TY - JOUR
T1 - Identifying pulmonary nodules or masses on chest radiography using deep learning
T2 - external validation and strategies to improve clinical practice
AU - Liang, C. H.
AU - Liu, Y. C.
AU - Wu, M. T.
AU - Garcia-Castro, F.
AU - Alberich-Bayarri, A.
AU - Wu, F. Z.
N1 - Publisher Copyright:
© 2019 The Royal College of Radiologists
PY - 2020/1
Y1 - 2020/1
N2 - AIM: To test the diagnostic performance of a deep learning-based system for the detection of clinically significant pulmonary nodules/masses on chest radiographs. MATERIALS AND METHODS: Using a retrospective study of 100 patients (47 with clinically significant pulmonary nodules/masses and 53 control subjects without pulmonary nodules), two radiologists verified clinically significantly pulmonary nodules/masses according to chest computed tomography (CT) findings. A computer-aided diagnosis (CAD) software using a deep-learning approach was used to detect pulmonary nodules/masses to determine the diagnostic performance in four algorithms (heat map, abnormal probability, nodule probability, and mass probability). RESULTS: A total of 100 cases were included in the analysis. Among the four algorithms, mass algorithm could achieve a 76.6% sensitivity (36/47, 11 false negative) and 88.68% specificity (47/53, six false-positive) in the detection of pulmonary nodules/masses at the optimal probability score cut-off of 0.2884. Compared to the other three algorithms, mass probability algorithm had best predictive ability for pulmonary nodule/mass detection at the optimal probability score cut-off of 0.2884 (AUCMass: 0.916 versus AUCHeat map: 0.682, p<0.001; AUCMass: 0.916 versus AUCAbnormal: 0.810, p=0.002; AUCMass: 0.916 versus AUCNodule: 0.813, p=0.014). CONCLUSION: In conclusion, the deep-learning based computer-aided diagnosis system will likely play a vital role in the early detection and diagnosis of pulmonary nodules/masses on chest radiographs. In future applications, these algorithms could support triage workflow via double reading to improve sensitivity and specificity during the diagnostic process.
AB - AIM: To test the diagnostic performance of a deep learning-based system for the detection of clinically significant pulmonary nodules/masses on chest radiographs. MATERIALS AND METHODS: Using a retrospective study of 100 patients (47 with clinically significant pulmonary nodules/masses and 53 control subjects without pulmonary nodules), two radiologists verified clinically significantly pulmonary nodules/masses according to chest computed tomography (CT) findings. A computer-aided diagnosis (CAD) software using a deep-learning approach was used to detect pulmonary nodules/masses to determine the diagnostic performance in four algorithms (heat map, abnormal probability, nodule probability, and mass probability). RESULTS: A total of 100 cases were included in the analysis. Among the four algorithms, mass algorithm could achieve a 76.6% sensitivity (36/47, 11 false negative) and 88.68% specificity (47/53, six false-positive) in the detection of pulmonary nodules/masses at the optimal probability score cut-off of 0.2884. Compared to the other three algorithms, mass probability algorithm had best predictive ability for pulmonary nodule/mass detection at the optimal probability score cut-off of 0.2884 (AUCMass: 0.916 versus AUCHeat map: 0.682, p<0.001; AUCMass: 0.916 versus AUCAbnormal: 0.810, p=0.002; AUCMass: 0.916 versus AUCNodule: 0.813, p=0.014). CONCLUSION: In conclusion, the deep-learning based computer-aided diagnosis system will likely play a vital role in the early detection and diagnosis of pulmonary nodules/masses on chest radiographs. In future applications, these algorithms could support triage workflow via double reading to improve sensitivity and specificity during the diagnostic process.
UR - http://www.scopus.com/inward/record.url?scp=85071985557&partnerID=8YFLogxK
U2 - 10.1016/j.crad.2019.08.005
DO - 10.1016/j.crad.2019.08.005
M3 - Article
C2 - 31521323
AN - SCOPUS:85071985557
SN - 0009-9260
VL - 75
SP - 38
EP - 45
JO - Clinical Radiology
JF - Clinical Radiology
IS - 1
ER -