# Adaptive Transformer Attention and Multi-Scale Fusion for Spine 3D Segmentation

arXiv: https://arxiv.org/abs/2503.12853 · HTML: https://mlsanity.com/paper/2503.12853/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 22 references that are in the map.
- First posted on arXiv 17 Mar 2025.

## Builds on (most cited first, 8 of 8)

- [Survival Prediction Across Diverse Cancer Types Using Neural Networks](https://mlsanity.com/paper/2404.08713/) (2024)
- [Graph Neural Network-Driven Hierarchical Mining for Complex Imbalanced Data](https://mlsanity.com/paper/2502.03803/) (2025)
- [Optimized Unet with Attention Mechanism for Multi-Scale Semantic Segmentation](https://mlsanity.com/paper/2502.03813/) (2025)
- [A Hybrid Model for Few-Shot Text Classification Using Transfer and Meta-Learning](https://mlsanity.com/paper/2502.09086/) (2025)
- [A Fine-Tuning Approach for T5 Using Knowledge Graphs to Address Complex Tasks](https://mlsanity.com/paper/2502.16484/) (2025)
- [Multi-Level Attention and Contrastive Learning for Enhanced Text Classification with an Optimized Transformer](https://mlsanity.com/paper/2501.13467/) (2025)
- [Lumbar Spine Tumor Segmentation and Localization in T2 MRI Images Using AI](https://mlsanity.com/paper/2405.04023/) (2024)
- [TSUBF-Net: Trans-Spatial UNet-like Network with Bi-direction Fusion for Segmentation of Adenoid Hypertrophy in CT](https://mlsanity.com/paper/2412.00787/) (2024)

## Built on by (most cited first, 1 of 1)

- [Pre-trained Language Models and Few-shot Learning for Medical Entity Extraction](https://mlsanity.com/paper/2504.04385/) (2025)

## Abstract (arXiv)

This study proposes a 3D semantic segmentation method for the spine based on the improved SwinUNETR to improve segmentation accuracy and robustness. Aiming at the complex anatomical structure of spinal images, this paper introduces a multi-scale fusion mechanism to enhance the feature extraction capability by using information of different scales, thereby improving the recognition accuracy of the model for the target area. In addition, the introduction of the adaptive attention mechanism enables the model to dynamically adjust the attention to the key area, thereby optimizing the boundary segmentation effect. The experimental results show that compared with 3D CNN, 3D U-Net, and 3D U-Net + Transformer, the model of this study has achieved significant improvements in mIoU, mDice, and mAcc indicators, and has better segmentation performance. The ablation experiment further verifies the effectiveness of the proposed improved method, proving that multi-scale fusion and adaptive attention mechanism have a positive effect on the segmentation task. Through the visualization analysis of the inference results, the model can better restore the real anatomical structure of the spinal image. Future research can further optimize the Transformer structure and expand the data scale to improve the generalization ability of the model. This study provides an efficient solution for the task of medical image segmentation, which is of great significance to intelligent medical image analysis.