Embracing the Disharmony in Medical Imaging: A Simple and Effective Framework for Domain Adaptation

Abstract

Domain shift, the mismatch between training and testing data characteristics, causes significant degradation in the predictive performance in multi-source imaging scenarios. In medical imaging, the heterogeneity of population, scanners and acquisition protocols at different sites presents a significant domain shift challenge and has limited the widespread clinical adoption of machine learning models. Harmonization methods which aim to learn a representation of data invariant to these differences are the prevalent tools to address domain shift, but they typically result in degradation of predictive accuracy. This paper takes a different perspective of the problem: we embrace this disharmony in data and design a simple but effective framework for tackling domain shift. The key idea, based on our theoretical arguments, is to build a pretrained classifier on the source data and adapt this model to new data. The classifier can be fine-tuned for intra-site domain adaptation. We can also tackle situations where we do not have access to ground-truth labels on target data; we show how one can use auxiliary tasks for adaptation; these tasks employ covariates such as age, gender and race which are easy to obtain but nevertheless correlated to the main task. We demonstrate substantial improvements in both intra-site domain adaptation and inter-site domain generalization on large-scale real-world 3D brain MRI datasets for classifying Alzheimer's disease and schizophrenia.

References in corpus (13)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Learning Transferable Features with Deep Adaptation Networks
• Deep Domain Confusion: Maximizing for Domain Invariance
• Theoretical Models of Learning to Learn
• A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises
• Detect and Correct Bias in Multi-Site Neuroimaging Datasets
• Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization
• A Causal View on Robustness of Neural Networks
• Domain Adaptation as a Problem of Inference on Graphical Models
• Image-level Harmonization of Multi-Site Data using Image-and-Spatial Transformer Networks
• Medical Image Harmonization Using Deep Learning Based Canonical Mapping: Toward Robust and Generalizable Learning in Imaging
• Learning Cross-domain Generalizable Features by Representation Disentanglement