HUR-MACL: High-Uncertainty Region-Guided Multi-Architecture Collaborative Learning for Head and Neck Multi-Organ Segmentation

TL;DR

This paper introduces HUR-MACL, a collaborative learning framework that adaptively targets high-uncertainty regions with multiple architectures to improve multi-organ segmentation accuracy in head and neck imaging.

Contribution

It proposes a novel high uncertainty region-guided multi-architecture collaborative learning approach with a heterogeneous feature distillation loss for improved segmentation.

Findings

Achieves state-of-the-art results on three datasets.

Effectively identifies and improves segmentation in high-uncertainty regions.

Demonstrates the benefit of multi-architecture collaboration in complex organ segmentation.

Abstract

Accurate segmentation of organs at risk in the head and neck is essential for radiation therapy, yet deep learning models often fail on small, complexly shaped organs. While hybrid architectures that combine different models show promise, they typically just concatenate features without exploiting the unique strengths of each component. This results in functional overlap and limited segmentation accuracy. To address these issues, we propose a high uncertainty region-guided multi-architecture collaborative learning (HUR-MACL) model for multi-organ segmentation in the head and neck. This model adaptively identifies high uncertainty regions using a convolutional neural network, and for these regions, Vision Mamba as well as Deformable CNN are utilized to jointly improve their segmentation accuracy. Additionally, a heterogeneous feature distillation loss was proposed to promote collaborative learning between the two architectures in high uncertainty regions to further enhance performance. Our method achieves SOTA results on two public datasets and one private dataset.