Abstract
The purposes of this study are to propose an unsupervised anomaly detection method based on a deep neural network (DNN) model, which requires only normal images for training, and to evaluate its performance with a large chest radiograph dataset. We used the auto-encoding generative adversarial network (α-GAN) framework, which is a combination of a GAN and a variational autoencoder, as a DNN model. A total of 29,684 frontal chest radiographs from the Radiological Society of North America Pneumonia Detection Challenge dataset were used for this study (16,880 male and 12,804 female patients; average age, 47.0 years). All these images were labeled as “Normal,” “No Opacity/Not Normal,” or “Opacity” by board-certified radiologists. About 70% (6,853/9,790) of the Normal images were randomly sampled as the training dataset, and the rest were randomly split into the validation and test datasets in a ratio of 1:2 (7,610 and 15,221). Our anomaly detection system could correctly visualize various lesions including a lung mass, cardiomegaly, pleural effusion, bilateral hilar lymphadenopathy, and even dextrocardia. Our system detected the abnormal images with an area under the receiver operating characteristic curve (AUROC) of 0.752. The AUROCs for the abnormal labels Opacity and No Opacity/Not Normal were 0.838 and 0.704, respectively. Our DNN-based unsupervised anomaly detection method could successfully detect various diseases or anomalies in chest radiographs by training with only the normal images.
Highlights
In recent years, deep neural network (DNN)–based approaches have made remarkable advances in the field of computer-aided diagnosis/detection (CAD) for chest radiographs [1,2,3,4,5,6,7,8]
The average receiver operating characteristic (ROC) curves of the per-image anomaly detection task are shown in Fig. 5 with the area under the receiver operating characteristic curve (AUROC) values and their 95% confidence intervals (CI)
The anomaly detection method with the code norm score on average detected 67.2% of the abnormal chest radiographs with a false-positive rate of 28.5%
Summary
Deep neural network (DNN)–based approaches have made remarkable advances in the field of computer-aided diagnosis/detection (CAD) for chest radiographs [1,2,3,4,5,6,7,8] Most of these works have been carried out in supervised learning, which is a type of training based. With the recent development of unsupervised methods in deep learning, several works on unsupervised anomaly detection in medical images have emerged [13,14,15,16,17,18] These have employed autoencoders, especially variational autoencoders (VAEs) [19], or generative adversarial networks (GANs) [20], which are the most well-known classes of DNN-based unsupervised learning models. Tang et al [17] proposed an unsupervised anomaly detection method for chest radiographs using a hybrid model of a traditional (not variational) autoencoder and a GAN
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
