Towards continuous learning for glioma segmentation with elastic weight consolidation
This addresses incremental learning challenges in medical imaging for glioma segmentation, though it is an incremental application of an existing method.
The study tackled catastrophic forgetting in convolutional neural networks when finetuning for glioma segmentation across datasets, finding that Elastic Weight Consolidation reduced forgetting but limited adaptation to new data.
When finetuning a convolutional neural network (CNN) on data from a new domain, catastrophic forgetting will reduce performance on the original training data. Elastic Weight Consolidation (EWC) is a recent technique to prevent this, which we evaluated while training and re-training a CNN to segment glioma on two different datasets. The network was trained on the public BraTS dataset and finetuned on an in-house dataset with non-enhancing low-grade glioma. EWC was found to decrease catastrophic forgetting in this case, but was also found to restrict adaptation to the new domain.