TY - GEN
T1 - Unsupervised Detection of Lung Nodules in Chest Radiography Using Generative Adversarial Networks
AU - Bhatt, Nitish
AU - Prados, David Ramon
AU - Hodzic, Nedim
AU - Karanassios, Christos
AU - Tizhoosh, H. R.
N1 - Funding Information:
Research supported by Faculty of Engineering, University of Waterloo
Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - Lung nodules are commonly missed in chest radiographs. We propose and evaluate P-AnoGAN, an unsupervised anomaly detection approach for lung nodules in radiographs. P-AnoGAN modifies the fast anomaly detection generative adversarial network (f-AnoGAN) by utilizing a progressive GAN and a convolutional encoder-decoder-encoder pipeline. Model training uses only unlabelled healthy lung patches extracted from the Indiana University Chest X-Ray Collection. External validation and testing are performed using healthy and unhealthy patches extracted from the ChestX-ray14 and Japanese Society for Radiological Technology datasets, respectively. Our model robustly identifies patches containing lung nodules in external validation and test data with ROC-AUC of 91.17% and 87.89%, respectively. These results show unsupervised methods may be useful in challenging tasks such as lung nodule detection in radiographs.
AB - Lung nodules are commonly missed in chest radiographs. We propose and evaluate P-AnoGAN, an unsupervised anomaly detection approach for lung nodules in radiographs. P-AnoGAN modifies the fast anomaly detection generative adversarial network (f-AnoGAN) by utilizing a progressive GAN and a convolutional encoder-decoder-encoder pipeline. Model training uses only unlabelled healthy lung patches extracted from the Indiana University Chest X-Ray Collection. External validation and testing are performed using healthy and unhealthy patches extracted from the ChestX-ray14 and Japanese Society for Radiological Technology datasets, respectively. Our model robustly identifies patches containing lung nodules in external validation and test data with ROC-AUC of 91.17% and 87.89%, respectively. These results show unsupervised methods may be useful in challenging tasks such as lung nodule detection in radiographs.
UR - http://www.scopus.com/inward/record.url?scp=85122511211&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85122511211&partnerID=8YFLogxK
U2 - 10.1109/EMBC46164.2021.9630340
DO - 10.1109/EMBC46164.2021.9630340
M3 - Conference contribution
C2 - 34892072
AN - SCOPUS:85122511211
T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
SP - 3842
EP - 3845
BT - 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2021
Y2 - 1 November 2021 through 5 November 2021
ER -