Biomedical Signal Processing & AI Research Group, Department of Health Technology, Technical University of Denmark, Oersteds Plads 345B, 2800, Kongens Lyngby, Denmark; Stanford University Center for Sleep and Circadian Sciences, Stanford University, 3165 Porter Dr., CA, 94304, Palo Alto, USA; Danish Center for Sleep Medicine, Department of Clinical Neurophysiology, Rigshospitalet, University of Copenhagen, Nordre Ringvej 57, 2600, Glostrup, Denmark.
Danish Center for Sleep Surgery, Department of Otorhinolaryngology, Head and Neck Surgery and Audiology, Copenhagen University Hospital (Rigshospitalet), Inge Lehmanns Vej 8, 2100, Copenhagen, Denmark.
Sleep Med. 2023 Feb;102:19-29. doi: 10.1016/j.sleep.2022.12.015. Epub 2022 Dec 20.
Treatment of obstructive sleep apnea is crucial for long term health and reduced economic burden. For those considered for surgery, drug-induced sleep endoscopy (DISE) is a method to characterize location and pattern of sleep-related upper airway collapse. According to the VOTE classification system, four upper airway sites of collapse are characterized: velum (V), oropharynx (O), tongue (T), and epiglottis (E). The degree of obstruction per site is classified as 0 (no obstruction), 1 (partial obstruction), or 2 (complete obstruction). Here we propose a deep learning approach for automatic scoring of VOTE obstruction degrees from DISE videos.
We included 281 DISE videos with varying durations (6 s-16 min) from two sleep clinics: Copenhagen University Hospital and Stanford University Hospital. Examinations were split into 5-s clips, each receiving annotations of 0, 1, 2, or X (site not visible) for each site (V, O, T, and E), which was used to train a deep learning model. Predicted VOTE obstruction degrees per examination was obtained by taking the highest predicted degree per site across 5-s clips, which was evaluated against VOTE degrees annotated by surgeons.
Mean F1 score of 70% was obtained across all DISE examinations (V: 85%, O: 72%, T: 57%, E: 65%). For each site, sensitivity was highest for degree 2 and lowest for degree 0. No bias in performance was observed between videos from different clinicians/hospitals.
This study demonstrates that automating scoring of DISE examinations show high validity and feasibility in degree of upper airway collapse.
阻塞性睡眠呼吸暂停的治疗对于长期健康和降低经济负担至关重要。对于那些考虑手术的患者，药物诱导睡眠内窥镜检查（DISE）是一种用于描述与睡眠相关的上呼吸道塌陷位置和模式的方法。根据 VOTE 分类系统，有四个上呼吸道塌陷部位：软腭（V）、口咽（O）、舌（T）和会厌（E）。每个部位的阻塞程度分为 0（无阻塞）、1（部分阻塞）或 2（完全阻塞）。在这里，我们提出了一种从 DISE 视频中自动评分 VOTE 阻塞程度的深度学习方法。
我们纳入了来自两个睡眠诊所（哥本哈根大学医院和斯坦福大学医院）的 281 个 DISE 视频，视频时长不一（6 秒-16 分钟）。检查被分为 5 秒的片段，每个片段都对每个部位（V、O、T 和 E）的 0、1、2 或 X（部位不可见）进行注释，用于训练深度学习模型。通过取每个部位的 5 秒片段中最高预测的阻塞程度来获得每个检查的预测 VOTE 阻塞程度，然后将其与外科医生标注的 VOTE 阻塞程度进行评估。
所有 DISE 检查的平均 F1 评分为 70%（V：85%，O：72%，T：57%，E：65%）。对于每个部位，2 级的敏感性最高，0 级的敏感性最低。来自不同临床医生/医院的视频之间没有表现出性能偏差。
这项研究表明，自动化评分 DISE 检查在评估上呼吸道塌陷程度方面具有较高的有效性和可行性。
