The Role of Chest Imaging in Patient Management during the COVID-19 Pandemic: A Multinational Consensus Statement from the Fleischner Society

Lung cancer masquerading as COVID-19 in a young non-smoking woman: case report

Introduction and importance

The clinical and radiological similarities between COVID-19 and lung cancer pose diagnostic challenges, particularly in young, non-smoking individuals. Ground glass opacities (GGO) on imaging, often associated with COVID-19, can also indicate lung cancer. Distinguishing between these conditions is crucial but complex, requiring a systematic approach.

Case presentation

The authors present a case of a 31-year-old non-smoking woman initially suspected of COVID-19 due to cough, dyspnea, and GGO on chest CT. Despite negative RT-PCR and inconclusive bronchial aspiration, symptoms persisted, prompting further investigation. A PET scan revealed hypermetabolic consolidation, leading to a biopsy confirming adenocarcinoma.

Clinical discussion

Lung cancer can mimic COVID-19 symptoms, complicating diagnosis, especially in young, non-smoking patients. While smoking remains the primary risk factor, lung cancer in non-smokers, particularly young individuals, is increasingly recognized. GGO, commonly associated with COVID-19, should prompt consideration of malignancy, emphasizing the importance of a comprehensive differential diagnosis.

Conclusion

Early detection of lung cancer in young, non-smoking individuals is vital yet challenging. Clinicians should maintain a high index of suspicion, promptly investigating persistent or worsening symptoms, even in the absence of traditional risk factors. Timely biopsy and intervention are critical for improving outcomes in this population.

129Xe MRI Ventilation Textures and Longitudinal Quality-of-Life Improvements in Long-COVID

RATIONALE AND OBJECTIVES

It remains difficult to predict longitudinal outcomes in long-COVID, even with chest CT and functional MRI. 129Xe MRI reflects airway dysfunction, measured using ventilation defect percent (VDP) and in long-COVID patients, MRI VDP was abnormal, suggestive of airways disease. While MRI VDP and quality-of-life improved 15-month post-COVID infection, both remained abnormal. To better understand the relationship of airways disease and quality-of-life improvements in patients with long-COVID, we extracted 129Xe ventilation MRI textures and generated machine-learning models in an effort to predict improved quality-of-life, 15-month post-infection.

MATERIALS AND METHODS

Long-COVID patients provided written-informed consent to 3-month and 15-month post-infection visits. Pyradiomics was used to extract 129Xe ventilation MRI texture features, which were ranked using a Random-Forest classifier. Top-ranking features were used in classification models to dichotomize patients based on St. George's Respiratory Questionnaire (SGRQ) score improvement greater than the minimal-clinically-important-difference (MCID). Classification performance was evaluated using the area under the receiver-operator-characteristic-curve (AUC), sensitivity, and specificity.

RESULTS

120 texture features were extracted from 129Xe ventilation MRI in 44 long-COVID participants (54 ± 14 years), including 30 (52 ± 12 years) with ΔSGRQ≥MCID and 14 (58 ± 18 years) with ΔSGRQ

CONCLUSION

A machine learning model exclusively trained on 129Xe MRI ventilation textures explained improved SGRQ-scores 12 months later, and outperformed clinical models. Their unique spatial-intensity information helps build our understanding about long-COVID airway dysfunction.

Collapse

Key Words Collapse

MESH Headings

• Humans
• COVID-19/diagnostic imaging
• COVID-19/complications
• Magnetic Resonance Imaging/methods
• Male
• Female
• Middle Aged
• Quality of Life
• Xenon Isotopes
• Aged
• Machine Learning
• Longitudinal Studies
• SARS-CoV-2
• Lung/diagnostic imaging

Collapse

Grants Collapse

Affiliation(s)

Harkiran K Kooner Robarts Research Institute, Western University, London, Canada; Department of Medical Biophysics, Western University, London, Canada
Maksym Sharma Robarts Research Institute, Western University, London, Canada; Department of Medical Biophysics, Western University, London, Canada
Marrissa J McIntosh Robarts Research Institute, Western University, London, Canada; Department of Medical Biophysics, Western University, London, Canada
Inderdeep Dhaliwal Division of Respirology, Department of Medicine, Western University, London, Canada
J Michael Nicholson Division of Respirology, Department of Medicine, Western University, London, Canada
Miranda Kirby Department of Physics, Toronto Metropolitan University, Toronto, Canada
Sarah Svenningsen Division of Respirology, Department of Medicine, McMaster University and Firestone Institute for Respiratory Health, St. Joseph's Health Care, Hamilton, Canada
Grace Parraga Robarts Research Institute, Western University, London, Canada; Department of Medical Biophysics, Western University, London, Canada; Division of Respirology, Department of Medicine, Western University, London, Canada.

Collapse

An emerging network for COVID-19 CT-scan classification using an ensemble deep transfer learning model

Over the past few years, the widespread outbreak of COVID-19 has caused the death of millions of people worldwide. Early diagnosis of the virus is essential to control its spread and provide timely treatment. Artificial intelligence methods are often used as powerful tools to reach a COVID-19 diagnosis via computed tomography (CT) samples. In this paper, artificial intelligence-based methods are introduced to diagnose COVID-19. At first, a network called CT6-CNN is designed, and then two ensemble deep transfer learning models are developed based on Xception, ResNet-101, DenseNet-169, and CT6-CNN to reach a COVID-19 diagnosis by CT samples. The publicly available SARS-CoV-2 CT dataset is utilized for our implementation, including 2481 CT scans. The dataset is separated into 2108, 248, and 125 images for training, validation, and testing, respectively. Based on experimental results, the CT6-CNN model achieved 94.66% accuracy, 94.67% precision, 94.67% sensitivity, and 94.65% F1-score rate. Moreover, the ensemble learning models reached 99.2% accuracy. Experimental results affirm the effectiveness of designed models, especially the ensemble deep learning models, to reach a diagnosis of COVID-19.

Anatomy-specific Progression Classification in Chest Radiographs via Weakly Supervised Learning

Purpose To develop a machine learning approach for classifying disease progression in chest radiographs using weak labels automatically derived from radiology reports. Materials and Methods In this retrospective study, a twin neural network was developed to classify anatomy-specific disease progression into four categories: improved, unchanged, worsened, and new. A two-step weakly supervised learning approach was employed, pretraining the model on 243 008 frontal chest radiographs from 63 877 patients (mean age, 51.7 years ± 17.0 [SD]; 34 813 [55%] female) included in the MIMIC-CXR database and fine-tuning it on the subset with progression labels derived from consecutive studies. Model performance was evaluated for six pathologic observations on test datasets of unseen patients from the MIMIC-CXR database. Area under the receiver operating characteristic (AUC) analysis was used to evaluate classification performance. The algorithm is also capable of generating bounding-box predictions to localize areas of new progression. Recall, precision, and mean average precision were used to evaluate the new progression localization. One-tailed paired t tests were used to assess statistical significance. Results The model outperformed most baselines in progression classification, achieving macro AUC scores of 0.72 ± 0.004 for atelectasis, 0.75 ± 0.007 for consolidation, 0.76 ± 0.017 for edema, 0.81 ± 0.006 for effusion, 0.7 ± 0.032 for pneumonia, and 0.69 ± 0.01 for pneumothorax. For new observation localization, the model achieved mean average precision scores of 0.25 ± 0.03 for atelectasis, 0.34 ± 0.03 for consolidation, 0.33 ± 0.03 for edema, and 0.31 ± 0.03 for pneumothorax. Conclusion Disease progression classification models were developed on a large chest radiograph dataset, which can be used to monitor interval changes and detect new pathologic conditions on chest radiographs. Keywords: Prognosis, Unsupervised Learning, Transfer Learning, Convolutional Neural Network (CNN), Emergency Radiology, Named Entity Recognition Supplemental material is available for this article. © RSNA, 2024 See also commentary by Alves and Venkadesh in this issue.

Evaluating the Accuracy of Chest CT in Detecting COVID-19 Through Tracheobronchial Wall Thickness: Insights From Emergency Department Patients in Mid-2023

Background The post-pandemic phase of the coronavirus infectious disease that emerged in 2019 (COVID-19) has necessitated updates in radiology, with emerging evidence suggesting tracheobronchial wall thickness as a potential new diagnostic marker. Purpose To evaluate the accuracy of chest computed tomography (CT) scans in identifying COVID-19 by assessing tracheobronchial wall thickness in mid-2023. Material and methods A retrospective review was conducted on 60 patients who underwent thoracoabdominal CT and the severe acute respiratory syndrome coronavirus (SARS-CoV-2) antigen tests during emergency visits between June and August 2023. Tracheobronchial wall thickness was measured using a 4-point scale (1=no thickening, 2=mild, 3=moderate, 4=significant). Lung assessment employed the COVID-19 Reporting and Data System (CO-RADS). Patients were classified based on antigen test results. The Mann-Whitney U test and Fisher's exact test compared characteristics and CT findings. Diagnostic performance was evaluated using the area under the receiver operating characteristic curves (AUC). Results The SARS-CoV-2-positive group showed significantly thicker tracheobronchial walls (median 1.5 mm vs. 1.2 mm, P < 0.001), especially in the trachea's membranous wall (median 1.2 mm vs. 0.9 mm, P < 0.001) and higher scores (median 3 vs. 2, P < 0.001). CO-RADS scores showed no significant difference. Quantitative and qualitative wall thickness assessments demonstrated high diagnostic value, with AUCs of 0.90 and 0.94, and accuracies of 85% and 87%, respectively. Conclusion Tracheobronchial wall thickness on chest CT exhibited high diagnostic accuracy, establishing it as a reliable marker for COVID-19 detection in mid-2023.

Lung pneumonia severity scoring in chest X-ray images using transformers

To create robust and adaptable methods for lung pneumonia diagnosis and the assessment of its severity using chest X-rays (CXR), access to well-curated, extensive datasets is crucial. Many current severity quantification approaches require resource-intensive training for optimal results. Healthcare practitioners require efficient computational tools to swiftly identify COVID-19 cases and predict the severity of the condition. In this research, we introduce a novel image augmentation scheme as well as a neural network model founded on Vision Transformers (ViT) with a small number of trainable parameters for quantifying COVID-19 severity and other lung diseases. Our method, named Vision Transformer Regressor Infection Prediction (ViTReg-IP), leverages a ViT architecture and a regression head. To assess the model's adaptability, we evaluate its performance on diverse chest radiograph datasets from various open sources. We conduct a comparative analysis against several competing deep learning methods. Our results achieved a minimum Mean Absolute Error (MAE) of 0.569 and 0.512 and a maximum Pearson Correlation Coefficient (PC) of 0.923 and 0.855 for the geographic extent score and the lung opacity score, respectively, when the CXRs from the RALO dataset were used in training. The experimental results reveal that our model delivers exceptional performance in severity quantification while maintaining robust generalizability, all with relatively modest computational requirements. The source codes used in our work are publicly available at https://github.com/bouthainas/ViTReg-IP .

Four Transformer-Based Deep Learning Classifiers Embedded with an Attention U-Net-Based Lung Segmenter and Layer-Wise Relevance Propagation-Based Heatmaps for COVID-19 X-ray Scans

Background: Diagnosing lung diseases accurately is crucial for proper treatment. Convolutional neural networks (CNNs) have advanced medical image processing, but challenges remain in their accurate explainability and reliability. This study combines U-Net with attention and Vision Transformers (ViTs) to enhance lung disease segmentation and classification. We hypothesize that Attention U-Net will enhance segmentation accuracy and that ViTs will improve classification performance. The explainability methodologies will shed light on model decision-making processes, aiding in clinical acceptance. Methodology: A comparative approach was used to evaluate deep learning models for segmenting and classifying lung illnesses using chest X-rays. The Attention U-Net model is used for segmentation, and architectures consisting of four CNNs and four ViTs were investigated for classification. Methods like Gradient-weighted Class Activation Mapping plus plus (Grad-CAM++) and Layer-wise Relevance Propagation (LRP) provide explainability by identifying crucial areas influencing model decisions. Results: The results support the conclusion that ViTs are outstanding in identifying lung disorders. Attention U-Net obtained a Dice Coefficient of 98.54% and a Jaccard Index of 97.12%. ViTs outperformed CNNs in classification tasks by 9.26%, reaching an accuracy of 98.52% with MobileViT. An 8.3% increase in accuracy was seen while moving from raw data classification to segmented image classification. Techniques like Grad-CAM++ and LRP provided insights into the decision-making processes of the models. Conclusions: This study highlights the benefits of integrating Attention U-Net and ViTs for analyzing lung diseases, demonstrating their importance in clinical settings. Emphasizing explainability clarifies deep learning processes, enhancing confidence in AI solutions and perhaps enhancing clinical acceptance for improved healthcare results.

Workplace factors impacting the wellbeing of diagnostic radiographers in clinical practice: A literature review

INTRODUCTION

The Coronavirus (COVID-19) pandemic resulted in an emphasis on external factors affecting the wellbeing of staff within the National Health Service. There is a national shortage of diagnostic radiographers in the United Kingdom, so maintaining the health and satisfaction of the current radiographic workforce is important. The aim of this literature review is to determine workplace-related factors affecting the wellbeing of diagnostic radiographers in their clinical practice.

METHODS

An interpretive phenomenological approach was selected to gain an insight of wellbeing from the perspective of radiographers and radiology managers. A systematic literature search was conducted, resulting in 10 core articles which were then thematically analysed.

RESULTS

Five themes were identified: Initial waves of COVID-19, Workload and Working Patterns, Mental Health, Sources of Support, and Recognition and Development.

DISCUSSION

COVID-19 has had a short and long-term impact on the working practices of radiographers, leading to a risk of burnout. Radiographers appreciated different forms of recognition from managers and support within their team but felt a lack of professional recognition outside the radiology department. Radiographers displayed resilience during the pandemic, using various strategies to cope with emotional challenges. A variety of external support was available to radiographers, but this was often self-directed, with in-person support difficult to access due to working patterns.

CONCLUSION

This review highlights the lack of tailored support addressing radiographers' unique experiences. As imaging modalities have different workloads and varying emotional involvement with patients, further research to provide evidence-based interventions to improve radiographers' mental health is advised.

Omni-dimensional dynamic convolution feature coordinate attention network for pneumonia classification

Pneumonia is a serious disease that can be fatal, particularly among children and the elderly. The accuracy of pneumonia diagnosis can be improved by combining artificial-intelligence technology with X-ray imaging. This study proposes X-ODFCANet, which addresses the issues of low accuracy and excessive parameters in existing deep-learning-based pneumonia-classification methods. This network incorporates a feature coordination attention module and an omni-dimensional dynamic convolution (ODConv) module, leveraging the residual module for feature extraction from X-ray images. The feature coordination attention module utilizes two one-dimensional feature encoding processes to aggregate feature information from different spatial directions. Additionally, the ODConv module extracts and fuses feature information in four dimensions: the spatial dimension of the convolution kernel, input and output channel quantities, and convolution kernel quantity. The experimental results demonstrate that the proposed method can effectively improve the accuracy of pneumonia classification, which is 3.77% higher than that of ResNet18. The model parameters are 4.45M, which was reduced by approximately 2.5 times. The code is available at https://github.com/limuni/X-ODFCANET .

Use of reporting templates for chest radiographs in a coronavirus disease 2019 context: measuring concordance of radiologists with three international templates

Purpose

Reporting templates for chest radiographs (CXRs) for patients presenting or being clinically managed for severe acute respiratory syndrome coronavirus 2 [coronavirus disease 2019 (COVID-19)] has attracted advocacy from international radiology societies. We aim to explore the effectiveness and useability of three international templates through the concordance of, and between, radiologists reporting on the presence and severity of COVID-19 on CXRs.

Approach

Seventy CXRs were obtained from a referral hospital, 50 from patients with COVID-19 (30 rated "classic" COVID-19 appearance and 20 "indeterminate") and 10 "normal" and 10 "alternative pathology" CXRs. The recruited radiologists were assigned to three test sets with the same CXRs but with different template orders. Each radiologist read their test set three times and assigned a classification to the CXR using the Royal Australian New Zealand College of Radiology (RANZCR), British Society of Thoracic Imaging (BSTI), and Modified COVID-19 Reporting and Data System (Dutch; mCO-RADS) templates. Inter-reader variability and intra-reader variability were measured using Fleiss' kappa coefficient.

Results

Twelve Australian radiologists participated. The BSTI template had the highest inter-reader agreement (0.46; "moderate" agreement), followed by RANZCR (0.45) and mCO-RADS (0.32). Concordance was driven by strong agreement in "normal" and "alternative" classifications and was lowest for "indeterminate." General consistency was observed across classifications and templates, with intra-reader variability ranging from "good" to "very good" for COVID-19 CXRs (0.61), "normal" CXRs (0.76), and "alternative" (0.68).

Conclusions

Reporting templates may be useful in reducing variation among radiology reports, with intra-reader variability showing promise. Feasibility and implementation require a wider approach including referring and treating doctors plus the development of training packages for radiologists specific to the template being used.

Effect of Model-Based Iterative Reconstruction on Image Quality of Chest Computed Tomography for COVID-19 Pneumonia

PURPOSE

This study aimed to compare the image quality of chest computed tomography (CT) scans for COVID-19 pneumonia using forward-projected model-based iterative reconstruction solution-LUNG (FIRST-LUNG) with filtered back projection (FBP) and hybrid iterative reconstruction (HIR).

METHOD

The CT images of 44 inpatients diagnosed with COVID-19 pneumonia between December 2022 and June 2023 were retrospectively analyzed. The CT images were reconstructed using FBP, HIR, and FIRST-LUNG-MILD/STANDARD/STRONG. The CT values and noise of the lumen of the main trachea and erector spine muscle were measured for each group. Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were calculated. Subjective evaluations included overall image quality, noise, streak artifact, visualization of normal lung structures, and abnormal CT features. One-way analysis of variance was used to compare the objective and subjective indicators among the five groups. The task-based transfer function was derived for three distinct contrasts representing anatomical structures, lower-contrast lesion, and higher-contrast lesion.

RESULTS

The results of the study demonstrated significant differences in image noise, SNR, and CNR among the five groups (P < 0.001). The FBP images exhibited the highest levels of noise and the lowest SNR and CNR among the five groups (P < 0.001). When compared to the FBP and HIR groups, the noise was lower in the FIRST-LUNG-MILD/STANDARD/STRONG group, while the SNR and CNR were higher (P < 0.001). The subjective overall image quality score of FIRST-LUNG-MILD/STANDARD was significantly better than FBP and FIRST-LUNG-STRONG (P < 0.001). FIRST-LUNG-MILD was superior to FBP, HIR, FIRST-LUNG-STANDARD, and FIRST-LUNG-STRONG in visualizing proximal and peripheral bronchovascular and subpleural vessels (P < 0.05). Additionally, FIRST-LUNG-MILD achieved the best scores in evaluating abnormal lung structure (P < 0.001). The overall interobserver agreement was substantial (intraclass correlation coefficient = 0.891). The task-based transfer function 50% values of FIRST reconstructions are consistently higher compared to FBP and HIR.

CONCLUSIONS

The FIRST-LUNG-MILD/STANDARD algorithm can enhance the image quality of chest CT in patients with COVID-19 pneumonia, while preserving important details of the lesions, better than the FBP and HIR algorithms. After evaluating various COVID-19 pneumonia lesions and considering the improvement in image quality, we recommend using the FIRST-LUNG-MILD reconstruction for diagnosing COVID-19 pneumonia.

CT semi-quantitative score used as risk factor for hyponatremia in patients with COVID-19: a cross-sectional study

Purpose

Chest computed tomography (CT) is used to determine the severity of COVID-19 pneumonia, and pneumonia is associated with hyponatremia. This study aims to explore the predictive value of the semi-quantitative CT visual score for hyponatremia in patients with COVID-19 to provide a reference for clinical practice.

Methods

In this cross-sectional study, 343 patients with RT-PCR confirmed COVID-19, all patients underwent CT, and the severity of lung lesions was scored by radiologists using the semi-quantitative CT visual score. The risk factors of hyponatremia in COVID-19 patients were analyzed and combined with laboratory tests. The thyroid function changes caused by SARS-CoV-2 infection and their interaction with hyponatremia were also analyzed.

Results

In patients with SARS-CoV-2 infection, the total severity score (TSS) of hyponatremia was higher [M(range), 3.5(2.5-5.5) vs 3.0(2.0-4.5) scores, P=0.001], implying that patients with hyponatremia had more severe lung lesions. The risk factors of hyponatremia in the multivariate regression model included age, vomiting, neutrophils, platelet, and total severity score. SARS-CoV-2 infection impacted thyroid function, and patients with hyponatremia showed a lower free triiodothyronine (3.1 ± 0.9 vs 3.7 ± 0.9, P=0.001) and thyroid stimulating hormone level [1.4(0.8-2.4) vs 2.2(1.2-3.4), P=0.038].

Conclusion

Semi-quantitative CT score can be used as a risk factor for hyponatremia in patients with COVID-19. There is a weak positive correlation between serum sodium and free triiodothyronine in patients with SARS-CoV-2 infection.

Coronary artery calcification score as a prognostic indicator for COVID-19 mortality: evidence from a retrospective cohort study in Iran

Background

Coronary artery calcification (CAC) has been established as an independent risk factor for major adverse cardiovascular events. Nevertheless, the effect of CAC on in-hospital mortality and adverse clinical outcomes in patients with COVID-19 has yet to be determined.

Objective

To investigate the association between CAC score and in-hospital mortality of COVID-19 patients.

Method

This retrospective cohort study was conducted across tertiary hospitals of University of Medical Sciences in Babol, a northern city in Iran, and enroled 551 confirmed COVID-19 patients with definitive clinical outcomes of death or discharge between March and October 2021. Demographic and clinical data, along with chest computed tomography (CT) findings and CAC score on admission, were systematically collected. The study utilized logistic regression analysis and Kaplan-Meier plots to explore the association between CAC score and in-hospital death and adverse clinical outcomes.

Results

The mean age was 60.05±12.8. A significant difference regarding CAC score, age, history of hypertension, hyperlipidemia, cardiovascular diseases, and respiratory diseases among survivors and non-survivors was observed; however, gender was not found to be different. Furthermore, in multivariate analysis, CAC score greater than or equal to 400 [odds ratio (OR): 4.2, 95% CI: 1.70-10.33, P value: 0.002], hospitalization time (OR: 1.31, 95% CI: 1.13-1.53, P value < 0.001), length of ICU stay (OR: 2.02, 95% CI: 1.47-2.77, P value < 0.001), severe or critical COVID-19 severity in time of admission (95% CI: 1.79-18.29, P value: 0.003), and history of respiratory diseases (95% CI: 2.18-40, P value: 0.003) were found to be associated with higher odds of in-hospital mortality. Log-rank test also revealed a significant difference regarding the time of admission to death between patients with CAC score greater than or equal to 400 and those with CAC score less than 400 (P value < 0.001).

Conclusion

Elevated CAC score is a crucial risk factor linked to in-hospital mortality and unfavourable clinical results in confirmed COVID-19 patients. This finding emphasizes the need for careful monitoring of individuals with high CAC scores.

Predicting oxygen needs in COVID-19 patients using chest radiography multi-region radiomics

The objective is to evaluate the performance of blood test results, radiomics, and a combination of the two data types on the prediction of the 24-h oxygenation support need for the Coronavirus disease 2019 (COVID-19) patients. In this retrospective cohort study, COVID-19 patients with confirmed real-time reverse transcription-polymerase chain reaction assay (RT-PCR) test results between February 2020 and August 2021 were investigated. Initial blood cell counts, chest radiograph, and the status of oxygenation support used within 24 h were collected (n = 290; mean age, 45 ± 19 years; 125 men). Radiomics features from six lung zones were extracted. Logistic regression and random forest models were developed using the clinical-only, radiomics-only, and combined data. Ten repeats of fivefold cross-validation with bootstrapping were used to identify the input features and models with the highest area under the receiver operating characteristic curve (AUC). Higher AUCs were achieved when using only radiomics features compared to using only clinical features (0.94 ± 0.03 vs. 0.88 ± 0.04). The best combined model using both radiomics and clinical features achieved highest in the cross-validation (0.95 ± 0.02) and test sets (0.96 ± 0.02). In comparison, the best clinical-only model yielded AUCs of 0.88 ± 0.04 in cross-validation and 0.89 ± 0.03 in test set. Both radiomics and clinical data can be used to predict 24-h oxygenation support need for COVID-19 patients with AUC > 0.88. Moreover, the combination of both data types further improved the performance.

Association between echocardiographic features, troponin levels, and survival time in hospitalized COVID-19 patients with cardiovascular events

Introduction

This study aims to explore the predictive roles of echocardiographic parameters and biomarkers in determining outcomes among hospitalized COVID-19 patients experiencing cardiovascular events.

Methods

A retrospective cohort study was conducted involving 49 COVID-19 patients who encountered cardiovascular events during hospitalization and underwent echocardiography. Our findings revealed notable associations between echocardiographic parameters and survival time.

Results

A decrease in left ventricular ejection fraction (LVEF) of 10% was linked to a 20% reduction in survival time (TR: 0.80, 95% CI: 0.67 - 0.96, p = .017). Similarly, an increase in left ventricular (LV) volume by 10 mL was associated with a 9% decrease in survival time (TR: 0.91, 95% CI: 0.84 - 0.98, p = .011). Moreover, an increase in left atrial (LA) volume by 10 mL corresponded to an 8% decrease in survival time (TR: 0.92, 95% CI: 0.86 - 0.99, p = .026). Additionally, each 1 cm increase in right ventricular (RV) diameter was linked to a 22% reduction in survival time (TR: 0.78, 95% CI: 0.61 - 0.99, p = .043). Furthermore, a 10 mL increase in right atrial (RA) volume was associated with a 12% decrease in survival time (TR: 0.88, 95% CI: 0.78 - 0.98, p = .017). Notably, a tenfold rise in troponin levels was linked to a 33% decrease in survival time (TR: 0.67, 95% CI: 0.48 - 0.93, p = .014).

Conclusions

Our study emphasizes the significant associations between various echocardiographic parameters and troponin levels with reduced survival time among COVID-19 patients experiencing cardiovascular events. These findings highlight the potential utility of echocardiography and troponin assessment in predicting outcomes and guiding management strategies in this patient population.

Multi-centre benchmarking of deep learning models for COVID-19 detection in chest x-rays

Introduction

This study is a retrospective evaluation of the performance of deep learning models that were developed for the detection of COVID-19 from chest x-rays, undertaken with the goal of assessing the suitability of such systems as clinical decision support tools.

Methods

Models were trained on the National COVID-19 Chest Imaging Database (NCCID), a UK-wide multi-centre dataset from 26 different NHS hospitals and evaluated on independent multi-national clinical datasets. The evaluation considers clinical and technical contributors to model error and potential model bias. Model predictions are examined for spurious feature correlations using techniques for explainable prediction.

Results

Models performed adequately on NHS populations, with performance comparable to radiologists, but generalised poorly to international populations. Models performed better in males than females, and performance varied across age groups. Alarmingly, models routinely failed when applied to complex clinical cases with confounding pathologies and when applied to radiologist defined "mild" cases.

Discussion

This comprehensive benchmarking study examines the pitfalls in current practices that have led to impractical model development. Key findings highlight the need for clinician involvement at all stages of model development, from data curation and label definition, to model evaluation, to ensure that all clinical factors and disease features are appropriately considered during model design. This is imperative to ensure automated approaches developed for disease detection are fit-for-purpose in a clinical setting.

Reinvestigating the performance of artificial intelligence classification algorithms on COVID-19 X-Ray and CT images

There are concerns that artificial intelligence (AI) algorithms may create underdiagnosis bias by mislabeling patient individuals with certain attributes (e.g., female and young) as healthy. Addressing this bias is crucial given the urgent need for AI diagnostics facing rapidly spreading infectious diseases like COVID-19. We find the prevalent AI diagnostic models show an underdiagnosis rate among specific patient populations, and the underdiagnosis rate is higher in some intersectional specific patient populations (for example, females aged 20-40 years). Additionally, we find training AI models on heterogeneous datasets (positive and negative samples from different datasets) may lead to poor model generalization. The model's classification performance varies significantly across test sets, with the accuracy of the better performance being over 40% higher than that of the poor performance. In conclusion, we developed an AI bias analysis pipeline to help researchers recognize and address biases that impact medical equality and ethics.

BarlowTwins-CXR: enhancing chest X-ray abnormality localization in heterogeneous data with cross-domain self-supervised learning

BACKGROUND

Chest X-ray imaging based abnormality localization, essential in diagnosing various diseases, faces significant clinical challenges due to complex interpretations and the growing workload of radiologists. While recent advances in deep learning offer promising solutions, there is still a critical issue of domain inconsistency in cross-domain transfer learning, which hampers the efficiency and accuracy of diagnostic processes. This study aims to address the domain inconsistency problem and improve autonomic abnormality localization performance of heterogeneous chest X-ray image analysis, particularly in detecting abnormalities, by developing a self-supervised learning strategy called "BarlwoTwins-CXR".

METHODS

We utilized two publicly available datasets: the NIH Chest X-ray Dataset and the VinDr-CXR. The BarlowTwins-CXR approach was conducted in a two-stage training process. Initially, self-supervised pre-training was performed using an adjusted Barlow Twins algorithm on the NIH dataset with a Resnet50 backbone pre-trained on ImageNet. This was followed by supervised fine-tuning on the VinDr-CXR dataset using Faster R-CNN with Feature Pyramid Network (FPN). The study employed mean Average Precision (mAP) at an Intersection over Union (IoU) of 50% and Area Under the Curve (AUC) for performance evaluation.

RESULTS

Our experiments showed a significant improvement in model performance with BarlowTwins-CXR. The approach achieved a 3% increase in mAP50 accuracy compared to traditional ImageNet pre-trained models. In addition, the Ablation CAM method revealed enhanced precision in localizing chest abnormalities. The study involved 112,120 images from the NIH dataset and 18,000 images from the VinDr-CXR dataset, indicating robust training and testing samples.

CONCLUSION

BarlowTwins-CXR significantly enhances the efficiency and accuracy of chest X-ray image-based abnormality localization, outperforming traditional transfer learning methods and effectively overcoming domain inconsistency in cross-domain scenarios. Our experiment results demonstrate the potential of using self-supervised learning to improve the generalizability of models in medical settings with limited amounts of heterogeneous data. This approach can be instrumental in aiding radiologists, particularly in high-workload environments, offering a promising direction for future AI-driven healthcare solutions.

The chest X-ray score baseline in predicting continuous oxygen therapy failure in low-risk aged patients after thoracic surgery

Background

Radiographic severity assessment can be instrumental in diagnosing postoperative pulmonary complications (PPCs) and guiding oxygen therapy. The radiographic assessment of lung edema (RALE) and Brixia scores correlate with disease severity, but research on low-risk elderly patients is lacking. This study aimed to assess the efficacy of two chest X-ray scores in predicting continuous oxygen therapy (COT) treatment failure in patients over 70 years of age after thoracic surgery.

Methods

From January 2019 to December 2021, we searched for patients aged 70 years and above who underwent thoracic surgery and received COT treatment, with a focus on those at low risk of respiratory complications. Bedside chest X-rays, RALE, Brixia scores, and patient data were collected. Univariate, multivariate analyses, and 1:2 matching identified risk factors. Receiver operating characteristic (ROC) curves determined score sensitivity, specificity, and predictive values.

Results

Among the 242 patients surviving to discharge, 19 (7.9%) patients experienced COT failure. COT failure correlated with esophageal cancer surgeries, thoracotomies (36.8% vs. 9%, P=0.003; 26.3% vs. 9.4%, P=0.004), and longer operation time (3.4 vs. 2.8 h, P=0.003). Surgical approach and RALE score were independent risk factors. The prediction model had an area under the curve (AUC) of 0.839 [95% confidence interval (CI), 0.740-0.938]. Brixia and RALE scores predicted COT failure with AUCs of 0.764 (95% CI, 0.650-0.878) with a cut-off value of 6.027 and 0.710 (95% CI, 0.588-0.832) with a cut-off value of 17.134, respectively, after 1:2 matching.

Conclusions

The RALE score predict the risk of COT failure in elderly, low-risk thoracic patients better than the Brixia score. This simple, cheap, and noninvasive method helps evaluate postoperative lung damage, monitor treatment response, and provide early warning for oxygen therapy escalation. Further studies are required to confirm the validity and applicability of this model in different settings and populations.

Tracheal computed tomography radiomics model for prediction of the Omicron variant of severe acute respiratory syndrome coronavirus 2

OBJECTIVES

The Omicron variant of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is highly contagious, fast-spreading, and insidious. Most patients present with normal findings on lung computed tomography (CT). The current study aimed to develop and validate a tracheal CT radiomics model to predict Omicron variant infection.

MATERIALS AND METHODS

In this retrospective study, a radiomics model was developed based on a training set consisting of 157 patients with an Omicron variant infection and 239 healthy controls between 1 January and 30 April 2022. A set of morphological expansions, with dilations of 1, 3, 5, 7, and 9 voxels, was applied to the trachea, and radiomic features were extracted from different dilation voxels of the trachea. Logistic regression (LR), support vector machines (SVM), and random forests (RF) were developed and evaluated; the models were validated on 67 patients with the Omicron variant and on 103 healthy controls between 1 May and 30 July 2022.

RESULTS

Logistic regression with 12 radiomic features extracted from the tracheal wall with dilation of 5 voxels achieved the highest classification performance compared with the other models. The LR model achieved an area under the curve of 0.993 (95% confidence interval [CI]: 0.987-0.998) in the training set and 0.989 (95% CI: 0.979-0.999) in the validation set. Sensitivity, specificity, and accuracy of the model for the training set were 0.994, 0.946, and 0.965, respectively, whereas those for the validation set were 0.970, 0.952, and 0.959, respectively.

CONCLUSION

The tracheal CT radiomics model reliably identified the Omicron variant of SARS-CoV‑2, and may help in clinical decision-making in future, especially in cases of normal lung CT findings.

Exploration of Interpretability Techniques for Deep COVID-19 Classification Using Chest X-ray Images

The outbreak of COVID-19 has shocked the entire world with its fairly rapid spread, and has challenged different sectors. One of the most effective ways to limit its spread is the early and accurate diagnosing of infected patients. Medical imaging, such as X-ray and computed tomography (CT), combined with the potential of artificial intelligence (AI), plays an essential role in supporting medical personnel in the diagnosis process. Thus, in this article, five different deep learning models (ResNet18, ResNet34, InceptionV3, InceptionResNetV2, and DenseNet161) and their ensemble, using majority voting, have been used to classify COVID-19, pneumoniæ and healthy subjects using chest X-ray images. Multilabel classification was performed to predict multiple pathologies for each patient, if present. Firstly, the interpretability of each of the networks was thoroughly studied using local interpretability methods-occlusion, saliency, input X gradient, guided backpropagation, integrated gradients, and DeepLIFT-and using a global technique-neuron activation profiles. The mean micro F1 score of the models for COVID-19 classifications ranged from 0.66 to 0.875, and was 0.89 for the ensemble of the network models. The qualitative results showed that the ResNets were the most interpretable models. This research demonstrates the importance of using interpretability methods to compare different models before making a decision regarding the best performing model.

CoSev: Data-Driven Optimizations for COVID-19 Severity Assessment in Low-Sample Regimes

Given the pronounced impact COVID-19 continues to have on society-infecting 700 million reported individuals and causing 6.96 million deaths-many deep learning works have recently focused on the virus's diagnosis. However, assessing severity has remained an open and challenging problem due to a lack of large datasets, the large dimensionality of images for which to find weights, and the compute limitations of modern graphics processing units (GPUs). In this paper, a new, iterative application of transfer learning is demonstrated on the understudied field of 3D CT scans for COVID-19 severity analysis. This methodology allows for enhanced performance on the MosMed Dataset, which is a small and challenging dataset containing 1130 images of patients for five levels of COVID-19 severity (Zero, Mild, Moderate, Severe, and Critical). Specifically, given the large dimensionality of the input images, we create several custom shallow convolutional neural network (CNN) architectures and iteratively refine and optimize them, paying attention to learning rates, layer types, normalization types, filter sizes, dropout values, and more. After a preliminary architecture design, the models are systematically trained on a simplified version of the dataset-building models for two-class, then three-class, then four-class, and finally five-class classification. The simplified problem structure allows the model to start learning preliminary features, which can then be further modified for more difficult classification tasks. Our final model CoSev boosts classification accuracies from below 60% at first to 81.57% with the optimizations, reaching similar performance to the state-of-the-art on the dataset, with much simpler setup procedures. In addition to COVID-19 severity diagnosis, the explored methodology can be applied to general image-based disease detection. Overall, this work highlights innovative methodologies that advance current computer vision practices for high-dimension, low-sample data as well as the practicality of data-driven machine learning and the importance of feature design for training, which can then be implemented for improvements in clinical practices.

Texture analysis of chest X-ray images for the diagnosis of COVID-19 pneumonia

Purpose

Medical imaging is one of the main methods of diagnosing COVID-19, along with real-time reverse trans-cription-polymerase chain reaction (RT-PCR) tests. The purpose of the study was to analyse the texture parameters of chest X-rays (CXR) of patients suspected of having COVID-19.

Material and methods

Texture parameters of the CXRs of 70 patients with symptoms typical of COVID-19 infection were analysed using LIFEx software. The regions of interest (ROIs) included each lung separately, for which 57 para-meters were tested. The control group consisted of 30 healthy, age-matched patients with no pathological findings in CXRs.

Results

According to the ROC analysis, 13 of the tested parameters differentiate the radiological image of lungs with COVID-19 features from the image of healthy lungs: GLRLM_LRHGE (AUC 0.91); DISCRETIZED_Q3 (AUC 0.90); GLZLM_HGZE (AUC 0.90); GLRLM_HGRE (AUC 0.89); DISCRETIZED_mean (AUC 0.89); DISCRETIZED_Q2 (AUC 0.61); GLRLM_SRHGE (AUC 0.87); GLZLM_LZHGE (AUC 0.87); GLZLM_SZHGE (AUC 0.84); DISCRETIZED_Q1 (AUC 0.81); NGLDM_Coarseness (AUC 0.70); DISCRETIZED_std (AUC 0.64); CONVENTIONAL_Q2 (AUC 0.61).

Conclusions

Selected texture parameters of radiological CXRs make it possible to distinguish COVID-19 features from healthy ones.

A Comprehensive Review of Extra Corporeal Membrane Oxygenation: The Lifeline in Critical Moments

Extracorporeal membrane oxygenation (ECMO) has evolved into a pivotal intervention in critical care, offering a lifeline for patients facing severe respiratory or cardiac failure. This review provides a comprehensive exploration of ECMO, spanning its definition and historical background to its contemporary advancements and ongoing impact in critical care. The versatility of ECMO in addressing diverse critical conditions, careful patient selection criteria, and the nuanced management of complications are discussed. Advances in technology, including miniaturization, novel circuit designs, and the integration of remote monitoring, showcase the evolving landscape of ECMO. The review underscores the ongoing impact of ECMO in improving survival rates, enhancing mobility, and enabling remote expertise. As a symbol of hope and innovation, ECMO's lifesaving potential is evident in its ability to navigate the complexities of critical care and redefine the boundaries of life support interventions.

Diagnosis of Covid-19 from CT slices using Whale Optimization Algorithm, Support Vector Machine and Multi-Layer Perceptron

BACKGROUND

The coronavirus disease 2019 is a serious and highly contagious disease caused by infection with a newly discovered virus, named severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2).

OBJECTIVE

A Computer Aided Diagnosis (CAD) system to assist physicians to diagnose Covid-19 from chest Computed Tomography (CT) slices is modelled and experimented.

METHODS

The lung tissues are segmented using Otsu's thresholding method. The Covid-19 lesions have been annotated as the Regions of Interest (ROIs), which is followed by texture and shape extraction. The obtained features are stored as feature vectors and split into 80:20 train and test sets. To choose the optimal features, Whale Optimization Algorithm (WOA) with Support Vector Machine (SVM) classifier's accuracy is employed. A Multi-Layer Perceptron (MLP) classifier is trained to perform classification with the selected features.

RESULTS

Comparative experimentations of the proposed system with existing eight benchmark Machine Learning classifiers using real-time dataset demonstrates that the proposed system with 88.94% accuracy outperforms the benchmark classifier's results. Statistical analysis namely, Friedman test, Mann Whitney U test and Kendall's Rank Correlation Coefficient Test has been performed which indicates that the proposed method has a significant impact on the novel dataset considered.

CONCLUSION

The MLP classifier's accuracy without feature selection yielded 80.40%, whereas with feature selection using WOA, it yielded 88.94%.

A Novel Combined Model to Predict the Prognosis of COVID-19: Radiologicalmetabolic Scoring

AIM

To investigate the performance of a novel radiological-metabolic scoring (RM-S) system to predict mortality and intensive care unit (ICU) requirements among COVID-19 patients and to compare performance with the chest computed-tomography severity-scoring (C-CT-SS). The RMS was created from scoring systems such as visual coronary-artery-calcification scoring (V-CAC-S), hepatic-steatosis scoring (HS-S) and pancreatic-steatosis scoring (PS-S).

METHODS

Between May 2021 and January 2022, 397 patients with COVID-19 were included in this retrospective cohort study. All demographic, clinical and laboratory data and chest CT images of patients were retrospectively reviewed. RM-S, V-CAC-S, HS-S, PS-S and C-CT-SS scores were calculated, and their performance in predicting mortality and ICU requirement were evaluated by univariate and multivariable analyses.

RESULTS

A total of 32 (8.1%) patients died, and 77 (19.4%) patients required ICU admission. Mortality and ICU admission were both associated with older age (p < 0.001). Sex distribution was similar in the deceased vs. survivor and ICU vs. non-ICU comparisons (p = 0.974 and p = 0.626, respectively). Multiple logistic regression revealed that mortality was independently associated with having a C-CT-SS score of ≥ 14 (p < 0.001) and severe RM-S category (p = 0.010), while ICU requirement was independently associated with having a C-CT-SS score of ≥ 14 (p < 0.001) and severe V-CAC-S category (p = 0.010).

CONCLUSION

RM-S, C-CT-SS, and V-CAC-S are useful tools that can be used to predict patients with poor prognoses for COVID-19. Long-term prospective follow-up of patients with high RM-S scores can be useful for predicting long COVID.

AFEX-Net: Adaptive feature extraction convolutional neural network for classifying computerized tomography images

Purpose

Deep convolutional neural networks are favored methods that are widely used in medical image processing due to their demonstrated performance in this area. Recently, the emergence of new lung diseases, such as COVID-19, and the possibility of early detection of their symptoms from chest computerized tomography images has attracted many researchers to classify diseases by training deep convolutional neural networks on lung computerized tomography images. The trained networks are expected to distinguish between different lung indications in various diseases, especially at the early stages. The purpose of this study is to introduce and assess an efficient deep convolutional neural network, called AFEX-Net, that can classify different lung diseases from chest computerized tomography images.

Methods

We designed a lightweight convolutional neural network called AFEX-Net with adaptive feature extraction layers, adaptive pooling layers, and adaptive activation functions. We trained and tested AFEX-Net on a dataset of more than 10,000 chest computerized tomography slices from different lung diseases (CC dataset), using an effective pre-processing method to remove bias. We also applied AFEX-Net to the public COVID-CTset dataset to assess its generalizability. The study was mainly conducted based on data collected over approximately six months during the pandemic outbreak in Afzalipour Hospital, Iran, which is the largest hospital in Southeast Iran.

Results

AFEX-Net achieved high accuracy and fast training on both datasets, outperforming several state-of-the-art convolutional neural networks. It has an accuracy of 99.7 % and 98.8 % on the CC and COVID-CTset datasets, respectively, with a learning speed that is 3 times faster compared to similar methods due to its lightweight structure. AFEX-Net was able to extract distinguishing features and classify chest computerized tomography images, especially at the early stages of lung diseases.

Conclusion

The AFEX-Net is a high-performing convolutional neural network for classifying lung diseases from chest CT images. It is efficient, adaptable, and compatible with input data, making it a reliable tool for early detection and diagnosis of lung diseases.

Inter-observer Variability in the Analysis of CO-RADS Classification for COVID-19 Patients

During the early stages of the pandemic, computed tomography (CT) of the chest, along with serological and clinical data, was frequently utilized in diagnosing COVID-19, particularly in regions facing challenges such as shortages of PCR kits. In these circumstances, CT scans played a crucial role in diagnosing COVID-19 and guiding patient management. The COVID-19 Reporting and Data System (CO-RADS) was established as a standardized reporting system for cases of COVID-19 pneumonia. Its implementation necessitates a high level of agreement among observers to prevent any potential confusion. This study aimed to assess the inter-observer agreement between physicians from different specialties with variable levels of experience in their CO-RADS scoring of CT chests for confirmed COVID-19 patients, and to assess the feasibility of applying this reporting system to those having little experience with it. All chest CT images of patients with positive RT-PCR tests for COVID-19 were retrospectively reviewed by seven observers. The observers were divided into three groups according to their type of specialty (three radiologists, three house officers, and one pulmonologist). The observers assessed each image and categorized the patients into five CO-RADS groups. A total of 630 participants were included in this study. The inter-observer agreement was almost perfect among the radiologists, substantial among a pulmonologist and the house officers, and moderate-to-substantial among the radiologists, the pulmonologist, and the house officers. There was substantial to almost perfect inter-observer agreement when reporting using the CO-RADS among observers with different experience levels. Although the inter-observer variability among the radiologists was high, it decreased compared to the pulmonologist and house officers. Radiologists, house officers, and pulmonologists applying the CO-RADS can accurately and promptly identify typical CT imaging features of lung involvement in COVID-19.

A Critical Assessment of Generative Models for Synthetic Data Augmentation on Limited Pneumonia X-ray Data

In medical imaging, deep learning models serve as invaluable tools for expediting diagnoses and aiding specialized medical professionals in making clinical decisions. However, effectively training deep learning models typically necessitates substantial quantities of high-quality data, a resource often lacking in numerous medical imaging scenarios. One way to overcome this deficiency is to artificially generate such images. Therefore, in this comparative study we train five generative models to artificially increase the amount of available data in such a scenario. This synthetic data approach is evaluated on a a downstream classification task, predicting four causes for pneumonia as well as healthy cases on 1082 chest X-ray images. Quantitative and medical assessments show that a Generative Adversarial Network (GAN)-based approach significantly outperforms more recent diffusion-based approaches on this limited dataset with better image quality and pathological plausibility. We show that better image quality surprisingly does not translate to improved classification performance by evaluating five different classification models and varying the amount of additional training data. Class-specific metrics like precision, recall, and F1-score show a substantial improvement by using synthetic images, emphasizing the data rebalancing effect of less frequent classes. However, overall performance does not improve for most models and configurations, except for a DreamBooth approach which shows a +0.52 improvement in overall accuracy. The large variance of performance impact in this study suggests a careful consideration of utilizing generative models for limited data scenarios, especially with an unexpected negative correlation between image quality and downstream classification improvement.

A medical multimodal large language model for future pandemics

Deep neural networks have been integrated into the whole clinical decision procedure which can improve the efficiency of diagnosis and alleviate the heavy workload of physicians. Since most neural networks are supervised, their performance heavily depends on the volume and quality of available labels. However, few such labels exist for rare diseases (e.g., new pandemics). Here we report a medical multimodal large language model (Med-MLLM) for radiograph representation learning, which can learn broad medical knowledge (e.g., image understanding, text semantics, and clinical phenotypes) from unlabelled data. As a result, when encountering a rare disease, our Med-MLLM can be rapidly deployed and easily adapted to them with limited labels. Furthermore, our model supports medical data across visual modality (e.g., chest X-ray and CT) and textual modality (e.g., medical report and free-text clinical note); therefore, it can be used for clinical tasks that involve both visual and textual data. We demonstrate the effectiveness of our Med-MLLM by showing how it would perform using the COVID-19 pandemic "in replay". In the retrospective setting, we test the model on the early COVID-19 datasets; and in the prospective setting, we test the model on the new variant COVID-19-Omicron. The experiments are conducted on 1) three kinds of input data; 2) three kinds of downstream tasks, including disease reporting, diagnosis, and prognosis; 3) five COVID-19 datasets; and 4) three different languages, including English, Chinese, and Spanish. All experiments show that our model can make accurate and robust COVID-19 decision-support with little labelled data.

Developing an interpretable machine learning model for predicting COVID-19 patients deteriorating prior to intensive care unit admission using laboratory markers

Coronavirus disease (COVID-19) remains a significant global health challenge, prompting a transition from emergency response to comprehensive management strategies. Furthermore, the emergence of new variants of concern, such as BA.2.286, underscores the need for early detection and response to new variants, which continues to be a crucial strategy for mitigating the impact of COVID-19, especially among the vulnerable population. This study aims to anticipate patients requiring intensive care or facing elevated mortality risk throughout their COVID-19 infection while also identifying laboratory predictive markers for early diagnosis of patients. Therefore, haematological, biochemical, and demographic variables were retrospectively evaluated in 8,844 blood samples obtained from 2,935 patients before intensive care unit admission using an interpretable machine learning model. Feature selection techniques were applied using precision-recall measures to address data imbalance and evaluate the suitability of the different variables. The model was trained using stratified cross-validation with k=5 and internally validated, achieving an accuracy of 77.27%, sensitivity of 78.55%, and area under the receiver operating characteristic (AUC) of 0.85; successfully identifying patients at increased risk of severe progression. From a medical perspective, the most important features of the progression or severity of patients with COVID-19 were lactate dehydrogenase, age, red blood cell distribution standard deviation, neutrophils, and platelets, which align with findings from several prior investigations. In light of these insights, diagnostic processes can be significantly expedited through the use of laboratory tests, with a greater focus on key indicators. This strategic approach not only improves diagnostic efficiency but also extends its reach to a broader spectrum of patients. In addition, it allows healthcare professionals to take early preventive measures for those most at risk of adverse outcomes, thereby optimising patient care and prognosis.

Comparison Between Lung Ultrasonography Score in the Emergency Department and Clinical Outcomes of Patients With or With Suspected COVID-19: An Observational Multicentric Study

OBJECTIVE

Chest CT is the reference test for assessing pulmonary injury in suspected or diagnosed COVID-19 with signs of clinical severity. This study aimed to evaluate the association of a lung ultrasonography score and unfavorable clinical evolution at 28 days.

METHODS

The eChoVid is a multicentric study based on routinely collected data that was conducted in 8 emergency units in France; patients were included between March 19, 2020 and April 28, 2020 and underwent lung ultrasonography, a short clinical assessment by 2 emergency physicians blinded to each other's assessment, and chest CT. Lung ultrasonography consisted of scoring lesions from 0 to 3 in 8 chest zones, thus defining a global score (GS) of severity from 0 to 24. The primary outcome was the association of lung damage severity as assessed by the GS at day 0 and patient status at 28 days. Secondary outcomes were comparing the performance between GS and CT scan and the performance between a new trainee physician and an ultrasonography expert in scores.

RESULTS

For the 328 patients analyzed, the GS showed good performance in predicting clinical worsening at 28 days (area under the receiver operating characteristic curve [AUC] 0.83, sensitivity 84.2%, specificity 76.4%). The GS showed good performance in predicting the CT severity assessment (AUC 0.84, sensitivity 77.2%, specificity 83.7%).

CONCLUSION

A lung ultrasonography GS is a simple tool that can be used in the emergency department to predict unfavorable assessment at 28 days in patients with COVID-19.

Handheld Lung Ultrasound to Detect COVID-19 Pneumonia in Inpatients: A Prospective Cohort Study

Background: Chest imaging, including chest X-ray (CXR) and computed tomography (CT), can be a helpful adjunct to nucleic acid test (NAT) in the diagnosis and management of Coronavirus Disease 2019 (COVID-19). Lung point of care ultrasound (POCUS), particularly with handheld devices, is an imaging alternative that is rapid, highly portable, and more accessible in low-resource settings. A standardized POCUS scanning protocol has been proposed to assess the severity of COVID-19 pneumonia, but it has not been sufficiently validated to assess diagnostic accuracy for COVID-19 pneumonia. Purpose: To assess the diagnostic performance of a standardized lung POCUS protocol using a handheld POCUS device to detect patients with either a positive NAT or a COVID-19-typical pattern on CT scan. Methods: Adult inpatients with confirmed or suspected COVID-19 and a recent CT were recruited from April to July 2020. Twelve lung zones were scanned with a handheld POCUS machine. Images were reviewed independently by blinded experts and scored according to the proposed protocol. Patients were divided into low, intermediate, and high suspicion based on their POCUS score. Results: Of 79 subjects, 26.6% had a positive NAT and 31.6% had a typical CT pattern. The receiver operator curve for POCUS had an area under the curve (AUC) of 0.787 for positive NAT and 0.820 for a typical CT. Using a two-point cutoff system, POCUS had a sensitivity of 0.90 and 1.00 compared to NAT and typical CT pattern, respectively, at the lower cutoff; it had a specificity of 0.90 and 0.89 compared to NAT and typical CT pattern at the higher cutoff, respectively. Conclusions: The proposed lung POCUS protocol with a handheld device showed reasonable diagnostic performance to detect inpatients with a positive NAT or typical CT pattern for COVID-19. Particularly in low-resource settings, POCUS with handheld devices may serve as a helpful adjunct for persons under investigation for COVID-19 pneumonia.

Dmbg-Net: Dilated multiresidual boundary guidance network for COVID-19 infection segmentation

Accurate segmentation of infected regions in lung computed tomography (CT) images is essential for the detection and diagnosis of coronavirus disease 2019 (COVID-19). However, lung lesion segmentation has some challenges, such as obscure boundaries, low contrast and scattered infection areas. In this paper, the dilated multiresidual boundary guidance network (Dmbg-Net) is proposed for COVID-19 infection segmentation in CT images of the lungs. This method focuses on semantic relationship modelling and boundary detail guidance. First, to effectively minimize the loss of significant features, a dilated residual block is substituted for a convolutional operation, and dilated convolutions are employed to expand the receptive field of the convolution kernel. Second, an edge-attention guidance preservation block is designed to incorporate boundary guidance of low-level features into feature integration, which is conducive to extracting the boundaries of the region of interest. Third, the various depths of features are used to generate the final prediction, and the utilization of a progressive multi-scale supervision strategy facilitates enhanced representations and highly accurate saliency maps. The proposed method is used to analyze COVID-19 datasets, and the experimental results reveal that the proposed method has a Dice similarity coefficient of 85.6% and a sensitivity of 84.2%. Extensive experimental results and ablation studies have shown the effectiveness of Dmbg-Net. Therefore, the proposed method has a potential application in the detection, labeling and segmentation of other lesion areas.

Investigation of the Radiographic Imaging Volume and Occupational Dose of Radiologic Technologists before and during the COVID-19 Pandemic

ABSTRACT

This study aimed to assess occupational radiation doses for radiologic technologists (RTs) in Saudi Arabia shortly before and during the COVID-19 pandemic, considering changes in imaging volume during that time. This retrospective study included the imaging volume data and the RTs' occupational dose records from a central hospital for 2019 and 2020. The occupational dose-in terms of annual and quarterly mean effective doses (AMEDs and QMEDs)-was estimated for 115 RTs using thermoluminescent dosimeter records. There was a 22% increase in the AMED in 2020 compared with 2019, though the overall imaging volume decreased by 9% in 2020. The percentage changes in AMEDs between 2019 and 2020 for general radiography (GR), computed tomography (CT), interventional radiology (IR), nuclear medicine (NM), and mammography (MG) were 45%, 56%, 9%, 18% and -2%, respectively. The highest contribution to AMEDs in 2020 for modalities was due to GR and CT procedures, accounting for 0.50 mSv and 0.58 mSv, respectively. The percentage change in imaging volumes between 2019 and 2020 depicted a slight decrease in Q2 (-1%) and a substantial decrease in Q1 (-10%), Q3 (-12%), and Q4 (-11%) for 2020. The overall percentage changes in imaging volumes in 2020 for GR (conventional and mobile), CT, IR, NM, and MG were -7% (-19% and 48%), -11%, 13%, -26%, and -46%, respectively. Investigating the changes in 2020 by comparing Q1 of 2020 (before the pandemic restrictions) with Q2 (during the pandemic restrictions and changes in workflow) revealed that the QMED during Q2 increased by 5% with a 17.4% decrease in the imaging volume. However, CT procedures were increased by 11.1% during the pandemic restrictions in Q2 of 2020, with an increase in the corresponding QMED of 66%. Moreover, mobile GR procedures increased by 21% in Q2 of 2020 compared to Q1. This study indicated the impact of the COVID-19 pandemic on imaging volume and occupational dose. Overall, the study observed a decrease in the imaging volume and an increase in RTs' effective doses by 2020. However, there was an increase in mobile GR and CT examinations during the COVID-19 pandemic restrictions in 2020. This study suggested that the increased mobile GR and CT examinations contributed to greater effective doses for RTs in 2020.

Augmentation strategies for an imbalanced learning problem on a novel COVID-19 severity dataset

Since the beginning of the COVID-19 pandemic, many different machine learning models have been developed to detect and verify COVID-19 pneumonia based on chest X-ray images. Although promising, binary models have only limited implications for medical treatment, whereas the prediction of disease severity suggests more suitable and specific treatment options. In this study, we publish severity scores for the 2358 COVID-19 positive images in the COVIDx8B dataset, creating one of the largest collections of publicly available COVID-19 severity data. Furthermore, we train and evaluate deep learning models on the newly created dataset to provide a first benchmark for the severity classification task. One of the main challenges of this dataset is the skewed class distribution, resulting in undesirable model performance for the most severe cases. We therefore propose and examine different augmentation strategies, specifically targeting majority and minority classes. Our augmentation strategies show significant improvements in precision and recall values for the rare and most severe cases. While the models might not yet fulfill medical requirements, they serve as an appropriate starting point for further research with the proposed dataset to optimize clinical resource allocation and treatment.

Challenges of AI driven diagnosis of chest X-rays transmitted through smart phones: a case study in COVID-19

Healthcare delivery during the initial days of outbreak of COVID-19 pandemic was badly impacted due to large number of severely infected patients posing an unprecedented global challenge. Although the importance of Chest X-rays (CXRs) in meeting this challenge has now been widely recognized, speedy diagnosis of CXRs remains an outstanding challenge because of fewer Radiologists. The exponential increase in Smart Phone ownership globally, including LMICs, provides an opportunity for exploring AI-driven diagnostic tools when provided with large volumes of CXRs transmitted through Smart Phones. However, the challenges associated with such systems have not been studied to the best of our knowledge. In this paper, we show that the predictions of AI-driven models on CXR images transmitted through Smart Phones via applications, such as WhatsApp, suffer both in terms of Predictability and Explainability, two key aspects of any automated Medical Diagnosis system. We find that several existing Deep learning based models exhibit prediction instability-disagreement between the prediction outcome of the original image and the transmitted image. Concomitantly we find that the explainability of the models deteriorate substantially, prediction on the transmitted CXR is often driven by features present outside the lung region, clearly a manifestation of Spurious Correlations. Our study reveals that there is significant compression of high-resolution CXR images, sometimes as high as 95%, and this could be the reason behind these two problems. Apart from demonstrating these problems, our main contribution is to show that Multi-Task learning (MTL) can serve as an effective bulwark against the aforementioned problems. We show that MTL models exhibit substantially more robustness, 40% over existing baselines. Explainability of such models, when measured by a saliency score dependent on out-of-lung features, also show a 35% improvement. The study is conducted on WaCXR dataset, a curated dataset of 6562 image pairs corresponding to original uncompressed and WhatsApp compressed CXR images. Keeping in mind that there are no previous datasets to study such problems, we open-source this data along with all implementations.

Dual Multiscale Mean Teacher Network for Semi-Supervised Infection Segmentation in Chest CT Volume for COVID-19

Automated detecting lung infections from computed tomography (CT) data plays an important role for combating coronavirus 2019 (COVID-19). However, there are still some challenges for developing AI system: 1) most current COVID-19 infection segmentation methods mainly relied on 2-D CT images, which lack 3-D sequential constraint; 2) existing 3-D CT segmentation methods focus on single-scale representations, which do not achieve the multiple level receptive field sizes on 3-D volume; and 3) the emergent breaking out of COVID-19 makes it hard to annotate sufficient CT volumes for training deep model. To address these issues, we first build a multiple dimensional-attention convolutional neural network (MDA-CNN) to aggregate multiscale information along different dimension of input feature maps and impose supervision on multiple predictions from different convolutional neural networks (CNNs) layers. Second, we assign this MDA-CNN as a basic network into a novel dual multiscale mean teacher network (DM [Formula: see text]-Net) for semi-supervised COVID-19 lung infection segmentation on CT volumes by leveraging unlabeled data and exploring the multiscale information. Our DM [Formula: see text]-Net encourages multiple predictions at different CNN layers from the student and teacher networks to be consistent for computing a multiscale consistency loss on unlabeled data, which is then added to the supervised loss on the labeled data from multiple predictions of MDA-CNN. Third, we collect two COVID-19 segmentation datasets to evaluate our method. The experimental results show that our network consistently outperforms the compared state-of-the-art methods.

Artificial intelligence-assisted quantification of COVID-19 pneumonia burden from computed tomography improves prediction of adverse outcomes over visual scoring systems

OBJECTIVE

We aimed to evaluate the effectiveness of utilizing artificial intelligence (AI) to quantify the extent of pneumonia from chest CT scans, and to determine its ability to predict clinical deterioration or mortality in patients admitted to the hospital with COVID-19 in comparison to semi-quantitative visual scoring systems.

METHODS

A deep-learning algorithm was utilized to quantify the pneumonia burden, while semi-quantitative pneumonia severity scores were estimated through visual means. The primary outcome was clinical deterioration, the composite end point including admission to the intensive care unit, need for invasive mechanical ventilation, or vasopressor therapy, as well as in-hospital death.

RESULTS

The final population comprised 743 patients (mean age 65  ±  17 years, 55% men), of whom 175 (23.5%) experienced clinical deterioration or death. The area under the receiver operating characteristic curve (AUC) for predicting the primary outcome was significantly higher for AI-assisted quantitative pneumonia burden (0.739, p = 0.021) compared with the visual lobar severity score (0.711, p < 0.001) and visual segmental severity score (0.722, p = 0.042). AI-assisted pneumonia assessment exhibited lower performance when applied for calculation of the lobar severity score (AUC of 0.723, p = 0.021). Time taken for AI-assisted quantification of pneumonia burden was lower (38 ± 10 s) compared to that of visual lobar (328 ± 54 s, p < 0.001) and segmental (698 ± 147 s, p < 0.001) severity scores.

CONCLUSION

Utilizing AI-assisted quantification of pneumonia burden from chest CT scans offers a more accurate prediction of clinical deterioration in patients with COVID-19 compared to semi-quantitative severity scores, while requiring only a fraction of the analysis time.

ADVANCES IN KNOWLEDGE

Quantitative pneumonia burden assessed using AI demonstrated higher performance for predicting clinical deterioration compared to current semi-quantitative scoring systems. Such an AI system has the potential to be applied for image-based triage of COVID-19 patients in clinical practice.

Prevalence, Risk Factors, Prognosis, and Management of Pericardial Effusion in COVID-19

Background: There is limited data in the literature about the clinical importance and prognosis of pericardial effusion (PE) in patients discharged after recovering from COVID-19, but large-scale studies have yet to be available. This study investigated the prevalence, risk factors, prognosis, late clinical outcomes, and management of PE in COVID-19. Materials and Methods: Between August 2020 and March 2021, 15,689 patients were followed up in our pandemic hospital due to COVID-19. Patients with positive polymerase chain reaction (PCR) test results and PE associated with COVID-19 in computed tomography (CT) were included in the study. The patients were divided into three groups according to PE size (mild, moderate, and large). Transthoracic echocardiography (TTE) records, laboratory data, clinical outcomes, and medical treatments of patients discharged from the hospital were retrospectively reviewed. Results: According to the PE size (mild, moderate, large) of 256 patients with PE at admission or discharge, the mean age was 62.17 ± 16.34, 69.12 ± 12.52, and 72.44 ± 15.26, respectively. The mean follow-up period of the patients was 25.2 ± 5.12 months. Of the patients in the study population, 53.5% were in the mild group, 30.4% in the moderate group, and 16.1% in the large group. PE became chronic in a total of 178 (69.6%) patients at the end of the mean three months, and chronicity increased as PE size increased. Despite the different anti-inflammatory treatments for PE in the acute phase, similar chronicity was observed. In addition, as the PE size increased, the patients' frequency of hospitalization, complications, and mortality rates showed statistical significance between the groups. Conclusions: The clinical prognosis of patients presenting with PE was quite poor; as PE in size increased, cardiac and noncardiac events and mortality rates were significantly higher. Patients with large PE associated with COVID-19 at discharge should be monitored at close intervals due to the chronicity of PE and the increased risk of tamponade.

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.

SuperMini-seg: An ultra lightweight network for COVID-19 lung infection segmentation from CT images

The automatic segmentation of lung lesions from COVID-19 computed tomography (CT) images is helpful in establishing a quantitative model to diagnose and treat COVID-19. To this end, this study proposes a lightweight segmentation network called the SuperMini-Seg. We propose a new module called the transformer parallel convolution module (TPCB), which introduces both transformer and convolution operations in one module. SuperMini-seg adopts the structure of a double-branch parallel to downsample the image and designs a gated attention mechanism in the middle of the two parallel branches. At the same time, the attentive hierarchical spatial pyramid (AHSP) module and criss-cross attention module are adopted, and more than 100K parameters are present in the model. At the same time, the model is scalable, and the parameter quantity of SuperMini-seg-V2 reaches more than 70K. Compared with other advanced methods, the segmentation accuracy was almost reached the state-of-art method. The calculation efficiency was high, which is convenient for practical deployment.

Exploring the Synergistic Potential of Radiomics and Laboratory Biomarkers for Enhanced Identification of Vulnerable COVID-19 Patients

BACKGROUND

Severe courses and high hospitalization rates were ubiquitous during the first pandemic SARS-CoV-2 waves. Thus, we aimed to examine whether integrative diagnostics may aid in identifying vulnerable patients using crucial data and materials obtained from COVID-19 patients hospitalized between 2020 and 2021 (n = 52). Accordingly, we investigated the potential of laboratory biomarkers, specifically the dynamic cell decay marker cell-free DNA and radiomics features extracted from chest CT.

METHODS

Separate forward and backward feature selection was conducted for linear regression with the Intensive-Care-Unit (ICU) period as the initial target. Three-fold cross-validation was performed, and collinear parameters were reduced. The model was adapted to a logistic regression approach and verified in a validation naïve subset to avoid overfitting.

RESULTS

The adapted integrated model classifying patients into "ICU/no ICU demand" comprises six radiomics and seven laboratory biomarkers. The models' accuracy was 0.54 for radiomics, 0.47 for cfDNA, 0.74 for routine laboratory, and 0.87 for the combined model with an AUC of 0.91.

CONCLUSION

The combined model performed superior to the individual models. Thus, integrating radiomics and laboratory data shows synergistic potential to aid clinic decision-making in COVID-19 patients. Under the need for evaluation in larger cohorts, including patients with other SARS-CoV-2 variants, the identified parameters might contribute to the triage of COVID-19 patients.

Evaluación de riesgos y mejora de la seguridad biológica y radiológica en la toma de radiografía torácica a pacientes con COVID-19

INTRODUCTION

Health workers are at high risk of becoming infected with COVID-19. The objective of the study was to evaluate the risks and improve the biological and radiological safety measures for taking chest X-rays in patients with COVID-19 in a Social Security hospital in Utcubamba (Peru).

MATERIAL AND METHODS

Quasi-experimental intervention study type before and after without a control group, carried out between May and September 2020. A process map and an analysis of failure modes and effects (FMEA) of radiological care were prepared. The gravity (G), occurrence (O), and detectability (D) values ??were found and the risk priority number (RPN) was calculated for each failure mode (FM). FM with RPN ≥ 100 and G ≥ 7 were prioritized. Improvement actions were implemented based on the recommendations of recognized institutions and the O and D values ??were re-evaluated.

RESULTS

The process map consisted of 6 threads and 30 steps. 54 FM were identified, 37 of whom had RPN ≥ 100 and 48 had G ≥ 7. Most of the errors occurred during the examination 50% (27). After entering the recommendations, 23 FM had RPN ≥ 100.

CONCLUSIONS

Although none of the measures applied through the FMEA made the failure mode impossible, they made it more detectable and less frequent and reduced the RPN for each failure mode; however, a periodic update of the process is necessary.

Could initial CT chest manifestation in patients hospitalized with COVID 19 pneumonia predict outcome on short term basis

Chest computed tomography (CT) can be used to monitor the course of the disease or response to therapy. Therefore, our study was designed to identify chest CT manifestations that can predict the outcome of patients on short term follow-up. This was a retrospective study wherein we reviewed chest CT scans of 112 real-time reverse transcription polymerase chain reaction positive patients admitted to our hospital. All 112 patients underwent follow-up chest CT at a time interval of 4 to 42 days. Our study included 83 male and 29 female who were positive for COVID 19 infection and admitted to the hospital with positive chest CT findings. All patients underwent follow-up chest CT, and the outcomes were categorized as resolution, regression, residual fibrosis, progression, or death. These proportions were 5.4%, 48.2%, 24.1%, 14.3%, and 8%, respectively. The only significant factor in determining the complete resolution of chest CT was oligo-segmental affection (P = .0001). The main CT feature that significantly affected the regression of chest CT manifestations was diffuse nodular shadows (P = .039). The CT features noted in patients with residual fibrosis were interstitial thickening, with a P value of .017. The mono-segmental process significantly affected progression (P = .044). The significant factors for fatality were diffuse crazy paving, pleural effusion, and extra-thoracic complications (P = .033, .029, and .007, respectively). The prognostic value of the first admission CT can help assess disease outcomes in the earliest phases of onset. This can improve resource distribution.

Quantitative Evaluation of COVID-19 Pneumonia CT Using AI Analysis-Feasibility and Differentiation from Other Common Pneumonia Forms

PURPOSE: To implement the technical feasibility of an AI-based software prototype optimized for the detection of COVID-19 pneumonia in CT datasets of the lung and the differentiation between other etiologies of pneumonia. METHODS: This single-center retrospective case-control-study consecutively yielded 144 patients (58 female, mean age 57.72 ± 18.25 y) with CT datasets of the lung. Subgroups including confirmed bacterial (n = 24, 16.6%), viral (n = 52, 36.1%), or fungal (n = 25, 16.6%) pneumonia and (n = 43, 30.7%) patients without detected pneumonia (comparison group) were evaluated using the AI-based Pneumonia Analysis prototype. Scoring (extent, etiology) was compared to reader assessment. RESULTS: The software achieved an optimal sensitivity of 80.8% with a specificity of 50% for the detection of COVID-19; however, the human radiologist achieved optimal sensitivity of 80.8% and a specificity of 97.2%. The mean postprocessing time was 7.61 ± 4.22 min. The use of a contrast agent did not influence the results of the software (p = 0.81). The mean evaluated COVID-19 probability is 0.80 ± 0.36 significantly higher in COVID-19 patients than in patients with fungal pneumonia (p < 0.05) and bacterial pneumonia (p < 0.001). The mean percentage of opacity (PO) and percentage of high opacity (PHO ≥ -200 HU) were significantly higher in COVID-19 patients than in healthy patients. However, the total mean HU in COVID-19 patients was -679.57 ± 112.72, which is significantly higher than in the healthy control group (p < 0.001). CONCLUSION: The detection and quantification of pneumonia beyond the primarily trained COVID-19 datasets is possible and shows comparable results for COVID-19 pneumonia to an experienced reader. The advantages are the fast, automated segmentation and quantification of the pneumonia foci.

Correlation of bone density measured on CT chest with the severity of COVID-19 infection: A retrospective study

PURPOSE

This retrospective study investigated the correlation between bone mineral density (BMD) and COVID-19 severity among COVID-19 patients who underwent chest computed tomography (CT) scans.

METHODS

This study was carried out at the King Abdullah Medical Complex in Jeddah, Saudi Arabia, one of the largest COVID-19 centers in the western province. All adult COVID-19 patients who had a chest CT between January 2020 and April 2022 were included in the study. The pulmonary severity scores (PSS) and vertebral BMD measurements were obtained from the patient's CT chest. Data from the patients' electronic records were collected.

RESULTS

The average patient age was 56.4 years, and most (73.5%) patients were men. Diabetes (n = 66, 48.5%), hypertension (n = 56, 41.2%), and coronary artery disease (n = 17, 12.5%) were the most prevalent comorbidities. Approximately two-thirds of hospitalized patients required ICU admission (64%), and one-third died (30%). The average length of stay in the hospital was 28.4 days. The mean CT pneumonia severity score (PSS) was 10.6 at the time of admission. Patients with lower vertebral BMD (< = 100) numbered 12 (8.8%), while those with higher vertebral BMD (>100) numbered 124 (91.2%). Only 46 out of the total survived patients (n = 95) were admitted to the ICU versus all deceased (P<0.01). The logistic regression analysis revealed that an elevated PSS upon admission resulted in a reduced chance of survival. Age, gender, and BMD did not predict survival chances.

CONCLUSION

The BMD had no prognostic advantage, and the PSS was the significant factor that could have predicted the outcome.

Leveraging human expert image annotations to improve pneumonia differentiation through human knowledge distillation

In medical imaging, deep learning models can be a critical tool to shorten time-to-diagnosis and support specialized medical staff in clinical decision making. The successful training of deep learning models usually requires large amounts of quality data, which are often not available in many medical imaging tasks. In this work we train a deep learning model on university hospital chest X-ray data, containing 1082 images. The data was reviewed, differentiated into 4 causes for pneumonia, and annotated by an expert radiologist. To successfully train a model on this small amount of complex image data, we propose a special knowledge distillation process, which we call Human Knowledge Distillation. This process enables deep learning models to utilize annotated regions in the images during the training process. This form of guidance by a human expert improves model convergence and performance. We evaluate the proposed process on our study data for multiple types of models, all of which show improved results. The best model of this study, called PneuKnowNet, shows an improvement of + 2.3% points in overall accuracy compared to a baseline model and also leads to more meaningful decision regions. Utilizing this implicit data quality-quantity trade-off can be a promising approach for many scarce data domains beyond medical imaging.

Progressive attention integration-based multi-scale efficient network for medical imaging analysis with application to COVID-19 diagnosis

In this paper, a novel deep learning-based medical imaging analysis framework is developed, which aims to deal with the insufficient feature learning caused by the imperfect property of imaging data. Named as multi-scale efficient network (MEN), the proposed method integrates different attention mechanisms to realize sufficient extraction of both detailed features and semantic information in a progressive learning manner. In particular, a fused-attention block is designed to extract fine-grained details from the input, where the squeeze-excitation (SE) attention mechanism is applied to make the model focus on potential lesion areas. A multi-scale low information loss (MSLIL)-attention block is proposed to compensate for potential global information loss and enhance the semantic correlations among features, where the efficient channel attention (ECA) mechanism is adopted. The proposed MEN is comprehensively evaluated on two COVID-19 diagnostic tasks, and the results show that as compared with some other advanced deep learning models, the proposed method is competitive in accurate COVID-19 recognition, which yields the best accuracy of 98.68% and 98.85%, respectively, and exhibits satisfactory generalization ability as well.