文献速递心血管US

一种用于低质量和高干扰心肌声学造影的形态一致深度学习分割架构

A Shape-Consistent Deep-Learning Segmentation Architecture for Low-Quality and High-Interference Myocardial Contrast Echocardiography.
PubMed 文献 · Ultrasound Med Biol · 2024-08-14

该研究提出一种深度学习网络用于心肌声学造影(MCE)图像分割,采用空洞卷积和改良多头自注意力机制,并与Transformer和卷积神经网络级联。在标准MCE视图、非标准视图和含干扰结构(肿块)的帧中,Dice分数分别为84.35%、83.33%和83.97%,优于多个先进分割模型。

要点

  • 该深度学习架构在标准MCE视图分割中Dice分数达84.35%,优于对比的先进模型。
  • 在非标准视图和含干扰结构(肿块)的帧中,Dice分数分别为83.33%和83.97%。
  • 该架构利用空洞卷积和改良多头自注意力提升分割形态一致性和鲁棒性。

核心结论

  • 该架构具有优良的形态一致性和鲁棒性,能够处理多种类型MCE的分割,为多种心脏疾病的自动化分析提供基础条件。

研究设计与样本

  • 研究提出并验证一种深度学习分割网络,采用空洞卷积捕获高尺度信息,改良多头自注意力增强全局上下文,并将Transformer与卷积神经网络级联应用;与多个先进分割模型进行对比实验。

诊断标准与关键数值

  • 标准MCE视图分割Dice分数84.35%,优于对比的先进分割模型。
  • 非标准视图分割Dice分数83.33%,为对比模型中最优。
  • 含干扰结构(肿块)的帧分割Dice分数83.97%,为对比模型中最优。

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: Myocardial contrast echocardiography (MCE) plays a crucial role in diagnosing ischemia, infarction, masses and other cardiac conditions. In the realm of MCE image analysis, accurate and consistent myocardial segmentation results are essential for enabling automated analysis of various heart diseases. However, current manual diagnostic methods in MCE suffer from poor repeatability and limited clinical applicability. MCE images often exhibit low quality and high noise due to the instability of ultrasound signals, while interference structures can further disrupt segmentation consistency.

METHODS: To overcome these challenges, we proposed a deep-learning network for the segmentation of MCE. This architecture leverages dilated convolutions to capture high-scale information without sacrificing positional accuracy and modifies multi-head self-attention to enhance global context and ensure consistency, effectively overcoming issues related to low image quality and interference. Furthermore, we also adapted the cascade application of transformers with convolutional neural networks for improved segmentation in MCE.

RESULTS: In our experiments, our architecture achieved the best Dice score of 84.35% for standard MCE views compared with that of several state-of-the-art segmentation models. For non-standard views and frames with interfering structures (mass), our models also attained the best Dice scores of 83.33% and 83.97%, respectively.

CONCLUSION: These studies proved that our architecture is of excellent shape consistency and robustness, which allows it to deal with segmentation of various types of MCE. Our relatively precise and consistent myocardial segmentation results provide fundamental conditions for the automated analysis of various heart diseases, with the potential to discover underlying pathological features and reduce healthcare costs.

来源:Ultrasound Med Biol,查看原文。版权归原作者所有。

引用

  1. Cui R, Liang S, Zhao W, et al. A Shape-Consistent Deep-Learning Segmentation Architecture for Low-Quality and High-Interference Myocardial Contrast Echocardiography. Ultrasound Med Biol. 2024. PMID: 39147622. doi:10.1016/j.ultrasmedbio.2024.06.001

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。