ABSTRACT
BACKGROUND: Deep learning (DL) based solutions have been proposed for interpretation of several imaging modalities including radiography, CT, and MR. For chest radiographs, DL algorithms have found success in the evaluation of abnormalities such as lung nodules, pulmonary tuberculosis, cystic fibrosis, pneumoconiosis, and location of peripherally inserted central catheters. Chest radiography represents the most commonly performed radiological test for a multitude of non-emergent and emergent clinical indications. This study aims to assess accuracy of deep learning (DL) algorithm for detection of abnormalities on routine frontal chest radiographs (CXR), and assessment of stability or change in findings over serial radiographs. METHODS AND FINDINGS: We processed 874 de-identified frontal CXR from 724 adult patients (> 18 years) with DL (Qure AI). Scores and prediction statistics from DL were generated and recorded for the presence of pulmonary opacities, pleural effusions, hilar prominence, and enlarged cardiac silhouette. To establish a standard of reference (SOR), two thoracic radiologists assessed all CXR for these abnormalities. Four other radiologists (test radiologists), unaware of SOR and DL findings, independently assessed the presence of radiographic abnormalities. A total 724 radiographs were assessed for detection of findings. A subset of 150 radiographs with follow up examinations was used to asses change over time. Data were analyzed with receiver operating characteristics analyses and post-hoc power analysis. RESULTS: About 42% (305/ 724) CXR had no findings according to SOR; single and multiple abnormalities were seen in 23% (168/724) and 35% (251/724) of CXR. There was no statistical difference between DL and SOR for all abnormalities (p = 0.2-0.8). The area under the curve (AUC) for DL and test radiologists ranged between 0.837-0.929 and 0.693-0.923, respectively. DL had lowest AUC (0.758) for assessing changes in pulmonary opacities over follow up CXR. Presence of chest wall implanted devices negatively affected the accuracy of DL algorithm for evaluation of pulmonary and hilar abnormalities. CONCLUSIONS: DL algorithm can aid in interpretation of CXR findings and their stability over follow up CXR. However, in its present version, it is unlikely to replace radiologists due to its limited specificity for categorizing specific findings.
Subject(s)
Lung/diagnostic imaging , Radiographic Image Enhancement/standards , Radiography, Thoracic/standards , Adult , Aged , Algorithms , Area Under Curve , Deep Learning , Female , Humans , Male , Middle Aged , Observer Variation , ROC Curve , Radiographic Image Enhancement/methods , Radiography, Thoracic/methods , Reference Standards , Retrospective StudiesABSTRACT
In this address, John A. Patti, MD, acknowledges the celebration and success that radiologists have experienced throughout their careers but also asks incisive questions about how they will face the future. Answers to those questions require an analysis of the past, an understanding of the present, serious and penetrating introspection, and engagement of a process for moving forward. An understanding of who we are and why we do what we do is essential to facilitate the changes that will be necessary if radiologists are to control the future, rather than having the future control radiologists.
Subject(s)
Delivery of Health Care/trends , Diagnostic Imaging/trends , Forecasting , Physician's Role , Radiology/trends , United StatesABSTRACT
The 2012 ACR Forum focused on the anticipated challenges and opportunities facing radiology in the next 10 years, centered on the themes of health care reform, future payment models, research and innovation, patient-centered radiology, and information management. The recommendations generated from the forum seek to inform ACR leadership on the best strategies to pursue to ensure the continued success of the profession in the coming decade.
Subject(s)
Diagnostic Imaging/standards , Practice Guidelines as Topic , Quality Improvement , Radiology/standards , Biomedical Research/standards , Biomedical Research/trends , Congresses as Topic , Diagnostic Imaging/trends , Evidence-Based Medicine , Forecasting , Health Care Reform , Humans , Leadership , Radiology/trends , United StatesABSTRACT
The 2011 ACR Forum focused on the impact of generational differences on the future of radiology, seeking to inform ACR leadership and members on how best to address the influence of the new integrated workforce on the specialty of radiology and on individual practices.
