Relation of impulse oscillometry and spirometry with quantitative thorax computed tomography after COVID-19 pneumonia.

OBJECTIVE: This study aimed to investigate if there is any correlation between the quantitative computed tomography and the impulse oscillometry or spirometry results of post-COVID-19 patients. METHODS: The study comprised 47 post-COVID-19 patients who had spirometry, impulse oscillometry, and high-resolution computed tomography examinations at the same time. The study group consisted of 33 patients with quantitative computed tomography involvement, while the control group included 14 patients who did not have CT findings. The quantitative computed tomography technology was used to calculate percentages of density range volumes. The relationship between percentages of density range volumes for different quantitative computed tomography density ranges and impulse oscillometry-spirometry findings was statistically analyzed. RESULTS: In quantitative computed tomography, the percentage of relatively high-density lung parenchyma, including fibrotic areas, was 1.76±0.43 and 5.65±3.73 in the control and study groups, respectively. The percentages of primarily ground-glass parenchyma areas were found to be 7.60±2.86 and 29.25±16.50 in the control and study groups, respectively. In the correlation analysis, the forced vital capacity% predicted in the study group was correlated with DRV%[(-750)-(-500)] (volume of the lung parenchyma that has density between (-750)-(-500) Hounsfield units), but no correlation with DRV%[(-500)-0] was detected. Also, reactance area and resonant frequency were correlated with DRV%[(-750)-(-500)], while X5 was correlated with both DRV%[(-500)-0] and DRV%[(-750)-(-500)] density. Modified Medical Research Council score was correlated with predicted percentages of forced vital capacity and X5. CONCLUSION: After COVID-19, forced vital capacity, reactance area, resonant frequency, and X5 correlated with the percentages of density range volumes of ground-glass opacity areas in the quantitative computed tomography. X5 was the only parameter correlated with density ranges consistent with both ground-glass opacity and fibrosis. Furthermore, the percentages of forced vital capacity and X5 were shown to be associated with the perception of dyspnea.

The role of Lung Ultrasound in the diagnosis of SARS-COV-2 disease in pregnant women.

AIM: To evaluate the role of lung ultrasound (LUS) in recognizing lung abnormalities in pregnant women affected by COVID-19 pneumonia. MATERIALS AND METHODS: An observational study analyzing LUS patterns in 60 consecutively enrolled pregnant women affected by COVID-19 infection was performed. LUS was performed by using a standardized protocol by Soldati et al. The scoring system of LUS findings ranged from 0 to 3 in increasing alteration severity. The highest score obtained from each landmark was reported and the sum of the 12 zones examined was calculated. RESULTS: Patients were divided into two groups: 26 (43.3%) patients with respiratory symptoms and 32 (53.3%) patients without respiratory symptoms; 2 patients were asymptomatic (3.3%). Among the patients with respiratory symptoms 3 (12.5%) had dyspnea that required a mild Oxygen therapy. A significant correlation was found between respiratory symptoms and LUS score (p < 0.001) and between gestational weeks and respiratory symptoms (p = 0.023). Regression analysis showed that age and respiratory symptoms were risk factors for highest LUS score (p < 0.005). DISCUSSION: LUS can affect the clinical decision course and can help in stratifying patients according to its findings. The lack of ionizing radiation and its repeatability makes it a reliable diagnostic tool in the management of pregnant women.

Pediatric COVID-19: Correlations between Clinical and Imaging Perspectives.

Background: Although SARS-CoV-2 infection primarily affects adults, the increasing emergence of infected pediatric patients has been recently reported. However, there is a paucity of data regarding the value of imaging in relation to the clinical severity of this pandemic emergency. Objectives: To demonstrate the relationships between clinical and radiological COVID-19 findings and to determine the most effective standardized pediatric clinical and imaging strategies predicting the disease severity. Patients and Methods. This observational study enrolled eighty pediatric patients with confirmed COVID-19 infection. The studied patients were categorized according to the disease severity and the presence of comorbidities. Patients' clinical findings, chest X-ray, and CT imaging results were analyzed. Patients' evaluations using several clinical and radiological severity scores were recorded. The relations between clinical and radiological severities were examined. Results: Significant associations were found between severe-to-critical illness and abnormal radiological findings (p = 0.009). In addition, chest X-ray score, chest CT severity score, and rapid evaluation of anamnesis, PO2, imaging disease, and dyspnea-COVID (RAPID-COVID) score were significantly higher among patients with severe infection (p < 0.001, <0.001, and 0.001) and those with comorbidities (p = 0.005, 0.002, and <0.001). Conclusions: Chest imaging of pediatric patients with COVID-19 infection may be of value during the evaluation of severe cases of infected pediatric patients and in those with underlying comorbid conditions, especially during the early stage of infection. Moreover, the combined use of specific clinical and radiological COVID-19 scores are likely to be a successful measure of the extent of disease severity.

Weakly-supervised lesion analysis with a CNN-based framework for COVID-19.

Objective.Lesions of COVID-19 can be clearly visualized using chest CT images, and hence provide valuable evidence for clinicians when making a diagnosis. However, due to the variety of COVID-19 lesions and the complexity of the manual delineation procedure, automatic analysis of lesions with unknown and diverse types from a CT image remains a challenging task. In this paper we propose a weakly-supervised framework for this task requiring only a series of normal and abnormal CT images without the need for annotations of the specific locations and types of lesions.Approach.A deep learning-based diagnosis branch is employed for classification of the CT image and then a lesion identification branch is leveraged to capture multiple types of lesions.Main Results.Our framework is verified on publicly available datasets and CT data collected from 13 patients of the First Affiliated Hospital of Shantou University Medical College, China. The results show that the proposed framework can achieve state-of-the-art diagnosis prediction, and the extracted lesion features are capable of distinguishing between lesions showing ground glass opacity and consolidation.Significance.The proposed approach integrates COVID-19 positive diagnosis and lesion analysis into a unified framework without extra pixel-wise supervision. Further exploration also demonstrates that this framework has the potential to discover lesion types that have not been reported and can potentially be generalized to lesion detection of other chest-based diseases.

COVID-19 detection based on self-supervised transfer learning using chest X-ray images.

PURPOSE: Considering several patients screened due to COVID-19 pandemic, computer-aided detection has strong potential in assisting clinical workflow efficiency and reducing the incidence of infections among radiologists and healthcare providers. Since many confirmed COVID-19 cases present radiological findings of pneumonia, radiologic examinations can be useful for fast detection. Therefore, chest radiography can be used to fast screen COVID-19 during the patient triage, thereby determining the priority of patient's care to help saturated medical facilities in a pandemic situation. METHODS: In this paper, we propose a new learning scheme called self-supervised transfer learning for detecting COVID-19 from chest X-ray (CXR) images. We compared six self-supervised learning (SSL) methods (Cross, BYOL, SimSiam, SimCLR, PIRL-jigsaw, and PIRL-rotation) with the proposed method. Additionally, we compared six pretrained DCNNs (ResNet18, ResNet50, ResNet101, CheXNet, DenseNet201, and InceptionV3) with the proposed method. We provide quantitative evaluation on the largest open COVID-19 CXR dataset and qualitative results for visual inspection. RESULTS: Our method achieved a harmonic mean (HM) score of 0.985, AUC of 0.999, and four-class accuracy of 0.953. We also used the visualization technique Grad-CAM++ to generate visual explanations of different classes of CXR images with the proposed method to increase the interpretability. CONCLUSIONS: Our method shows that the knowledge learned from natural images using transfer learning is beneficial for SSL of the CXR images and boosts the performance of representation learning for COVID-19 detection. Our method promises to reduce the incidence of infections among radiologists and healthcare providers.

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

PROBLEM: Detecting COVID-19 from chest X-ray (CXR) images has become one of the fastest and easiest methods for detecting COVID-19. However, the existing methods usually use supervised transfer learning from natural images as a pretraining process. These methods do not consider the unique features of COVID-19 and the similar features between COVID-19 and other pneumonia. AIM: In this paper, we want to design a novel high-accuracy COVID-19 detection method that uses CXR images, which can consider the unique features of COVID-19 and the similar features between COVID-19 and other pneumonia. METHODS: Our method consists of two phases. One is self-supervised learning-based pertaining; the other is batch knowledge ensembling-based fine-tuning. Self-supervised learning-based pretraining can learn distinguished representations from CXR images without manually annotated labels. On the other hand, batch knowledge ensembling-based fine-tuning can utilize category knowledge of images in a batch according to their visual feature similarities to improve detection performance. Unlike our previous implementation, we introduce batch knowledge ensembling into the fine-tuning phase, reducing the memory used in self-supervised learning and improving COVID-19 detection accuracy. RESULTS: On two public COVID-19 CXR datasets, namely, a large dataset and an unbalanced dataset, our method exhibited promising COVID-19 detection performance. Our method maintains high detection accuracy even when annotated CXR training images are reduced significantly (e.g., using only 10% of the original dataset). In addition, our method is insensitive to changes in hyperparameters. CONCLUSION: The proposed method outperforms other state-of-the-art COVID-19 detection methods in different settings. Our method can reduce the workloads of healthcare providers and radiologists.

Organ Donation, the Non-Perfect Lung Donor, and Variability in Conversion to Transplant.

Rates of lung donation have increased over the past several years. This has been accomplished through the utilization of donors with extended criteria, the creation of donor hospitals or centers, and the optimization of lungs through the implementation of donor management protocols. These measures have resulted in augmenting the pool of available donors thereby decreasing the wait time for lung transplantation candidates. Although transplant programs vary significantly in their acceptance rates of these organs, studies have not shown any difference in the incidence of primary graft dysfunction or overall mortality for the recipient when higher match-run sequence organs are accepted. Yet, the level of comfort in accepting these donors varies among transplant programs. This deviation in practice results in these organs going to lower-priority candidates thereby increasing the waitlist time of other recipients and ultimately has a deleterious effect on an institution's waitlist mortality.

Deep learning based classification of multi-label chest X-ray images via dual-weighted metric loss.

-Thoracic disease, like many other diseases, can lead to complications. Existing multi-label medical image learning problems typically include rich pathological information, such as images, attributes, and labels, which are crucial for supplementary clinical diagnosis. However, the majority of contemporary efforts exclusively focus on regression from input to binary labels, ignoring the relationship between visual features and semantic vectors of labels. In addition, there is an imbalance in data amount between diseases, which frequently causes intelligent diagnostic systems to make erroneous disease predictions. Therefore, we aim to improve the accuracy of the multi-label classification of chest X-ray images. Chest X-ray14 pictures were utilized as the multi-label dataset for the experiments in this study. By fine-tuning the ConvNeXt network, we got visual vectors, which we combined with semantic vectors encoded by BioBert to map the two different forms of features into a common metric space and made semantic vectors the prototype of each class in metric space. The metric relationship between images and labels is then considered from the image level and disease category level, respectively, and a new dual-weighted metric loss function is proposed. Finally, the average AUC score achieved in the experiment reached 0.826, and our model outperformed the comparison models.

Importance of physician history taking in complementing patient-reported interstitial lung disease questionnaire.

BACKGROUND: Patient-reported interstitial lung disease (ILD) questionnaires are commonly used for the evaluation of ILD patients. However, research to test their performance is scarce. METHODS: This study aimed to assess the performance of the Chest Questionnaire in consecutive ILD patients presenting to a tertiary ILD center. The results of Chest Questionnaires routinely filled by patients were analyzed together with clinical and demographic data retrieved from the patients' medical records. The ability of each questionnaire item to detect positive findings, such as environmental and occupational exposures, was examined relative to any additional findings detected by physician-acquired history. History was obtained by an experienced ILD pulmonologist who had access to the results of the questionnaire during the clinic visit. RESULTS: The final cohort for analysis included 62 patients. Shortness of breath frequency and duration were the questionnaire items with the lowest probability of being filled out by patients. The questionnaire performed well in identifying 96.2% of patients with a positive family history and 90.9% of patients with occupational exposures. However, exposures to mold or birds were frequently missed, self-reported by only 53.1% of exposed patients. Questionnaire's performance was also lower for other exposures associated with ILD (48.3%). An ILD-related exposure was less likely to be identified by the questionnaire in males (p = 0.03), while age had no such effect. CONCLUSIONS: The Chest Questionnaire performed well in several domains, while failing to detect some relevant exposures. Therefore, its use should be accompanied by careful history taking by the physician.

A hybrid CNN and ensemble model for COVID-19 lung infection detection on chest CT scans.

COVID-19 is highly infectious and causes acute respiratory disease. Machine learning (ML) and deep learning (DL) models are vital in detecting disease from computerized chest tomography (CT) scans. The DL models outperformed the ML models. For COVID-19 detection from CT scan images, DL models are used as end-to-end models. Thus, the performance of the model is evaluated for the quality of the extracted feature and classification accuracy. There are four contributions included in this work. First, this research is motivated by studying the quality of the extracted feature from the DL by feeding these extracted to an ML model. In other words, we proposed comparing the end-to-end DL model performance against the approach of using DL for feature extraction and ML for the classification of COVID-19 CT scan images. Second, we proposed studying the effect of fusing extracted features from image descriptors, e.g., Scale-Invariant Feature Transform (SIFT), with extracted features from DL models. Third, we proposed a new Convolutional Neural Network (CNN) to be trained from scratch and then compared to the deep transfer learning on the same classification problem. Finally, we studied the performance gap between classic ML models against ensemble learning models. The proposed framework is evaluated using a CT dataset, where the obtained results are evaluated using five different metrics The obtained results revealed that using the proposed CNN model is better than using the well-known DL model for the purpose of feature extraction. Moreover, using a DL model for feature extraction and an ML model for the classification task achieved better results in comparison to using an end-to-end DL model for detecting COVID-19 CT scan images. Of note, the accuracy rate of the former method improved by using ensemble learning models instead of the classic ML models. The proposed method achieved the best accuracy rate of 99.39%.

Medical image captioning via generative pretrained transformers.

The proposed model for automatic clinical image caption generation combines the analysis of radiological scans with structured patient information from the textual records. It uses two language models, the Show-Attend-Tell and the GPT-3, to generate comprehensive and descriptive radiology records. The generated textual summary contains essential information about pathologies found, their location, along with the 2D heatmaps that localize each pathology on the scans. The model has been tested on two medical datasets, the Open-I, MIMIC-CXR, and the general-purpose MS-COCO, and the results measured with natural language assessment metrics demonstrated its efficient applicability to chest X-ray image captioning.

Temporal evolution of diaphragm thickness and diaphragm excursion among subjects hospitalized with COVID-19: A prospective observational study.

BACKGROUND: The severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) has an affinity for the angiotensin-converting enzyme 2 (ACE2) receptors, which are present abundantly on the diaphragm. This study aims to describe temporal changes in diaphragmatic thickness and excursion using ultrasonography in subjects with acute COVID-19. METHODS: This prospective observational study included adults hospitalized with COVID-19 in the past 48 hours. The diaphragm thickness at end-expiration (DTE), diaphragm thickening fraction (DTF), and diaphragm excursion during tidal breathing (DE) and maximal inspiration (DEmax) were measured using ultrasonography daily for 5 days. The changes in DTE, DTF, DE, and Demax from day 1 to day 5 were assessed. RESULTS: This study included 64 adults (62.5% male) with a mean (SD) age of 50.2 (17.5) years. A majority (91%) of the participants had mild or moderate illness. The median (IQR) DTE, DTF (%), DE and Demax on day 1 were 2.2 (1.9, 3.0) mm, 21.5% (14.2, 31.0), 19.2 (16.5, 24.0) mm, and 26.7 (22.0, 30.2) mm, respectively. On day 5, there was a significant reduction in the DTE (p=0.002) with a median (IQR) percentage change of -15.7% (-21.0, 0.0). The DTF significantly increased on day 5 with a median (IQR) percentage change of 25.0% (-19.2, 98.4), p=0.03. There was no significant change in DE and Demax from day 1 to day 5, with a median (IQR) percentage change of 3.6% (-5.2, 15) and 0% (-6.7, 5.9), respectively. CONCLUSIONS: Non-intubated patients with COVID-19 exhibited a temporal decline in diaphragm thickness with increase in thickening fraction over 5 days of hospital admission. Further research is warranted to assess the impact of COVID-19 pneumonia on diaphragmatic function.

COVID-19 Classification on Chest X-ray Images Using Deep Learning Methods.

Since December 2019, the coronavirus disease has significantly affected millions of people. Given the effect this disease has on the pulmonary systems of humans, there is a need for chest radiographic imaging (CXR) for monitoring the disease and preventing further deaths. Several studies have been shown that Deep Learning models can achieve promising results for COVID-19 diagnosis towards the CXR perspective. In this study, five deep learning models were analyzed and evaluated with the aim of identifying COVID-19 from chest X-ray images. The scope of this study is to highlight the significance and potential of individual deep learning models in COVID-19 CXR images. More specifically, we utilized the ResNet50, ResNet101, DenseNet121, DenseNet169 and InceptionV3 using Transfer Learning. All models were trained and validated on the largest publicly available repository for COVID-19 CXR images. Furthermore, they were evaluated on unknown data that was not used for training or validation, authenticating their performance and clarifying their usage in a medical scenario. All models achieved satisfactory performance where ResNet101 was the superior model achieving 96% in Precision, Recall and Accuracy, respectively. Our outcomes show the potential of deep learning models on COVID-19 medical offering a promising way for the deeper understanding of COVID-19.

Long-term lung perfusion changes related to COVID-19: a dual energy computed tomography study

PURPOSE: Although the findings of acute new coronavirus disease (COVID-19) infection on dual-energy computed tomography (DECT) have recently been defined, the long-term changes in lung perfusion associated with COVID-19 pneumonia have not yet been clarified. We aimed to examine the longterm course of lung perfusion in COVID-19 pneumonia cases using DECT and to compare changes in lung perfusion to clinical and laboratory findings. METHODS: On initial and follow-up DECT scans, the presence and extent of perfusion deficit (PD) and parenchymal changes were assessed. The associations between PD presence and laboratory parameters, initial DECT severity score, and symptoms were evaluated. RESULTS: The study population included 18 females and 26 males with an average age of 61.32 ± 11.3 years. Follow-up DECT examinations were performed after the mean of 83.12 ± 7.1 (80-94 days) days. PDs were detected on the follow-up DECT scans of 16 (36.3%) patients. These 16 patients also had ground-glass parenchymal lesions on the follow-up DECT scans. Patients with persistent lung PDs had significantly higher mean initial D-dimer, fibrinogen, and C-reactive protein values than patients without PDs. Patients with persistent PDs also had significantly higher rates of persistent symptoms. CONCLUSION: Ground-glass opacities and lung PDs associated with COVID-19 pneumonia can persist for up to 80-90 days. Dual-energy computed tomography can be used to reveal long-term parenchymal and perfusion changes. Persistent PDs are commonly seen together with persistent COVID-19 symptoms.

Origins of and lessons from quantitative functional X-ray computed tomography of the lung.

Functional CT of the lung has emerged from quantitative CT (qCT). Structural details extracted at multiple lung volumes offer indices of function. Additionally, single volumetric images, if acquired at standardized lung volumes and body posture, can be used to model function by employing such engineering techniques as computational fluid dynamics. With the emergence of multispectral CT imaging including dual energy from energy integrating CT scanners and multienergy binning using the newly released photon counting CT technology, function is tagged via use of contrast agents. Lung disease phenotypes have previously been lumped together by the limitations of spirometry and plethysmography. QCT and its functional embodiment have been imbedded into studies seeking to characterize chronic obstructive pulmonary disease, severe asthma, interstitial lung disease and more. Reductions in radiation dose by an order of magnitude or more have been achieved. At the same time, we have seen significant increases in spatial and density resolution along with methodologic validations of extracted metrics. Together, these have allowed attention to turn towards more mild forms of disease and younger populations. In early applications, clinical CT offered anatomic details of the lung. Functional CT offers regional measures of lung mechanics, the assessment of functional small airways disease, as well as regional ventilation-perfusion matching (V/Q) and more. This paper will focus on the use of quantitative/functional CT for the non-invasive exploration of dynamic three-dimensional functioning of the breathing lung and beating heart within the unique negative pressure intrathoracic environment of the closed chest.

LDANet: Automatic lung parenchyma segmentation from CT images.

Automatic segmentation of the lung parenchyma from computed tomography (CT) images is helpful for the subsequent diagnosis and treatment of patients. In this paper, based on a deep learning algorithm, a lung dense attention network (LDANet) is proposed with two mechanisms: residual spatial attention (RSA) and gated channel attention (GCA). RSA is utilized to weight the spatial information of the lung parenchyma and suppress feature activation in irrelevant regions, while the weights of each channel are adaptively calibrated using GCA to implicitly predict potential key features. Then, a dual attention guidance module (DAGM) is designed to maximize the integration of the advantages of both mechanisms. In addition, LDANet introduces a lightweight dense block (LDB) that reuses feature information and a positioned transpose block (PTB) that realizes accurate positioning and gradually restores the image resolution until the predicted segmentation map is generated. Experiments are conducted on two public datasets, LIDC-IDRI and COVID-19 CT Segmentation, on which LDANet achieves Dice similarity coefficient values of 0.98430 and 0.98319, respectively, outperforming a state-of-the-art lung segmentation model. Additionally, the effectiveness of the main components of LDANet is demonstrated through ablation experiments.