College of Computer Science, Sichuan University, Chengdu, China.
Department of Cardiology, West China Hospital, Sichuan University, Chengdu, China.
Ultrasound Med Biol. 2024 Nov;50(11):1602-1610. doi: 10.1016/j.ultrasmedbio.2024.06.001. Epub 2024 Aug 14.
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.
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.
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.
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.
心肌对比超声心动图（MCE）在诊断缺血、梗死、肿块和其他心脏疾病方面发挥着关键作用。在 MCE 图像分析领域，准确且一致的心肌分割结果对于实现各种心脏病的自动分析至关重要。然而，目前 MCE 中的手动诊断方法存在可重复性差和临床应用受限的问题。由于超声信号不稳定，MCE 图像通常质量较低且噪声较高，而干扰结构会进一步破坏分割的一致性。
为了克服这些挑战，我们提出了一种用于 MCE 分割的深度学习网络。该架构利用扩张卷积来捕获高尺度信息，同时保持位置准确性，并修改多头自注意力机制来增强全局上下文并确保一致性，从而有效解决图像质量低和干扰问题。此外，我们还采用了带有卷积神经网络的级联转换器，以提高 MCE 中的分割性能。
在实验中，我们的架构在标准 MCE 视图中取得了 84.35%的最佳 Dice 得分，优于几个最先进的分割模型。对于非标准视图和存在干扰结构（肿块）的帧，我们的模型也分别取得了 83.33%和 83.97%的最佳 Dice 得分。
这些研究证明了我们的架构具有出色的形状一致性和鲁棒性，能够处理各种类型的 MCE 分割。我们较为精确和一致的心肌分割结果为各种心脏病的自动分析提供了基本条件，有望发现潜在的病理特征并降低医疗成本。
