hest radiography, one of the most common diagnostic imaging tests in medicine, is used for screening, diagnostic work-ups, and monitoring of various thoracic diseases (1,2). One of its major objectives is detection of pulmonary nodules because pulmonary nodules are often the initial radiologic manifestation of lung cancers (1,2). However, to date, pulmonary nodule detection on chest radiographs has not been completely satisfactory, with a reported sensitivity ranging between 36%-84%, varying widely according to the tumor size and study population (2-6). Indeed, chest radiography has been shown to be prone to many reading errors with low interobserver and intraobserver agreements because of its limited spatial resolution, noise from overlapping anatomic structures, and the variable perceptual ability of radiologists. Recent work shows that 19%-26% of lung cancers visible on chest radiographs were in fact missed at their first readings (6,7). Of course, hindsight is always perfect when one knows where to look. For this reason, there has been increasing dependency on chest CT images over chest radiographs in pulmonary nodule detection. However, even low-dose CT scans require approximately 50-100 times higher radiation dose than single-view chest radiographic examinations (8,9)

I n 2015, approximately 137 million patients presented to the emergency department (ED) in the United States (43.3 visits per 100 persons) (1). Respiratory diseases were the second most common primary diagnosis in these patients, accounting for 9.8% of all visits (1). Chest radiography is the first-line examination for the evaluation of various thoracic diseases (2-8). The number of chest radiographs per ED visit increased by 81% between 1994 and 2014, suggesting an increasing dependency on chest radiographs (9). The interpretation of chest radiographs is a challenging task, requiring experience and expertise. Previous studies have reported suboptimal performance in the interpretation of chest radiographs by ED physicians compared with expert radiologists (10-13). In addition, the American College of Radiology recommends that qualified radiologists be available to interpret all radiographs obtained in the ED (14). However, there is a practical limitation with regard to the full-time availability of expert radiologists, especially for after-hours coverage. In a 2014 survey (15), 73% of the academic radiology departments in the United States did not provide overnight coverage by faculty. Thus, for after-hours ED coverage, a computer-aided detection system for clinically relevant findings on chest radiographs may help improve the quality of radiographic interpretation and overall turnaround time. Recently, deep learning (DL) algorithms with medical image analysis systems have been evaluated for retinal fundus photographs (16,17), pathologic images (18), and

In COVID-19 patients, considerable variation was found in the QCTmass (72.4±120.8 g; range, 0.7-420.7 g) and relative 3D opacity extent on CT (3.2±5.8% of lung area; range, 0.1-19.8%). 2. Chest radiographs in patients under investigation for COVID-19 provided a sensitivity of 25% (5/20) and specificity of 90% (18/20) for COVID-19-related opacities. 3. The QCTmass (p<.001) and the 3D opacity volume on CT (p<.001) significantly affected the visibility of COVID-19-related opacities on radiographs. I n p r e s s Summary Statement Quantitative opacity mass and 3D opacity volume on CT were quantifiable metrics affecting the visibility of COVID-19-related opacities on chest radiographs.

We aimed to develop a deep-learning algorithm detecting 10 common abnormalities (DLAD-10) on chest radiographs and to evaluate its impact in diagnostic accuracy, timeliness of reporting, and workflow efficacy.DLAD-10 was trained with 146 717 radiographs from 108 053 patients using a ResNet34-based neural network with lesion-specific channels for 10 common radiologic abnormalities (pneumothorax, mediastinal widening, pneumoperitoneum, nodule/mass, consolidation, pleural effusion, linear atelectasis, fibrosis, calcification, and cardiomegaly). For external validation, the performance of DLAD-10 on a same-day CT-confirmed dataset (normal:abnormal, 53:147) and an open-source dataset (PadChest; normal:abnormal, 339:334) was compared to that of three radiologists. Separate simulated reading tests were conducted on another dataset adjusted to real-world disease prevalence in the emergency department, consisting of four critical, 52 urgent, and 146 non-urgent cases. Six radiologists participated in the simulated reading sessions with and without DLAD-10.DLAD-10 exhibited areas under the receiver-operating characteristic curves (AUROCs) of 0.895–1.00 in the CT-confirmed dataset and 0.913–0.997 in the PadChest dataset. DLAD-10 correctly classified significantly more critical abnormalities (95.0% [57/60]) than pooled radiologists (84.4% [152/180]; p=0.01). In simulated reading tests for emergency department patients, pooled readers detected significantly more critical (70.8% [17/24] versus 29.2% [7/24]; p=0.006) and urgent (82.7% [258/312] versus 78.2% [244/312]; p=0.04) abnormalities when aided by DLAD-10. DLAD-10 assistance shortened the mean time-to-report critical and urgent radiographs (640.5±466.3 versus 3371.0±1352.5 s and 1840.3±1141.1 versus 2127.1±1468.2, respectively; p-values<0.01) and reduced the mean interpretation time (20.5±22.8 versus 23.5±23.7 s; p<0.001).DLAD-10 showed excellent performance, improving radiologists' performance and shortening the reporting time for critical and urgent cases.

This erratum corrects an error in the software listed for automatic generation of a volumetric mask of the lungs, lobes, intrapulmonary vessels, and airways. In Quantitative CT analysis, first paragraph, first sentence, the software should be listed as follows: "After uploading CT images from each patient to commercially available segmentation software (MEDIP PRO v2.0.0.0, MEDICALIP Co. Ltd., Seoul, Korea), a deep neural network (Deep Catch v1.0.0.0, MEDICALIP Co. Ltd., Seoul, Korea), automatically generated a volumetric mask of the lungs, lobes, intrapulmonary vessels, and airways. The change was made online on April 6, 2020.