AI-Based CXR First Reading: Current Limitations to Ensure Practical Value.

We performed a multicenter external evaluation of the practical and clinical efficacy of a commercial AI algorithm for chest X-ray (CXR) analysis (Lunit INSIGHT CXR). A retrospective evaluation was performed with a multi-reader study. For a prospective evaluation, the AI model was run on CXR studies; the results were compared to the reports of 226 radiologists. In the multi-reader study, the area under the curve (AUC), sensitivity, and specificity of the AI were 0.94 (CI95%: 0.87-1.0), 0.9 (CI95%: 0.79-1.0), and 0.89 (CI95%: 0.79-0.98); the AUC, sensitivity, and specificity of the radiologists were 0.97 (CI95%: 0.94-1.0), 0.9 (CI95%: 0.79-1.0), and 0.95 (CI95%: 0.89-1.0). In most regions of the ROC curve, the AI performed a little worse or at the same level as an average human reader. The McNemar test showed no statistically significant differences between AI and radiologists. In the prospective study with 4752 cases, the AUC, sensitivity, and specificity of the AI were 0.84 (CI95%: 0.82-0.86), 0.77 (CI95%: 0.73-0.80), and 0.81 (CI95%: 0.80-0.82). Lower accuracy values obtained during the prospective validation were mainly associated with false-positive findings considered by experts to be clinically insignificant and the false-negative omission of human-reported "opacity", "nodule", and calcification. In a large-scale prospective validation of the commercial AI algorithm in clinical practice, lower sensitivity and specificity values were obtained compared to the prior retrospective evaluation of the data of the same population.

A phantom study to optimise the automatic tube current modulation for chest CT in COVID-19.

On March 11, 2020, the World Health Organization declared the coronavirus disease 2019 (COVID-19) pandemic. The expert organisations recommend more cautious use of thoracic computed tomography (CT), opting for low-dose protocols. We aimed at determining a threshold value of automatic tube current modulation noise index below which there is a chance to miss an onset of ground-glass opacities (GGO) in COVID-19. A team of radiologists and medical physicists performed 25 phantom CT studies using different automatic tube current modulation settings (SUREExposure3D technology). We then conducted a retrospective evaluation of the chest CT images from 22 patients with COVID-19 and calculated the density difference between the GGO and unaffected tissue. Finally, the results were matched to the phantom study results to determine the minimum noise index threshold value. The minimum density difference at the onset of COVID-19 was 252 HU (p < 0.001). This was found to correspond to the SUREExposure 3D noise index of 36. We established the noise index threshold of 36 for the Canon scanner without iterative reconstructions, allowing for a decrease in the dose-length product by 80%. The proposed protocol needs to be validated in a prospective study.

CT-Based COVID-19 triage: Deep multitask learning improves joint identification and severity quantification.

The current COVID-19 pandemic overloads healthcare systems, including radiology departments. Though several deep learning approaches were developed to assist in CT analysis, nobody considered study triage directly as a computer science problem. We describe two basic setups: Identification of COVID-19 to prioritize studies of potentially infected patients to isolate them as early as possible; Severity quantification to highlight patients with severe COVID-19, thus direct them to a hospital or provide emergency medical care. We formalize these tasks as binary classification and estimation of affected lung percentage. Though similar problems were well-studied separately, we show that existing methods could provide reasonable quality only for one of these setups. We employ a multitask approach to consolidate both triage approaches and propose a convolutional neural network to leverage all available labels within a single model. In contrast with the related multitask approaches, we show the benefit from applying the classification layers to the most spatially detailed feature map at the upper part of U-Net instead of the less detailed latent representation at the bottom. We train our model on approximately 1500 publicly available CT studies and test it on the holdout dataset that consists of 123 chest CT studies of patients drawn from the same healthcare system, specifically 32 COVID-19 and 30 bacterial pneumonia cases, 30 cases with cancerous nodules, and 31 healthy controls. The proposed multitask model outperforms the other approaches and achieves ROC AUC scores of 0.87±0.01 vs. bacterial pneumonia, 0.93±0.01 vs. cancerous nodules, and 0.97±0.01 vs. healthy controls in Identification of COVID-19, and achieves 0.97±0.01 Spearman Correlation in Severity quantification. We have released our code and shared the annotated lesions masks for 32 CT images of patients with COVID-19 from the test dataset.