Do Edges Matter? Investigating Edge-Enhanced Pre-Training for Medical Image Segmentation

TL;DR

This paper investigates the impact of edge-enhanced pre-training on medical image segmentation across multiple modalities, proposing a meta-learning strategy to select optimal pre-training data, resulting in significant performance improvements.

Contribution

It systematically examines the effects of edge-focused pre-training and introduces a meta-learning approach for optimal model selection across diverse medical imaging modalities.

Findings

Edge pre-training can both improve and impair segmentation depending on the modality.

The proposed meta-learning strategy effectively guides the choice of pre-training data.

Overall segmentation performance improved by up to 19.30% with the new approach.

Abstract

Medical image segmentation is crucial for disease diagnosis and treatment planning, yet developing robust segmentation models often requires substantial computational resources and large datasets. Existing research shows that pre-trained and finetuned foundation models can boost segmentation performance. However, questions remain about how particular image preprocessing steps may influence segmentation performance across different medical imaging modalities. In particular, edges-abrupt transitions in pixel intensity-are widely acknowledged as vital cues for object boundaries but have not been systematically examined in the pre-training of foundation models. We address this gap by investigating to which extend pre-training with data processed using computationally efficient edge kernels, such as kirsch, can improve cross-modality segmentation capabilities of a foundation model. Two versions of a foundation model are first trained on either raw or edge-enhanced data across multiple medical imaging modalities, then finetuned on selected raw subsets tailored to specific medical modalities. After systematic investigation using the medical domains Dermoscopy, Fundus, Mammography, Microscopy, OCT, US, and XRay, we discover both increased and reduced segmentation performance across modalities using edge-focused pre-training, indicating the need for a selective application of this approach. To guide such selective applications, we propose a meta-learning strategy. It uses standard deviation and image entropy of the raw image to choose between a model pre-trained on edge-enhanced or on raw data for optimal performance. Our experiments show that integrating this meta-learning layer yields an overall segmentation performance improvement across diverse medical imaging tasks by 16.42% compared to models pre-trained on edge-enhanced data only and 19.30% compared to models pre-trained on raw data only.