Segmentation of Multiple Sclerosis Lesions across Hospitals: Learn Continually or Train from Scratch?
This addresses the challenge of model generalization in medical imaging for MS diagnosis, but it is incremental as it applies an existing continual learning method to a specific domain.
The paper tackles the problem of segmenting Multiple Sclerosis lesions across datasets from different hospitals, showing that continual learning with experience replay reduces catastrophic forgetting and outperforms multi-domain training.
Segmentation of Multiple Sclerosis (MS) lesions is a challenging problem. Several deep-learning-based methods have been proposed in recent years. However, most methods tend to be static, that is, a single model trained on a large, specialized dataset, which does not generalize well. Instead, the model should learn across datasets arriving sequentially from different hospitals by building upon the characteristics of lesions in a continual manner. In this regard, we explore experience replay, a well-known continual learning method, in the context of MS lesion segmentation across multi-contrast data from 8 different hospitals. Our experiments show that replay is able to achieve positive backward transfer and reduce catastrophic forgetting compared to sequential fine-tuning. Furthermore, replay outperforms the multi-domain training, thereby emerging as a promising solution for the segmentation of MS lesions. The code is available at this link: https://github.com/naga-karthik/continual-learning-ms