Performance and educational training of radiographers in lung nodule or mass detection: Retrospective comparison with different deep learning algorithms

• Published in: Medicine (Baltimore) Vol. 100; no. 23; p. e26270
• Main Authors: Teng, Pai-Hsueh, Liang, Chia-Hao, Lin, Yun, Alberich-Bayarri, Angel, González, Rafael López, Li, Pin-Wei, Weng, Yu-Hsin, Chen, Yi-Ting, Lin, Chih-Hsien, Chou, Kang-Ju, Chen, Yao-Shen, Wu, Fu-Zong
• Format: Journal Article
• Language: English
• Published: United States Lippincott Williams & Wilkins 11.06.2021
• Subjects: Algorithms; Burnout, Professional - etiology; Burnout, Professional - prevention & control; Clinical Competence; Deep Learning; Diagnostic Accuracy Study; Female; Humans; Lung - diagnostic imaging; Male; Middle Aged; Multiple Pulmonary Nodules - diagnosis; Radiography, Thoracic - methods; Radiography, Thoracic - standards; Radiologists - education; Radiologists - psychology; Radiologists - standards; Sensitivity and Specificity; Solitary Pulmonary Nodule - diagnosis; Taiwan; Taiwan
• ISSN: 0025-7974; 1536-5964; 1536-5964
• DOI: 10.1097/MD.0000000000026270

The aim of this investigation was to compare the diagnostic performance of radiographers and deep learning algorithms in pulmonary nodule/mass detection on chest radiograph.A test set of 100 chest radiographs containing 53 cases with no pathology (normal) and 47 abnormal cases (pulmonary nodules/masses) independently interpreted by 6 trained radiographers and deep learning algorithems in a random order. The diagnostic performances of both deep learning algorithms and trained radiographers for pulmonary nodules/masses detection were compared.QUIBIM Chest X-ray Classifier, a deep learning through mass algorithm that performs superiorly to practicing radiographers in the detection of pulmonary nodules/masses (AUCMass: 0.916 vs AUCTrained radiographer: 0.778, P < .001). In addition, heat-map algorithm could automatically detect and localize pulmonary nodules/masses in chest radiographs with high specificity.In conclusion, the deep-learning based computer-aided diagnosis system through 4 algorithms could potentially assist trained radiographers by increasing the confidence and access to chest radiograph interpretation in the age of digital age with the growing demand of medical imaging usage and radiologist burnout.