Learn the new, keep the old: Extending pretrained models with new anatomy and images

TL;DR

This paper proposes a framework for incremental learning in medical image segmentation, enabling models to incorporate new anatomical and imaging data without retraining from scratch, thus saving computational resources.

Contribution

It introduces novel data selection methods for incremental learning and demonstrates their effectiveness on MR image segmentation tasks.

Findings

Improved segmentation performance with incremental learning methods

Efficient data selection reduces training complexity

Validated on diverse MR imaging scenarios

Abstract

Deep learning has been widely accepted as a promising solution for medical image segmentation, given a sufficiently large representative dataset of images with corresponding annotations. With ever increasing amounts of annotated medical datasets, it is infeasible to train a learning method always with all data from scratch. This is also doomed to hit computational limits, e.g., memory or runtime feasible for training. Incremental learning can be a potential solution, where new information (images or anatomy) is introduced iteratively. Nevertheless, for the preservation of the collective information, it is essential to keep some "important" (i.e. representative) images and annotations from the past, while adding new information. In this paper, we introduce a framework for applying incremental learning for segmentation and propose novel methods for selecting representative data therein. We comparatively evaluate our methods in different scenarios using MR images and validate the increased learning capacity with using our methods.