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.

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.

Background: To evaluate the diagnostic efficacy of Densely Connected Convolutional Networks (DenseNet) for detection of COVID-19 features on high resolution computed tomography (HRCT). Methods: The Ethic Committee of our institution approved the protocol of this study and waived the requirement for patient informed consent. Two hundreds and ninety-five patients were enrolled in this study (healthy person: 149; COVID-19 patients: 146), which were divided into three separate non-overlapping cohorts (training set, n=135, healthy person, n=69, patients, n=66; validation set, n=20, healthy person, n=10, patients, n=10; test set, n=140, healthy person, n=70, patients, n=70). The DenseNet was trained and tested to classify the images as having manifestation of COVID-19 or as healthy. A radiologist also blindly evaluated all the test images and rechecked the misdiagnosed cases by DenseNet. Receiver operating characteristic curves (ROC) and areas under the curve (AUCs) were used to assess the model performance. The sensitivity, specificity and accuracy of DenseNet model and radiologist were also calculated. Results: The DenseNet algorithm model yielded an AUC of 0.99 (95% CI: 0.958–1.0) in the validation set and 0.98 (95% CI: 0.972–0.995) in the test set. The threshold value was selected as 0.8, while for validation and test sets, the accuracies were 95% and 92%, the sensitivities were 100% and 97%, the specificities were 90% and 87%, and the F1 values were 95% and 93%, respectively. The sensitivity of radiologist was 94%, the specificity was 96%, while the accuracy was 95%. Conclusions: Deep learning (DL) with DenseNet can accurately classify COVID-19 on HRCT with an AUC of 0.98, which can reduce the miss diagnosis rate (combined with radiologists’ evaluation) and radiologists’ workload.

To counter the outbreak of COVID-19, the accurate diagnosis of suspected cases plays a crucial role in timely quarantine, medical treatment, and preventing the spread of the pandemic. Considering the limited training cases and resources (e.g, time and budget), we propose a Multi-task Multi-slice Deep Learning System ( $M^3$ Lung-Sys) for multi-class lung pneumonia screening from CT imaging, which only consists of two 2D CNN networks, i.e., slice- and patient-level classification networks. The former aims to seek the feature representations from abundant CT slices instead of limited CT volumes, and for the overall pneumonia screening, the latter one could recover the temporal information by feature refinement and aggregation between different slices. In addition to distinguish COVID-19 from Healthy, H1N1, and CAP cases, our $M^3$ Lung-Sys also be able to locate the areas of relevant lesions, without any pixel-level annotation. To further demonstrate the effectiveness of our model, we conduct extensive experiments on a chest CT imaging dataset with a total of 734 patients (251 healthy people, 245 COVID-19 patients, 105 H1N1 patients, and 133 CAP patients). The quantitative results with plenty of metrics indicate the superiority of our proposed model on both slice- and patient-level classification tasks. More importantly, the generated lesion location maps make our system interpretable and more valuable to clinicians.

To evaluate the clinical features and radiomics nomograms of tumors and peritumoral regions for the preoperative prediction of the presence of spread through air spaces (STAS) in patients with lung adenocarcinoma. A total of 107 STAS-positive lung adenocarcinomas were selected and matched to 105 STAS-negative lung adenocarcinomas. Thin-slice CT imaging annotation and region of interest (ROI) segmentation were performed with semi-automatic in-house software. Radiomics features were extracted from all nodules and incremental distances of 5, 10, and 15 mm outside the lesion segmentation. A radiomics nomogram was established with multivariable logistic regression based on clinical and radiomics features. The maximum diameter of the solid component and mediastinal lymphadenectasis were selected as independent predictors of STAS. The radiomics nomogram of lung nodules showed especially good prediction in the training set [area under the curve (AUC), 0.98; 95% confidence interval (CI), 0.97–1.00] and test set (AUC, 0.99; 95% CI, 0.97–1.00). The radiomics nomogram of peritumoral regions also showed good prediction, but the fitting degrees of the calibration curves were not good. Our study may provide guidance for surgical methods in patients with lung adenocarcinoma.