Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization

Abstract

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.

Accepted by NeurIPS, 2020

References in corpus (7)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• mixup: Beyond Empirical Risk Minimization
• Learning Transferable Features with Deep Adaptation Networks
• Domain Generalization via Invariant Feature Representation
• Task Driven Generative Modeling for Unsupervised Domain Adaptation: Application to X-ray Image Segmentation
• Heterogeneous Domain Generalization via Domain Mixup
• PnP-AdaNet: Plug-and-Play Adversarial Domain Adaptation Network with a Benchmark at Cross-modality Cardiac Segmentation

Cited by in corpus (13)

• Automated Detection and Forecasting of COVID-19 using Deep Learning Techniques: A Review
• Towards contrast-agnostic soft segmentation of the spinal cord
• Variational Disentanglement for Domain Generalization
• Learning Domain Invariant Representations by Joint Wasserstein Distance Minimization
• Parameter Exchange for Robust Dynamic Domain Generalization
• Model-Based Domain Generalization
• Experts' cognition-driven ensemble deep learning for external validation of predicting pathological complete response to neoadjuvant chemotherapy from histological images in breast cancer
• On the Generalization Properties of Deep Learning for Aircraft Fuel Flow Estimation Models
• Embracing the Dark Knowledge: Domain Generalization Using Regularized Knowledge Distillation
• Embracing the Disharmony in Medical Imaging: A Simple and Effective Framework for Domain Adaptation
• Collaborative Semantic Aggregation and Calibration for Federated Domain Generalization
• Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification
• Privacy-Preserving Constrained Domain Generalization via Gradient Alignment