SA$^{2}$Net: Scale-Adaptive Structure-Affinity Transformation for Spine Segmentation from Ultrasound Volume Projection Imaging

2025-10-30

AI Summary

In vertebral segmentation for ultrasound volume projection imaging (VPI), challenges include strong spatial correlations and complex morphologies of bony structures, leading to insufficient global contextual modeling and weak structural awareness. To address these, we propose a Scale-Adaptive Structural-aware Network (SAS-Net). SAS-Net innovatively integrates scale-adaptive complementary feature learning with a structural affinity transformation mechanism, coupled with a Transformer-based decoder for cross-dimensional long-range dependency modeling. It further incorporates multi-head self-attention and a feature-mixing loss to jointly optimize global semantic consistency and local structural fidelity. Evaluated on a public VPI dataset, SAS-Net achieves significant improvements over existing state-of-the-art methods. Moreover, it is backbone-agnostic—demonstrating strong generalizability across diverse architectures—and exhibits promising potential for clinical deployment.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Structured Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

Spine segmentation, based on ultrasound volume projection imaging (VPI), plays a vital role for intelligent scoliosis diagnosis in clinical applications. However, this task faces several significant challenges. Firstly, the global contextual knowledge of spines may not be well-learned if we neglect the high spatial correlation of different bone features. Secondly, the spine bones contain rich structural knowledge regarding their shapes and positions, which deserves to be encoded into the segmentation process. To address these challenges, we propose a novel scale-adaptive structure-aware network (SA$^{2}$Net) for effective spine segmentation. First, we propose a scale-adaptive complementary strategy to learn the cross-dimensional long-distance correlation features for spinal images. Second, motivated by the consistency between multi-head self-attention in Transformers and semantic level affinity, we propose structure-affinity transformation to transform semantic features with class-specific affinity and combine it with a Transformer decoder for structure-aware reasoning. In addition, we adopt a feature mixing loss aggregation method to enhance model training. This method improves the robustness and accuracy of the segmentation process. The experimental results demonstrate that our SA$^{2}$Net achieves superior segmentation performance compared to other state-of-the-art methods. Moreover, the adaptability of SA$^{2}$Net to various backbones enhances its potential as a promising tool for advanced scoliosis diagnosis using intelligent spinal image analysis. The code and experimental demo are available at https://github.com/taetiseo09/SA2Net.

Problem

• Addresses learning global contextual spine features in ultrasound images
• Encodes structural knowledge of spine shapes into segmentation
• Improves robustness and accuracy of spinal segmentation process

Innovation

• Scale-adaptive strategy learns cross-dimensional correlation features
• Structure-affinity transformation combines semantic features with class affinity
• Feature mixing loss aggregation enhances model training robustness