文献速递神经MR

T1加权脑MRI灰质结构的全面分割:卷积神经网络、卷积神经网络混合Transformer或Mamba架构的比较研究

Comprehensive Segmentation of Gray Matter Structures on T1-Weighted Brain MRI: A Comparative Study of Convolutional Neural Network, Convolutional Neural Network Hybrid-Transformer or -Mamba Architectures.
PubMed 文献 · AJNR Am J Neuroradiol · 2025-04-02

本研究用1510例T1加权脑MRI比较6种深度学习模型对122个灰质结构的分割性能,U-Mamba_Bot中位DSC最高(0.9112),nnU-Net的HD95最高(1.392),分割所得体积变化与文献一致。

要点

  • U-Mamba_Bot分割122个灰质结构的中位DSC最高,为0.9112。
  • nnU-Net的HD95为1.392,各模型HD95均小于3 mm。
  • 13个脑亚结构的体积变化与现有文献报道一致。

核心结论

  • U-Mamba_Bot是T1加权MRI上详细脑结构分割的稳健工具,体积分析与文献一致,先进深度学习模型可能有助于加深对AD等神经退行性疾病的理解。

研究设计与样本

  • 比较研究,使用1510例T1加权脑MRI比较6种深度学习模型(nnU-Net、SegResNet、SwinUNETR、UNETR、U-Mamba_BOT、U-Mamba_Enc)对122个灰质结构的分割性能,以DSC和HD95评价准确性,并计算各结构体积在正常对照与阿尔茨海默病患者间进行比较。

诊断标准与关键数值

  • U-Mamba_Bot中位DSC为0.9112(IQR:0.8957,0.9250);nnU-Net中位DSC为0.9027(IQR:0.8847,0.9205),HD95为1.392(IQR:1.174,2.029);各模型HD95均小于3 mm。

临床应用与阅片要点

  • 作者认为U-Mamba_Bot可作为T1加权MRI详细脑结构分割的稳健工具,其体积分析结果与文献一致,可能有助于增进对AD等神经退行性疾病的理解。

局限性

  • 未来研究应考虑更大的数据集以进一步验证这些发现。
  • 未来研究应探索这些模型在其他神经系统疾病中的适用性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

BACKGROUND AND PURPOSE: Recent advances in deep learning have shown promising results in medical image analysis and segmentation. However, most brain MRI segmentation models are limited by the size of their data sets and/or the number of structures they can identify. This study evaluates the performance of 6 advanced deep learning models in segmenting 122 brain structures from T1-weighted MRI scans, aiming to identify the most effective model for clinical and research applications.

MATERIALS AND METHODS: A total of 1510 T1-weighted MRIs were used to compare 6 deep learning models for the segmentation of 122 distinct gray matter structures: nnU-Net, SegResNet, SwinUNETR, UNETR, U-Mamba_BOT, and U-Mamba_ Enc. Each model was rigorously tested for accuracy by using the dice similarity coefficient (DSC) and the 95th percentile Hausdorff distance (HD95). Additionally, the volume of each structure was calculated and compared between normal controls (NCs) and patients with Alzheimer disease (AD).

RESULTS: U-Mamba_Bot achieved the highest performance with a median DSC of 0.9112 (interquartile range [IQR]: 0.8957, 0.9250). nnU-Net achieved a median DSC of 0.9027 [IQR: 0.8847, 0.9205], and had the highest HD95 of 1.392 [IQR: 1.174, 2.029]. The value of each HD95 (<3 mm) indicates its superior capability in capturing detailed brain structures accurately. Following segmentation, volume calculations were performed, and the resultant volumes of NCs and patients with AD were compared. The volume changes observed in 13 brain substructures were all consistent with those reported in existing literature, reinforcing the reliability of the segmentation outputs.

CONCLUSIONS: This study underscores the efficacy of U-Mamba_Bot as a robust tool for detailed brain structure segmentation in T1-weighted MRI scans. The congruence of our volumetric analysis with the literature further validates the potential of advanced deep learning models to enhance the understanding of neurodegenerative diseases such as AD. Future research should consider larger data sets to validate these findings further and explore the applicability of these models in other neurologic conditions.

来源:AJNR Am J Neuroradiol,查看原文。版权归原作者所有。

引用

  1. Wei Y, Jagtap JM, Singh Y, et al. Comprehensive Segmentation of Gray Matter Structures on T1-Weighted Brain MRI: A Comparative Study of Convolutional Neural Network, Convolutional Neural Network Hybrid-Transformer or -Mamba Architectures. AJNR Am J Neuroradiol. 2025. PMID: 39433334. doi:10.3174/ajnr.A8544

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。