文献速递乳腺甲状腺与浅表妇产影像US

频率感知视觉曼巴网络结合可变形窗口选择性扫描用于超声图像分割

Frequency-aware Vision Mamba With Deformable Windowed Selective Scan for Ultrasound Image Segmentation.
PubMed 文献 · Ultrasound Med Biol · 2026-03-19

该研究提出一种频率感知视觉曼巴网络,利用快速傅里叶变换提取频域信息并进行频率感知加权,同时设计可变形窗口选择性扫描模块动态调整扫描路径以聚焦模糊边界。在4个跨域超声数据集上,该方法在乳腺超声、甲状腺腺体分割、甲状腺结节分割与分类、多模态卵巢肿瘤超声数据集上的Dice系数分别为0.84、0.83、0.84和0.87,对应交并比分别为0.76、0.76、0.76和0.80,优于其他先进方法。

要点

  • 频率感知视觉曼巴网络在4个跨域超声数据集上Dice系数为0.83–0.87,交并比为0.76–0.80。
  • 频率感知选择性状态空间层利用快速傅里叶变换提取频域信息并加权,以缓解类内不一致。
  • 可变形窗口选择性扫描模块通过可学习偏移场动态调整扫描路径,以聚焦模糊边界、减少类间混淆。

核心结论

  • 所提方法为临床超声图像分析提供了稳健解决方案,可应对类间混淆和类内不一致挑战。

研究设计与样本

  • 研究为方法学论文,提出频率感知视觉曼巴网络结合可变形窗口选择性扫描。
  • 在4个跨域超声数据集上进行广泛实验,包括乳腺超声图像、甲状腺腺体分割、甲状腺结节分割与分类、多模态卵巢肿瘤超声数据集。

诊断标准与关键数值

  • 乳腺超声图像上Dice系数0.84,交并比0.76。
  • 甲状腺腺体分割上Dice系数0.83,交并比0.76。
  • 甲状腺结节分割与分类上Dice系数0.84,交并比0.76。
  • 多模态卵巢肿瘤超声数据集上Dice系数0.87,交并比0.80。

局限性

  • 原文未报告局限性。

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

OBJECTIVE: Accurate segmentation of ultrasound images is crucial for medical diagnosis and treatment. However, achieving precise lesion segmentation is challenging owing to inter-class indistinction caused by low contrast, high speckle noise and blurred boundaries, as well as intra-class inconsistency resulting from variations in lesion size, shape and location.

METHODS: To address these challenges, we propose a frequency-aware vision mamba network with deformable windowed selective scan. Specifically, we introduce the frequency-aware selective state space layer, which uses fast Fourier transform to extract frequency-domain information and applies frequency-aware weighting to enhance discriminative features, effectively mitigating intra-class inconsistency. Moreover, we developed a deformable windowed selective scan module that dynamically adjusts scanning paths by a learnable offset field to focus on ambiguous boundaries, significantly reducing inter-class indistinction.

RESULTS: Extensive experiments on 4 cross-domain ultrasound datasets demonstrate that the frequency-aware vision mamba network outperforms other state-of-the-art methods, achieving Dice coefficient scores of 0.84, 0.83,0.84 and 0.87 on breast ultrasound images, thyroid gland segmentation, thyroid nodule segmentation and classification in ultrasound images and multi-modal ovarian tumor ultrasound datasets, respectively, with corresponding intersection over union scores of 0.76,0.76,0.76 and 0.80, respectively.

CONCLUSION: Our results show that the proposed method provides a robust solution for clinical ultrasound image analysis, addressing inter-class indistinction and intra-class inconsistency challenges.

来源:Ultrasound Med Biol,查看原文。版权归原作者所有。

引用

  1. Liu Y, Yang Y, Jiang Y, et al. Frequency-aware Vision Mamba With Deformable Windowed Selective Scan for Ultrasound Image Segmentation. Ultrasound Med Biol. 2026. PMID: 41856816. doi:10.1016/j.ultrasmedbio.2026.02.015

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。