基于CSWin Transformer的颈动脉三维超声图像分割方法
本文提出一种U形CSWin Transformer(U-CSWT)用于颈动脉三维超声图像中中膜-外膜边界(MAB)及管腔-内膜边界(LIB)的自动分割。在颈动脉三维超声数据集上,U-CSWT优于基于CNN及CNN-Transformer混合方法,在颈总动脉和分叉处获得较高Dice系数。
要点
- U-CSWT可自动分割颈动脉三维超声的MAB和LIB,性能优于CNN及混合方法。
- 颈总动脉MAB和LIB的Dice系数分别为94.6±3.0%和90.8±5.1%。
- 分叉处MAB和LIB的Dice系数分别为92.9±4.9%和89.6±6.2%。
核心结论
- U-CSWT在颈动脉三维超声图像分割中表现优于基于CNN和CNN-Transformer混合的方法,有望成为颈动脉结构自动分割的有效方法。
研究设计与样本
- 研究为方法学论文,提出U-CSWT模型并在颈动脉三维超声图像数据集上进行实验,未报告样本量、中心数及参考标准细节。
诊断标准与关键数值
- 颈总动脉MAB的Dice系数为94.6±3.0%,LIB为90.8±5.1%。
- 分叉处MAB的Dice系数为92.9±4.9%,LIB为89.6±6.2%。
临床应用与阅片要点
- 该自动分割方法可用于辅助颈动脉三维超声图像中MAB和LIB的勾画,提升评估效率。
- 从摘要看,分叉处LIB的Dice系数相对较低(89.6±6.2%),阅片时需注意分叉处边界的准确性。
局限性
- 摘要未报告样本量、中心数及参考标准,无法评估泛化能力。
- 仅报告Dice系数,未提供敏感度、特异度、AUC等其他分割评价指标。
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
Precise segmentation of carotid artery (CA) structure is an important prerequisite for the medical assessment and detection of carotid plaques. For automatic segmentation of the media-adventitia boundary (MAB) and lumen-intima boundary (LIB) in 3-D ultrasound images of the CA, a U-shaped CSWin transformer (U-CSWT) is proposed. Both the encoder and decoder of the U-CSWT are composed of hierarchical CSWT modules, which can capture rich global context information in the 3-D image. Experiments were performed on a 3-D ultrasound image data set of the CA, and the results indicate that the U-CSWT performs better than other convolutional neural network (CNN)-based and CNN-transformer hybrid methods. The model yields Dice coefficients of 94.6 ± 3.0% and 90.8 ± 5.1% for the MAB and LIB in the common carotid artery (CCA) and 92.9 ± 4.9% and 89.6 ± 6.2% for MAB and LIB in the bifurcation, respectively. Our U-CSWT is expected to become an effective method for automatic segmentation of 3-D ultrasound images of CA.
引用
- Lin, Huang, Xu, et al. Method for Carotid Artery 3-D Ultrasound Image Segmentation Based on CSWin Transformer. Ultrasound Med Biol. 2022. PMID: 36460566. doi:10.1016/j.ultrasmedbio.2022.11.005
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。