Deep learning in chest radiography: Detection of findings and presence of change

Autor: Victorine V. Muse, Atul Padole, Subba R. Digumarthy, Fatemeh Homayounieh, Pooja Rao, Mannudeep K. Kalra, Chayanin Nitiwarangkul, Preetham Putha, Ramandeep Singh, Amita Sharma, John A. Patti
Rok vydání: 2018
Předmět:
Male
Pulmonology
Pleural effusion
Radiography
lcsh:Medicine
030218 nuclear medicine & medical imaging
0302 clinical medicine
Mathematical and Statistical Techniques
Medicine and Health Sciences
Medical Personnel
lcsh:Science
Lung
Optical Properties
Observer Variation
Multidisciplinary
Pneumoconiosis
Applied Mathematics
Simulation and Modeling
Middle Aged
Reference Standards
Radiographic Image Enhancement
Professions
medicine.anatomical_structure
030220 oncology & carcinogenesis
Radiological weapon
Area Under Curve
Physical Sciences
Female
Radiography
Thoracic
Radiology
Algorithms
Statistics (Mathematics)
Research Article
Biotechnology
Adult
Opacity
medicine.medical_specialty
Catheters
Materials Science
Material Properties
Research and Analysis Methods
03 medical and health sciences
Deep Learning
Radiologists
medicine
Humans
Statistical Methods
Aged
Retrospective Studies
Multiple abnormalities
Receiver operating characteristic
business.industry
lcsh:R
Biology and Life Sciences
Retrospective cohort study
medicine.disease
Fibrosis
Pleural Effusion
ROC Curve
People and Places
lcsh:Q
Population Groupings
Medical Devices and Equipment
business
Mathematics
Developmental Biology
Forecasting
Zdroj: PLoS ONE
PLoS ONE, Vol 13, Iss 10, p e0204155 (2018)
ISSN: 1932-6203
Popis: 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.
Databáze: OpenAIRE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje