FOAL: Fast Online Adaptive Learning for Cardiac Motion Estimation
This addresses the challenge of adapting cardiac motion estimation models to diverse clinical datasets, though it is incremental as it builds on existing meta-learning and online adaptation techniques.
The paper tackled the problem of performance drops in deep learning-based cardiac MRI motion estimation due to mismatched training-testing distributions in clinical settings, proposing a fast online adaptive learning framework that achieved superior accuracy and required only 0.4 seconds per video for online optimization.
Motion estimation of cardiac MRI videos is crucial for the evaluation of human heart anatomy and function. Recent researches show promising results with deep learning-based methods. In clinical deployment, however, they suffer dramatic performance drops due to mismatched distributions between training and testing datasets, commonly encountered in the clinical environment. On the other hand, it is arguably impossible to collect all representative datasets and to train a universal tracker before deployment. In this context, we proposed a novel fast online adaptive learning (FOAL) framework: an online gradient descent based optimizer that is optimized by a meta-learner. The meta-learner enables the online optimizer to perform a fast and robust adaptation. We evaluated our method through extensive experiments on two public clinical datasets. The results showed the superior performance of FOAL in accuracy compared to the offline-trained tracking method. On average, the FOAL took only $0.4$ second per video for online optimization.