A fully automatic deep learning system for COVID-19 diagnostic and prognostic analysis

Performance of AI Approaches for COVID-19 Diagnosis Using Chest CT Scans: The Impact of Architecture and Dataset

AI is emerging as a promising tool for diagnosing COVID-19 based on chest CT scans. The aim of this study was the comparison of AI models for COVID-19 diagnosis. Therefore, we: (1) trained three distinct AI models for classifying COVID-19 and non-COVID-19 pneumonia (nCP) using a large, clinically relevant CT dataset, (2) evaluated the models' performance using an independent test set, and (3) compared the models both algorithmically and experimentally.In this multicenter multi-vendor study, we collected n=1591 chest CT scans of COVID-19 (n=762) and nCP (n=829) patients from China and Germany. In Germany, the data was collected from three RACOON sites. We trained and validated three COVID-19 AI models with different architectures: COVNet based on 2D-CNN, DeCoVnet based on 3D-CNN, and AD3D-MIL based on 3D-CNN with attention module. 991 CT scans were used for training the AI models using 5-fold cross-validation. 600 CT scans from 6 different centers were used for independent testing. The models' performance was evaluated using accuracy (Acc), sensitivity (Se), and specificity (Sp).The average validation accuracy of the COVNet, DeCoVnet, and AD3D-MIL models over the 5 folds was 80.9%, 82.0%, and 84.3%, respectively. On the independent test set with n=600 CT scans, COVNet yielded Acc=76.6%, Se=67.8%, Sp=85.7%; DeCoVnet provided Acc=75.1%, Se=61.2%, Sp=89.7%; and AD3D-MIL achieved Acc=73.9%, Se=57.7%, Sp=90.8%.The classification performance of the evaluated AI models is highly dependent on the training data rather than the architecture itself. Our results demonstrate a high specificity and moderate sensitivity. The AI classification models should not be used unsupervised but could potentially assist radiologists in COVID-19 and nCP identification. · This study compares AI approaches for diagnosing COVID-19 in chest CT scans, which is essential for further optimizing the delivery of healthcare and for pandemic preparedness.. · Our experiments using a multicenter, multi-vendor, diverse dataset show that the training data is the key factor in determining the diagnostic performance.. · The AI models should not be used unsupervised but as a tool to assist radiologists.. · Jaiswal A, Fervers P, Meng F et al. Performance of AI Approaches for COVID-19 Diagnosis Using Chest CT Scans: The Impact of Architecture and Dataset. Rofo 2025; DOI 10.1055/a-2577-3928.

Assessing severe pneumonia risk in children via clinical prognostic model based on laboratory markers

Pneumonia represents a significant cause of mortality in children globally, emphasizing the importance of identifying high-risk patients to improve clinical outcomes. There is a lack of reliable laboratory markers and robust risk stratification models for clinical decision support in pediatric pneumonia. This study extracted data from the Paediatric Intensive Care database for 749 children under 3 years with severe pneumonia. The relationship between laboratory parameters and prognostic outcomes was evaluated using Cox proportional hazards regression analyses. Oxygen saturation, hemoglobin, lipase, urea, and uric acid were identified as laboratory parameters significantly associated with severe pneumonia outcomes. Leveraging these laboratory markers, a prognosis model was constructed employing the XGBoost classifier. The model was validated in a hold-out test cohort and an external validation cohort, with its performance assessed by the area under the receiver operating characteristic curve (AUC). The validation cohort was derived from 129 children with severe pneumonia admitted to the PICU of the Children's Hospital, Zhejiang University School of Medicine in 2019. The model demonstrated efficacy in predicting the death and survival of patients (AUC = 0.943), as well as in distinguishing between children at high- and low-risk of death in advance (HR = 2.930, 95 % CI: 2.551-3.366, P < 0.001). The robust performance of this model was further validated in the test cohort (AUC = 0.871), and the validation cohort (AUC = 0.872). In conclusion, this novel model enables the prediction of individualized mortality risk in children diagnosed with severe pneumonia, offering personalized risk assessments to inform and enhance clinical decision-making processes.

Ultrasound-based artificial intelligence model for prediction of Ki-67 proliferation index in soft tissue tumors

RATIONALE AND OBJECTIVES

To investigate the value of deep learning (DL) combined with radiomics and clinical and imaging features in predicting the Ki-67 proliferation index of soft tissue tumors (STTs).

MATERIALS AND METHODS

In this retrospective study, a total of 394 patients with STTs admitted from January 2021 to December 2023 in two separate hospitals were collected. Hospital-1 was the training cohort (323 cases, of which 89 and 234 were high and low Ki-67, respectively) and Hospital-2 was the external validation cohort (71 cases, of which 23 and 48 were high and low Ki-67, respectively). Clinical and ultrasound characteristics including age, sex, tumor size, morphology, margins, internal echoes and blood flow were assessed. Risk factors with significant correlations were screened by univariate and multivariate logistic regression analyses. After extracting the radiomics and DL features, the feature fusion model is constructed by Support Vector Machine. The prediction results obtained from separate clinical features, radiomics features and DL features were combined to construct decision fusion models. Finally, the DeLong test was used to compare whether the AUCs between the models were significantly different.

RESULTS

The three feature fusion models and three decision fusion models constructed demonstrated excellent diagnostic performance in predicting Ki-67 expression levels in STTs. Among them, the feature fusion model based on clinical, radiomics, and DL performed the best with an AUC of 0.911 (95% CI: 0.886-0.935) in the training cohort and 0.923 (95% CI: 0.873-0.972) in the validation cohort, and proved to be well-calibrated and clinically useful. The DeLong test showed that the decision fusion models based on clinical, radiomics and DL performed significantly worse than the three feature fusion models on the validation set. There was no statistical difference in diagnostic performance between the other models.

CONCLUSION

The ultrasound-based fusion model of clinical, radiomics, and DL features showed good performance in predicting Ki-67 expression levels in STTs.

A method of deep network auto-training based on the MTPI auto-transfer learning and a reinforcement learning algorithm for vegetation detection in a dry thermal valley environment

UAV image acquisition and deep learning techniques have been widely used in field hydrological monitoring to meet the increasing data volume demand and refined quality. However, manual parameter training requires trial-and-error costs (T&E), and existing auto-trainings adapt to simple datasets and network structures, which is low practicality in unstructured environments, e.g., dry thermal valley environment (DTV). Therefore, this research combined a transfer learning (MTPI, maximum transfer potential index method) and an RL (the MTSA reinforcement learning, Multi-Thompson Sampling Algorithm) in dataset auto-augmentation and networks auto-training to reduce human experience and T&E. Firstly, to maximize the iteration speed and minimize the dataset consumption, the best iteration conditions (MTPI conditions) were derived with the improved MTPI method, which shows that subsequent iterations required only 2.30% dataset and 6.31% time cost. Then, the MTSA was improved under MTPI conditions (MTSA-MTPI) to auto-augmented datasets, and the results showed a 16.0% improvement in accuracy (human error) and a 20.9% reduction in standard error (T&E cost). Finally, the MTPI-MTSA was used for four networks auto-training (e.g., FCN, Seg-Net, U-Net, and Seg-Res-Net 50) and showed that the best Seg-Res-Net 50 gained 95.2% WPA (accuracy) and 90.9% WIoU. This study provided an effective auto-training method for complex vegetation information collection, which provides a reference for reducing the manual intervention of deep learning.

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.

An AI-Based Low-Risk Lung Health Image Visualization Framework Using LR-ULDCT

In this article, we propose an AI-based low-risk visualization framework for lung health monitoring using low-resolution ultra-low-dose CT (LR-ULDCT). We present a novel deep cascade processing workflow to achieve diagnostic visualization on LR-ULDCT (<0.3 mSv) at par high-resolution CT (HRCT) of 100 mSV radiation technology. To this end, we build a low-risk and affordable deep cascade network comprising three sequential deep processes: restoration, super-resolution (SR), and segmentation. Given degraded LR-ULDCT, the first novel network unsupervisedly learns restoration function from augmenting patch-based dictionaries and residuals. The restored version is then super-resolved (SR) for target (sensor) resolution. Here, we combine perceptual and adversarial losses in novel GAN to establish the closeness between probability distributions of generated SR-ULDCT and restored LR-ULDCT. Thus SR-ULDCT is presented to the segmentation network that first separates the chest portion from SR-ULDCT followed by lobe-wise colorization. Finally, we extract five lobes to account for the presence of ground glass opacity (GGO) in the lung. Hence, our AI-based system provides low-risk visualization of input degraded LR-ULDCT to various stages, i.e., restored LR-ULDCT, restored SR-ULDCT, and segmented SR-ULDCT, and achieves diagnostic power of HRCT. We perform case studies by experimenting on real datasets of COVID-19, pneumonia, and pulmonary edema/congestion while comparing our results with state-of-the-art. Ablation experiments are conducted for better visualizing different operating pipelines. Finally, we present a verification report by fourteen (14) experienced radiologists and pulmonologists.

SFPL: Sample-specific fine-grained prototype learning for imbalanced medical image classification

Imbalanced classification is a common and difficult task in many medical image analysis applications. However, most existing approaches focus on balancing feature distribution and classifier weights between classes, while ignoring the inner-class heterogeneity and the individuality of each sample. In this paper, we proposed a sample-specific fine-grained prototype learning (SFPL) method to learn the fine-grained representation of the majority class and learn a cosine classifier specifically for each sample such that the classification model is highly tuned to the individual's characteristic. SFPL first builds multiple prototypes to represent the majority class, and then updates the prototypes through a mixture weighting strategy. Moreover, we proposed a uniform loss based on set representations to make the fine-grained prototypes distribute uniformly. To establish associations between fine-grained prototypes and cosine classifier, we propose a selective attention aggregation module to select the effective fine-grained prototypes for final classification. Extensive experiments on three different tasks demonstrate that SFPL outperforms the state-of-the-art (SOTA) methods. Importantly, as the imbalance ratio increases from 10 to 100, the improvement of SFPL over SOTA methods increases from 2.2% to 2.4%; as the training data decreases from 800 to 100, the improvement of SFPL over SOTA methods increases from 2.2% to 3.8%.

Non-contrasted computed tomography (NCCT) based chronic thromboembolic pulmonary hypertension (CTEPH) automatic diagnosis using cascaded network with multiple instance learning

Objective.The diagnosis of chronic thromboembolic pulmonary hypertension (CTEPH) is challenging due to nonspecific early symptoms, complex diagnostic processes, and small lesion sizes. This study aims to develop an automatic diagnosis method for CTEPH using non-contrasted computed tomography (NCCT) scans, enabling automated diagnosis without precise lesion annotation.Approach.A novel cascade network (CN) with multiple instance learning (CNMIL) framework was developed to improve the diagnosis of CTEPH. This method uses a CN architecture combining two Resnet-18 CNN networks to progressively distinguish between normal and CTEPH cases. Multiple instance learning (MIL) is employed to treat each 3D CT case as a 'bag' of image slices, using attention scoring to identify the most important slices. An attention module helps the model focus on diagnostically relevant regions within each slice. The dataset comprised NCCT scans from 300 subjects, including 117 males and 183 females, with an average age of 52.5 ± 20.9 years, consisting of 132 normal cases and 168 cases of lung diseases, including 88 cases of CTEPH. The CNMIL framework was evaluated using sensitivity, specificity, and the area under the curve (AUC) metrics, and compared with common 3D supervised classification networks and existing CTEPH automatic diagnosis networks.Main results. The CNMIL framework demonstrated high diagnostic performance, achieving an AUC of 0.807, accuracy of 0.833, sensitivity of 0.795, and specificity of 0.849 in distinguishing CTEPH cases. Ablation studies revealed that integrating MIL and the CN significantly enhanced performance, with the model achieving an AUC of 0.978 and perfect sensitivity (1.000) in normal classification. Comparisons with other 3D network architectures confirmed that the integrated model outperformed others, achieving the highest AUC of 0.8419.Significance. The CNMIL network requires no additional scans or annotations, relying solely on NCCT. This approach can improve timely and accurate CTEPH detection, resulting in better patient outcomes.

A novel AI-based diagnostic model for pertussis pneumonia

It is still very difficult to diagnose pertussis based on a doctor's experience. Our aim is to develop a model based on machine learning algorithms combined with biochemical blood tests to diagnose pertussis. A total of 295 patients with pertussis and 295 patients with non-pertussis lower respiratory infections between January 2022 and January 2023, matched for age and gender ratio, were included in our study. Patients underwent a reverse transcription polymerase chain reaction test for pertussis and other viruses. Univariate logistic regression analysis was used to screen for clinical and blood biochemical features associated with pertussis. The optimal features and 3 machine learning algorithms including K-nearest neighbor, support vector machine, and eXtreme Gradient Boosting (XGBoost) were used to develop diagnostic models. Using univariate logistic regression analysis, 18 out of the 27 features were considered optimal features associated with pertussis The XGBoost model was significantly superior to both the support vector machine model (Delong test, P = .01) and the K-nearest neighbor model (Delong test, P = .01), with the area under the receiver operating characteristic curve of 0.96 and an accuracy of 0.923. Our diagnostic model based on blood biochemical test results at admission and XGBoost algorithm can help doctors effectively diagnose pertussis.

Differential privacy preserved federated learning for prognostic modeling in COVID-19 patients using large multi-institutional chest CT dataset

BACKGROUND

Notwithstanding the encouraging results of previous studies reporting on the efficiency of deep learning (DL) in COVID-19 prognostication, clinical adoption of the developed methodology still needs to be improved. To overcome this limitation, we set out to predict the prognosis of a large multi-institutional cohort of patients with COVID-19 using a DL-based model.

PURPOSE

This study aimed to evaluate the performance of deep privacy-preserving federated learning (DPFL) in predicting COVID-19 outcomes using chest CT images.

METHODS

After applying inclusion and exclusion criteria, 3055 patients from 19 centers, including 1599 alive and 1456 deceased, were enrolled in this study. Data from all centers were split (randomly with stratification respective to each center and class) into a training/validation set (70%/10%) and a hold-out test set (20%). For the DL model, feature extraction was performed on 2D slices, and averaging was performed at the final layer to construct a 3D model for each scan. The DensNet model was used for feature extraction. The model was developed using centralized and FL approaches. For FL, we employed DPFL approaches. Membership inference attack was also evaluated in the FL strategy. For model evaluation, different metrics were reported in the hold-out test sets. In addition, models trained in two scenarios, centralized and FL, were compared using the DeLong test for statistical differences.

RESULTS

The centralized model achieved an accuracy of 0.76, while the DPFL model had an accuracy of 0.75. Both the centralized and DPFL models achieved a specificity of 0.77. The centralized model achieved a sensitivity of 0.74, while the DPFL model had a sensitivity of 0.73. A mean AUC of 0.82 and 0.81 with 95% confidence intervals of (95% CI: 0.79-0.85) and (95% CI: 0.77-0.84) were achieved by the centralized model and the DPFL model, respectively. The DeLong test did not prove statistically significant differences between the two models (p-value = 0.98). The AUC values for the inference attacks fluctuate between 0.49 and 0.51, with an average of 0.50 ± 0.003 and 95% CI for the mean AUC of 0.500 to 0.501.

CONCLUSION

The performance of the proposed model was comparable to centralized models while operating on large and heterogeneous multi-institutional datasets. In addition, the model was resistant to inference attacks, ensuring the privacy of shared data during the training process.

Personalized and privacy-preserving federated heterogeneous medical image analysis with PPPML-HMI

Heterogeneous data is endemic due to the use of diverse models and settings of devices by hospitals in the field of medical imaging. However, there are few open-source frameworks for federated heterogeneous medical image analysis with personalization and privacy protection without the demand to modify the existing model structures or to share any private data. Here, we proposed PPPML-HMI, a novel open-source learning paradigm for personalized and privacy-preserving federated heterogeneous medical image analysis. To our best knowledge, personalization and privacy protection were discussed simultaneously for the first time under the federated scenario by integrating the PerFedAvg algorithm and designing the novel cyclic secure aggregation with the homomorphic encryption algorithm. To show the utility of PPPML-HMI, we applied it to a simulated classification task namely the classification of healthy people and patients from the RAD-ChestCT Dataset, and one real-world segmentation task namely the segmentation of lung infections from COVID-19 CT scans. Meanwhile, we applied the improved deep leakage from gradients to simulate adversarial attacks and showed the strong privacy-preserving capability of PPPML-HMI. By applying PPPML-HMI to both tasks with different neural networks, a varied number of users, and sample sizes, we demonstrated the strong generalizability of PPPML-HMI in privacy-preserving federated learning on heterogeneous medical images.

Machine and deep learning methods for clinical outcome prediction based on physiological data of COVID-19 patients: a scoping review

INTRODUCTION

Since the beginning of the COVID-19 pandemic, numerous machine and deep learning (MDL) methods have been proposed in the literature to analyze patient physiological data. The objective of this review is to summarize various aspects of these methods and assess their practical utility for predicting various clinical outcomes.

METHODS

We searched PubMed, Scopus, and Cochrane Library, screened and selected the studies matching the inclusion criteria. The clinical analysis focused on the characteristics of the patient cohorts in the studies included in this review, the specific tasks in the context of the COVID-19 pandemic that machine and deep learning methods were used for, and their practical limitations. The technical analysis focused on the details of specific MDL methods and their performance.

RESULTS

Analysis of the 48 selected studies revealed that the majority (∼54 %) of them examined the application of MDL methods for the prediction of survival/mortality-related patient outcomes, while a smaller fraction (∼13 %) of studies also examined applications to the prediction of patients' physiological outcomes and hospital resource utilization. 21 % of the studies examined the application of MDL methods to multiple clinical tasks. Machine and deep learning methods have been shown to be effective at predicting several outcomes of COVID-19 patients, such as disease severity, complications, intensive care unit (ICU) transfer, and mortality. MDL methods also achieved high accuracy in predicting the required number of ICU beds and ventilators.

CONCLUSION

Machine and deep learning methods have been shown to be valuable tools for predicting disease severity, organ dysfunction and failure, patient outcomes, and hospital resource utilization during the COVID-19 pandemic. The discovered knowledge and our conclusions and recommendations can also be useful to healthcare professionals and artificial intelligence researchers in managing future pandemics.

Deep-learning models for image-based gynecological cancer diagnosis: a systematic review and meta- analysis

Introduction

Gynecological cancers pose a significant threat to women worldwide, especially those in resource-limited settings. Human analysis of images remains the primary method of diagnosis, but it can be inconsistent and inaccurate. Deep learning (DL) can potentially enhance image-based diagnosis by providing objective and accurate results. This systematic review and meta-analysis aimed to summarize the recent advances of deep learning (DL) techniques for gynecological cancer diagnosis using various images and explore their future implications.

Methods

The study followed the PRISMA-2 guidelines, and the protocol was registered in PROSPERO. Five databases were searched for articles published from January 2018 to December 2022. Articles that focused on five types of gynecological cancer and used DL for diagnosis were selected. Two reviewers assessed the articles for eligibility and quality using the QUADAS-2 tool. Data was extracted from each study, and the performance of DL techniques for gynecological cancer classification was estimated by pooling and transforming sensitivity and specificity values using a random-effects model.

Results

The review included 48 studies, and the meta-analysis included 24 studies. The studies used different images and models to diagnose different gynecological cancers. The most popular models were ResNet, VGGNet, and UNet. DL algorithms showed more sensitivity but less specificity compared to machine learning (ML) methods. The AUC of the summary receiver operating characteristic plot was higher for DL algorithms than for ML methods. Of the 48 studies included, 41 were at low risk of bias.

Conclusion

This review highlights the potential of DL in improving the screening and diagnosis of gynecological cancer, particularly in resource-limited settings. However, the high heterogeneity and quality of the studies could affect the validity of the results. Further research is necessary to validate the findings of this study and to explore the potential of DL in improving gynecological cancer diagnosis.

Combating COVID-19 Crisis using Artificial Intelligence (AI) Based Approach: Systematic Review

BACKGROUND

SARS-CoV-2, the unique coronavirus that causes COVID-19, has wreaked damage around the globe, with victims displaying a wide range of difficulties that have encouraged medical professionals to look for innovative technical solutions and therapeutic approaches. Artificial intelligence-based methods have contributed a significant part in tackling complicated issues, and some institutions have been quick to embrace and tailor these solutions in response to the COVID-19 pandemic's obstacles. Here, in this review article, we have covered a few DL techniques for COVID-19 detection and diagnosis, as well as ML techniques for COVID-19 identification, severity classification, vaccine and drug development, mortality rate prediction, contact tracing, risk assessment, and public distancing. This review illustrates the overall impact of AI/ML tools on tackling and managing the outbreak.

PURPOSE

The focus of this research was to undertake a thorough evaluation of the literature on the part of Artificial Intelligence (AI) as a complete and efficient solution in the battle against the COVID-19 epidemic in the domains of detection and diagnostics of disease, mortality prediction and vaccine as well as drug development.

METHODS

A comprehensive exploration of PubMed, Web of Science, and Science Direct was conducted using PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analysis) regulations to find all possibly suitable papers conducted and made publicly available between December 1, 2019, and August 2023. COVID-19, along with AI-specific words, was used to create the query syntax.

RESULTS

During the period covered by the search strategy, 961 articles were published and released online. Out of these, a total of 135 papers were chosen for additional investigation. Mortality rate prediction, early detection and diagnosis, vaccine as well as drug development, and lastly, incorporation of AI for supervising and controlling the COVID-19 pandemic were the four main topics focused entirely on AI applications used to tackle the COVID-19 crisis. Out of 135, 60 research papers focused on the detection and diagnosis of the COVID-19 pandemic. Next, 19 of the 135 studies applied a machine-learning approach for mortality rate prediction. Another 22 research publications emphasized the vaccine as well as drug development. Finally, the remaining studies were concentrated on controlling the COVID-19 pandemic by applying AI AI-based approach to it.

CONCLUSION

We compiled papers from the available COVID-19 literature that used AI-based methodologies to impart insights into various COVID-19 topics in this comprehensive study. Our results suggest crucial characteristics, data types, and COVID-19 tools that can aid in medical and translational research facilitation.

Supervised training models with or without manual lesion delineation outperform clinicians in distinguishing pulmonary cryptococcosis from lung adenocarcinoma on chest CT

BACKGROUND

The role of artificial intelligence (AI) in the discrimination between pulmonary cryptococcosis (PC) and lung adenocarcinoma (LA) warrants further research.

OBJECTIVES

To compare the performances of AI models with clinicians in distinguishing PC from LA on chest CT.

METHODS

Patients diagnosed with confirmed PC or LA were retrospectively recruited from three tertiary hospitals in Guangzhou. A deep learning framework was employed to develop two models: an undelineated supervised training (UST) model utilising original CT images, and a delineated supervised training (DST) model utilising CT images with manual lesion annotations provided by physicians. A subset of 20 cases was randomly selected from the entire dataset and reviewed by clinicians through a network questionnaire. The sensitivity, specificity and accuracy of the models and the clinicians were calculated.

RESULTS

A total of 395 PC cases and 249 LA cases were included in the final analysis. The internal validation results for the UST model showed a sensitivity of 85.3%, specificity of 81.0%, accuracy of 83.6% and an area under the curve (AUC) of 0.93. Similarly, the DST model exhibited a sensitivity of 88.2%, specificity of 88.1%, accuracy of 88.2% and an AUC of 0.94. The external validation of the two models yielded AUC values of 0.74 and 0.77, respectively. The average sensitivity, specificity and accuracy of 102 clinicians were determined to be 63.1%, 53.7% and 59.3%, respectively.

CONCLUSIONS

Both models outperformed the clinicians in distinguishing between PC and LA on chest CT, with the UST model exhibiting comparable performance to the DST model.

Chronic Lung Injury after COVID-19 Pneumonia: Clinical, Radiologic, and Histopathologic Perspectives

With the COVID-19 pandemic having lasted more than 3 years, concerns are growing about prolonged symptoms and respiratory complications in COVID-19 survivors, collectively termed post-COVID-19 condition (PCC). Up to 50% of patients have residual symptoms and physiologic impairment, particularly dyspnea and reduced diffusion capacity. Studies have also shown that 24%-54% of patients hospitalized during the 1st year of the pandemic exhibit radiologic abnormalities, such as ground-glass opacity, reticular opacity, bronchial dilatation, and air trapping, when imaged more than 1 year after infection. In patients with persistent respiratory symptoms but normal results at chest CT, dual-energy contrast-enhanced CT, xenon 129 MRI, and low-field-strength MRI were reported to show abnormal ventilation and/or perfusion, suggesting that some lung injury may not be detectable with standard CT. Histologic patterns in post-COVID-19 lung disease include fibrosis, organizing pneumonia, and vascular abnormality, indicating that different pathologic mechanisms may contribute to PCC. Therefore, a comprehensive imaging approach is necessary to evaluate and diagnose patients with persistent post-COVID-19 symptoms. This review will focus on the long-term findings of clinical and radiologic abnormalities and describe histopathologic perspectives. It also addresses advanced imaging techniques and deep learning approaches that can be applied to COVID-19 survivors. This field remains an active area of research, and further follow-up studies are warranted for a better understanding of the chronic stage of the disease and developing a multidisciplinary approach for patient management.

Development and external validation of a prediction model for the transition from mild to moderate or severe form of COVID-19

OBJECTIVES

COVID-19 pandemic seems to be under control. However, despite the vaccines, 5 to 10% of the patients with mild disease develop moderate to critical forms with potential lethal evolution. In addition to assess lung infection spread, chest CT helps to detect complications. Developing a prediction model to identify at-risk patients of worsening from mild COVID-19 combining simple clinical and biological parameters with qualitative or quantitative data using CT would be relevant to organizing optimal patient management.

METHODS

Four French hospitals were used for model training and internal validation. External validation was conducted in two independent hospitals. We used easy-to-obtain clinical (age, gender, smoking, symptoms' onset, cardiovascular comorbidities, diabetes, chronic respiratory diseases, immunosuppression) and biological parameters (lymphocytes, CRP) with qualitative or quantitative data (including radiomics) from the initial CT in mild COVID-19 patients.

RESULTS

Qualitative CT scan with clinical and biological parameters can predict which patients with an initial mild presentation would develop a moderate to critical form of COVID-19, with a c-index of 0.70 (95% CI 0.63; 0.77). CT scan quantification improved the performance of the prediction up to 0.73 (95% CI 0.67; 0.79) and radiomics up to 0.77 (95% CI 0.71; 0.83). Results were similar in both validation cohorts, considering CT scans with or without injection.

CONCLUSION

Adding CT scan quantification or radiomics to simple clinical and biological parameters can better predict which patients with an initial mild COVID-19 would worsen than qualitative analyses alone. This tool could help to the fair use of healthcare resources and to screen patients for potential new drugs to prevent a pejorative evolution of COVID-19.

CLINICAL TRIAL REGISTRATION

NCT04481620.

CLINICAL RELEVANCE STATEMENT

CT scan quantification or radiomics analysis is superior to qualitative analysis, when used with simple clinical and biological parameters, to determine which patients with an initial mild presentation of COVID-19 would worsen to a moderate to critical form.

KEY POINTS

• Qualitative CT scan analyses with simple clinical and biological parameters can predict which patients with an initial mild COVID-19 and respiratory symptoms would worsen with a c-index of 0.70. • Adding CT scan quantification improves the performance of the clinical prediction model to an AUC of 0.73. • Radiomics analyses slightly improve the performance of the model to a c-index of 0.77.

Prediction of oxygen supplementation by a deep-learning model integrating clinical parameters and chest CT images in COVID-19

PURPOSE

As of March 2023, the number of patients with COVID-19 worldwide is declining, but the early diagnosis of patients requiring inpatient treatment and the appropriate allocation of limited healthcare resources remain unresolved issues. In this study we constructed a deep-learning (DL) model to predict the need for oxygen supplementation using clinical information and chest CT images of patients with COVID-19.

MATERIALS AND METHODS

We retrospectively enrolled 738 patients with COVID-19 for whom clinical information (patient background, clinical symptoms, and blood test findings) was available and chest CT imaging was performed. The initial data set was divided into 591 training and 147 evaluation data. We developed a DL model that predicted oxygen supplementation by integrating clinical information and CT images. The model was validated at two other facilities (n = 191 and n = 230). In addition, the importance of clinical information for prediction was assessed.

RESULTS

The proposed DL model showed an area under the curve (AUC) of 89.9% for predicting oxygen supplementation. Validation from the two other facilities showed an AUC > 80%. With respect to interpretation of the model, the contribution of dyspnea and the lactate dehydrogenase level was higher in the model.

CONCLUSIONS

The DL model integrating clinical information and chest CT images had high predictive accuracy. DL-based prediction of disease severity might be helpful in the clinical management of patients with COVID-19.

Pneumonia-Plus: a deep learning model for the classification of bacterial, fungal, and viral pneumonia based on CT tomography

OBJECTIVES

This study aims to develop a deep learning algorithm, Pneumonia-Plus, based on computed tomography (CT) images for accurate classification of bacterial, fungal, and viral pneumonia.

METHODS

A total of 2763 participants with chest CT images and definite pathogen diagnosis were included to train and validate an algorithm. Pneumonia-Plus was prospectively tested on a nonoverlapping dataset of 173 patients. The algorithm's performance in classifying three types of pneumonia was compared to that of three radiologists using the McNemar test to verify its clinical usefulness.

RESULTS

Among the 173 patients, area under the curve (AUC) values for viral, fungal, and bacterial pneumonia were 0.816, 0.715, and 0.934, respectively. Viral pneumonia was accurately classified with sensitivity, specificity, and accuracy of 0.847, 0.919, and 0.873. Three radiologists also showed good consistency with Pneumonia-Plus. The AUC values of bacterial, fungal, and viral pneumonia were 0.480, 0.541, and 0.580 (radiologist 1: 3-year experience); 0.637, 0.693, and 0.730 (radiologist 2: 7-year experience); and 0.734, 0.757, and 0.847 (radiologist 3: 12-year experience), respectively. The McNemar test results for sensitivity showed that the diagnostic performance of the algorithm was significantly better than that of radiologist 1 and radiologist 2 (p < 0.05) in differentiating bacterial and viral pneumonia. Radiologist 3 had a higher diagnostic accuracy than the algorithm.

CONCLUSIONS

The Pneumonia-Plus algorithm is used to differentiate between bacterial, fungal, and viral pneumonia, which has reached the level of an attending radiologist and reduce the risk of misdiagnosis. The Pneumonia-Plus is important for appropriate treatment and avoiding the use of unnecessary antibiotics, and provide timely information to guide clinical decision-making and improve patient outcomes.

CLINICAL RELEVANCE STATEMENT

Pneumonia-Plus algorithm could assist in the accurate classification of pneumonia based on CT images, which has great clinical value in avoiding the use of unnecessary antibiotics, and providing timely information to guide clinical decision-making and improve patient outcomes.

KEY POINTS

• The Pneumonia-Plus algorithm trained from data collected from multiple centers can accurately identify bacterial, fungal, and viral pneumonia. • The Pneumonia-Plus algorithm was found to have better sensitivity in classifying viral and bacterial pneumonia in comparison to radiologist 1 (5-year experience) and radiologist 2 (7-year experience). • The Pneumonia-Plus algorithm is used to differentiate between bacterial, fungal, and viral pneumonia, which has reached the level of an attending radiologist.

Ensemble classification of integrated CT scan datasets in detecting COVID-19 using feature fusion from contourlet transform and CNN

The COVID-19 disease caused by coronavirus is constantly changing due to the emergence of different variants and thousands of people are dying every day worldwide. Early detection of this new form of pulmonary disease can reduce the mortality rate. In this paper, an automated method based on machine learning (ML) and deep learning (DL) has been developed to detect COVID-19 using computed tomography (CT) scan images extracted from three publicly available datasets (A total of 11,407 images; 7397 COVID-19 images and 4010 normal images). An unsupervised clustering approach that is a modified region-based clustering technique for segmenting COVID-19 CT scan image has been proposed. Furthermore, contourlet transform and convolution neural network (CNN) have been employed to extract features individually from the segmented CT scan images and to fuse them in one feature vector. Binary differential evolution (BDE) approach has been employed as a feature optimization technique to obtain comprehensible features from the fused feature vector. Finally, a ML/DL-based ensemble classifier considering bagging technique has been employed to detect COVID-19 from the CT images. A fivefold and generalization cross-validation techniques have been used for the validation purpose. Classification experiments have also been conducted with several pre-trained models (AlexNet, ResNet50, GoogleNet, VGG16, VGG19) and found that the ensemble classifier technique with fused feature has provided state-of-the-art performance with an accuracy of 99.98%.

COVID-19 screening in low resource settings using artificial intelligence for chest radiographs and point-of-care blood tests

Artificial intelligence (AI) systems for detection of COVID-19 using chest X-Ray (CXR) imaging and point-of-care blood tests were applied to data from four low resource African settings. The performance of these systems to detect COVID-19 using various input data was analysed and compared with antigen-based rapid diagnostic tests. Participants were tested using the gold standard of RT-PCR test (nasopharyngeal swab) to determine whether they were infected with SARS-CoV-2. A total of 3737 (260 RT-PCR positive) participants were included. In our cohort, AI for CXR images was a poor predictor of COVID-19 (AUC = 0.60), since the majority of positive cases had mild symptoms and no visible pneumonia in the lungs. AI systems using differential white blood cell counts (WBC), or a combination of WBC and C-Reactive Protein (CRP) both achieved an AUC of 0.74 with a suggested optimal cut-off point at 83% sensitivity and 63% specificity. The antigen-RDT tests in this trial obtained 65% sensitivity at 98% specificity. This study is the first to validate AI tools for COVID-19 detection in an African setting. It demonstrates that screening for COVID-19 using AI with point-of-care blood tests is feasible and can operate at a higher sensitivity level than antigen testing.

Deep learning models of ultrasonography significantly improved the differential diagnosis performance for superficial soft-tissue masses: a retrospective multicenter study

BACKGROUND

Most of superficial soft-tissue masses are benign tumors, and very few are malignant tumors. However, persistent growth, of both benign and malignant tumors, can be painful and even life-threatening. It is necessary to improve the differential diagnosis performance for superficial soft-tissue masses by using deep learning models. This study aimed to propose a new ultrasonic deep learning model (DLM) system for the differential diagnosis of superficial soft-tissue masses.

METHODS

Between January 2015 and December 2022, data for 1615 patients with superficial soft-tissue masses were retrospectively collected. Two experienced radiologists (radiologists 1 and 2 with 8 and 30 years' experience, respectively) analyzed the ultrasound images of each superficial soft-tissue mass and made a diagnosis of malignant mass or one of the five most common benign masses. After referring to the DLM results, they re-evaluated the diagnoses. The diagnostic performance and concerns of the radiologists were analyzed before and after referring to the results of the DLM results.

RESULTS

In the validation cohort, DLM-1 was trained to distinguish between benign and malignant masses, with an AUC of 0.992 (95% CI: 0.980, 1.0) and an ACC of 0.987 (95% CI: 0.968, 1.0). DLM-2 was trained to classify the five most common benign masses (lipomyoma, hemangioma, neurinoma, epidermal cyst, and calcifying epithelioma) with AUCs of 0.986, 0.993, 0.944, 0.973, and 0.903, respectively. In addition, under the condition of the DLM-assisted diagnosis, the radiologists greatly improved their accuracy of differential diagnosis between benign and malignant tumors.

CONCLUSIONS

The proposed DLM system has high clinical application value in the differential diagnosis of superficial soft-tissue masses.

Predicting acute pancreatitis severity with enhanced computed tomography scans using convolutional neural networks

This study aimed to evaluate acute pancreatitis (AP) severity using convolutional neural network (CNN) models with enhanced computed tomography (CT) scans. Three-dimensional DenseNet CNN models were developed and trained using the enhanced CT scans labeled with two severity assessment methods: the computed tomography severity index (CTSI) and Atlanta classification. Each labeling method was used independently for model training and validation. Model performance was evaluated using confusion matrices, areas under the receiver operating characteristic curve (AUC-ROC), accuracy, precision, recall, F1 score, and respective macro-average metrics. A total of 1,798 enhanced CT scans met the inclusion criteria were included in this study. The dataset was randomly divided into a training dataset (n = 1618) and a test dataset (n = 180) with a ratio of 9:1. The DenseNet model demonstrated promising predictions for both CTSI and Atlanta classification-labeled CT scans, with accuracy greater than 0.7 and AUC-ROC greater than 0.8. Specifically, when trained with CT scans labeled using CTSI, the DenseNet model achieved good performance, with a macro-average F1 score of 0.835 and a macro-average AUC-ROC of 0.980. The findings of this study affirm the feasibility of employing CNN models to predict the severity of AP using enhanced CT scans.

Validation of a risk prediction model for COVID-19: the PERIL prospective cohort study

Aim: This study aims to perform an external validation of a recently developed prognostic model for early prediction of the risk of progression to severe COVID-19. Patients & methods/materials: Patients were recruited at their initial diagnosis at two facilities within Hamad Medical Corporation in Qatar. 356 adults were included for analysis. Predictors for progression of COVID-19 were all measured at disease onset and first contact with the health system. Results: The C statistic was 83% (95% CI: 78%-87%) and the calibration plot showed that the model was well-calibrated. Conclusion: The published prognostic model for the progression of COVID-19 infection showed satisfactory discrimination and calibration and the model is easy to apply in clinical practice.d.

Using risk factors and markers to predict bacterial respiratory co-/superinfections in COVID-19 patients: is the antibiotic steward's toolbox full or empty?

BACKGROUND

Adequate diagnosis of bacterial respiratory tract co-/superinfection (bRTI) in coronavirus disease (COVID-19) patients is challenging, as there is insufficient knowledge about the role of risk factors and (para)clinical parameters in the identification of bacterial co-/superinfection in the COVID-19 setting. Empirical antibiotic therapy is mainly based on COVID-19 severity and expert opinion, rather than on scientific evidence generated since the start of the pandemic.

PURPOSE

We report the best available evidence regarding the predictive value of risk factors and (para)clinical markers in the diagnosis of bRTI in COVID-19 patients.

METHODS

A multidisciplinary team identified different potential risk factors and (para)clinical predictors of bRTI in COVID-19 and formulated one or two research questions per topic. After a thorough literature search, research gaps were identified, and suggestions concerning further research were formulated. The quality of this narrative review was ensured by following the Scale for the Assessment of Narrative Review Articles.

RESULTS

Taking into account the scarcity of scientific evidence for markers and risk factors of bRTI in COVID-19 patients, to date, COVID-19 severity is the only parameter which can be associated with higher risk of developing bRTI.

CONCLUSIONS

Evidence on the usefulness of risk factors and (para)clinical factors as predictors of bRTI in COVID-19 patients is scarce. Robust studies are needed to optimise antibiotic prescribing and stewardship activities in the context of COVID-19.

Applying the digital data and the bioinformatics tools in SARS-CoV-2 research

Bioinformatics has been playing a crucial role in the scientific progress to fight against the pandemic of the coronavirus disease 2019 (COVID-19) caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The advances in novel algorithms, mega data technology, artificial intelligence and deep learning assisted the development of novel bioinformatics tools to analyze daily increasing SARS-CoV-2 data in the past years. These tools were applied in genomic analyses, evolutionary tracking, epidemiological analyses, protein structure interpretation, studies in virus-host interaction and clinical performance. To promote the in-silico analysis in the future, we conducted a review which summarized the databases, web services and software applied in SARS-CoV-2 research. Those digital resources applied in SARS-CoV-2 research may also potentially contribute to the research in other coronavirus and non-coronavirus viruses.

Utilization of Deep Convolutional Neural Networks for Accurate Chest X-Ray Diagnosis and Disease Detection

Chest radiography is a widely used diagnostic imaging procedure in medical practice, which involves prompt reporting of future imaging tests and diagnosis of diseases in the images. In this study, a critical phase in the radiology workflow is automated using the three convolutional neural network (CNN) models, viz. DenseNet121, ResNet50, and EfficientNetB1 for fast and accurate detection of 14 class labels of thoracic pathology diseases based on chest radiography. These models were evaluated on an AUC score for normal versus abnormal chest radiographs using 112120 chest X-ray14 datasets containing various class labels of thoracic pathology diseases to predict the probability of individual diseases and warn clinicians of potential suspicious findings. With DenseNet121, the AUROC scores for hernia and emphysema were predicted as 0.9450 and 0.9120, respectively. Compared to the score values obtained for each class on the dataset, the DenseNet121 outperformed the other two models. This article also aims to develop an automated server to capture fourteen thoracic pathology disease results using a tensor processing unit (TPU). The results of this study demonstrate that our dataset can be used to train models with high diagnostic accuracy for predicting the likelihood of 14 different diseases in abnormal chest radiographs, enabling accurate and efficient discrimination between different types of chest radiographs. This has the potential to bring benefits to various stakeholders and improve patient care.

Attention fusion network with self-supervised learning for staging of osteonecrosis of the femoral head (ONFH) using multiple MR protocols

BACKGROUND

Osteonecrosis of the femoral head (ONFH) is characterized as bone cell death in the hip joint, involving a severe pain in the groin. The staging of ONFH is commonly based on Magnetic resonance imaging and computed tomography (CT), which are important for establishing effective treatment plans. There have been some attempts to automate ONFH staging using deep learning, but few of them used only MR images.

PURPOSE

To propose a deep learning model for MR-only ONFH staging, which can reduce additional cost and radiation exposure from the acquisition of CT images.

METHODS

We integrated information from the MR images of five different imaging protocols by a newly proposed attention fusion method, which was composed of intra-modality attention and inter-modality attention. In addition, a self-supervised learning was used to learn deep representations from a large amount of paired MR-CT dataset. The encoder part of the MR-CT translation network was used as a pretraining network for the staging, which aimed to overcome the lack of annotated data for staging. Ablation studies were performed to investigate the contributions of each proposed method. The area under the receiver operating characteristic curve (AUROC) was used to evaluate the performance of the networks.

RESULTS

Our model improved the performance of the four-way classification of the association research circulation osseous (ARCO) stage using MR images of the multiple protocols by 6.8%p in AUROC over a plain VGG network. Each proposed method increased the performance by 4.7%p (self-supervised learning) and 2.6%p (attention fusion) in AUROC, which was demonstrated by the ablation experiments.

CONCLUSIONS

We have shown the feasibility of the MR-only ONFH staging by using self-supervised learning and attention fusion. A large amount of paired MR-CT data in hospitals can be used to further improve the performance of the staging, and the proposed method has potential to be used in the diagnosis of various diseases that require staging from multiple MR protocols.

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.

Machine learning predicts lung recruitment in acute respiratory distress syndrome using single lung CT scan

BACKGROUND

To develop and validate classifier models that could be used to identify patients with a high percentage of potentially recruitable lung from readily available clinical data and from single CT scan quantitative analysis at intensive care unit admission. 221 retrospectively enrolled mechanically ventilated, sedated and paralyzed patients with acute respiratory distress syndrome (ARDS) underwent a PEEP trial at 5 and 15 cmH2O of PEEP and two lung CT scans performed at 5 and 45 cmH2O of airway pressure. Lung recruitability was defined at first as percent change in not aerated tissue between 5 and 45 cmH2O (radiologically defined; recruiters: Δ45-5non-aerated tissue  > 15%) and secondly as change in PaO2 between 5 and 15 cmH2O (gas exchange-defined; recruiters: Δ15-5PaO2  > 24 mmHg). Four machine learning (ML) algorithms were evaluated as classifiers of radiologically defined and gas exchange-defined lung recruiters using different models including different variables, separately or combined, of lung mechanics, gas exchange and CT data.

RESULTS

ML algorithms based on CT scan data at 5 cmH2O classified radiologically defined lung recruiters with similar AUC as ML based on the combination of lung mechanics, gas exchange and CT data. ML algorithm based on CT scan data classified gas exchange-defined lung recruiters with the highest AUC.

CONCLUSIONS

ML based on a single CT data at 5 cmH2O represented an easy-to-apply tool to classify ARDS patients in recruiters and non-recruiters according to both radiologically defined and gas exchange-defined lung recruitment within the first 48 h from the start of mechanical ventilation.

Predicting intensive care need for COVID-19 patients using deep learning on chest radiography

Purpose

Image-based prediction of coronavirus disease 2019 (COVID-19) severity and resource needs can be an important means to address the COVID-19 pandemic. In this study, we propose an artificial intelligence/machine learning (AI/ML) COVID-19 prognosis method to predict patients' needs for intensive care by analyzing chest X-ray radiography (CXR) images using deep learning.

Approach

The dataset consisted of 8357 CXR exams from 5046 COVID-19-positive patients as confirmed by reverse transcription polymerase chain reaction (RT-PCR) tests for the SARS-CoV-2 virus with a training/validation/test split of 64%/16%/20% on a by patient level. Our model involved a DenseNet121 network with a sequential transfer learning technique employed to train on a sequence of gradually more specific and complex tasks: (1) fine-tuning a model pretrained on ImageNet using a previously established CXR dataset with a broad spectrum of pathologies; (2) refining on another established dataset to detect pneumonia; and (3) fine-tuning using our in-house training/validation datasets to predict patients' needs for intensive care within 24, 48, 72, and 96 h following the CXR exams. The classification performances were evaluated on our independent test set (CXR exams of 1048 patients) using the area under the receiver operating characteristic curve (AUC) as the figure of merit in the task of distinguishing between those COVID-19-positive patients who required intensive care following the imaging exam and those who did not.

Results

Our proposed AI/ML model achieved an AUC (95% confidence interval) of 0.78 (0.74, 0.81) when predicting the need for intensive care 24 h in advance, and at least 0.76 (0.73, 0.80) for 48 h or more in advance using predictions based on the AI prognostic marker derived from CXR images.

Conclusions

This AI/ML prediction model for patients' needs for intensive care has the potential to support both clinical decision-making and resource management.

Deep learning for deterioration prediction of COVID-19 patients based on time-series of three vital signs

Unrecognized deterioration of COVID-19 patients can lead to high morbidity and mortality. Most existing deterioration prediction models require a large number of clinical information, typically collected in hospital settings, such as medical images or comprehensive laboratory tests. This is infeasible for telehealth solutions and highlights a gap in deterioration prediction models based on minimal data, which can be recorded at a large scale in any clinic, nursing home, or even at the patient's home. In this study, we develop and compare two prognostic models that predict if a patient will experience deterioration in the forthcoming 3 to 24 h. The models sequentially process routine triadic vital signs: (a) oxygen saturation, (b) heart rate, and (c) temperature. These models are also provided with basic patient information, including sex, age, vaccination status, vaccination date, and status of obesity, hypertension, or diabetes. The difference between the two models is the way that the temporal dynamics of the vital signs are processed. Model #1 utilizes a temporally-dilated version of the Long-Short Term Memory model (LSTM) for temporal processes, and Model #2 utilizes a residual temporal convolutional network (TCN) for this purpose. We train and evaluate the models using data collected from 37,006 COVID-19 patients at NYU Langone Health in New York, USA. The convolution-based model outperforms the LSTM based model, achieving a high AUROC of 0.8844-0.9336 for 3 to 24 h deterioration prediction on a held-out test set. We also conduct occlusion experiments to evaluate the importance of each input feature, which reveals the significance of continuously monitoring the variation of the vital signs. Our results show the prospect for accurate deterioration forecast using a minimum feature set that can be relatively easily obtained using wearable devices and self-reported patient information.

A comprehensive review of COVID-19 detection with machine learning and deep learning techniques

Purpose

The first transmission of coronavirus to humans started in Wuhan city of China, took the shape of a pandemic called Corona Virus Disease 2019 (COVID-19), and posed a principal threat to the entire world. The researchers are trying to inculcate artificial intelligence (Machine learning or deep learning models) for the efficient detection of COVID-19. This research explores all the existing machine learning (ML) or deep learning (DL) models, used for COVID-19 detection which may help the researcher to explore in different directions. The main purpose of this review article is to present a compact overview of the application of artificial intelligence to the research experts, helping them to explore the future scopes of improvement.

Methods

The researchers have used various machine learning, deep learning, and a combination of machine and deep learning models for extracting significant features and classifying various health conditions in COVID-19 patients. For this purpose, the researchers have utilized different image modalities such as CT-Scan, X-Ray, etc. This study has collected over 200 research papers from various repositories like Google Scholar, PubMed, Web of Science, etc. These research papers were passed through various levels of scrutiny and finally, 50 research articles were selected.

Results

In those listed articles, the ML / DL models showed an accuracy of 99% and above while performing the classification of COVID-19. This study has also presented various clinical applications of various research. This study specifies the importance of various machine and deep learning models in the field of medical diagnosis and research.

Conclusion

In conclusion, it is evident that ML/DL models have made significant progress in recent years, but there are still limitations that need to be addressed. Overfitting is one such limitation that can lead to incorrect predictions and overburdening of the models. The research community must continue to work towards finding ways to overcome these limitations and make machine and deep learning models even more effective and efficient. Through this ongoing research and development, we can expect even greater advances in the future.

AI support for accurate and fast radiological diagnosis of COVID-19: an international multicenter, multivendor CT study

OBJECTIVES

Differentiation between COVID-19 and community-acquired pneumonia (CAP) in computed tomography (CT) is a task that can be performed by human radiologists and artificial intelligence (AI). The present study aims to (1) develop an AI algorithm for differentiating COVID-19 from CAP and (2) evaluate its performance. (3) Evaluate the benefit of using the AI result as assistance for radiological diagnosis and the impact on relevant parameters such as accuracy of the diagnosis, diagnostic time, and confidence.

METHODS

We included n = 1591 multicenter, multivendor chest CT scans and divided them into AI training and validation datasets to develop an AI algorithm (n = 991 CT scans; n = 462 COVID-19, and n = 529 CAP) from three centers in China. An independent Chinese and German test dataset of n = 600 CT scans from six centers (COVID-19 / CAP; n = 300 each) was used to test the performance of eight blinded radiologists and the AI algorithm. A subtest dataset (180 CT scans; n = 90 each) was used to evaluate the radiologists' performance without and with AI assistance to quantify changes in diagnostic accuracy, reporting time, and diagnostic confidence.

RESULTS

The diagnostic accuracy of the AI algorithm in the Chinese-German test dataset was 76.5%. Without AI assistance, the eight radiologists' diagnostic accuracy was 79.1% and increased with AI assistance to 81.5%, going along with significantly shorter decision times and higher confidence scores.

CONCLUSION

This large multicenter study demonstrates that AI assistance in CT-based differentiation of COVID-19 and CAP increases radiological performance with higher accuracy and specificity, faster diagnostic time, and improved diagnostic confidence.

KEY POINTS

• AI can help radiologists to get higher diagnostic accuracy, make faster decisions, and improve diagnostic confidence. • The China-German multicenter study demonstrates the advantages of a human-machine interaction using AI in clinical radiology for diagnostic differentiation between COVID-19 and CAP in CT scans.

Development and validation of a CT-based radiomics model for differentiating pneumonia-like primary pulmonary lymphoma from infectious pneumonia: A multicenter study

BACKGROUND

Pneumonia-like primary pulmonary lymphoma (PPL) was commonly misdiagnosed as infectious pneumonia, leading to delayed treatment. The purpose of this study was to establish a computed tomography (CT)-based radiomics model to differentiate pneumonia-like PPL from infectious pneumonia.

METHODS

In this retrospective study, 79 patients with pneumonia-like PPL and 176 patients with infectious pneumonia from 12 medical centers were enrolled. Patients from center 1 to center 7 were assigned to the training or validation cohort, and the remaining patients from other centers were used as the external test cohort. Radiomics features were extracted from CT images. A three-step procedure was applied for radiomics feature selection and radiomics signature building, including the inter- and intra-class correlation coefficients (ICCs), a one-way analysis of variance (ANOVA), and least absolute shrinkage and selection operator (LASSO). Univariate and multivariate analyses were used to identify the significant clinicoradiological variables and construct a clinical factor model. Two radiologists reviewed the CT images for the external test set. Performance of the radiomics model, clinical factor model, and each radiologist were assessed by receiver operating characteristic, and area under the curve (AUC) was compared.

RESULTS

A total of 144 patients (44 with pneumonia-like PPL and 100 infectious pneumonia) were in the training cohort, 38 patients (12 with pneumonia-like PPL and 26 infectious pneumonia) were in the validation cohort, and 73 patients (23 with pneumonia-like PPL and 50 infectious pneumonia) were in the external test cohort. Twenty-three radiomics features were selected to build the radiomics model, which yielded AUCs of 0.95 (95% confidence interval [CI]: 0.94-0.99), 0.93 (95% CI: 0.85-0.98), and 0.94 (95% CI: 0.87-0.99) in the training, validation, and external test cohort, respectively. The AUCs for the two readers and clinical factor model were 0.74 (95% CI: 0.63-0.83), 0.72 (95% CI: 0.62-0.82), and 0.73 (95% CI: 0.62-0.84) in the external test cohort, respectively. The radiomics model outperformed both the readers' interpretation and clinical factor model ( P <0.05).

CONCLUSIONS

The CT-based radiomics model may provide an effective and non-invasive tool to differentiate pneumonia-like PPL from infectious pneumonia, which might provide assistance for clinicians in tailoring precise therapy.

Harnessing Machine Learning in Early COVID-19 Detection and Prognosis: A Comprehensive Systematic Review

During the early phase of the COVID-19 pandemic, reverse transcriptase-polymerase chain reaction (RT-PCR) testing faced limitations, prompting the exploration of machine learning (ML) alternatives for diagnosis and prognosis. Providing a comprehensive appraisal of such decision support systems and their use in COVID-19 management can aid the medical community in making informed decisions during the risk assessment of their patients, especially in low-resource settings. Therefore, the objective of this study was to systematically review the studies that predicted the diagnosis of COVID-19 or the severity of the disease using ML. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA), we conducted a literature search of MEDLINE (OVID), Scopus, EMBASE, and IEEE Xplore from January 1 to June 31, 2020. The outcomes were COVID-19 diagnosis or prognostic measures such as death, need for mechanical ventilation, admission, and acute respiratory distress syndrome. We included peer-reviewed observational studies, clinical trials, research letters, case series, and reports. We extracted data about the study's country, setting, sample size, data source, dataset, diagnostic or prognostic outcomes, prediction measures, type of ML model, and measures of diagnostic accuracy. Bias was assessed using the Prediction model Risk Of Bias ASsessment Tool (PROBAST). This study was registered in the International Prospective Register of Systematic Reviews (PROSPERO), with the number CRD42020197109. The final records included for data extraction were 66. Forty-three (64%) studies used secondary data. The majority of studies were from Chinese authors (30%). Most of the literature (79%) relied on chest imaging for prediction, while the remainder used various laboratory indicators, including hematological, biochemical, and immunological markers. Thirteen studies explored predicting COVID-19 severity, while the rest predicted diagnosis. Seventy percent of the articles used deep learning models, while 30% used traditional ML algorithms. Most studies reported high sensitivity, specificity, and accuracy for the ML models (exceeding 90%). The overall concern about the risk of bias was "unclear" in 56% of the studies. This was mainly due to concerns about selection bias. ML may help identify COVID-19 patients in the early phase of the pandemic, particularly in the context of chest imaging. Although these studies reflect that these ML models exhibit high accuracy, the novelty of these models and the biases in dataset selection make using them as a replacement for the clinicians' cognitive decision-making questionable. Continued research is needed to enhance the robustness and reliability of ML systems in COVID-19 diagnosis and prognosis.

Emerging technologies for COVID (ET-CoV) detection and diagnosis: Recent advancements, applications, challenges, and future perspectives

In light of the constantly changing terrain of the COVID outbreak, medical specialists have implemented proactive schemes for vaccine production. Despite the remarkable COVID-19 vaccine development, the virus has mutated into new variants, including delta and omicron. Currently, the situation is critical in many parts of the world, and precautions are being taken to stop the virus from spreading and mutating. Early identification and diagnosis of COVID-19 are the main challenges faced by emerging technologies during the outbreak. In these circumstances, emerging technologies to tackle Coronavirus have proven magnificent. Artificial intelligence (AI), big data, the internet of medical things (IoMT), robotics, blockchain technology, telemedicine, smart applications, and additive manufacturing are suspicious for detecting, classifying, monitoring, and locating COVID-19. Henceforth, this research aims to glance at these COVID-19 defeating technologies by focusing on their strengths and limitations. A CiteSpace-based bibliometric analysis of the emerging technology was established. The most impactful keywords and the ongoing research frontiers were compiled. Emerging technologies were unstable due to data inconsistency, redundant and noisy datasets, and the inability to aggregate the data due to disparate data formats. Moreover, the privacy and confidentiality of patient medical records are not guaranteed. Hence, Significant data analysis is required to develop an intelligent computational model for effective and quick clinical diagnosis of COVID-19. Remarkably, this article outlines how emerging technology has been used to counteract the virus disaster and offers ongoing research frontiers, directing readers to concentrate on the real challenges and thus facilitating additional explorations to amplify emerging technologies.

uRP: An integrated research platform for one-stop analysis of medical images

Introduction

Medical image analysis is of tremendous importance in serving clinical diagnosis, treatment planning, as well as prognosis assessment. However, the image analysis process usually involves multiple modality-specific software and relies on rigorous manual operations, which is time-consuming and potentially low reproducible.

Methods

We present an integrated platform - uAI Research Portal (uRP), to achieve one-stop analyses of multimodal images such as CT, MRI, and PET for clinical research applications. The proposed uRP adopts a modularized architecture to be multifunctional, extensible, and customizable.

Results and Discussion

The uRP shows 3 advantages, as it 1) spans a wealth of algorithms for image processing including semi-automatic delineation, automatic segmentation, registration, classification, quantitative analysis, and image visualization, to realize a one-stop analytic pipeline, 2) integrates a variety of functional modules, which can be directly applied, combined, or customized for specific application domains, such as brain, pneumonia, and knee joint analyses, 3) enables full-stack analysis of one disease, including diagnosis, treatment planning, and prognosis assessment, as well as full-spectrum coverage for multiple disease applications. With the continuous development and inclusion of advanced algorithms, we expect this platform to largely simplify the clinical scientific research process and promote more and better discoveries.

Deep Convolutional Neural Networks for Detecting COVID-19 Using Medical Images: A Survey

Coronavirus Disease 2019 (COVID-19), which is caused by Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-COV-2), surprised the world in December 2019 and has threatened the lives of millions of people. Countries all over the world closed worship places and shops, prevented gatherings, and implemented curfews to stand against the spread of COVID-19. Deep Learning (DL) and Artificial Intelligence (AI) can have a great role in detecting and fighting this disease. Deep learning can be used to detect COVID-19 symptoms and signs from different imaging modalities, such as X-Ray, Computed Tomography (CT), and Ultrasound Images (US). This could help in identifying COVID-19 cases as a first step to curing them. In this paper, we reviewed the research studies conducted from January 2020 to September 2022 about deep learning models that were used in COVID-19 detection. This paper clarified the three most common imaging modalities (X-Ray, CT, and US) in addition to the DL approaches that are used in this detection and compared these approaches. This paper also provided the future directions of this field to fight COVID-19 disease.

Digital health-high tech or high touch?

Digital transformation in medicine refers to the implementation of information technology-driven developments in the healthcare system and their impact on the way we teach, share, and practice medicine. We would like to provide an overview of current developments and opportunities but also of the risks of digital transformation in medicine. Therefore, we examine the possibilities wearables and digital biomarkers provide for early detection and monitoring of diseases and discuss the potential of artificial intelligence applications in medicine. Furthermore, we outline new opportunities offered by telemedicine applications and digital therapeutics, discuss the aspects of social media in healthcare, and provide an outlook on "Health 4.0."

Prediction of pulp exposure risk of carious pulpitis based on deep learning

OBJECTIVES

This study aims to predict the risk of deep caries exposure in radiographic images based on the convolutional neural network model, compare the prediction results of the network model with those of senior dentists, evaluate the performance of the model for teaching and training stomatological students and young dentists, and assist dentists to clarify treatment plans and conduct good doctor-patient communication before surgery.

METHODS

A total of 206 cases of pulpitis caused by deep caries were selected from the Department of Stomatological Hospital of Tianjin Medical University from 2019 to 2022. According to the inclusion and exclusion criteria, 104 cases of pulpitis were exposed during the decaying preparation period and 102 cases of pulpitis were not exposed. The 206 radiographic images collected were randomly divided into three groups according to the proportion: 126 radiographic images in the training set, 40 radiographic images in the validation set, and 40 radiographic images in the test set. Three convolutional neural networks, visual geometry group network (VGG), residual network (ResNet), and dense convolutional network (DenseNet) were selected to analyze the rules of the radiographic images in the training set. The radiographic images of the validation set were used to adjust the super parameters of the network. Finally, 40 radiographic images of the test set were used to evaluate the performance of the three network models. A senior dentist specializing in dental pulp was selected to predict whether the deep caries of 40 radiographic images in the test set were exposed. The gold standard is whether the pulp is exposed after decaying the prepared hole during the clinical operation. The prediction effect of the three network models (VGG, ResNet, and DenseNet) and the senior dentist on the pulp exposure of 40 radiographic images in the test set were compared using receiver operating characteristic (ROC) curve, area under the ROC curve (AUC), accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1 score to select the best network model.

RESULTS

The best network model was DenseNet model, with AUC of 0.97. The AUC values of the ResNet model, VGG model, and the senior dentist were 0.89, 0.78, and 0.87, respectively. Accuracy was not statistically different between the senior dentist (0.850) and the DenseNet model (0.850)(P>0.05). Kappa consistency test showed moderate reliability (Kappa=0.6>0.4, P<0.05).

CONCLUSIONS

Among the three convolutional neural network models, the DenseNet model has the best predictive effect on whether deep caries are exposed in imaging. The predictive effect of this model is equivalent to the level of senior dentists specializing in dental pulp.

Prediction of COVID-19 patients in danger of death using radiomic features of portable chest radiographs

INTRODUCTION

Computer-aided diagnostic systems have been developed for the detection and differential diagnosis of coronavirus disease 2019 (COVID-19) pneumonia using imaging studies to characterise a patient's current condition. In this radiomic study, we propose a system for predicting COVID-19 patients in danger of death using portable chest X-ray images.

METHODS

In this retrospective study, we selected 100 patients, including ten that died and 90 that recovered from the COVID-19-AR database of the Cancer Imaging Archive. Since it can be difficult to analyse portable chest X-ray images of patients with COVID-19 because bone components overlap with the abnormal patterns of this disease, we employed a bone-suppression technique during pre-processing. A total of 620 radiomic features were measured in the left and right lung regions, and four radiomic features were selected using the least absolute shrinkage and selection operator technique. We distinguished death from recovery cases using a linear discriminant analysis (LDA) and a support vector machine (SVM). The leave-one-out method was used to train and test the classifiers, and the area under the receiver-operating characteristic curve (AUC) was used to evaluate discriminative performance.

RESULTS

The AUCs for LDA and SVM were 0.756 and 0.959, respectively. The discriminative performance was improved when the bone-suppression technique was employed. When the SVM was used, the sensitivity for predicting disease severity was 90.9% (9/10), and the specificity was 95.6% (86/90).

CONCLUSIONS

We believe that the radiomic features of portable chest X-ray images can predict COVID-19 patients in danger of death.

The race to understand immunopathology in COVID-19: Perspectives on the impact of quantitative approaches to understand within-host interactions

The COVID-19 pandemic has revealed the need for the increased integration of modelling and data analysis to public health, experimental, and clinical studies. Throughout the first two years of the pandemic, there has been a concerted effort to improve our understanding of the within-host immune response to the SARS-CoV-2 virus to provide better predictions of COVID-19 severity, treatment and vaccine development questions, and insights into viral evolution and the impacts of variants on immunopathology. Here we provide perspectives on what has been accomplished using quantitative methods, including predictive modelling, population genetics, machine learning, and dimensionality reduction techniques, in the first 26 months of the COVID-19 pandemic approaches, and where we go from here to improve our responses to this and future pandemics.

Deep Learning-Based Time-to-Death Prediction Model for COVID-19 Patients Using Clinical Data and Chest Radiographs

Accurate estimation of mortality and time to death at admission for COVID-19 patients is important and several deep learning models have been created for this task. However, there are currently no prognostic models which use end-to-end deep learning to predict time to event for admitted COVID-19 patients using chest radiographs and clinical data. We retrospectively implemented a new artificial intelligence model combining DeepSurv (a multiple-perceptron implementation of the Cox proportional hazards model) and a convolutional neural network (CNN) using 1356 COVID-19 inpatients. For comparison, we also prepared DeepSurv only with clinical data, DeepSurv only with images (CNNSurv), and Cox proportional hazards models. Clinical data and chest radiographs at admission were used to estimate patient outcome (death or discharge) and duration to the outcome. The Harrel's concordance index (c-index) of the DeepSurv with CNN model was 0.82 (0.75-0.88) and this was significantly higher than the DeepSurv only with clinical data model (c-index = 0.77 (0.69-0.84), p = 0.011), CNNSurv (c-index = 0.70 (0.63-0.79), p = 0.001), and the Cox proportional hazards model (c-index = 0.71 (0.63-0.79), p = 0.001). These results suggest that the time-to-event prognosis model became more accurate when chest radiographs and clinical data were used together.

Multi-domain medical image translation generation for lung image classification based on generative adversarial networks

OBJECTIVE

Lung image classification-assisted diagnosis has a large application market. Aiming at the problems of poor attention to existing translation models, the insufficient ability of key transfer and generation, insufficient quality of generated images, and lack of detailed features, this paper conducts research on lung medical image translation and lung image classification based on generative adversarial networks.

METHODS

This paper proposes a medical image multi-domain translation algorithm MI-GAN based on the key migration branch. After the actual analysis of the imbalanced medical image data, the key target domain images are selected, the key migration branch is established, and a single generator is used to complete the medical image multi-domain translation. The conversion between domains ensures the attention performance of the medical image multi-domain translation model and the quality of the synthesized images. At the same time, a lung image classification model based on synthetic image data augmentation is proposed. The synthetic lung CT medical images and the original real medical images are used as the training set together to study the performance of the auxiliary diagnosis model in the classification of normal healthy subjects, and also of the mild and severe COVID-19 patients.

RESULTS

Based on the chest CT image dataset, MI-GAN has completed the mutual conversion and generation of normal lung images without disease, viral pneumonia and Mild COVID-19 images. The synthetic images GAN-test and GAN-train indicators reached, respectively 92.188% and 85.069%, compared with other generative models in terms of authenticity and diversity, there is a considerable improvement. The accuracy rate of pneumonia diagnosis of the lung image classification model is 93.85%, which is 3.1% higher than that of the diagnosis model trained only with real images; the sensitivity of disease diagnosis is 96.69%, a relative improvement of 7.1%. 1%, the specificity was 89.70%; the area under the ROC curve (AUC) increased from 94.00% to 96.17%.

CONCLUSION

In this paper, a multi-domain translation model of medical images based on the key transfer branch is proposed, which enables the translation network to have key transfer and attention performance. It is verified on lung CT images and achieved good results. The required medical images are synthesized by the above medical image translation model, and the effectiveness of the synthesized images on the lung image classification network is verified experimentally.

Comparison of the Diagnostic Performance of Deep Learning Algorithms for Reducing the Time Required for COVID-19 RT-PCR Testing

(1) Background: Rapid and accurate negative discrimination enables efficient management of scarce isolated bed resources and adequate patient accommodation in the majority of areas experiencing an explosion of confirmed cases due to Omicron mutations. Until now, methods for artificial intelligence or deep learning to replace time-consuming RT-PCR have relied on CXR, chest CT, blood test results, or clinical information. (2) Methods: We proposed and compared five different types of deep learning algorithms (RNN, LSTM, Bi-LSTM, GRU, and transformer) for reducing the time required for RT-PCR diagnosis by learning the change in fluorescence value derived over time during the RT-PCR process. (3) Results: Among the five deep learning algorithms capable of training time series data, Bi-LSTM and GRU were shown to be able to decrease the time required for RT-PCR diagnosis by half or by 25% without significantly impairing the diagnostic performance of the COVID-19 RT-PCR test. (4) Conclusions: The diagnostic performance of the model developed in this study when 40 cycles of RT-PCR are used for diagnosis shows the possibility of nearly halving the time required for RT-PCR diagnosis.

Is the generalizability of a developed artificial intelligence algorithm for COVID-19 on chest CT sufficient for clinical use? Results from the International Consortium for COVID-19 Imaging AI (ICOVAI)

OBJECTIVES

Only few published artificial intelligence (AI) studies for COVID-19 imaging have been externally validated. Assessing the generalizability of developed models is essential, especially when considering clinical implementation. We report the development of the International Consortium for COVID-19 Imaging AI (ICOVAI) model and perform independent external validation.

METHODS

The ICOVAI model was developed using multicenter data (n = 1286 CT scans) to quantify disease extent and assess COVID-19 likelihood using the COVID-19 Reporting and Data System (CO-RADS). A ResUNet model was modified to automatically delineate lung contours and infectious lung opacities on CT scans, after which a random forest predicted the CO-RADS score. After internal testing, the model was externally validated on a multicenter dataset (n = 400) by independent researchers. CO-RADS classification performance was calculated using linearly weighted Cohen's kappa and segmentation performance using Dice Similarity Coefficient (DSC).

RESULTS

Regarding internal versus external testing, segmentation performance of lung contours was equally excellent (DSC = 0.97 vs. DSC = 0.97, p = 0.97). Lung opacities segmentation performance was adequate internally (DSC = 0.76), but significantly worse on external validation (DSC = 0.59, p < 0.0001). For CO-RADS classification, agreement with radiologists on the internal set was substantial (kappa = 0.78), but significantly lower on the external set (kappa = 0.62, p < 0.0001).

CONCLUSION

In this multicenter study, a model developed for CO-RADS score prediction and quantification of COVID-19 disease extent was found to have a significant reduction in performance on independent external validation versus internal testing. The limited reproducibility of the model restricted its potential for clinical use. The study demonstrates the importance of independent external validation of AI models.

KEY POINTS

• The ICOVAI model for prediction of CO-RADS and quantification of disease extent on chest CT of COVID-19 patients was developed using a large sample of multicenter data. • There was substantial performance on internal testing; however, performance was significantly reduced on external validation, performed by independent researchers. The limited generalizability of the model restricts its potential for clinical use. • Results of AI models for COVID-19 imaging on internal tests may not generalize well to external data, demonstrating the importance of independent external validation.

A deep learning-based application for COVID-19 diagnosis on CT: The Imaging COVID-19 AI initiative

BACKGROUND

Recently, artificial intelligence (AI)-based applications for chest imaging have emerged as potential tools to assist clinicians in the diagnosis and management of patients with coronavirus disease 2019 (COVID-19).

OBJECTIVES

To develop a deep learning-based clinical decision support system for automatic diagnosis of COVID-19 on chest CT scans. Secondarily, to develop a complementary segmentation tool to assess the extent of lung involvement and measure disease severity.

METHODS

The Imaging COVID-19 AI initiative was formed to conduct a retrospective multicentre cohort study including 20 institutions from seven different European countries. Patients with suspected or known COVID-19 who underwent a chest CT were included. The dataset was split on the institution-level to allow external evaluation. Data annotation was performed by 34 radiologists/radiology residents and included quality control measures. A multi-class classification model was created using a custom 3D convolutional neural network. For the segmentation task, a UNET-like architecture with a backbone Residual Network (ResNet-34) was selected.

RESULTS

A total of 2,802 CT scans were included (2,667 unique patients, mean [standard deviation] age = 64.6 [16.2] years, male/female ratio 1.3:1). The distribution of classes (COVID-19/Other type of pulmonary infection/No imaging signs of infection) was 1,490 (53.2%), 402 (14.3%), and 910 (32.5%), respectively. On the external test dataset, the diagnostic multiclassification model yielded high micro-average and macro-average AUC values (0.93 and 0.91, respectively). The model provided the likelihood of COVID-19 vs other cases with a sensitivity of 87% and a specificity of 94%. The segmentation performance was moderate with Dice similarity coefficient (DSC) of 0.59. An imaging analysis pipeline was developed that returned a quantitative report to the user.

CONCLUSION

We developed a deep learning-based clinical decision support system that could become an efficient concurrent reading tool to assist clinicians, utilising a newly created European dataset including more than 2,800 CT scans.