AGENet: Adaptive Edge-aware Geodesic Distance Learning for Few-Shot Medical Image Segmentation

TL;DR

AGENet introduces a lightweight, edge-aware geodesic distance learning framework that enhances few-shot medical image segmentation by accurately capturing anatomical boundaries and spatial relationships, outperforming existing methods.

Contribution

The paper presents a novel adaptive framework combining geodesic distance learning, boundary-aware prototype extraction, and automatic parameter tuning for improved few-shot medical segmentation.

Findings

Reduces boundary errors significantly.

Outperforms state-of-the-art methods on multiple datasets.

Maintains computational efficiency suitable for clinical use.

Abstract

Medical image segmentation requires large annotated datasets, creating a significant bottleneck for clinical applications. While few-shot segmentation methods can learn from minimal examples, existing approaches demonstrate suboptimal performance in precise boundary delineation for medical images, particularly when anatomically similar regions appear without sufficient spatial context. We propose AGENet (Adaptive Geodesic Edge-aware Network), a novel framework that incorporates spatial relationships through edge-aware geodesic distance learning. Our key insight is that medical structures follow predictable geometric patterns that can guide prototype extraction even with limited training data. Unlike methods relying on complex architectural components or heavy neural networks, our approach leverages computationally lightweight geometric modeling. The framework combines three main components: (1) An edge-aware geodesic distance learning module that respects anatomical boundaries through iterative Fast Marching refinement, (2) adaptive prototype extraction that captures both global structure and local boundary details via spatially-weighted aggregation, and (3) adaptive parameter learning that automatically adjusts to different organ characteristics. Extensive experiments across diverse medical imaging datasets demonstrate improvements over state-of-the-art methods. Notably, our method reduces boundary errors compared to existing approaches while maintaining computational efficiency, making it highly suitable for clinical applications requiring precise segmentation with limited annotated data.