通过自适应遮蔽和自监督学习实现儿科重症监护室的非接触式生理监测
Non-Contact Physiological Monitoring in Pediatric Intensive Care Units via Adaptive Masking and Self-Supervised Learning
AI总结：
本文提出了一种自适应遮蔽和自监督学习方法，用于在儿科重症监护室中实现非接触式生理监测，有效降低了均方误差，提升了在临床环境中的鲁棒性。
摘要：
在儿科重症监护室（PICUs）中持续监测生命体征对于早期发现临床恶化和有效临床决策至关重要。然而，基于接触的传感器如脉搏血氧仪可能导致皮肤刺激、增加感染风险并导致患者不适。远程脉氧图（rPPG）提供了一种无接触的替代方法，通过面部视频监测心率，但在PICUs中仍因运动伪影、遮挡、照明变化以及实验室与临床数据之间的域偏移而未被充分利用。我们介绍了一种基于渐进课程策略的自监督预训练框架，用于PICU环境中的rPPG估计。该方法利用VisionMamba架构，并整合了自适应遮蔽机制，其中轻量级的Mamba基控制器为概率补丁采样分配时空重要性分数。该策略动态增加重建难度，同时保持生理相关性。为了解决缺乏标注临床数据的问题，我们采用教师-学生蒸馏设置。一个在公共数据集上训练的监督专家模型为学生提供潜在的生理指导。课程通过三个阶段进行：清洁的公共视频、合成遮挡场景和来自500名儿童患者的未标记视频。我们的框架相对于标准的遮蔽自动编码器实现了均方误差减少42%，并且比PhysFormer高出31%，最终达到3.2 bpm的MAE。在没有显式感兴趣区域提取的情况下，模型始终关注脉搏丰富的区域，并在临床遮挡和噪声下表现出鲁棒性。
英文摘要：
Continuous monitoring of vital signs in Pediatric Intensive Care Units (PICUs) is essential for early detection of clinical deterioration and effective clinical decision-making. However, contact-based sensors such as pulse oximeters may cause skin irritation, increase infection risk, and lead to patient discomfort. Remote photoplethysmography (rPPG) offers a contactless alternative to monitor heart rate using facial video, but remains underutilized in PICUs due to motion artifacts, occlusions, variable lighting, and domain shifts between laboratory and clinical data. We introduce a self-supervised pretraining framework for rPPG estimation in the PICU setting, based on a progressive curriculum strategy. The approach leverages the VisionMamba architecture and integrates an adaptive masking mechanism, where a lightweight Mamba-based controller assigns spatiotemporal importance scores to guide probabilistic patch sampling. This strategy dynamically increases reconstruction difficulty while preserving physiological relevance. To address the lack of labeled clinical data, we adopt a teacher-student distillation setup. A supervised expert model, trained on public datasets, provides latent physiological guidance to the student. The curriculum progresses through three stages: clean public videos, synthetic occlusion scenarios, and unlabeled videos from 500 pediatric patients. Our framework achieves a 42% reduction in mean absolute error relative to standard masked autoencoders and outperforms PhysFormer by 31%, reaching a final MAE of 3.2 bpm. Without explicit region-of-interest extraction, the model consistently attends to pulse-rich areas and demonstrates robustness under clinical occlusions and noise.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
