Unsupervised anomaly detection in digital pathology using GANs
This work addresses the need for reliable anomaly detection in digital pathology for clinical deployment, though it appears incremental as it builds on existing GAN methods with domain-specific adaptations.
The paper tackled the problem of detecting anomalous data in digital pathology to prevent incorrect clinical decisions, proposing an unsupervised GAN-based approach that significantly improves performance for histopathology imagery, which is more complex than previous medical imaging data.
Machine learning (ML) algorithms are optimized for the distribution represented by the training data. For outlier data, they often deliver predictions with equal confidence, even though these should not be trusted. In order to deploy ML-based digital pathology solutions in clinical practice, effective methods for detecting anomalous data are crucial to avoid incorrect decisions in the outlier scenario. We propose a new unsupervised learning approach for anomaly detection in histopathology data based on generative adversarial networks (GANs). Compared to the existing GAN-based methods that have been used in medical imaging, the proposed approach improves significantly on performance for pathology data. Our results indicate that histopathology imagery is substantially more complex than the data targeted by the previous methods. This complexity requires not only a more advanced GAN architecture but also an appropriate anomaly metric to capture the quality of the reconstructed images.