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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Zhiqing, Liu, Tianyong, Fan, Guojia, Li, Bin, Feng, Qianjin, Zhou, Shoujun
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912004788191232
author Zhang, Zhiqing
Liu, Tianyong
Fan, Guojia
Li, Bin
Feng, Qianjin
Zhou, Shoujun
author_facet Zhang, Zhiqing
Liu, Tianyong
Fan, Guojia
Li, Bin
Feng, Qianjin
Zhou, Shoujun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_15887
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SpineMamba: Enhancing 3D Spinal Segmentation in Clinical Imaging through Residual Visual Mamba Layers and Shape Priors
Zhang, Zhiqing
Liu, Tianyong
Fan, Guojia
Li, Bin
Feng, Qianjin
Zhou, Shoujun
Image and Video Processing
Computer Vision and Pattern Recognition
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.
title SpineMamba: Enhancing 3D Spinal Segmentation in Clinical Imaging through Residual Visual Mamba Layers and Shape Priors
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.15887