基于U-Net架构的膜性声门间隙面积自动分割
研究使用137例患者的2507张视频频闪喉镜图像开发了五种基于U-Net的深度学习分割模型,用于自动勾画膜性声门间隙面积,并用41例不同患者的410张图像进行验证。验证中Efficient U-Net的并集交比为0.8455、Dice系数为0.9163、Hausdorff距离为1.5626,均表现最佳。作者认为Efficient U-Net在分割质量和速度上是该任务的合理选择。
要点
- 基于U-Net的深度学习模型可实现膜性声门间隙面积的自动分割。
- 验证中Efficient U-Net的并集交比为0.8455、Dice系数为0.9163、Hausdorff距离为1.5626。
- Efficient U-Net和VGG19 U-Net的归一化膜性声门间隙面积指数均方误差分别为3.5476和3.3842。
核心结论
- 基于U-Net架构可实现膜性声门间隙面积的自动分割。
- 综合考虑分割质量和速度,Efficient U-Net是该任务的合理选择,其余四种模型仍是有价值的竞争者。
- 模型勾画的掩膜区域使归一化膜性声门间隙面积的计算和声门面积波形分析成为可能,显示出有前景的临床应用。
研究设计与样本
- 研究使用来自137例患者的共2507张视频频闪喉镜图像,开发了五种基于U-Net的深度学习图像分割模型,用于自动掩膜膜性声门间隙面积。
- 为进一步验证模型,研究另使用来自41例不同患者的410张图像。
主要发现
- 开发过程中,五种模型均表现出可接受且相似的指标。
- VGG19 U-Net的推理时间为1654 ms,其余四种模型的推理时间在16至138 ms之间,更具实用性。
- 进一步验证中,Efficient U-Net表现出最高的并集交比0.8455、最高的Dice系数0.9163和最低的Hausdorff距离1.5626。
- 归一化膜性声门间隙面积指数亦被计算并验证,Efficient U-Net和VGG19 U-Net表现出最低的均方误差(分别为3.5476和3.3842)和最低的平均绝对误差(分别为1.8835和1.8396)。
临床怎么用
- 作者认为,综合考虑分割质量和速度,Efficient U-Net是该任务的合理选择,其余四种模型仍是有价值的竞争者。
- 作者指出,模型勾画的掩膜区域使归一化膜性声门间隙面积的计算和声门面积波形分析成为可能,显示出有前景的临床应用。
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)。
原文
BACKGROUND: While videostroboscopy is recognized as the most popular approach for investigating vocal fold function, evaluating the numerical values, such as the membranous glottal gap area, remains too time consuming for clinical applications. METHODS: We used a total of 2507 videostroboscopy images from 137 patients and developed five U-Net-based deep-learning image segmentation models for automatic masking of the membranous glottal gap area. To further validate the models, we used another 410 images from 41 different patients. RESULTS: During development, all five models exhibited acceptable and similar metrics. While the VGG19 U-Net had a long inference time of 1654 ms, the other four models had more practical inference times, ranging from 16 to 138 ms. During further validation, Efficient U-Net demonstrated the highest intersection over union of 0.8455, the highest Dice coefficient of 0.9163, and the lowest Hausdorff distance of 1.5626. The normalized membranous glottal gap area index was also calculated and validated. Efficient U-Net and VGG19 U-Net exhibited the lowest mean squared errors (3.5476 and 3.3842) and the lowest mean absolute errors (1.8835 and 1.8396). CONCLUSIONS: Automatic segmentation of the membranous glottal gap area can be achieved through U-net-based architecture. Considering the segmentation quality and speed, Efficient U-Net is a reasonable choice for this task, while the other four models remain valuable competitors. The models' masked area enables possible calculation of the normalized membranous glottal gap area and analysis of the glottal area waveform, revealing promising clinical applications for this model. LEVEL OF EVIDENCE: NA Laryngoscope, 134:2835-2843, 2024.
引用
- Hackman A, Chen CH, Chen AW, et al. Automatic Segmentation of Membranous Glottal Gap Area with U-Net-Based Architecture. Laryngoscope. 2024. PMID: 38217455. doi:10.1002/lary.31266
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。