# Anatomy-Aware Text-Visual Fusion with Dual-Perspective Prompts for Fine-Grained Lumbar Spine Segmentation

Source: [Anatomy-Aware Text-Visual Fusion with Dual-Perspective Prompts for Fine-Grained Lumbar Spine Segmentation](<https://www.sota2.com/research/paper/68fa77c41e209131cea7532c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-25T05:00:04.395Z

Authors: Sheng Lian, Jianlong Cai, Dengfeng Pan, Guang-Yong Chen, Hao Xu, Fan Zhang, Guodong Fan, Shuo Li

Published: 2025-04-04T14:36:12.000Z

## Abstract

Accurate lumbar spine segmentation is crucial for diagnosing spinal disorders. Existing methods typically use coarse-grained segmentation strategies that lack the fine detail needed for precise diagnosis. Additionally, their reliance on visual-only models hinders the capture of anatomical semantics, leading to misclassified categories and poor segmentation details. To address these limitations, we present ATM-Net, an innovative framework that employs an anatomy-aware, text-guided, multi-modal fusion mechanism for fine-grained segmentation of lumbar substructures, i.e., vertebrae (VBs), intervertebral discs (IDs), and spinal canal (SC). ATM-Net adopts the Anatomy-aware Text Prompt Generator (ATPG) to adaptively convert image annotations into anatomy-aware prompts in different views. These insights are further integrated with image features via the Holistic Anatomy-aware Semantic Fusion (HASF) module, building a comprehensive anatomical context. The Channel-wise Contrastive Anatomy-Aware Enhancement (CCAE) module further enhances class discrimination and refines segmentation through class-wise channel-level multi-modal contrastive learning. Extensive experiments on the MRSpineSeg and SPIDER datasets demonstrate that ATM-Net significantly outperforms state-of-the-art methods, with consistent improvements regarding class discrimination and segmentation details. For example, ATM-Net achieves Dice of 79.39% and HD95 of 9.91 pixels on SPIDER, outperforming the competitive SpineParseNet by 8.31% and 4.14 pixels, respectively.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Lumbar Spine Segmentation on MRSpineSeg](<https://www.sota2.com/research/sota/lumbar-spine-segmentation-on-mrspineseg.md>): Lumbar spine segmentation; MRSpineSeg; DSC: 81.72.

- [Lumbar Spine Segmentation on SPIDER](<https://www.sota2.com/research/sota/lumbar-spine-segmentation-on-spider.md>): Lumbar spine segmentation; Spider; DSC: 79.39.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2504.03476>)

[PDF](<https://arxiv.org/pdf/2504.03476.pdf>)
