Domain Generalization with Adversarial Intensity Attack for Medical Image Segmentation
This addresses the problem of model performance degradation on unseen medical imaging domains for researchers and practitioners, though it is incremental as it builds on existing adversarial training methods.
The paper tackles domain generalization for medical image segmentation by introducing Adversarial Intensity Attack (AdverIN), which uses adversarial training to generate diverse training data, resulting in significant improvements in generalization on datasets like 2D retinal fundus and 3D prostate MRI.
Most statistical learning algorithms rely on an over-simplified assumption, that is, the train and test data are independent and identically distributed. In real-world scenarios, however, it is common for models to encounter data from new and different domains to which they were not exposed to during training. This is often the case in medical imaging applications due to differences in acquisition devices, imaging protocols, and patient characteristics. To address this problem, domain generalization (DG) is a promising direction as it enables models to handle data from previously unseen domains by learning domain-invariant features robust to variations across different domains. To this end, we introduce a novel DG method called Adversarial Intensity Attack (AdverIN), which leverages adversarial training to generate training data with an infinite number of styles and increase data diversity while preserving essential content information. We conduct extensive evaluation experiments on various multi-domain segmentation datasets, including 2D retinal fundus optic disc/cup and 3D prostate MRI. Our results demonstrate that AdverIN significantly improves the generalization ability of the segmentation models, achieving significant improvement on these challenging datasets. Code is available upon publication.