利用自监督螺旋变分流形学习改进阻塞性睡眠呼吸暂停的上气道塌陷成像

文献信息

中文摘要

目的： 提出一种自监督变分流形学习框架，用于在自然睡眠期间从前瞻性欠采样螺旋数据重建阻塞性睡眠呼吸暂停的动态上气道MRI，且无需完全采样的训练数据。
方法： CNN生成器和低维潜在向量直接从前瞻性欠采样螺旋k空间测量中联合优化，学习受试者特定的时间流形，而无需显式运动模型。验证损失引导的自适应学习率在无真实标签的情况下提供了有原则的早停。在自然睡眠期间对8例OSA患者和4名执行Müller动作的健康志愿者，以183 ms时间分辨率和11倍加速重建了从腭帆到咽下的11个连续轴位层面。重建质量与并行成像、压缩感知、视图共享和分析流形重建进行了比较。三名专家评分者使用四点序数量表独立评估图像质量。
结果： 所提出的方法在11个连续层面上解析了多位点气道塌陷，包括同时可视化完全同心性腭后塌陷、腭帆至口咽过渡处的侧壁塌陷以及部分舌根和口咽狭窄。专家评分在混叠、空间模糊和时间模糊类别中均更优（p < 0.001，成对Mann-Whitney U检验）。重建的气道动力学由同步呼吸努力和SpO2信号佐证，在单次成像运行中识别出多达13次阻塞事件。132个层面中有8个（6%）出现重建伪影，但未影响气道可视化。
结论： 自监督变分流形学习证明了在自然睡眠期间进行稳健动态上气道MRI的可行性，并有望为未来的OSA表型分析和手术规划研究提供信息。

英文摘要

PURPOSE: To propose a self-supervised variational manifold learning framework for dynamic upper-airway MRI reconstruction in obstructive sleep apnea from prospectively under-sampled spiral data during natural sleep, without requiring fully sampled training data.
METHODS: A CNN generator and low-dimensional latent vectors were jointly optimized directly from prospectively under-sampled spiral k-space measurements, learning a subject-specific temporal manifold without an explicit motion model. A validation loss guided adaptive learning rate provided principled early stopping without ground truth. Eleven concurrent axial slices from velo-pharynx to hypo-pharynx were reconstructed at 183 ms temporal resolution and 11 × acceleration across 8 OSA patients during natural sleep and 4 healthy volunteers performing the Müller maneuver. Reconstruction quality was compared against parallel imaging, compressed sensing, view sharing, and analysis-manifold reconstruction. Three expert raters independently assessed image quality using a four-point ordinal rubric.
RESULTS: The proposed method resolved multi-site airway collapse across 11 contiguous slices, including simultaneous visualization of complete concentric retro-palatal collapse, lateral collapse at the velo-pharyngeal to oro-pharyngeal transition, and partial tongue-base and oropharyngeal narrowing. Expert scores were superior across aliasing, spatial blurring, and temporal blurring categories ( p < 0.001 , pairwise Mann-Whitney U tests). Reconstructed airway dynamics were corroborated by concurrent respiratory effort and SpO 2 signals, with up to 13 obstructive events identified within a single imaging run. Reconstruction artifacts occurred in 8 of 132 slices (6%) and did not compromise airway visualization.
CONCLUSION: Self-supervised variational manifold learning demonstrates the feasibility of robust dynamic upper-airway MRI during natural sleep, with potential to inform future OSA phenotyping and surgical-planning studies.