Unsupervised Detection of Lung Nodules in Chest Radiography Using Generative Adversarial Networks [article]

Nitish Bhatt, David Ramon Prados, Nedim Hodzic, Christos Karanassios, H.R. Tizhoosh
2021 arXiv   pre-print
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
more » ... d 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.
arXiv:2108.02233v1 fatcat:yrg2i644ffc6dcyxmmshgajr7m