Industrial and medical anomaly detection through cycle-consistent adversarial networks

In this study, a new Anomaly Detection (AD) approach for industrial and medical images is proposed. This method leverages the theoretical strengths of unsupervised learning and the data availability of both normal and abnormal classes. Indeed, the AD is often formulated as an unsupervised task, implying only normal images during training. These normal images are devoted to be reconstructed through an autoencoder architecture, for instance. However, the information contained in abnormal data, when available, is also valuable for this reconstruction. The model would be able to identify its weaknesses by also learning how to transform an abnormal image into a normal one. This abnormal-to-normal reconstruction helps the entire model to learn better than a single normal-to-normal reconstruction. To be able to exploit abnormal images, the proposed method uses Cycle-Generative Adversarial Networks (Cycle-GAN) for (ab)normal-to-normal translation. After an input image has been reconstructed by the normal generator, an anomaly score quantifies the differences between the input and its reconstruction. Based on a threshold set to satisfy a business quality constraint, the input image is then flagged as normal or not. The proposed method is evaluated on industrial and medical datasets. The results demonstrate accurate performance with a zero false negative constraint compared to state-of-the-art methods. Quantitatively, our method reaches an accuracy under a zero false negative constraint of 79.89%, representing an improvement of about 17% compared to competitors. The code is available at https://github.com/ValDelch/CycleGANS-AnomalyDetection.