Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization
This work addresses the domain generalization problem in medical imaging classification, which is crucial for deploying models in clinically realistic environments with diverse data sources, though it appears incremental as it builds on existing variational encoding approaches.
The paper tackles the problem of poor generalization of deep neural networks in medical imaging classification when trained on limited datasets from specific domains, and introduces a linear-dependency regularization method that improves cross-domain generalization, achieving better performance than state-of-the-art baselines on two challenging tasks.
Recently, we have witnessed great progress in the field of medical imaging classification by adopting deep neural networks. However, the recent advanced models still require accessing sufficiently large and representative datasets for training, which is often unfeasible in clinically realistic environments. When trained on limited datasets, the deep neural network is lack of generalization capability, as the trained deep neural network on data within a certain distribution (e.g. the data captured by a certain device vendor or patient population) may not be able to generalize to the data with another distribution. In this paper, we introduce a simple but effective approach to improve the generalization capability of deep neural networks in the field of medical imaging classification. Motivated by the observation that the domain variability of the medical images is to some extent compact, we propose to learn a representative feature space through variational encoding with a novel linear-dependency regularization term to capture the shareable information among medical data collected from different domains. As a result, the trained neural network is expected to equip with better generalization capability to the "unseen" medical data. Experimental results on two challenging medical imaging classification tasks indicate that our method can achieve better cross-domain generalization capability compared with state-of-the-art baselines.