SpineMamba: Enhancing 3D Spinal Segmentation in Clinical Imaging through Residual Visual Mamba Layers and Shape Priors

TL;DR

SpineMamba introduces residual visual Mamba layers and shape priors to improve 3D spinal segmentation accuracy, robustness, and generalization in clinical imaging, outperforming existing models on CT and MR datasets.

Contribution

The paper proposes a novel neural network architecture with residual visual Mamba layers and shape priors for enhanced 3D spinal segmentation.

Findings

Achieves up to 94.40% Dice score on CT data.

Outperforms nnU-Net by up to 2 percentage points.

Demonstrates superior robustness and generalization.

Abstract

Accurate segmentation of 3D clinical medical images is critical in the diagnosis and treatment of spinal diseases. However, the inherent complexity of spinal anatomy and uncertainty inherent in current imaging technologies, poses significant challenges for semantic segmentation of spinal images. Although convolutional neural networks (CNNs) and Transformer-based models have made some progress in spinal segmentation, their limitations in handling long-range dependencies hinder further improvements in segmentation accuracy.To address these challenges, we introduce a residual visual Mamba layer to effectively capture and model the deep semantic features and long-range spatial dependencies of 3D spinal data. To further enhance the structural semantic understanding of the vertebrae, we also propose a novel spinal shape prior module that captures specific anatomical information of the spine from medical images, significantly enhancing the model's ability to extract structural semantic information of the vertebrae. Comparative and ablation experiments on two datasets demonstrate that SpineMamba outperforms existing state-of-the-art models. On the CT dataset, the average Dice similarity coefficient for segmentation reaches as high as 94.40, while on the MR dataset, it reaches 86.95. Notably, compared to the renowned nnU-Net, SpineMamba achieves superior segmentation performance, exceeding it by up to 2 percentage points. This underscores its accuracy, robustness, and excellent generalization capabilities.