. Usage of deep learning models is known to be helpful for automated diagnosis of COVID-19 from the X-ray images. However, the widely used convolutional neural network architectures typically have many layers causing them to be computationally expensive. To address these problems, this study aims to design a lightweight differential diagnosis model based on convolutional neural networks. The proposed model is designed to classify the X-ray images belonging to one of the four classes that are Healthy, COVID-19, viral pneumonia, and bacterial pneumonia. To evaluate the model performance, accuracy, precision, recall, and F1-Score were calculated. The performance of the proposed model was compared with those obtained by applying transfer learning to the widely used convolutional neural network models. The results showed that the proposed model with low number of computational layers outperforms the pre-trained benchmark models, achieving an accuracy value of 89.89% while the best pre-trained model (Efficient-Net B2) achieved accuracy of 85.7%. In conclusion, the proposed lightweight model achieved the best overall result in classifying lung diseases allowing it to be used on devices with limited computational power. On the other hand, all the models showed a poor precision on viral pneumonia class and confusion in distinguishing it from bacterial pneumonia class, thus a decrease in the overall accuracy.

SCovNet: A skip connection-based feature union deep learning technique with statistical approach analysis for the detection of COVID-19

Background and Objective

The global population has been heavily impacted by the COVID-19 pandemic of coronavirus. Infections are spreading quickly around the world, and new spikes (Delta, Delta Plus, and Omicron) are still being made. The real-time reverse transcription-polymerase chain reaction (RT-PCR) is the method most often used to find viral RNA in a nasopharyngeal swab. However, these diagnostic approaches require human involvement and consume more time per prediction. Moreover, the existing conventional test mainly suffers from false negatives, so there is a chance for the virus to spread quickly. Therefore, a rapid and early diagnosis of COVID-19 patients is needed to overcome these problems.

Methods

Existing approaches based on deep learning for COVID detection are suffering from unbalanced datasets, poor performance, and gradient vanishing problems. A customized skip connection-based network with a feature union approach has been developed in this work to overcome some of the issues mentioned above. Gradient information from chest X-ray (CXR) images to subsequent layers is bypassed through skip connections. In the script's title, "SCovNet" refers to a skip-connection-based feature union network for detecting COVID-19 in a short notation. The performance of the proposed model was tested with two publicly available CXR image databases, including balanced and unbalanced datasets.

Results

A modified skip connection-based CNN model was suggested for a small unbalanced dataset (Kaggle) and achieved remarkable performance. In addition, the proposed model was also tested with a large GitHub database of CXR images and obtained an overall best accuracy of 98.67% with an impressive low false-negative rate of 0.0074.

Conclusions

The results of the experiments show that the proposed method works better than current methods at finding early signs of COVID-19. As an additional point of interest, we must mention the innovative hierarchical classification strategy provided for this work, which considered both balanced and unbalanced datasets to get the best COVID-19 identification rate.

Utility of an Automated Artificial Intelligence Echocardiography Software in Risk Stratification of Hospitalized COVID-19 Patients

Cardiovascular risk factors, biomarkers, and diseases are associated with poor prognosis in COVID-19 infections. Significant progress in artificial intelligence (AI) applied to cardiac imaging has recently been made. We assessed the utility of AI analytic software EchoGo in COVID-19 inpatients. Fifty consecutive COVID-19+ inpatients (age 66 ± 13 years, 22 women) who had echocardiography in 4/17/2020−8/5/2020 were analyzed with EchoGo software, with output correlated against standard echocardiography measurements. After adjustment for the APACHE-4 score, associations with clinical outcomes were assessed. Mean EchoGo outputs were left ventricular end-diastolic volume (LVEDV) 121 ± 42 mL, end-systolic volume (LVESV) 53 ± 30 mL, ejection fraction (LVEF) 58 ± 11%, and global longitudinal strain (GLS) −16.1 ± 5.1%. Pearson correlation coefficients (p-value) with standard measurements were 0.810 (<0.001), 0.873 (<0.001), 0.528 (<0.001), and 0.690 (<0.001). The primary endpoint occurred in 26 (52%) patients. Adjusting for APACHE-4 score, EchoGo LVEF and LVGLS were associated with the primary endpoint, odds ratios (95% confidence intervals) of 0.92 (0.85−0.99) and 1.22 (1.03−1.45) per 1% increase, respectively. Automated AI software is a new clinical tool that may assist with patient care. EchoGo LVEF and LVGLS were associated with adverse outcomes in hospitalized COVID-19 patients and can play a role in their risk stratification.