基于Vision Transformer的上气道三维亚区自动识别
本研究开发了一种基于Swin Transformer和U-Net的轻量级多任务深度学习模型,用于上气道整体及亚区的自动分割。使用50例锥形束CT(CBCT)扫描(共24,502层)作为标注数据,模型在三维上气道整体及亚区的分割中DSC达90.95-96.29%,在二维横截面亚区中DSC达90.92-97.55%,精度误差导致的体积和面积差异不影响临床结果,与Dolphin软件具有临床可接受的一致性。
要点
- 模型可自动分割上气道整体及鼻腔、咽部等亚区。
- 三维分割DSC为90.95-96.29%,二维横截面亚区DSC为90.92-97.55%。
- 精度误差导致的体积和面积差异不影响临床结果。
核心结论
- 新型深度学习模型实现了上气道整体及亚区的自动分割,尤其适用于复杂结构的三维评估。
研究设计与样本
- 研究纳入50例锥形束CT扫描,共24,502层,由一名正畸医生和两名耳鼻喉科医生标注作为参考标准。
- 构建了基于Swin Transformer和U-Net的轻量级多任务网络,用于上气道整体及亚区的自动分割。
主要发现
- 三维上气道整体及亚区分割的精确度为85.88-94.25%,召回率为93.74-98.44%,DSC为90.95-96.29%,IoU为83.68-92.85%。
- 二维横截面亚区分割的精确度为91.22-97.51%,召回率为90.70-97.62%,DSC为90.92-97.55%,IoU为83.41-95.29%。
- 精度误差导致的体积和面积差异不影响临床结果,AI模型与Dolphin软件在咽气道评估中具有临床可接受的一致性。
临床怎么用
- 该系统可快速评估上气道整体及亚区,辅助正畸治疗、正颌手术和耳鼻喉手术中的气道管理。
- 为牙颌面畸形和阻塞性睡眠呼吸暂停的病因、风险、严重程度、治疗效果和预后提供参考。
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
OBJECTIVES: Upper airway assessment requires a fully-automated segmentation system for complete or sub-regional identification. This study aimed to develop a novel Deep Learning (DL) model for accurate segmentation of the upper airway and achieve entire and subregional identification. METHODS: Fifty cone-beam computed tomography (CBCT) scans, including 24,502 slices, were labelled as the ground truth by one orthodontist and two otorhinolaryngologists. A novel model, a lightweight multitask network based on the Swin Transformer and U-Net, was built for automatic segmentation of the entire upper airway and subregions. Segmentation performance was evaluated using Precision, Recall, Dice similarity coefficient (DSC) and Intersection over union (IoU). The clinical implications of the precision errors were quantitatively analysed, and comparisons between the AI model and Dolphin software were conducted. RESULTS: Our model achieved good performance with a precision of 85.88-94.25%, recall of 93.74-98.44%, DSC of 90.95-96.29%, IoU of 83.68-92.85% in the overall and subregions of three-dimensional (3D) upper airway, and a precision of 91.22-97.51%, recall of 90.70-97.62%, DSC of 90.92-97.55%, and IoU of 83.41-95.29% in the subregions of two-dimensional (2D) crosssections. Discrepancies in volume and area caused by precision errors did not affect clinical outcomes. Both our AI model and the Dolphin software provided clinically acceptable consistency for pharyngeal airway assessments. CONCLUSION: The novel DL model not only achieved segmentation of the entire upper airway, including the nasal cavity and subregion identification, but also performed exceptionally well, making it well suited for 3D upper airway assessment from the nasal cavity to the hypopharynx, especially for intricate structures. CLINICAL SIGNIFICANCE: This system provides insights into the aetiology, risk, severity, treatment effect, and prognosis of dentoskeletal deformities and obstructive sleep apnea. It achieves rapid assessment of the entire upper airway and its subregions, making airway management-an integral part of orthodontic treatment, orthognathic surgery, and ENT surgery-easier.
引用
- Jin S, Han H, Huang Z, et al. Automatic three-dimensional nasal and pharyngeal airway subregions identification via Vision Transformer. J Dent. 2023. PMID: 37343616. doi:10.1016/j.jdent.2023.104595
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。