Development and validation of a deep learning algorithm detecting 10 common abnormalities on chest radiographs
Authors:
Open Access
- 26 November 2020
- journal article
- research article
- Published by European Respiratory Society (ERS) in European Respiratory Journal
- Vol. 57 (5) , 2003061
Abstract
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 radiological 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 computed tomography (CT)-confirmed dataset (normal:abnormal 53:147) and an open-source dataset (PadChest; normal:abnormal 339:334) was compared with 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 nonurgent cases. Six radiologists participated in the simulated reading sessions with and without DLAD-10.DLAD-10 exhibited area under the receiver operating characteristic curve values 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)versus29.2% (7/24); p=0.006) and urgent (82.7% (258/312)versus78.2% (244/312); p=0.04) abnormalities when aided by DLAD-10. DLAD-10 assistance shortened the mean±sdtime-to-report critical and urgent radiographs (640.5±466.3versus3371.0±1352.5 s and 1840.3±1141.1versus2127.1±1468.2 s, respectively; all pversus23.5±23.7 s; p<0.001).DLAD-10 showed excellent performance, improving radiologists' performance and shortening the reporting time for critical and urgent cases.Keywords
Funding Information
- National Research Foundation of Korea (grant number: NRF-2018R1A5A1060031)
- Seoul National University Hospital (grant number: 03-2019-0190)
This publication has 26 references indexed in Scilit:
- Patient Exposure from Radiologic and Nuclear Medicine Procedures in the United States: Procedure Volume and Effective Dose for the Period 2006–2016Radiology, 2020
- Deep learning algorithm for surveillance of pneumothorax after lung biopsy: a multicenter diagnostic cohort studyEuropean Radiology, 2020
- Deep learning-based detection system for multiclass lesions on chest radiographs: comparison with observer readingsEuropean Radiology, 2019
- Application of deep learning–based computer-aided detection system: detecting pneumothorax on chest radiograph after biopsyEuropean Radiology, 2019
- Development and Validation of a Deep Learning–Based Automated Detection Algorithm for Major Thoracic Diseases on Chest RadiographsJAMA Network Open, 2019
- High-performance medicine: the convergence of human and artificial intelligenceNature Medicine, 2019
- Development and Validation of Deep Learning–based Automatic Detection Algorithm for Malignant Pulmonary Nodules on Chest RadiographsRadiology, 2019
- Development and Validation of a Deep Learning–based Automatic Detection Algorithm for Active Pulmonary Tuberculosis on Chest RadiographsClinical Infectious Diseases, 2018
- Deep Learning at Chest Radiography: Automated Classification of Pulmonary Tuberculosis by Using Convolutional Neural NetworksRadiology, 2017
- Use of a Computer-aided Detection System to Detect Missed Lung Cancer at Chest RadiographyRadiology, 2009