基于深度学习的经胸超声心动图二尖瓣分割与追踪
研究对127例患者2931张二尖瓣超声图像标注瓣叶及瓣环铰链点,采用带深度监督和注意力系数权重调度的Attention UNet分割,Dice评分0.63±0.14、瓣环误差3.64±2.53、瓣叶角度误差8.7±8.3°,并据此提取生物标志物识别二尖瓣脱垂、狭窄及健康参照。
要点
- Attention UNet联合深度监督可自动分割二尖瓣瓣叶与瓣环铰链点,Dice评分0.63±0.14。
- 瓣环误差3.64±2.53、瓣叶角度误差8.7±8.3°,模型可提取瓣叶扇区定量生物标志物。
- 较UNet降低标准差2.7°(角度误差)和0.73 mm(瓣环误差),提升临床指标稳健性。
核心结论
- 利用注意力门与深度监督可实现二尖瓣形态与运动的稳健深度学习分割与追踪,作者认为有望改善瓣膜性心脏病诊断与治疗监测。
研究设计与样本
- 研究论文;标注127例患者共2931张二尖瓣超声图像,采用Attention UNet结合深度监督及注意力系数权重调度进行分割,以标注特征为参考。
关键影像表现/征象
- 分割掩膜用于提取心动周期中特定二尖瓣瓣叶扇区的定量生物标志物。
- 利用所提取生物标志物可从临床资料中正确识别二尖瓣脱垂病例、狭窄病例及健康参照。
诊断标准与关键数值
- 分割性能以Dice评分0.63±0.14、瓣环误差3.64±2.53、瓣叶角度误差8.7±8.3°汇总。
- Attention UNet较UNet降低标准差2.7°(角度误差)和0.73 mm(瓣环误差)。
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: Valvular heart diseases (VHDs) pose a significant public health burden, and deciding the best treatment strategy necessitates accurate assessment of heart valve function. Transthoracic echocardiography (TTE) is the key modality to evaluate VHDs, but the lack of standardized quantitative measurements leads to subjective and time-consuming assessments. We aimed to use deep learning to automate the extraction of mitral valve (MV) leaflets and annular hinge points from echocardiograms of the MV, improving standardization and reducing workload in quantitative assessment of MV disease.
METHODS: We annotated the MV leaflets and annulus points in 2931 images from 127 patients. We propose an approach for segmenting the annotated features using Attention UNet with deep supervision and weight scheduling of the attention coefficients to enforce saliency surrounding the MV. The derived segmentation masks were used to extract quantitative biomarkers for specific MV leaflet scallops throughout the heart cycle.
RESULTS: Evaluation performance was summarized using a Dice score of 0.63 ± 0.14, annulus error of 3.64 ± 2.53 and leaflet angle error of 8.7 ± 8.3°. Leveraging Attention UNet with deep supervision robustness of clinically relevant metrics was improved compared with UNet, reducing standard deviations by 2.7° (angle error) and 0.73 mm (annulus error). We correctly identified cases of MV prolapse, cases of stenosis and healthy references from a clinical material using the derived biomarkers.
CONCLUSION: Robust deep learning segmentation and tracking of MV morphology and motion is possible by leveraging attention gates and deep supervision, and holds promise for enhancing VHD diagnosis and treatment monitoring.
引用
- Wifstad SV, Kildahl HA, Grenne B, et al. Mitral Valve Segmentation and Tracking from Transthoracic Echocardiography Using Deep Learning. Ultrasound Med Biol. 2024. PMID: 38341361. doi:10.1016/j.ultrasmedbio.2023.12.023
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。