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.

Clinical Features and Chest CT Manifestations of Coronavirus Disease 2019 (COVID-19) in a Single-Center Study in Shanghai, China.

OBJECTIVE. Confronting the new coronavirus infection known as coronavirus disease 2019 (COVID-19) is challenging and requires excluding patients with suspected COVID-19 who actually have other diseases. The purpose of this study was to assess the clinical features and CT manifestations of COVID-19 by comparing patients with COVID-19 pneumonia with patients with non-COVID-19 pneumonia who presented at a fever observation department in Shanghai, China. MATERIALS AND METHODS. Patients were retrospectively enrolled in the study from January 19 through February 6, 2020. All patients underwent real-time reverse transcription-polymerase chain reaction (RT-PCR) testing. RESULTS. Eleven patients had RT-PCR test results that were positive for severe acute respiratory syndrome coronavirus 2, whereas 22 patients had negative results. No statistical difference in clinical features was observed (p > 0.05), with the exception of leukocyte and platelet counts (p < 0.05). The mean (± SD) interval between onset of symptoms and admission to the fever observation department was 4.40 ± 2.00 and 5.52 ± 4.00 days for patients with positive and negative RT-PCR test results, respectively. The frequency of opacifications in patients with positive results and patients with negative results, respectively, was as follows: ground-glass opacities (GGOs), 100.0% versus 90.9%; mixed GGO, 63.6% versus 72.7%; and consolidation, 54.5% versus 77.3%. In patients with positive RT-PCR results, GGOs were the most commonly observed opacification (seen in 100.0% of patients) and were predominantly located in the peripheral zone (100.0% of patients), compared with patients with negative results (31.8%) (p = 0.05). The median number of affected lung lobes and segments was higher in patients with positive RT-PCR results than in those with negative RT-PCR results (five vs 3.5 affected lobes and 15 vs nine affected segments; p < 0.05). Although the air bronchogram reticular pattern was more frequently seen in patients with positive results, centrilobular nodules were less frequently seen in patients with positive results. CONCLUSION. At the point during the COVID-19 outbreak when this study was performed, imaging patterns of multifocal, peripheral, pure GGO, mixed GGO, or consolidation with slight predominance in the lower lung and findings of more extensive GGO than consolidation on chest CT scans obtained during the first week of illness were considered findings highly suspicious of COVID-19.

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.

Deep learning for differentiating novel coronavirus pneumonia and influenza pneumonia.

BACKGROUND: Chest computed tomography (CT) has been found to have high sensitivity in diagnosing novel coronavirus pneumonia (NCP) at the early stage, giving it an advantage over nucleic acid detection during the current pandemic. In this study, we aimed to develop and validate an integrated deep learning framework on chest CT images for the automatic detection of NCP, focusing particularly on differentiating NCP from influenza pneumonia (IP). METHODS: A total of 148 confirmed NCP patients [80 male; median age, 51.5 years; interquartile range (IQR), 42.5-63.0 years] treated in 4 NCP designated hospitals between January 11, 2020 and February 23, 2020 were retrospectively enrolled as a training cohort, along with 194 confirmed IP patients (112 males; median age, 65.0 years; IQR, 55.0-78.0 years) treated in 5 hospitals from May 2015 to February 2020. An external validation set comprising 57 NCP patients and 50 IP patients from 8 hospitals was also enrolled. Two deep learning schemes (the Trinary scheme and the Plain scheme) were developed and compared using receiver operating characteristic (ROC) curves. RESULTS: Of the NCP lesions, 96.6% were >1 cm and 76.8% were of a density <-500 Hu, indicating them to have less consolidation than IP lesions, which had nodules ranging from 5-10 mm. The Trinary scheme accurately distinguished NCP from IP lesions, with an area under the curve (AUC) of 0.93. For patient-level classification in the external validation set, the Trinary scheme outperformed the Plain scheme (AUC: 0.87 vs. 0.71) and achieved human specialist-level performance. CONCLUSIONS: Our study has potentially provided an accurate tool on chest CT for early diagnosis of NCP with high transferability and showed high efficiency in differentiating between NCP and IP; these findings could help to reduce misdiagnosis and contain the pandemic transmission.

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.

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.

COVID-19 and early-stage lung cancer both featuring ground-glass opacities: a propensity score-matched study.

BACKGROUND: Radiological manifestations of coronavirus disease 2019 (COVID-19) featured ground-glass opacities (GGOs), especially in the early stage, which might create confusion in differential diagnosis with early lung cancer. We aimed to specify the radiological characteristics of COVID-19 and early lung cancer and to unveil the discrepancy between them. METHODS: One hundred and fifty-seven COVID-19 patients and 374 early lung cancer patients from four hospitals in China were retrospectively enrolled. Epidemiological, clinical, radiological, and pathological characteristics were compared between the two groups using propensity score-matched (PSM) analysis. RESULTS: COVID-19 patients had more distinct symptoms, tended to be younger (P<0.0001), male (P<0.0001), and had a higher body mass index (P=0.014). After 1:1 PSM, 121 matched pairs were identified. Regarding radiological characteristics, patients with a single lesion accounted for 17% in COVID-19 and 89% in lung cancer (P<0.0001). Most lesions were peripherally found in both groups. Lesions in COVID-19 involved more lobes (median 3.5 vs. 1; P<0.0001) and segments (median 6 vs. 1; P<0.0001) and tended to have multiple types (67%) with patchy form (54%). Early lung cancer was more likely to have a single type (92%) with oval form (66%). Also, COVID-19 and early lung cancer either had some distinctive features on computed tomography (CT) images. CONCLUSIONS: Both COVID-19 and early lung cancers showed GGOs, with similar but independent features. The imaging characteristics should be fully understood and combined with epidemiological history, pathogen detection, laboratory tests, short-term CT reexamination, and pathological results to aid differential diagnosis.

Dual-Sampling Attention Network for Diagnosis of COVID-19 From Community Acquired Pneumonia.

The coronavirus disease (COVID-19) is rapidly spreading all over the world, and has infected more than 1,436,000 people in more than 200 countries and territories as of April 9, 2020. Detecting COVID-19 at early stage is essential to deliver proper healthcare to the patients and also to protect the uninfected population. To this end, we develop a dual-sampling attention network to automatically diagnose COVID-19 from the community acquired pneumonia (CAP) in chest computed tomography (CT). In particular, we propose a novel online attention module with a 3D convolutional network (CNN) to focus on the infection regions in lungs when making decisions of diagnoses. Note that there exists imbalanced distribution of the sizes of the infection regions between COVID-19 and CAP, partially due to fast progress of COVID-19 after symptom onset. Therefore, we develop a dual-sampling strategy to mitigate the imbalanced learning. Our method is evaluated (to our best knowledge) upon the largest multi-center CT data for COVID-19 from 8 hospitals. In the training-validation stage, we collect 2186 CT scans from 1588 patients for a 5-fold cross-validation. In the testing stage, we employ another independent large-scale testing dataset including 2796 CT scans from 2057 patients. Results show that our algorithm can identify the COVID-19 images with the area under the receiver operating characteristic curve (AUC) value of 0.944, accuracy of 87.5%, sensitivity of 86.9%, specificity of 90.1%, and F1-score of 82.0%. With this performance, the proposed algorithm could potentially aid radiologists with COVID-19 diagnosis from CAP, especially in the early stage of the COVID-19 outbreak.

COVID-19 patients with progressive and non-progressive CT manifestations.

OBJECTIVE: To explore the clinical and radiological characteristics of COVID-19 patients with progressive and non-progressive CT manifestations. METHODS: 160 patients with COVID-19 were retrospectively included from Wenzhou and Wuhan, China. CT features including lesion position, attenuation, form and total scores (0-4) at the segment level were evaluated. Other images signs were also assessed. 65 patients were classified as progressive (group 1) and 95 as non-progressive CT (group 2) groups according to score changes between the initial and second CT. RESULTS: Symptoms onset-initial CT interval time in group 1 [5 (2, 7) days] were significantly shorter than that in group 2 [10 (8, 14) days] (P < 0.001). Group 2 had higher radiological scores, with more lobes and segments affected, and other CT signs (P < 0.05). In group 1, radiological scores, the number of lobes and segments affected as well as lesions in both peripheral and central distribution, mixed ground grass opacity and consolidation density, and patchy form increased in the second CT (P < 0.05). More reticular pattern, subpleural linear opacity and bronchial dilatation were also found (P < 0.05). CONCLUSION: Typically radiological characteristics of progressive CT patients could potentially help to predict changes and increase understanding of the natural history of COVID-19.

A predictive model and scoring system combining clinical and CT characteristics for the diagnosis of COVID-19.

OBJECTIVES: To develop a predictive model and scoring system to enhance the diagnostic efficiency for coronavirus disease 2019 (COVID-19). METHODS: From January 19 to February 6, 2020, 88 confirmed COVID-19 patients presenting with pneumonia and 80 non-COVID-19 patients suffering from pneumonia of other origins were retrospectively enrolled. Clinical data and laboratory results were collected. CT features and scores were evaluated at the segmental level according to the lesions' position, attenuation, and form. Scores were calculated based on the size of the pneumonia lesion, which graded at the range of 1 to 4. Air bronchogram, tree-in-bud sign, crazy-paving pattern, subpleural curvilinear line, bronchiectasis, air space, pleural effusion, and mediastinal and/or hilar lymphadenopathy were also evaluated. RESULTS: Multivariate logistic regression analysis showed that history of exposure (ß = 3.095, odds ratio (OR) = 22.088), leukocyte count (ß = - 1.495, OR = 0.224), number of segments with peripheral lesions (ß = 1.604, OR = 1.604), and crazy-paving pattern (ß = 2.836, OR = 2.836) were used for establishing the predictive model to identify COVID-19-positive patients (p < 0.05). In this model, values of area under curve (AUC) in the training and testing groups were 0.910 and 0.914, respectively (p < 0.001). A predicted score for COVID-19 (PSC-19) was calculated based on the predictive model by the following formula: PSC-19 = 2 × history of exposure (0-1 point) - 1 × leukocyte count (0-2 points) + 1 × peripheral lesions (0-1 point) + 2 × crazy-paving pattern (0-1 point), with an optimal cutoff point of 1 (sensitivity, 88.5%; specificity, 91.7%). CONCLUSIONS: Our predictive model and PSC-19 can be applied for identification of COVID-19-positive cases, assisting physicians and radiologists until receiving the results of reverse transcription-polymerase chain reaction (RT-PCR) tests. KEY POINTS: • Prediction of RT-PCR positivity is crucial for fast diagnosis of patients suspected of having coronavirus disease 2019 (COVID-19). • Typical CT manifestations are advantageous for diagnosing COVID-19 and differentiation of COVID-19 from other types of pneumonia. • A predictive model and scoring system combining both clinical and CT features were herein developed to enable high diagnostic efficiency for COVID-19.

Diagnosis of Coronavirus Disease 2019 (COVID-19) With Structured Latent Multi-View Representation Learning.

Recently, the outbreak of Coronavirus Disease 2019 (COVID-19) has spread rapidly across the world. Due to the large number of infected patients and heavy labor for doctors, computer-aided diagnosis with machine learning algorithm is urgently needed, and could largely reduce the efforts of clinicians and accelerate the diagnosis process. Chest computed tomography (CT) has been recognized as an informative tool for diagnosis of the disease. In this study, we propose to conduct the diagnosis of COVID-19 with a series of features extracted from CT images. To fully explore multiple features describing CT images from different views, a unified latent representation is learned which can completely encode information from different aspects of features and is endowed with promising class structure for separability. Specifically, the completeness is guaranteed with a group of backward neural networks (each for one type of features), while by using class labels the representation is enforced to be compact within COVID-19/community-acquired pneumonia (CAP) and also a large margin is guaranteed between different types of pneumonia. In this way, our model can well avoid overfitting compared to the case of directly projecting high-dimensional features into classes. Extensive experimental results show that the proposed method outperforms all comparison methods, and rather stable performances are observed when varying the number of training data.

Infection Control for CT Equipment and Radiographers' Personal Protection During the Coronavirus Disease (COVID-19) Outbreak in China.

OBJECTIVE. Because CT plays an important role in diagnosis, isolation, treatment, and effective evaluation of coronavirus disease (COVID-19), infection prevention and control management of CT examination rooms is important. CONCLUSION. We describe modifications to the CT examination process, strict disinfection of examination rooms, arrangement of waiting areas, and efforts to increase radiographers' awareness of personal protection made at our institution during the COVID-19 outbreak. In addition, we discuss the potential of using artificial intelligence in imaging patients with contagious diseases.

Quantitative computed tomography of the coronavirus disease 2019 (COVID-19) pneumonia.

OBJECTIVE: To quantify coronavirus diseases 2019 (COVID-19) pneumonia and to explore whether quantitative computer tomography (CT) could be used to assess severity on admission. MATERIALS AND METHODS: From January 17 to February 9, 2020, 38 hospitalized patients with COVID-19 pneumonia were consecutively enrolled in our hospitals. All clinical data and the chest CT on admission were retrospectively reviewed and analyzed. Firstly, a quantitative method based on multi-scale convolutional neural networks was used to assess the infected lung segments and this was compared with the semi-quantitative method. Secondly, the quantitative method was tested with laboratory results and the pneumonia severity index (PSI) by correlation analyses. Thirdly, both quantitative and semi-quantitative parameters between patients with different PSI were compared. RESULTS: Thirty cases were finally enrolled: 16 (53.33%) of them were male, and the mean age was 48 years old. The interval from onset symptoms to first chest CT scan was 8 days. The proportion of ground glass opacity (GGO), consolidation and the total lesion based on the quantitative method was positively correlated with the semi-quantitative CT score (P < 0.001 for all; rs = 0.88, 0.87, 0.90), CRP (P = 0.0278, 0.0168, 0.0078; rs = 0.40, 0.43, 0.48) and ESR (P = 0.0296, 0.0408, 0.0048; rs = 0.46, 0.44, 0.58), respectively, and was negatively correlated with the lymphocyte count (P = 0.0222, 0.0024, 0.0068; rs = -0.42, -0.53, -0.48). There was a positive correlation trend between the proportion of total infection and the pneumonia severity index (P = 0.0994; rs = 0.30) and a tendency that patients with severe COVID-19 pneumonia had higher percentage of consolidation and total infection (P = 0.0903, 0.0989). CONCLUSIONS: Quantitative CT may have potential in assessing the severity of COVID-19 pneumonia on admission.

Clinical characteristics and imaging manifestations of the 2019 novel coronavirus disease (COVID-19):A multi-center study in Wenzhou city, Zhejiang, China.

BACKGROUND: Little is known about COVID-19 outside Hubei. The aim of this paper was to describe the clinical characteristics and imaging manifestations of hospitalized patients with confirmed COVID-19 infection in Wenzhou, Zhejiang, China. METHODS: In this retrospective cohort study, 149 RT-PCR confirmed positive patients were consecutively enrolled from January 17th to February 10th, 2020 in three tertiary hospitals of Wenzhou. Outcomes were followed up until Feb 15th, 2020. FINDINGS: A total of 85 patients had Hubei travel/residence history, while another 49 had contact with people from Hubei and 15 had no traceable exposure history to Hubei. Fever, cough and expectoration were the most common symptoms, 14 patients had decreased oxygen saturation, 33 had leukopenia, 53 had lymphopenia, and 82 had elevated C-reactive protein. On chest computed tomography (CT), lung segments 6 and 10 were mostly involved. A total of 287 segments presented ground glass opacity, 637 presented mixed opacity and 170 presented consolidation. Lesions were more localized in the peripheral lung with a patchy form. No significant difference was found between patients with or without Hubei exposure history. Seventeen patients had normal CT on admission of these, 12 had negative findings even10 days later. INTERPRETATION: Most patients presented with a mild infection in our study. The imaging pattern of multifocal peripheral ground glass or mixed opacity with predominance in the lower lung is highly suspicious of COVID-19 in the first week of disease onset. Nevetheless, some patients can present with a normal chest finding despite testing positive for COVID-19. FUNDING: We did not receive any fundings.