Detection of COVID-19 from CT and Chest X-ray Images Using Deep Learning Models

Deep learning models for CT image classification: a comprehensive literature review

Background and Objective

Computed tomography (CT) imaging plays a crucial role in the early detection and diagnosis of life-threatening diseases, particularly in respiratory illnesses and oncology. The rapid advancement of deep learning (DL) has revolutionized CT image analysis, enhancing diagnostic accuracy and efficiency. This review explores the impact of advanced DL methodologies in CT imaging, with a particular focus on their applications in coronavirus disease 2019 (COVID-19) detection and lung nodule classification.

Methods

A comprehensive literature search was conducted, examining the evolution of DL architectures in medical imaging from conventional convolutional neural networks (CNNs) to sophisticated foundational models (FMs). We reviewed publications from major databases, focusing on developments in CT image analysis using DL from 2013 to 2023. Our search criteria included all types of articles, with a focus on peer-reviewed research papers and review articles in English.

Key Content and Findings

The review reveals that DL, particularly advanced architectures like FMs, has transformed CT image analysis by streamlining interpretation processes and enhancing diagnostic capabilities. We found significant advancements in addressing global health challenges, especially during the COVID-19 pandemic, and in ongoing efforts for lung cancer screening. The review also addresses technical challenges in CT image analysis, including data variability, the need for large high-quality datasets, and computational demands. Innovative strategies such as transfer learning, data augmentation, and distributed computing are explored as solutions to these challenges.

Conclusions

This review underscores the pivotal role of DL in advancing CT image analysis, particularly for COVID-19 and lung nodule detection. The integration of DL models into clinical workflows shows promising potential to enhance diagnostic accuracy and efficiency. However, challenges remain in areas of interpretability, validation, and regulatory compliance. The review advocates for continued research, interdisciplinary collaboration, and ethical considerations as DL technologies become integral to clinical practice. While traditional imaging techniques remain vital, the integration of DL represents a significant advancement in medical diagnostics, with far-reaching implications for future research, clinical practice, and healthcare policy.

A comparison of CXR-CAD software to radiologists in identifying COVID-19 in individuals evaluated for Sars CoV-2 infection in Malawi and Zambia

AI based software, including computer aided detection software for chest radiographs (CXR-CAD), was developed during the pandemic to improve COVID-19 case finding and triage. In high burden TB countries, the use of highly portable CXR and computer aided detection software has been adopted more broadly to improve the screening and triage of individuals for TB, but there is little evidence in these settings regarding COVID-19 CAD performance. We performed a multicenter, retrospective cross-over study evaluating CXRs from individuals at risk for COVID-19. We evaluated performance of CAD software and radiologists in comparison to COVID-19 laboratory results in 671 individuals evaluated for COVID-19 at sites in Zambia and Malawi between January 2021 and June 2022. All CXRs were interpreted by an expert radiologist and two commercially available COVID-19 CXR-CAD software. Radiologists interpreted CXRs for COVID-19 with a sensitivity of 73% (95% CI: 69%- 76%) and specificity of 49% (95% CI: 40%-58%). One CAD software (CAD2) showed performance in diagnosing COVID-19 that was comparable to that of radiologists, (AUC-ROC of 0.70 (95% CI: 0.65-0.75)), while a second (CAD1) showed inferior performance (AUC-ROC of 0.57 (95% CI: 0.52-0.63)). Agreement between CAD software and radiologists was moderate for diagnosing COVID-19, and agreement was very good in differentiating normal and abnormal CXRs in this high prevalent population. The study highlights the potential of CXR-CAD as a tool to support effective triage of individuals in Malawi and Zambia during the pandemic, particularly for distinguishing normal from abnormal CXRs. These findings suggest that while current AI-based diagnostics like CXR-CAD show promise, their effectiveness varies significantly. In order to better prepare for future pandemics, there is a need for representative training data to optimize performance in key populations, and ongoing data collection to maintain diagnostic accuracy, especially as new disease strains emerge.

Integrating ensemble and machine learning models for early prediction of pneumonia mortality using laboratory tests

Background

The recent use of artificial intelligence (AI) in medical research is noteworthy. However, most research has focused on medical imaging. Although the importance of laboratory tests in the clinical field is acknowledged by clinicians, they are undervalued in medical AI research. Our study aims to develop an early prediction AI model for pneumonia mortality, primarily using laboratory test results.

Materials and methods

We developed a mortality prediction model using initial laboratory results and basic clinical information of patients with pneumonia. Several machine learning (ML) models and a deep learning method-multilayer perceptron (MLP)-were selected for model development. The area under the receiver operating characteristic curve (AUROC) and F1-score were optimized to improve model performance. In addition, an ensemble model was developed by blending several models to improve the prediction performance. We used 80,940 data instances for model development.

Results

Among the ML models, XGBoost exhibited the best performance (AUROC = 0.8989, accuracy = 0.88, F1-score = 0.80). MLP achieved an AUROC of 0.8498, accuracy of 0.86, and F1-score of 0.75. The performance of the ensemble model was the best among the developed models, with an AUROC of 0.9006, accuracy of 0.90, and F1-score of 0.81. Several laboratory tests were conducted to identify risk factors that affect pneumonia mortality using the "Feature importance" technique and SHapley Additive exPlanations. We identified several laboratory results, including systolic blood pressure, serum glucose level, age, aspartate aminotransferase-to-alanine aminotransferase ratio, and monocyte-to-lymphocyte ratio, as significant predictors of mortality in patients with pneumonia.

Conclusions

Our study demonstrates that the ensemble model, incorporating XGBoost, CatBoost, and LGBM techniques, outperforms individual ML and deep learning models in predicting pneumonia mortality. Our findings emphasize the importance of integrating AI techniques to leverage laboratory test data effectively, offering a promising direction for advancing AI applications in medical research and clinical decision-making.

[Dielectric properties of tidal volume changes in rabbit lung tissue in the 100 MHz~1 GHz band]

This paper investigates the variation of lung tissue dielectric properties with tidal volume under in vivo conditions to provide reliable and valid a priori information for techniques such as microwave imaging. In this study, the dielectric properties of the lung tissue of 30 rabbits were measured in vivo using the open-end coaxial probe method in the frequency band of 100 MHz to 1 GHz, and 6 different sets of tidal volumes (30, 40, 50, 60, 70, 80 mL) were set up to study the trends of the dielectric properties, and the data at 2 specific frequency points (433 and 915 MHz) were analyzed statistically. It was found that the dielectric coefficient and conductivity of lung tissue tended to decrease with increasing tidal volume in the frequency range of 100 MHz to 1 GHz, and the differences in the dielectric properties of lung tissue for the 6 groups of tidal volumes at 2 specific frequency points were statistically significant. This paper showed that the dielectric properties of lung tissue tend to vary non-linearly with increasing tidal volume. Based on this, more accurate biological tissue parameters can be provided for bioelectromagnetic imaging techniques such as microwave imaging, which could provide a scientific basis and experimental data support for the improvement of diagnostic methods and equipment for lung diseases.

Lung Ultrasonography in the Evaluation of Late Sequelae of COVID-19 Pneumonia-A Comparison with Chest Computed Tomography: A Prospective Study

The onset of the COVID-19 pandemic allowed physicians to gain experience in lung ultrasound (LUS) during the acute phase of the disease. However, limited data are available on LUS findings during the recovery phase. The aim of this study was to evaluate the utility of LUS to assess lung involvement in patients with post-COVID-19 syndrome. This study prospectively enrolled 72 patients who underwent paired LUS and chest CT scans (112 pairs including follow-up). The most frequent CT findings were ground glass opacities (83.3%), subpleural lines (72.2%), traction bronchiectasis (37.5%), and consolidations (31.9%). LUS revealed irregular pleural lines as a common abnormality initially (56.9%), along with subpleural consolidation >2.5 mm ≤10 mm (26.5%) and B-lines (26.5%). A strong correlation was found between LUS score, calculated by artificial intelligence percentage involvement in ground glass opacities described in CT (r = 0.702, p < 0.05). LUS score was significantly higher in the group with fibrotic changes compared to the non-fibrotic group with a mean value of 19.4 ± 5.7 to 11 ± 6.6, respectively (p < 0.0001). LUS might be considered valuable for examining patients with persistent symptoms after recovering from COVID-19 pneumonia. Abnormalities identified through LUS align with CT scan findings; thus, LUS might potentially reduce the need for frequent chest CT examinations.

Novel Automatic Classification of Human Adult Lung Alveolar Type II Cells Infected with SARS-CoV-2 through the Deep Transfer Learning Approach

Transmission electron microscopy imaging provides a unique opportunity to inspect the detailed structure of infected lung cells with SARS-CoV-2. Unlike previous studies, this novel study aims to investigate COVID-19 classification at the lung cellular level in response to SARS-CoV-2. Particularly, differentiating between healthy and infected human alveolar type II (hAT2) cells with SARS-CoV-2. Hence, we explore the feasibility of deep transfer learning (DTL) and introduce a highly accurate approach that works as follows: First, we downloaded and processed 286 images pertaining to healthy and infected hAT2 cells obtained from the electron microscopy public image archive. Second, we provided processed images to two DTL computations to induce ten DTL models. The first DTL computation employs five pre-trained models (including DenseNet201 and ResNet152V2) trained on more than one million images from the ImageNet database to extract features from hAT2 images. Then, it flattens and provides the output feature vectors to a trained, densely connected classifier with the Adam optimizer. The second DTL computation works in a similar manner, with a minor difference in that we freeze the first layers for feature extraction in pre-trained models while unfreezing and jointly training the next layers. The results using five-fold cross-validation demonstrated that TFeDenseNet201 is 12.37× faster and superior, yielding the highest average ACC of 0.993 (F1 of 0.992 and MCC of 0.986) with statistical significance (P<2.2×10−16 from a t-test) compared to an average ACC of 0.937 (F1 of 0.938 and MCC of 0.877) for the counterpart (TFtDenseNet201), showing no significance results (P=0.093 from a t-test).

A Promising Start and Not a Panacea: ChatGPT's Early Impact and Potential in Medical Science and Biomedical Engineering Research

The advent of artificial intelligence (AI) has catalyzed a revolutionary transformation across various industries, including healthcare. Medical applications of ChatGPT, a powerful language model based on the generative pre-trained transformer (GPT) architecture, encompass the creation of conversational agents capable of accessing and generating medical information from multiple sources and formats. This study investigates the research trends of large language models such as ChatGPT, GPT 4, and Google Bard, comparing their publication trends with early COVID-19 research. The findings underscore the current prominence of AI research and its potential implications in biomedical engineering. A search of the Scopus database on July 23, 2023, yielded 1,096 articles related to ChatGPT, with approximately 26% being medical science-related. Keywords related to artificial intelligence, natural language processing (NLP), LLM, and generative AI dominate ChatGPT research, while a focused representation of medical science research emerges, with emphasis on biomedical research and engineering. This analysis serves as a call to action for researchers, healthcare professionals, and policymakers to recognize and harness AI's potential in healthcare, particularly in the realm of biomedical research.

Small bowel capsule endoscopy examination and open access database with artificial intelligence: The SEE-artificial intelligence project

OBJECTIVES

Artificial intelligence (AI) may be practical for image classification of small bowel capsule endoscopy (CE). However, creating a functional AI model is challenging. We attempted to create a dataset and an object detection CE AI model to explore modeling problems to assist in reading small bowel CE.

METHODS

We extracted 18,481 images from 523 small bowel CE procedures performed at Kyushu University Hospital from September 2014 to June 2021. We annotated 12,320 images with 23,033 disease lesions, combined them with 6161 normal images as the dataset, and examined the characteristics. Based on the dataset, we created an object detection AI model using YOLO v5 and we tested validation.

RESULTS

We annotated the dataset with 12 types of annotations, and multiple annotation types were observed in the same image. We test validated our AI model with 1396 images, and sensitivity for all 12 types of annotations was about 91%, with 1375 true positives, 659 false positives, and 120 false negatives detected. The highest sensitivity for individual annotations was 97%, and the highest area under the receiver operating characteristic curve was 0.98, but the quality of detection varied depending on the specific annotation.

CONCLUSIONS

Object detection AI model in small bowel CE using YOLO v5 may provide effective and easy-to-understand reading assistance. In this SEE-AI project, we open our dataset, the weights of the AI model, and a demonstration to experience our AI. We look forward to further improving the AI model in the future.

COVID-19 lateral flow test image classification using deep CNN and StyleGAN2

Introduction

Artificial intelligence (AI) in healthcare can enhance clinical workflows and diagnoses, particularly in large-scale operations like COVID-19 mass testing. This study presents a deep Convolutional Neural Network (CNN) model for automated COVID-19 RATD image classification.

Methods

To address the absence of a RATD image dataset, we crowdsourced 900 real-world images focusing on positive and negative cases. Rigorous data augmentation and StyleGAN2-ADA generated simulated images to overcome dataset limitations and class imbalances.

Results

The best CNN model achieved a 93% validation accuracy. Test accuracies were 88% for simulated datasets and 82% for real datasets. Augmenting simulated images during training did not significantly improve real-world test image performance but enhanced simulated test image performance.

Discussion

The findings of this study highlight the potential of the developed model in expediting COVID-19 testing processes and facilitating large-scale testing and tracking systems. The study also underscores the challenges in designing and developing such models, emphasizing the importance of addressing dataset limitations and class imbalances.

Conclusion

This research contributes to the deployment of large-scale testing and tracking systems, offering insights into the potential applications of AI in mitigating outbreaks similar to COVID-19. Future work could focus on refining the model and exploring its adaptability to other healthcare scenarios.

A Systematic Review on Deep Structured Learning for COVID-19 Screening Using Chest CT from 2020 to 2022

The emergence of the COVID-19 pandemic in Wuhan in 2019 led to the discovery of a novel coronavirus. The World Health Organization (WHO) designated it as a global pandemic on 11 March 2020 due to its rapid and widespread transmission. Its impact has had profound implications, particularly in the realm of public health. Extensive scientific endeavors have been directed towards devising effective treatment strategies and vaccines. Within the healthcare and medical imaging domain, the application of artificial intelligence (AI) has brought significant advantages. This study delves into peer-reviewed research articles spanning the years 2020 to 2022, focusing on AI-driven methodologies for the analysis and screening of COVID-19 through chest CT scan data. We assess the efficacy of deep learning algorithms in facilitating decision making processes. Our exploration encompasses various facets, including data collection, systematic contributions, emerging techniques, and encountered challenges. However, the comparison of outcomes between 2020 and 2022 proves intricate due to shifts in dataset magnitudes over time. The initiatives aimed at developing AI-powered tools for the detection, localization, and segmentation of COVID-19 cases are primarily centered on educational and training contexts. We deliberate on their merits and constraints, particularly in the context of necessitating cross-population train/test models. Our analysis encompassed a review of 231 research publications, bolstered by a meta-analysis employing search keywords (COVID-19 OR Coronavirus) AND chest CT AND (deep learning OR artificial intelligence OR medical imaging) on both the PubMed Central Repository and Web of Science platforms.

Milani A, Madani Tonekaboni SA, Rabbani H, Hekmatnia A, Kafieh R. Biased Deep Learning Methods in Detection of COVID-19 Using CT Images: A Challenge Mounted by Subject-Wise-Split ISFCT Dataset

Accurate detection of respiratory system damage including COVID-19 is considered one of the crucial applications of deep learning (DL) models using CT images. However, the main shortcoming of the published works has been unreliable reported accuracy and the lack of repeatability with new datasets, mainly due to slice-wise splits of the data, creating dependency between training and test sets due to shared data across the sets. We introduce a new dataset of CT images (ISFCT Dataset) with labels indicating the subject-wise split to train and test our DL algorithms in an unbiased manner. We also use this dataset to validate the real performance of the published works in a subject-wise data split. Another key feature provides more specific labels (eight characteristic lung features) rather than being limited to COVID-19 and healthy labels. We show that the reported high accuracy of the existing models on current slice-wise splits is not repeatable for subject-wise splits, and distribution differences between data splits are demonstrated using t-distribution stochastic neighbor embedding. We indicate that, by examining subject-wise data splitting, less complicated models show competitive results compared to the exiting complicated models, demonstrating that complex models do not necessarily generate accurate and repeatable results.

Diagnostic Test Accuracy of Deep Learning Prediction Models on COVID-19 Severity: Systematic Review and Meta-Analysis

BACKGROUND

Deep learning (DL) prediction models hold great promise in the triage of COVID-19.

OBJECTIVE

We aimed to evaluate the diagnostic test accuracy of DL prediction models for assessing and predicting the severity of COVID-19.

METHODS

We searched PubMed, Scopus, LitCovid, Embase, Ovid, and the Cochrane Library for studies published from December 1, 2019, to April 30, 2022. Studies that used DL prediction models to assess or predict COVID-19 severity were included, while those without diagnostic test accuracy analysis or severity dichotomies were excluded. QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies 2), PROBAST (Prediction Model Risk of Bias Assessment Tool), and funnel plots were used to estimate the bias and applicability.

RESULTS

A total of 12 retrospective studies involving 2006 patients reported the cross-sectionally assessed value of DL on COVID-19 severity. The pooled sensitivity and area under the curve were 0.92 (95% CI 0.89-0.94; I²=0.00%) and 0.95 (95% CI 0.92-0.96), respectively. A total of 13 retrospective studies involving 3951 patients reported the longitudinal predictive value of DL for disease severity. The pooled sensitivity and area under the curve were 0.76 (95% CI 0.74-0.79; I²=0.00%) and 0.80 (95% CI 0.76-0.83), respectively.

CONCLUSIONS

DL prediction models can help clinicians identify potentially severe cases for early triage. However, high-quality research is lacking.

TRIAL REGISTRATION

PROSPERO CRD42022329252; https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD 42022329252.

COVID-ConvNet: A Convolutional Neural Network Classifier for Diagnosing COVID-19 Infection

The novel coronavirus (COVID-19) pandemic still has a significant impact on the worldwide population's health and well-being. Effective patient screening, including radiological examination employing chest radiography as one of the main screening modalities, is an important step in the battle against the disease. Indeed, the earliest studies on COVID-19 found that patients infected with COVID-19 present with characteristic anomalies in chest radiography. In this paper, we introduce COVID-ConvNet, a deep convolutional neural network (DCNN) design suitable for detecting COVID-19 symptoms from chest X-ray (CXR) scans. The proposed deep learning (DL) model was trained and evaluated using 21,165 CXR images from the COVID-19 Database, a publicly available dataset. The experimental results demonstrate that our COVID-ConvNet model has a high prediction accuracy at 97.43% and outperforms recent related works by up to 5.9% in terms of prediction accuracy.

Chest X-Ray Images to Differentiate COVID-19 from Pneumonia with Artificial Intelligence Techniques

This paper presents an automated and noninvasive technique to discriminate COVID-19 patients from pneumonia patients using chest X-ray images and artificial intelligence. The reverse transcription-polymerase chain reaction (RT-PCR) test is commonly administered to detect COVID-19. However, the RT-PCR test necessitates person-to-person contact to administer, requires variable time to produce results, and is expensive. Moreover, this test is still unreachable to the significant global population. The chest X-ray images can play an important role here as the X-ray machines are commonly available at any healthcare facility. However, the chest X-ray images of COVID-19 and viral pneumonia patients are very similar and often lead to misdiagnosis subjectively. This investigation has employed two algorithms to solve this problem objectively. One algorithm uses lower-dimension encoded features extracted from the X-ray images and applies them to the machine learning algorithms for final classification. The other algorithm relies on the inbuilt feature extractor network to extract features from the X-ray images and classifies them with a pretrained deep neural network VGG16. The simulation results show that the proposed two algorithms can extricate COVID-19 patients from pneumonia with the best accuracy of 100% and 98.1%, employing VGG16 and the machine learning algorithm, respectively. The performances of these two algorithms have also been collated with those of other existing state-of-the-art methods.

An evaluation of lightweight deep learning techniques in medical imaging for high precision COVID-19 diagnostics

Timely and rapid diagnoses are core to informing on optimum interventions that curb the spread of COVID-19. The use of medical images such as chest X-rays and CTs has been advocated to supplement the Reverse-Transcription Polymerase Chain Reaction (RT-PCR) test, which in turn has stimulated the application of deep learning techniques in the development of automated systems for the detection of infections. Decision support systems relax the challenges inherent to the physical examination of images, which is both time consuming and requires interpretation by highly trained clinicians. A review of relevant reported studies to date shows that most deep learning algorithms utilised approaches are not amenable to implementation on resource-constrained devices. Given the rate of infections is increasing, rapid, trusted diagnoses are a central tool in the management of the spread, mandating a need for a low-cost and mobile point-of-care detection systems, especially for middle- and low-income nations. The paper presents the development and evaluation of the performance of lightweight deep learning technique for the detection of COVID-19 using the MobileNetV2 model. Results demonstrate that the performance of the lightweight deep learning model is competitive with respect to heavyweight models but delivers a significant increase in the efficiency of deployment, notably in the lowering of the cost and memory requirements of computing resources.

COVID-AleXception: A Deep Learning Model Based on a Deep Feature Concatenation Approach for the Detection of COVID-19 from Chest X-ray Images

The novel coronavirus 2019 (COVID-19) spread rapidly around the world and its outbreak has become a pandemic. Due to an increase in afflicted cases, the quantity of COVID-19 tests kits available in hospitals has decreased. Therefore, an autonomous detection system is an essential tool for reducing infection risks and spreading of the virus. In the literature, various models based on machine learning (ML) and deep learning (DL) are introduced to detect many pneumonias using chest X-ray images. The cornerstone in this paper is the use of pretrained deep learning CNN architectures to construct an automated system for COVID-19 detection and diagnosis. In this work, we used the deep feature concatenation (DFC) mechanism to combine features extracted from input images using the two modern pre-trained CNN models, AlexNet and Xception. Hence, we propose COVID-AleXception: a neural network that is a concatenation of the AlexNet and Xception models for the overall improvement of the prediction capability of this pandemic. To evaluate the proposed model and build a dataset of large-scale X-ray images, there was a careful selection of multiple X-ray images from several sources. The COVID-AleXception model can achieve a classification accuracy of 98.68%, which shows the superiority of the proposed model over AlexNet and Xception that achieved a classification accuracy of 94.86% and 95.63%, respectively. The performance results of this proposed model demonstrate its pertinence to help radiologists diagnose COVID-19 more quickly.

Prediction Model of Residual Neural Network for Pathological Confirmed Lymph Node Metastasis of Ovarian Cancer

Purpose. We want to develop a model for predicting lymph node status based on positron emission computed tomography (PET) images of untreated ovarian cancer patients. We use the feature map formed by wavelet transform and the parameters obtained by image segmentation to build the model. The model is expected to help clinicians and provide additional information about what to do with first-visit patients. Materials and Methods. Our study included 224 patients with ovarian cancer. We have chosen two main methods to extract information from images. On the one hand, we segmented the image to extract the parameters to evaluate the clustering effect. On the other hand, we used wavelet transform to extract the image’s texture information to form the image’s feature map. Based on the above two kinds of information, we used residual neural network and support vector machine for modeling. Results. We established a model to predict lymph node metastasis in patients with primary ovarian cancer using PET images. On the training set, our accuracy was 0.8854, AUC: 0.9472, CI: 0.9098-0.9752, sensitivity was 0.9865, and specificity was 0.7952. On the test set, our accuracy was 0.9104, AUC: 0.9259, CI: 0.8417-0.9889, sensitivity was 0.8125, and specificity was 1.0000. Conclusions. We used wavelet transform to process the preoperative medical images of ovarian cancer patients, and the residual neural network can effectively predict the lymph node metastasis of ovarian cancer patients, which is undoubted of great significance for patients’ staging and treatment options.