Severity prediction of pulmonary diseases using chest CT scans via cost-sensitive label multi-kernel distribution learning.

BACKGROUND AND OBJECTIVES: The progression of pulmonary diseases is a complex progress. Timely predicting whether the patients will progress to the severe stage or not in its early stage is critical to take appropriate hospital treatment. However, this task suffers from the "insufficient and incomplete" data issue since it is clinically impossible to have adequate training samples for one patient at each day. Besides, the training samples are extremely imbalanced since the patients who will progress to the severe stage is far less than those who will not progress to the non-severe stage. METHOD: We consider the severity prediction of pulmonary diseases as a time estimation problem based on CT scans. To handle the issue of "insufficient and incomplete" training samples, we introduced label distribution learning (LDL). Specifically, we generate a label distribution for each patient, making a CT image contribute to not only the learning of its chronological day, but also the learning of its neighboring days. In addition, a cost-sensitive mechanism is introduced to explore the imbalance data issue. To identify the importance of pulmonary segments in pulmonary disease severity prediction, multi-kernel learning in composite kernel space is further incorporated and particle swarm optimization (PSO) is used to find the optimal kernel weights. RESULTS: We compare the performance of the proposed CS-LD-MKSVR algorithm with several classical machine learning algorithms and deep learning (DL) algorithms. The proposed method has obtained the best classification results on the in-house data, fully indicating its effectiveness in pulmonary disease severity prediction. CONTRIBUTIONS: The severity prediction of pulmonary diseases is considered as a time estimation problem, and label distribution is introduced to describe the conversion time from non-severe stage to severe stage. The cost-sensitive mechanism is also introduced to handle the data imbalance issue to further improve the classification performance.

Large-scale screening of COVID-19 from community acquired pneumonia using infection size-aware classification.

The worldwide spread of coronavirus disease (COVID-19) has become a threatening risk for global public health. It is of great importance to rapidly and accurately screen patients with COVID-19 from community acquired pneumonia (CAP). In this study, a total of 1658 patients with COVID-19 and 1027 CAP patients underwent thin-section CT. All images were preprocessed to obtain the segmentations of infections and lung fields. A set of handcrafted location-specific features was proposed to best capture the COVID-19 distribution pattern, in comparison to conventional CT severity score (CT-SS) and Radiomics features. An infection Size Aware Random Forest method (iSARF) was used for classification. Experimental results show that the proposed method yielded best performance when using the handcrafted features with sensitivity of 91.6%, specificity of 86.8%, and accuracy of 89.8% over state-of-the-art classifiers. Additional test on 734 subjects with thick slice images demonstrates great generalizability. It is anticipated that our proposed framework could assist clinical decision making. Furthermore, the data of extracted features will be made available after the review process.

Adaptive Feature Selection Guided Deep Forest for COVID-19 Classification With Chest CT.

Chest computed tomography (CT) becomes an effective tool to assist the diagnosis of coronavirus disease-19 (COVID-19). Due to the outbreak of COVID-19 worldwide, using the computed-aided diagnosis technique for COVID-19 classification based on CT images could largely alleviate the burden of clinicians. In this paper, we propose an Adaptive Feature Selection guided Deep Forest (AFS-DF) for COVID-19 classification based on chest CT images. Specifically, we first extract location-specific features from CT images. Then, in order to capture the high-level representation of these features with the relatively small-scale data, we leverage a deep forest model to learn high-level representation of the features. Moreover, we propose a feature selection method based on the trained deep forest model to reduce the redundancy of features, where the feature selection could be adaptively incorporated with the COVID-19 classification model. We evaluated our proposed AFS-DF on COVID-19 dataset with 1495 patients of COVID-19 and 1027 patients of community acquired pneumonia (CAP). The accuracy (ACC), sensitivity (SEN), specificity (SPE), AUC, precision and F1-score achieved by our method are 91.79%, 93.05%, 89.95%, 96.35%, 93.10% and 93.07%, respectively. Experimental results on the COVID-19 dataset suggest that the proposed AFS-DF achieves superior performance in COVID-19 vs. CAP classification, compared with 4 widely used machine learning methods.

Structural Attention Graph Neural Network for Diagnosis and Prediction of COVID-19 Severity.

With rapid worldwide spread of Coronavirus Disease 2019 (COVID-19), jointly identifying severe COVID-19 cases from mild ones and predicting the conversion time (from mild to severe) is essential to optimize the workflow and reduce the clinician's workload. In this study, we propose a novel framework for COVID-19 diagnosis, termed as Structural Attention Graph Neural Network (SAGNN), which can combine the multi-source information including features extracted from chest CT, latent lung structural distribution, and non-imaging patient information to conduct diagnosis of COVID-19 severity and predict the conversion time from mild to severe. Specifically, we first construct a graph to incorporate structural information of the lung and adopt graph attention network to iteratively update representations of lung segments. To distinguish different infection degrees of left and right lungs, we further introduce a structural attention mechanism. Finally, we introduce demographic information and develop a multi-task learning framework to jointly perform both tasks of classification and regression. Experiments are conducted on a real dataset with 1687 chest CT scans, which includes 1328 mild cases and 359 severe cases. Experimental results show that our method achieves the best classification (e.g., 86.86% in terms of Area Under Curve) and regression (e.g., 0.58 in terms of Correlation Coefficient) performance, compared with other comparison methods.

Severity detection of COVID-19 infection with machine learning of clinical records and CT images.

BACKGROUND: Coronavirus disease 2019 (COVID-19) is a deadly viral infection spreading rapidly around the world since its outbreak in 2019. In the worst case a patient's organ may fail leading to death. Therefore, early diagnosis is crucial to provide patients with adequate and effective treatment. OBJECTIVE: This paper aims to build machine learning prediction models to automatically diagnose COVID-19 severity with clinical and computed tomography (CT) radiomics features. METHOD: P-V-Net was used to segment the lung parenchyma and then radiomics was used to extract CT radiomics features from the segmented lung parenchyma regions. Over-sampling, under-sampling, and a combination of over- and under-sampling methods were used to solve the data imbalance problem. RandomForest was used to screen out the optimal number of features. Eight different machine learning classification algorithms were used to analyze the data. RESULTS: The experimental results showed that the COVID-19 mild-severe prediction model trained with clinical and CT radiomics features had the best prediction results. The accuracy of the GBDT classifier was 0.931, the ROUAUC 0.942, and the AUCPRC 0.694, which indicated it was better than other classifiers. CONCLUSION: This study can help clinicians identify patients at risk of severe COVID-19 deterioration early on and provide some treatment for these patients as soon as possible. It can also assist physicians in prognostic efficacy assessment and decision making.

The value of longitudinal clinical data and paired CT scans in predicting the deterioration of COVID-19 revealed by an artificial intelligence system.

The respective value of clinical data and CT examinations in predicting COVID-19 progression is unclear, because the CT scans and clinical data previously used are not synchronized in time. To address this issue, we collected 119 COVID-19 patients with 341 longitudinal CT scans and paired clinical data, and we developed an AI system for the prediction of COVID-19 deterioration. By combining features extracted from CT and clinical data with our system, we can predict whether a patient will develop severe symptoms during hospitalization. Complementary to clinical data, CT examinations show significant add-on values for the prediction of COVID-19 progression in the early stage of COVID-19, especially in the 6th to 8th day after the symptom onset, indicating that this is the ideal time window for the introduction of CT examinations. We release our AI system to provide clinicians with additional assistance to optimize CT usage in the clinical workflow.

Hymecromone: a clinical prescription hyaluronan inhibitor for efficiently blocking COVID-19 progression.

Currently, there is no effective drugs for treating clinically COVID-19 except dexamethasone. We previously revealed that human identical sequences of SARS-CoV-2 promote the COVID-19 progression by upregulating hyaluronic acid (HA). As the inhibitor of HA synthesis, hymecromone is an approved prescription drug used for treating biliary spasm. Here, we aimed to investigate the relation between HA and COVID-19, and evaluate the therapeutic effects of hymecromone on COVID-19. Firstly, HA was closely relevant to clinical parameters, including lymphocytes (n = 158; r = -0.50; P < 0.0001), C-reactive protein (n = 156; r = 0.55; P < 0.0001), D-dimer (n = 154; r = 0.38; P < 0.0001), and fibrinogen (n = 152; r = 0.37; P < 0.0001), as well as the mass (n = 78; r = 0.43; P < 0.0001) and volume (n = 78; r = 0.41; P = 0.0002) of ground-glass opacity, the mass (n = 78; r = 0.48; P < 0.0001) and volume (n = 78; r = 0.47; P < 0.0001) of consolidation in patient with low level of hyaluronan (HA < 48.43 ng/mL). Furthermore, hyaluronan could directly cause mouse pulmonary lesions. Besides, hymecromone remarkably reduced HA via downregulating HAS2/HAS3 expression. Moreover, 89% patients with hymecromone treatment had pulmonary lesion absorption while only 42% patients in control group had pulmonary lesion absorption (P < 0.0001). In addition, lymphocytes recovered more quickly in hymecromone-treated patients (n = 8) than control group (n = 5) (P < 0.05). These findings suggest that hymecromone is a promising drug for COVID-19 and deserves our further efforts to determine its effect in a larger cohort.

Longitudinal trajectories of pneumonia lesions and lymphocyte counts associated with disease severity among convalescent COVID-19 patients: a group-based multi-trajectory analysis.

BACKGROUND: To explore the long-term trajectories considering pneumonia volumes and lymphocyte counts with individual data in COVID-19. METHODS: A cohort of 257 convalescent COVID-19 patients (131 male and 126 females) were included. Group-based multi-trajectory modelling was applied to identify different trajectories in terms of pneumonia lesion percentage and lymphocyte counts covering the time from onset to post-discharge follow-ups. We studied the basic characteristics and disease severity associated with the trajectories. RESULTS: We characterised four distinct trajectory subgroups. (1) Group 1 (13.9%), pneumonia increased until a peak lesion percentage of 1.9% (IQR 0.7-4.4) before absorption. The slightly decreased lymphocyte rapidly recovered to the top half of the normal range. (2) Group 2 (44.7%), the peak lesion percentage was 7.2% (IQR 3.2-12.7). The abnormal lymphocyte count restored to normal soon. (3) Group 3 (26.0%), the peak lesion percentage reached 14.2% (IQR 8.5-19.8). The lymphocytes continuously dropped to 0.75 × 109/L after one day post-onset before slowly recovering. (4) Group 4 (15.4%), the peak lesion percentage reached 41.4% (IQR 34.8-47.9), much higher than other groups. Lymphopenia was aggravated until the lymphocytes declined to 0.80 × 109/L on the fourth day and slowly recovered later. Patients in the higher order groups were older and more likely to have hypertension and diabetes (all P values < 0.05), and have more severe disease. CONCLUSIONS: Our findings provide new insights to understand the heterogeneous natural courses of COVID-19 patients and the associations of distinct trajectories with disease severity, which is essential to improve the early risk assessment, patient monitoring, and follow-up schedule.

Differential Diagnosis of COVID-19 Pneumonia From Influenza A (H1N1) Pneumonia Using a Model Based on Clinicoradiologic Features.

Objectives: Both coronavirus disease 2019 (COVID-19) pneumonia and influenza A (H1N1) pneumonia are highly contagious diseases. We aimed to characterize initial computed tomography (CT) and clinical features and to develop a model for differentiating COVID-19 pneumonia from H1N1 pneumonia. Methods: In total, we enrolled 291 patients with COVID-19 pneumonia from January 20 to February 13, 2020, and 97 patients with H1N1 pneumonia from May 24, 2009, to January 29, 2010 from two hospitals. Patients were randomly grouped into a primary cohort and a validation cohort using a seven-to-three ratio, and their clinicoradiologic data on admission were compared. The clinicoradiologic features were optimized by the least absolute shrinkage and selection operator (LASSO) logistic regression analysis to generate a model for differential diagnosis. Receiver operating characteristic (ROC) curves were plotted for assessing the performance of the model in the primary and validation cohorts. Results: The COVID-19 pneumonia mainly presented a peripheral distribution pattern (262/291, 90.0%); in contrast, H1N1 pneumonia most commonly presented a peribronchovascular distribution pattern (52/97, 53.6%). In LASSO logistic regression, peripheral distribution patterns, older age, low-grade fever, and slightly elevated aspartate aminotransferase (AST) were associated with COVID-19 pneumonia, whereas, a peribronchovascular distribution pattern, centrilobular nodule or tree-in-bud sign, consolidation, bronchial wall thickening or bronchiectasis, younger age, hyperpyrexia, and a higher level of AST were associated with H1N1 pneumonia. For the primary and validation cohorts, the LASSO model containing above eight clinicoradiologic features yielded an area under curve (AUC) of 0.963 and 0.943, with sensitivity of 89.7 and 86.2%, specificity of 89.7 and 89.7%, and accuracy of 89.7 and 87.1%, respectively. Conclusions: Combination of distribution pattern and category of pulmonary opacity on chest CT with clinical features facilitates the differentiation of COVID-19 pneumonia from H1N1 pneumonia.

Periphery-aware COVID-19 diagnosis with contrastive representation enhancement.

Computer-aided diagnosis has been extensively investigated for more rapid and accurate screening during the outbreak of COVID-19 epidemic. However, the challenge remains to distinguish COVID-19 in the complex scenario of multi-type pneumonia classification and improve the overall diagnostic performance. In this paper, we propose a novel periphery-aware COVID-19 diagnosis approach with contrastive representation enhancement to identify COVID-19 from influenza-A (H1N1) viral pneumonia, community acquired pneumonia (CAP), and healthy subjects using chest CT images. Our key contributions include: 1) an unsupervised Periphery-aware Spatial Prediction (PSP) task which is designed to introduce important spatial patterns into deep networks; 2) an adaptive Contrastive Representation Enhancement (CRE) mechanism which can effectively capture the intra-class similarity and inter-class difference of various types of pneumonia. We integrate PSP and CRE to obtain the representations which are highly discriminative in COVID-19 screening. We evaluate our approach comprehensively on our constructed large-scale dataset and two public datasets. Extensive experiments on both volume-level and slice-level CT images demonstrate the effectiveness of our proposed approach with PSP and CRE for COVID-19 diagnosis.

Computing infection distributions and longitudinal evolution patterns in lung CT images.

BACKGROUND: Spatial and temporal lung infection distributions of coronavirus disease 2019 (COVID-19) and their changes could reveal important patterns to better understand the disease and its time course. This paper presents a pipeline to analyze statistically these patterns by automatically segmenting the infection regions and registering them onto a common template. METHODS: A VB-Net is designed to automatically segment infection regions in CT images. After training and validating the model, we segmented all the CT images in the study. The segmentation results are then warped onto a pre-defined template CT image using deformable registration based on lung fields. Then, the spatial distributions of infection regions and those during the course of the disease are calculated at the voxel level. Visualization and quantitative comparison can be performed between different groups. We compared the distribution maps between COVID-19 and community acquired pneumonia (CAP), between severe and critical COVID-19, and across the time course of the disease. RESULTS: For the performance of infection segmentation, comparing the segmentation results with manually annotated ground-truth, the average Dice is 91.6% ± 10.0%, which is close to the inter-rater difference between two radiologists (the Dice is 96.1% ± 3.5%). The distribution map of infection regions shows that high probability regions are in the peripheral subpleural (up to 35.1% in probability). COVID-19 GGO lesions are more widely spread than consolidations, and the latter are located more peripherally. Onset images of severe COVID-19 (inpatients) show similar lesion distributions but with smaller areas of significant difference in the right lower lobe compared to critical COVID-19 (intensive care unit patients). About the disease course, critical COVID-19 patients showed four subsequent patterns (progression, absorption, enlargement, and further absorption) in our collected dataset, with remarkable concurrent HU patterns for GGO and consolidations. CONCLUSIONS: By segmenting the infection regions with a VB-Net and registering all the CT images and the segmentation results onto a template, spatial distribution patterns of infections can be computed automatically. The algorithm provides an effective tool to visualize and quantify the spatial patterns of lung infection diseases and their changes during the disease course. Our results demonstrate different patterns between COVID-19 and CAP, between severe and critical COVID-19, as well as four subsequent disease course patterns of the severe COVID-19 patients studied, with remarkable concurrent HU patterns for GGO and consolidations.

Early cardiac involvement in patients with acute COVID-19 infection identified by multiparametric cardiovascular magnetic resonance imaging.

AIMS: In order to determine acute cardiac involvement in patients with COVID-19, we quantitatively evaluated tissue characteristics and mechanics by non-invasive cardiac magnetic resonance (CMR) in a cohort of patients within the first 10 days of the onset of COVID symptoms. METHODS AND RESULTS: Twenty-five patients with reverse transcription polymerase chain reaction confirmed COVID-19 and at least one marker of cardiac involvement [cardiac symptoms, abnormal electrocardiograph (ECG), or abnormal cardiac biomarkers] and 25 healthy age- and gender-matched control subjects were recruited to the study. Patients were divided into those with elevated (n = 8) or normal TnI (n = 17). There were significant differences in global longitudinal strain among patients who were positive and negative for hs-TnI, and controls [-12.3 (-13.3, -11.5)%, -13.1 (-14.2, -9.8)%, and -15.7 (-18.3, -12.7)%, P = 0.004]. Native myocardial T1 relaxation times in patients with positive and negative hs-TnI manifestation (1169.8 ± 12.9 and 1113.2 ± 31.2 ms) were significantly higher than the normal (1065 ± 57 ms) subjects, respectively (P < 0.001). The extracellular volume (ECV) of patients who were positive and negative for hs-TnI was higher than that of the normal controls [32 (31, 33)%, 29 (27, 30)%, and 26 (24, 27.5)%, P < 0.001]. In our study, quantitative T2 mapping in patients who were positive and negative for hs-TnI [51 (47.9, 52.8) and 48 (47, 49.4) ms] was significantly higher than the normal [42 (41, 45.2) ms] subjects (P < 0.001). CONCLUSION: In patients with early-stage COVID-19, myocardial oedema, and functional abnormalities are a frequent finding, while irreversible regional injury such as necrosis may be infrequent.

A deep learning-based quantitative computed tomography model for predicting the severity of COVID-19: a retrospective study of 196 patients.

BACKGROUND: The assessment of the severity of coronavirus disease 2019 (COVID-19) by clinical presentation has not met the urgent clinical need so far. We aimed to establish a deep learning (DL) model based on quantitative computed tomography (CT) and initial clinical features to predict the severity of COVID-19. METHODS: One hundred ninety-six hospitalized patients with confirmed COVID-19 were enrolled from January 20 to February 10, 2020 in our centre, and were divided into severe and non-severe groups. The clinico-radiological data on admission were retrospectively collected and compared between the two groups. The optimal clinico-radiological features were determined based on least absolute shrinkage and selection operator (LASSO) logistic regression analysis, and a predictive nomogram model was established by five-fold cross-validation. Receiver operating characteristic (ROC) analyses were conducted, and the areas under the receiver operating characteristic curve (AUCs) of the nomogram model, quantitative CT parameters that were significant in univariate analysis, and pneumonia severity index (PSI) were compared. RESULTS: In comparison with the non-severe group (151 patients), the severe group (45 patients) had a higher PSI (P<0.001). DL-based quantitative CT indicated that the mass of infection (MOICT) and the percentage of infection (POICT) in the whole lung were higher in the severe group (both P<0.001). The nomogram model was based on MOICT and clinical features, including age, cluster of differentiation 4 (CD4)+ T cell count, serum lactate dehydrogenase (LDH), and C-reactive protein (CRP). The AUC values of the model, MOICT, POICT, and PSI scores were 0.900, 0.813, 0.805, and 0.751, respectively. The nomogram model performed significantly better than the other three parameters in predicting severity (P=0.003, P=0.001, and P<0.001, respectively). CONCLUSIONS: Although quantitative CT parameters and the PSI can well predict the severity of COVID-19, the DL-based quantitative CT model is more efficient.

Lung volume reduction and infection localization revealed in Big data CT imaging of COVID-19.

The ongoing worldwide COVID-19 pandemic has become a huge threat to global public health. Using CT image, 3389 COVID-19 patients, 1593 community-acquired pneumonia (CAP) patients, and 1707 nonpneumonia subjects were included to explore the different patterns of lung and lung infection. We found that COVID-19 patients have a significant reduced lung volume with increased density and mass, and the infections tend to present as bilateral lower lobes. The findings provide imaging evidence to improve our understanding of COVID-19.

A clinical pilot study on the safety and efficacy of aerosol inhalation treatment of IFN-κ plus TFF2 in patients with moderate COVID-19.

BACKGROUND: The outbreak of a new coronavirus (SARS-CoV-2) poses a great challenge to global public health. New and effective intervention strategies are urgently needed to combat the disease. METHODS: We conducted an open-label, non-randomized, clinical trial involving moderate COVID-19 patients according to study protocol. Patients were assigned in a 1:2 ratio to receive either aerosol inhalation treatment with IFN-κ and TFF2, every 48 h for three consecutive dosages, in addition to standard treatment (experimental group), or standard treatment alone (control group). The end point was the time to discharge from the hospital. This study is registered with chictr.org.cn, ChiCTR2000030262. FINDINGS: A total of thirty-three eligible COVID-19 patients were enrolled from February 1, 2020 to April 6, 2020, eleven were assigned to the IFN-κ plus TFF2 group, and twenty-two to the control group. Safety and efficacy were evaluated for both groups. No treatment-associated severe adverse effects (SAE) were observed in the group treated with aerosol inhalation of IFN-κ plus TFF2, and no significant differences in the safety evaluations were observed between experimental and control groups. CT imaging was performed in all patients with the median improvement time of 5.0 days (IQR 3.0-9.0) in the experimental group versus 8.5 days (IQR 3.0-17.0) in the control group (p<0.05). In addition, the experimental group had a significant shorten median time in cough relief (4.5 days [IQR 2.0-7.0]) than the control group did (10.0 days [IQR 6.0-21.0])(p<0.005), in viral RNA reversion of 6.0 days (IQR 2.0-13.0) in the experimental group vs 9.5 days (IQR 3.0-23.0) in the control group (p < 0.05), and in the median hospitalization stays of 12.0 days (IQR 7.0-20.0) in the experimental group vs 15.0 days (IQR 10.0-25.0) in the control group (p<0.001), respectively. INTERPRETATION: Aerosol inhalation of IFN-κ plus TFF2 is a safe treatment and is likely to significantly facilitate clinical improvement, including cough relief, CT imaging improvement, and viral RNA reversion, thereby achieves an early release from hospitalization. These data support to explore a scale-up trial with IFN-κ plus TFF2. FUNDING: National Major Project for Control and Prevention of Infectious Disease in China, Shanghai Science and Technology Commission, Shanghai Municipal Health Commission.

Evaluation of antiviral therapies for coronavirus disease 2019 pneumonia in Shanghai, China.

The aim of our study was to evaluate the therapeutic effect of antiviral drugs on coronavirus disease 2019 (COVID-19) pneumonia. Patients confirmed with COVID-19 pneumonia were enrolled and divided into seven groups according to the treatment option. Information including age, sex, and duration from illness onset to admission, clinical manifestations, and laboratory data at admission, and length of hospital stay were evaluated. The chest computed tomography (CT) imaging obtained at admission and after a 5-day treatment cycle were assessed. The clinical symptoms and laboratory tests at discharge were also assessed. At admission, no significant differences were found among the groups, including the duration from illness onset to admission, clinical symptoms, and main laboratory results. No significant differences were found among the groups in terms of the proportion of patients with pneumonia resolution (P = .151) after treatment or the length of hospital stay (P = .116). At discharge, 7 of 184 (4%) patients had a mild cough while their other symptoms had disappeared, and the proportion of patients with abnormal liver function and with increased leukocytes, neutrophils or erythrocyte sedimentation rate among the 184 patients were close to those at admission. According to the results, the inclusion of antiviral drugs in therapeutic regimens based on symptomatic treatment had no significant additional impact on the improvement in COVID-19 patients. In addition, the results of chest CT imaging, clinical manifestations, and laboratory tests at discharge were not completely consistent.

Hypergraph learning for identification of COVID-19 with CT imaging.

The coronavirus disease, named COVID-19, has become the largest global public health crisis since it started in early 2020. CT imaging has been used as a complementary tool to assist early screening, especially for the rapid identification of COVID-19 cases from community acquired pneumonia (CAP) cases. The main challenge in early screening is how to model the confusing cases in the COVID-19 and CAP groups, with very similar clinical manifestations and imaging features. To tackle this challenge, we propose an Uncertainty Vertex-weighted Hypergraph Learning (UVHL) method to identify COVID-19 from CAP using CT images. In particular, multiple types of features (including regional features and radiomics features) are first extracted from CT image for each case. Then, the relationship among different cases is formulated by a hypergraph structure, with each case represented as a vertex in the hypergraph. The uncertainty of each vertex is further computed with an uncertainty score measurement and used as a weight in the hypergraph. Finally, a learning process of the vertex-weighted hypergraph is used to predict whether a new testing case belongs to COVID-19 or not. Experiments on a large multi-center pneumonia dataset, consisting of 2148 COVID-19 cases and 1182 CAP cases from five hospitals, are conducted to evaluate the prediction accuracy of the proposed method. Results demonstrate the effectiveness and robustness of our proposed method on the identification of COVID-19 in comparison to state-of-the-art methods.

Abnormal lung quantification in chest CT images of COVID-19 patients with deep learning and its application to severity prediction.

OBJECTIVE: Computed tomography (CT) provides rich diagnosis and severity information of COVID-19 in clinical practice. However, there is no computerized tool to automatically delineate COVID-19 infection regions in chest CT scans for quantitative assessment in advanced applications such as severity prediction. The aim of this study was to develop a deep learning (DL)-based method for automatic segmentation and quantification of infection regions as well as the entire lungs from chest CT scans. METHODS: The DL-based segmentation method employs the "VB-Net" neural network to segment COVID-19 infection regions in CT scans. The developed DL-based segmentation system is trained by CT scans from 249 COVID-19 patients, and further validated by CT scans from other 300 COVID-19 patients. To accelerate the manual delineation of CT scans for training, a human-involved-model-iterations (HIMI) strategy is also adopted to assist radiologists to refine automatic annotation of each training case. To evaluate the performance of the DL-based segmentation system, three metrics, that is, Dice similarity coefficient, the differences of volume, and percentage of infection (POI), are calculated between automatic and manual segmentations on the validation set. Then, a clinical study on severity prediction is reported based on the quantitative infection assessment. RESULTS: The proposed DL-based segmentation system yielded Dice similarity coefficients of 91.6% ± 10.0% between automatic and manual segmentations, and a mean POI estimation error of 0.3% for the whole lung on the validation dataset. Moreover, compared with the cases with fully manual delineation that often takes hours, the proposed HIMI training strategy can dramatically reduce the delineation time to 4 min after three iterations of model updating. Besides, the best accuracy of severity prediction was 73.4% ± 1.3% when the mass of infection (MOI) of multiple lung lobes and bronchopulmonary segments were used as features for severity prediction, indicating the potential clinical application of our quantification technique on severity prediction. CONCLUSIONS: A DL-based segmentation system has been developed to automatically segment and quantify infection regions in CT scans of COVID-19 patients. Quantitative evaluation indicated high accuracy in automatic infection delineation and severity prediction.

Preliminary investigation of relationship between clinical indicators and CT manifestation patterns of COVID-19 pneumonia improvement.

BACKGROUND: To retrospectively evaluate several clinical indicators related to the improvement of COVID-19 pneumonia on CT. METHODS: A total of 62 patients with COVID-19 pneumonia were included. The CT scores based on lesion patterns and distributions in serial CT were investigated. The improvement and deterioration of pneumonia was assessed based on the changes of CT scores. Grouped by using the temperature, serum lymphocytes and high sensitivity CRP (hs-CRP) on admission respectively, the CT scores on admission, at peak time and at discharge were evaluated. Correlation analysis was carried out between the time to onset of pneumonia resolution on CT images and the recovery time of temperature, negative conversion of viral nucleic acid, serum lymphocytes and hs-CRP. RESULTS: The CT scores of the fever group and lymphopenia group were significantly higher than those of normal group on admission, at peak time and at discharge; and the CT scores of normal hs-CRP group were significantly lower than those of the elevated hs-CRP group at peak time and at discharge (P all<0.05). The time to onset of pneumonia resolution on CT image was moderately correlated with negative conversion duration of viral nucleic acid (r =0.501, P<0.05) and the recovery time of hs-CPR (r =0.496, P<0.05). CONCLUSIONS: COVID-19 pneumonia patients with no fever, normal lymphocytes and hs-CRP had mild lesions on admission, and presented with more absorption and fewer pulmonary lesions on discharge. The negative conversion duration of viral nucleic acid and the recovery time of hs-CPR may be the indicator of the pneumonia resolution.