key: cord-0695953-ee0u795n
authors: Lessmann, Nikolas; Sánchez, Clara I.; Beenen, Ludo; Boulogne, Luuk H.; Brink, Monique; Calli, Erdi; Charbonnier, Jean-Paul; Dofferhoff, Ton; van Everdingen, Wouter M.; Gerke, Paul K.; Geurts, Bram; Gietema, Hester A.; Groeneveld, Miriam; van Harten, Louis; Hendrix, Nils; Hendrix, Ward; Huisman, Henkjan J.; Išgum, Ivana; Jacobs, Colin; Kluge, Ruben; Kok, Michel; Krdzalic, Jasenko; Lassen-Schmidt, Bianca; van Leeuwen, Kicky; Meakin, James; Overkamp, Mike; van Rees Vellinga, Tjalco; van Rikxoort, Eva M.; Samperna, Riccardo; Schaefer-Prokop, Cornelia; Schalekamp, Steven; Scholten, Ernst Th.; Sital, Cheryl; Stöger, Lauran; Teuwen, Jonas; Vaidhya Venkadesh, Kiran; de Vente, Coen; Vermaat, Marieke; Xie, Weiyi; de Wilde, Bram; Prokop, Mathias; van Ginneken, Bram
title: Automated Assessment of CO-RADS and Chest CT Severity Scores in Patients with Suspected COVID-19 Using Artificial Intelligence
date: 2020-07-30
journal: Radiology
DOI: 10.1148/radiol.2020202439
sha: 77d2998052da2dce4efd48dbc009b20cc81e674e
doc_id: 695953
cord_uid: ee0u795n

BACKGROUND: The COVID-19 pandemic has spread across the globe with alarming speed, morbidity and mortality. Immediate triage of suspected patients with chest infections caused by COVID-19 using chest CT may be of assistance when results from definitive viral testing are delayed. PURPOSE: To develop and validate an artificial intelligence (AI) system to score the likelihood and extent of pulmonary COVID-19 on chest CT scans using the CO-RADS and CT severity scoring systems. MATERIALS AND METHODS: CORADS-AI consists of three deep learning algorithms that automatically segment the five pulmonary lobes, assign a CO-RADS score for the suspicion of COVID-19 and assign a CT severity score for the degree of parenchymal involvement per lobe. This study retrospectively included patients who received an unenhanced chest CT scan due to clinical suspicion of COVID-19 at two medical centers. The system was trained, validated, and tested with data from one of the centers. Data from the second center served as an external test set. Diagnostic performance and agreement with scores assigned by eight independent observers were measured using receiver operating characteristic (ROC) analysis, linearly-weighted kappa and classification accuracy. RESULTS: 105 patients (62 ± 16 years, 61 men) and 262 patients (64 ± 16 years, 154 men) were evaluated in the internal and the external test set, respectively. The system discriminated between COVID-19 positive and negative patients with areas under the ROC curve of 0.95 (95% CI: 0.91-0.98) and 0.88 (95% CI: 0.84-0.93). Agreement with the eight human observers was moderate to substantial with a mean linearly-weighted kappa of 0.60 ± 0.01 for CO-RADS scores and 0.54 ± 0.01 for CT severity scores. CONCLUSION: CORADS-AI correctly identified COVID-19 positive patients with high diagnostic performance from chest CT exams, assigned standardized CO-RADS and CT severity scores in good agreement with eight independent observers and generalized well to external data.

During the COVID-19 pandemic, chest CT imaging has been found useful for diagnosis and follow-up of COVID-19 patients (1) . Standardized CT scoring systems, such as CO-RADS (2) , have been advocated to improve the communication between radiologists and other healthcare providers by translating radiological findings into standardized scores (2) (3) (4) . The CO-RADS scoring system assigns scores from 1 to 5 that increase with the level of suspicion of COVID-19 based on features seen on an unenhanced chest CT. Additionally, beyond assessing the likelihood of COVID-19, this and similar scoring systems also report on the extent of parenchymal involvement by assigning a CT severity score (CTSS) to patients with high suspicion of COVID-19 (5, 6) . Such standardized scoring systems enable fast and consistent clinical decision making, especially valuable in these enduring times of crisis (2, 3) .

Artificial Intelligence (AI) using deep learning has been advocated for automated reading of COVID-19 CT scans, including diagnosing COVID-19 (7) (8) (9) (10) (11) (12) (13) (14) and quantifying parenchymal involvement (15) (16) (17) (18) . While these studies illustrate the potential of AI algorithms, their practical value is debatable (19) . Without adhering to radiological reporting standards, it is doubtful whether these algorithms provide any real benefit in addition to or instead of manual reading, limiting their adoption in daily practice. Also, algorithms that follow a standardized scoring system need validation to confirm that they assign scores in a similar way to radiologists and can identify COVID-19 positive patients with similar or even better performance.

The purpose of this study was to develop and validate an AI algorithm (CORADS-AI) that automatically scores chest CT scans of patients with suspected COVID-19 according to the CO-RADS and CT severity score systems. We compared CORADS-AI with readings of eight observers and to clinical assessment of the patients including RT-PCR testing.

Medical ethics committee approval was obtained prior to the study. The need for written informed consent was waived and data was collected and anonymized in accordance with local guidelines.

We retrospectively included consecutive patients presenting at the emergency wards of an academic center and a large teaching hospital in the Netherlands in March and April 2020 and underwent chest CT imaging for clinical suspicion of moderate to severe COVID-19.

Criteria for CT were symptoms of lower respiratory tract infection including cough, clinically relevant dyspnea requiring hospital admission and fever with anosmia. CO-RADS and CT severity scores were reported as part of routine interpretation of the scans. Patients without scores in their radiological report were excluded. Additionally, patients from the teaching hospital were excluded if they were known to have COVID-19 (RT-PCR proven) prior to imaging or if RT-PCR test results were missing. The CT scanners were from different manufacturers; the protocols are described in Appendix E1.

Since RT-PCR testing may initially produce false negative results, we considered patients positive for COVID-19 if they either had a positive RT-PCR or if their clinical presentation made COVID-19 probable. Criteria were the lack of an alternative diagnosis explaining the symptoms plus intensive care admission due to respiratory failure, the need for high oxygen delivery, or unexplained death during admission.

The data of 476 patients from the academic center was used for model development, 520

CT scans in total. CO-RADS scores were extracted from the radiological reports. Scans scored CO-RADS 6, which signifies a positive RT-PCR prior to imaging, were rescored I n P r e s s independently by a chest radiologist with more than 30 years of experience (E.Th.S.) who assigned CO-RADS 1-5 to simulate unknown RT-PCR status (n=52). This observer was blinded to the original radiological report and all non-imaging data except for age and sex.

A prior observer study assessing CO-RADS (2) reported on the remaining 105 patients included at the academic center. The data of these patients was set aside to verify the performance of the AI model. For each patient at least one RT-PCR was available within five days after CT acquisition. The earliest available scan of each patient was scored independently following the CO-RADS classification by seven chest radiologists and one radiology resident (B.G., J.K., L.F.B., M.P., H.A.G., J.L.S., C.M.S-P., T.R.V.) using a dedicated browser-based workstation (CIRRUS 1 ). Any available later scans from these 105 patients were not used in this study. The observers were familiar with the CO-RADS and CT severity scoring systems from interpreting at least 30 scans. Four of them had <5 years of experience in reading chest CTs, the others up to 27 years. All observers were blinded to the RT-PCR test results and could therefore not assign CO-RADS 6. Instead, they assigned CO-RADS 1-5 based on their suspicion for pulmonary involvement of COVID-19. Also, they semi-quantitatively described the extent of parenchymal involvement per lobe using a predefined CT severity score on a 6-point scale (0=0%, 1=0%-5%, 2=5%-25%, 3=25%-50%, 4=50%-75%, 5=>75%) (5) .

The data of all patients included at the teaching hospital was set aside to verify the performance of the AI model on an external cohort. All these patients underwent RT-PCR testing on the same day as CT imaging. The CO-RADS score and the total CT severity 1 Available at https://grand-challenge.org/reader-studies/ I n P r e s s score (the sum of the scores per lobe as described above) were extracted from the radiological report of the earliest available scan of each patient.

Reference delineations of lung and lobar boundaries were automatically obtained for a convenience sample of 400 scans from the training and development set and for all 105 scans in the internal test set using commercial software (LungQ v1.1.1, Thirona, Nijmegen, The Netherlands), followed by manual correction. Reference delineations of areas with ground-glass opacities, consolidation, and mixed patterns were obtained for a convenience sample of 108 scans from the training and development set as follows. Regions of parenchymal lung tissue with increased attenuation were identified with thresholding and morphological operations. Vessels and airways were removed using automatic methods.

Lesion candidates in lobes not affected by COVID-19 following the radiological report were removed. The remaining lesion candidates were reviewed by a certified image analyst with at least one year of experience in correcting segmentations of pulmonary structures on chest CT exams. The analyst corrected the delineations and added and removed lesions as needed.

CT scans were scored fully automatically using three successively applied deep learning algorithms. These performed (1) pulmonary lobe segmentation and labeling, (2) lesion segmentation and CT severity score prediction, and (3) CO-RADS score prediction.

For lobe segmentation and labeling, we used a relational two-stage U-Net architecture specifically developed for robust pulmonary lobe segmentation (20) . The model was pretrained on 4000 chest CT scans from the COPDGene study (21) and fine-tuned with 400 scans from the present study.

For CT severity score prediction, we trained a 3D U-net using the nnU-Net framework (22) in a cross-validated fashion with 108 scans and corresponding reference delineations to segment ground-glass opacities and consolidation in the lungs. The CT severity score was derived from the segmentation results by computing the percentage of affected parenchymal tissue per lobe.

For CO-RADS score prediction, we used the 3D-inflated Inception architecture (23, 24) , a 3D extension of the state-of-the-art Inception image classification architecture (25) . The model was pre-trained on the ImageNet (26) and Kinetics (27) data sets and trained with 368 CT scans from our present study to predict the corresponding CO-RADS score. The remaining scans from the training and development set were used to monitor the performance during training. Input to the model was the CT image together with areas of abnormal parenchymal lung tissue detected by the severity scoring algorithm.

Further details about the methods are provided in Appendix E2. The algorithm is freely accessible online 2 .

Lobe segmentation was evaluated using the average Dice coefficient per lobe in the internal test set. Diagnostic performance of the automated CO-RADS scoring algorithm was evaluated using receiver operating characteristic curves (ROC) and the area under the ROC curve (AUC). Youden's index was used to determine the optimal threshold. Non-parametric bootstrapping with 1000 iterations was used to calculate 95% confidence intervals (95% CI).

To quantify agreement, linearly-weighted kappa and classification accuracy were determined by comparing the predicted CO-RADS and CT severity scores to the median of all 2 https://grand-challenge.org/algorithms/corads-ai/ I n P r e s s combinations of seven observers. The agreement of the AI system in terms of the linearlyweighted kappa was compared with the agreement of the left-out observer using Monte-Carlo permutation tests. CT severity scores were evaluated only for patients with a diagnosis of COVID-19. We tested for differences in demographic characteristics between training and test cohorts using t-tests (age) and chi-squared tests (sex), and for differences in sensitivity of observers and algorithm at the specificity of the observers using McNemar tests. The significance level was .05. Analyses were performed with statistical software (R 3.6.2) and 

A total of 581 and 262 consecutive patients were included at the academic center and the teaching hospital, respectively. Training and development set comprised 520 scans of 476 patients from the academic center, the internal test set comprised 105 scans of the remaining 105 patients. The external test set comprised 262 scans of 262 patients from the teaching hospital. Six patients were excluded due to CO-RADS scores missing from their radiological reports ( Figure 1 ). Patient characteristics for training and test sets are given in Table 1 .

There were 58 patients with a clinical diagnosis of COVID-19 among the 105 patients in the internal test set (55%) and 179 among the 262 patients in the external test set (68%). Of these patients, 53/58 (91%) and 145/179 (81%) had a positive RT-PCR while the remaining positive patients had one or multiple negative RT-PCR tests but were diagnosed with COVID-19 based on their clinical presentation. Table 2 

Reference delineations of lung and lobar boundaries were available for 104 of the 105 scans in the internal test set. In one image, the lobar boundaries could not be identified due to severe emphysema and the presence of an open window thoracostomy after a Clagett procedure in the right lung. In the remaining 104 images, the average Dice scores of the automatic lobe segmentations were 95.2% ± 2.0% for the left upper lobes, 92.4% ± 10.1%

for the left lower lobes, 95.2% ± 3.1% for the right upper lobes, 92.2% ± 10.7% for the right middle lobes and 94.7% ± 3.7% for the right lower lobes.

In the internal test set, the algorithm distinguished between negative and positive COVID-19 patients with an AUC of 0.95 (95% CI: 0.91-0.98) based on the CO-RADS 5 probability that the algorithm predicted. At the optimal threshold, the sensitivity of the algorithm was 85.7% (95% CI: 73.1-98.2) and the specificity was 89.8% (95% CI: 79.6-100). In the external test set, the AUC was 0.88 (95% CI: 0.84-0.93) and sensitivity and specificity at the optimal threshold were 82% (95% CI: 69.7-94.3) and 80.5% (95% CI: 67.9-93.1), respectively. The corresponding ROC curves are shown in Figure 2 together with the operating points of the eight observers for the internal test set, and with the operating points for the routinely reported CO-RADS scores for the external test set. In the internal test set, the mean (± standard deviation) sensitivity of the eight observers was 61.4% (± 7.9%) at a mean specificity of 99.7% (± 0.7%) based on patients that they scored CO-RADS 5. In the external test set, the CO-RADS scores reported as part of clinical routine corresponded to a sensitivity of 134 of 179 (74.9%) and a specificity of 74 of 83 (89.2%). The sensitivities and specificities of the observers for each operating point and the sensitivities of the AI algorithm I n P r e s s at the same specificities are given in Table 3 . There was enough evidence for significantly better sensitivity of the observer for only 3 of the tested 36 operating points (8.3%) of all observers combined.

When compared with the median CO-RADS score of all combinations of seven of the eight readers of the internal test set, the automatically assigned CO-RADS score was in absolute agreement in 54.8% (460 of 8x105=840) of the patients and within one category in 80.5% There was moderate to substantial agreement between AI-predicted CO-RADS scores and the observers according to the linearly-weighted kappa (Table 4) . For the internal test set, the mean (± standard deviation) kappa was 0.60 ± 0.01 for the AI system and 0.79 ± 0.04 for the left-out observer (p<0.001 for all observers). For the external test set, kappa was 0.69 (95% CI: 0.63-0.75) for the AI system.

Since the automatic prediction is based on a segmentation of the lobes and abnormal regions in the lung, the algorithm outputs the percentage of affected parenchymal tissue rather than just the categorical severity score. There was moderate agreement between AI-predicted severity scores and the observers according to the linearly-weighted kappa ( Table 4 ). For the internal test set, the mean (± standard deviation) kappa was 0.54 ± 0.01 for the AI system and 0.77 ± 0.03 for the left-out 

AI might be helpful in interpreting CT scans of patients with high suspicion of COVID-19, especially when it produces standardized output that radiologists and other healthcare providers are familiar with. In this study, we evaluated the performance of an AI system for automated scoring of chest CT scans of patients suspected of COVID-19 based on the CO-RADS and CT severity score classifications. This system identified COVID-19 patients with high diagnostic performance, achieving an AUC of 0.95 on the test set with similar sensitivity and specificity as the eight observers, and 0.88 on the external test set. The automated CO-RADS was in good agreement with the observers, although agreement was significantly higher between observers (mean kappa of 0.60 for AI vs. 0.79 inter-observer, p<0.001).

Likewise, the automated CT severity score agreed well with the observers with a mean kapa of 0.54 ± 0.01, which was also lower than the agreement between the observers (kappa of I n P r e s s 0.77 ± 0.03, p<0.001). An explanation may be that visually estimating the amount of affected lung parenchyma is subjective; studies have shown that human readers tend to overestimate the extent of disease (28) . In the four cases where automatic measurements were >10 points higher than the reference, underlying causes were severe motion artifacts in three cases and one patient with opacifications caused by aspiration pneumonia. This underlines the importance of verification of automatically determined severity scores by humans.

In the short period since the outbreak, many groups have already developed AI algorithms 9) with such a 2D approach showed performance on an independent test set comparable to ours but did not compare AI results with human reading. We experimented with their CovNet architecture but found that our three-dimensional inflated Inception approach gave higher performance.

Zhang et al. (17) also followed a 2D approach and showed on a large data set that segmentation of lesions per axial section and feeding these slices into a classification network gave excellent results on several Chinese data sets, outperforming junior radiologists. Their method separates consolidations and ground glass lesions, and this seems a promising approach. We followed the CT severity score that is part of CO-RADS and therefore have not separated different types of lesions. When tested on data from Ecuador, performance of their system dropped considerably. We also saw reduced performance on the external validation set for our method, but for that set the CO-RADS scores obtained from routine practice also showed lower performance, comparable to the AI None of the previously published works followed a standardized reporting scheme, and therefore these systems provide an unstandardized, uncalibrated output. The lack of explainability of the output of AI systems is often seen as a limitation. By adhering to a standardized reporting system already validated in human observers (2), the proposed system overcomes this obstacle. The lobar output of the CT severity system is also familiar to radiologists. We did not find any other publications where the accuracy of automated lobar segmentation and lesion segmentation in CT scans of COVID-19 suspects was quantitatively evaluated and compared with human readers.

Our study has several limitations. First, we trained the AI system with data from a single medical center. More training is needed with multi-center data sets. Second, the study sample represented the population of patients that presented in a high-prevalence situation at our hospital and receive chest CT scans due to suspicion of COVID-19. There were only a limited number of patients with extensive pre-existing lung disease in the training set. Third, inclusion of the study group took place after the influenza and RS-virus season.

Consequently, most CT images in this study were either normal or demonstrated COVID-19

features. Ultimately, AI systems need to be trained with a larger dataset before they can be expected to correctly interpret studies with overlapping abnormalities due to other types of I n P r e s s pneumonia or other diseases such as congestive heart failure, pulmonary fibrosis or acute respiratory distress syndrome in non-COVID-19 patients.

In conclusion, our study demonstrates that an AI system can identify COVID-19 positive patients based on unenhanced chest CT images with diagnostic performance comparable to that of radiological observers. It is noteworthy that the algorithm was trained to adhere to the CO-RADS categories and is thus directly interpretable by radiologists. We believe the AI system may be of use to support radiologists in standardized CT reporting during busy periods. The automatically assessed CT severity scores per lobe may have prognostic information and could be used to quantify lung damage, also during patient follow-up. CT Severity Score 8 (9) 10 (7) 11 (7) CO-RADS data are numbers of CT scans with percentages in parentheses. CT severity score data are median and interquartile ranges and were reported only for cases with CO-RADS ≥ 3. I n P r e s s I n P r e s s I n P r e s s I n P r e s s In both centers, a deep inspiration breath-hold technique was applied whenever feasible.

The CORADS-AI system for automatic assessment of CO-RADS score and CT Severity Score in chest CT scans of patients with suspected COVID-19 is composed of three successively applied deep learning algorithms for (1) pulmonary lobe segmentation and labeling, (2) CT severity score prediction and (3) CO-RADS score prediction. Following standard practice, we chose the architectures and hyper-parameters that obtained the highest accuracy on our development set (520 CT images). The test sets were not used for model development.

The first component of the CORADS-AI system automatically segments the pulmonary lobes in a CT scan using a deep learning algorithm based on a relational two-stage U-Net architecture (RTSU-Net) [1] . RTSU-Net is based on a cascade of two 3D U-Net architectures [2] and integrates a relational module to capture the global context of a large 3D CT volume using appearance and geometric information. This architecture takes a full CT volume as input and outputs the corresponding segmentation mask of the five pulmonary lobes. The algorithm was first trained with 4000 chest CT scans from the COPDGene study [3] and then fine-tuned with 400 scans from the present study to increase the robustness to COVID-19

typical pulmonary abnormalities, such as consolidated areas. The remaining scans were used for validation during training, i.e., for tuning the model parameters. Further details of the RTSU-Net architecture and training procedure can be found elsewhere [1] .

Prior to executing the second and third components, which perform automated CO-RADS and CT severity scoring, the original CT volumes were resampled to an isotropic resolution of 1.5 mm x 1.5 mm x 1.5 mm voxel spacing to ensure that all images are interpreted at the same resolution. The volumes were cropped to the lungs based on the automatic lobe segmentation by cropping to the minimum bounding box of the union of all five lobes plus a I n P r e s s learning and therefore expected input values in the range 0 to 1, the images were additionally normalized for this model by clipping intensities below -1100 HU and above 300 HU and mapping the range -1100 HU to 300 HU to the range 0 to 1.

For CT severity score prediction, we trained a 3D U-net using the nnU-Net framework 3 [4] with 108 scans in which we semi-automatically delineated ground-glass opacities and pulmonary consolidation. The network was trained using a five-fold cross-validation scheme.

The resulting probability maps were resampled to the original resolution of the CT scan and then thresholded at 50% probability. False-positive detections outside the lobes were automatically removed using the lobe segmentation mask. The volume of all detected lesions per lobe was divided by the volume of the corresponding lobe and the resulting percentage of affected parenchymal tissue was used to derive the CT severity score (0% = CTSS 0, 0% -5% = CTSS 1, 5% -25% = CTSS 2, 25% -50% = CTSS 3, 50% -75% = CTSS 4, >75% = CTSS 5).

For CO-RADS score prediction, we used a deep learning model based on a 3D inflated Inception V1 architecture (I3D) 4 [5, 6] . The I3D architecture builds upon the state-of-the-art Inception v1 model for 2D image classification but inflates the filters and pooling kernels into 3D. This enables the use of an image classification model pre-trained with 2D data for a 3D

image classification task. The model was pre-trained in 2D with the ImageNet dataset [7] , converted into a 3D model and then further pre-trained using the Kinetics dataset [8] , a 3D

image classification dataset. The resulting pre-trained 3D image classification model was trained with 368 scans of patients with a clinical suspicion of COVID-19 for CO-RADS score prediction, the remaining scans were used for validation during training, i.e., for tuning the model parameters. Because the pre-trained I3D models expect the 3D input data to have the same dimensions as the data the model was pre-trained with, the cropped and isotropically I n P r e s s resampled CT volumes were further cropped or padded to a fixed size of 240 x 240 pixels inplane. In axial direction, 128 slices were uniformly sampled from the lung region. Lesion masks generated by the CT severity score model were pre-processed to the same shape and fed to the model together with the CT image. Since the I3D model expected a 3-channel input due to pre-training with RGB data, the first channel was the image, the second the lesion mask and the third was all zeros. All batch normalization layers in the model were fixed after pre-training. We trained the model with a batch size of 2, a learning rate of 0.0001

with Adam optimizer and cross entropy loss.

I n P r e s s Appendix E3: Additional Results I n P r e s s

We randomly selected two images for each CO-RADS score category (1 to 5) from the 105 CT scans in the internal test set, i.e., images that the CORADS-AI system was not trained with, using the CO-RADS scores from the radiological reports. The images, segmentation results and CO-RADS score and CTSS predictions are shown in Figures D-1 to D-5. Note that the CT severity score is intended for assessment of patients with clinical suspicion of COVID-19 who require hospitalization and is therefore typically not reported for unsuspicious cases. The radiological reports of these 10 example cases therefore contained CT severity scores only for cases scored CO-RADS 3 or higher, these are reported in the figure captions.

I n P r e s s 

The role of imaging in 2019 novel coronavirus pneumonia (COVID-19)

CO-RADS -A categorical CT assessment scheme for patients with suspected COVID-19: definition and evaluation

Radiological Society of North America Expert Consensus Statement on Reporting Chest CT Findings Related to COVID-19. Endorsed by the Society of Thoracic Radiology, the American College of Radiology, and RSNA

Coronavirus disease 2019 (COVID-19) imaging reporting and data system (COVID-RADS) and common lexicon: a proposal based on the imaging data of 37 studies

The Clinical and Chest CT Features Associated With Severe and Critical COVID-19 Pneumonia

Pulmonary sequelae in convalescent patients after severe acute respiratory syndrome: evaluation with thin-section CT

Deep learning system to screen coronavirus disease 2019 pneumonia

Artificial Intelligence Distinguishes COVID-19 from

A deep learning algorithm using CT images to screen for Corona Virus Disease (COVID-19)

AI-assisted CT imaging analysis for COVID-19 screening: Building and deploying a medical AI system in four weeks

AI Augmentation of Radiologist Performance in Distinguishing COVID-19 from Pneumonia of

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

Prior-Attention Residual Learning for More Discriminative COVID-19 Screening in CT Images

Rapid AI Development Cycle for the Coronavirus (COVID-19) Pandemic: Initial Results for

Automated Detection &amp

Lung Infection Quantification of COVID-19 in

Clinically Applicable AI System for Accurate Diagnosis, Quantitative Measurements, and Prognosis of COVID-19 Pneumonia Using Computed Tomography

Artificial intelligence-enabled rapid diagnosis of patients with COVID-19

How Might AI and Chest Imaging Help Unravel COVID-19's Mysteries?

Relational Modeling for Robust and Efficient Pulmonary Lobe Segmentation in CT Scans

Genetic Epidemiology of COPD (COPDGene) Study Design

Automated Design of Deep Learning Methods for Biomedical Image Segmentation

Action Recognition? A New Model and the Kinetics Dataset. 2017 IEEE Conference on Computer Vision and Pattern Recognition

End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography

Going deeper with convolutions

ImageNet Large Scale Visual Recognition Challenge

The AVA-Kinetics Localized Human Actions Video Dataset. arXiv e-prints 2020

Quantifying the extent of emphysema: factors associated with radiologists' estimations and quantitative indices of emphysema severity using the ECLIPSE cohort

Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation and Diagnosis for COVID-19

A review on the use of artificial intelligence for medical imaging of the lungs of patients with coronavirus disease 2019

A collaborative online AI engine for CT-based COVID-19 diagnosis

Rapid identification of SARS-CoV-2-infected patients at the emergency department using routine testing

Relational Modeling for Robust and Efficient Pulmonary Lobe Segmentation in CT Scans

Learning Dense Volumetric Segmentation from Sparse Annotation

Genetic Epidemiology of COPD (COPDGene) Study Design

Automated Design of Deep Learning Methods for Biomedical Image Segmentation

Action Recognition? A New Model and the Kinetics Dataset. 2017 IEEE Conference on Computer Vision and Pattern Recognition

End-to-end lung cancer screening with three-dimensional I n P r e s s deep learning on low-dose chest computed tomography

ImageNet Large Scale Visual Recognition Challenge

The AVA-Kinetics Localized Human Actions Video Dataset. arXiv e-prints 2020