Towards Continuous Domain adaptation for Healthcare
This addresses the critical issue of model robustness in healthcare applications, where data variability can lead to failures, though it is incremental as it builds on existing domain adaptation methods.
The paper tackles the problem of deep learning models failing after deployment due to data distribution shifts in medical imaging, proposing ContextNets for continuous domain adaptation without retraining, achieving state-of-the-art performance on X-ray lung segmentation across three diverse cohorts.
Deep learning algorithms have demonstrated tremendous success on challenging medical imaging problems. However, post-deployment, these algorithms are susceptible to data distribution variations owing to \emph{limited data issues} and \emph{diversity} in medical images. In this paper, we propose \emph{ContextNets}, a generic memory-augmented neural network framework for semantic segmentation to achieve continuous domain adaptation without the necessity of retraining. Unlike existing methods which require access to entire source and target domain images, our algorithm can adapt to a target domain with a few similar images. We condition the inference on any new input with features computed on its support set of images (and masks, if available) through contextual embeddings to achieve site-specific adaptation. We demonstrate state-of-the-art domain adaptation performance on the X-ray lung segmentation problem from three independent cohorts that differ in disease type, gender, contrast and intensity variations.