Non-Contact Physiological Monitoring in Pediatric Intensive Care Units via Adaptive Masking and Self-Supervised Learning

• URL: http://arxiv.org/abs/2602.15967v1
• Date: Tue, 17 Feb 2026 19:34:50 GMT
• Title: Non-Contact Physiological Monitoring in Pediatric Intensive Care Units via Adaptive Masking and Self-Supervised Learning
• Authors: Mohamed Khalil Ben Salah, Philippe Jouvet, Rita Noumeir,
• Abstract summary: Contact-based sensors such as pulse oximeters may cause skin irritation and lead to patient discomfort.<n>Remote photometers offer a contactless alternative to monitor vital signs using facial video.<n>We introduce a progressive curriculum strategy for pretraining an expert model in the PICU setting.<n>Our framework achieves a reduction in mean absolute error relative to standard masked autoencoders and outperforms PhysFormer by 31%.
• Score: 1.2744523252873352
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Uncertainty-Aware Concept and Motion Segmentation for Semi-Supervised Angiography Videos [15.975499220724044]
  We propose a SAM3-based Teacher-student framework with Motion-Aware consistency and Progressive Confidence Regularization.<n>Our method utilizes SAM3's unique promptable concept segmentation design and innovates a SAM3-based teacher-student framework to maximize the performance potential of both the teacher and the student.
  arXiv  Detail & Related papers  (2026-03-01T03:04:43Z)
• A Non-Invasive 3D Gait Analysis Framework for Quantifying Psychomotor Retardation in Major Depressive Disorder [4.909486568908741]
  We propose a non-invasive computational framework that transforms monocular RGB video into clinically relevant 3D gait kinematics.<n>This novel pipeline enables the extraction of 297 explicit gait biomechanical biomarkers from a single camera capture.<n>Our method achieves an 83.3% accuracy in detecting Psychomotor retardation (PMR) and explains 64% of the variance in overall depression severity.
  arXiv  Detail & Related papers  (2026-01-27T12:07:21Z)
• Estimating Clinical Lab Test Result Trajectories from PPG using Physiological Foundation Model and Patient-Aware State Space Model -- a UNIPHY+ Approach [5.103773025435573]
  Photoplethysmogram (PHY) is a non-invasive, continuously recorded signal in intensive care units (ICUs) that reflects cardiovascular dynamics.<n>We propose UNI+Lab, a framework that combines a large-scale PPG foundation model for local waveform encoding with a patient-aware Mamba model for long-range temporal modeling.
  arXiv  Detail & Related papers  (2025-09-19T18:38:06Z)
• STROKEVISION-BENCH: A Multimodal Video And 2D Pose Benchmark For Tracking Stroke Recovery [41.140934816875806]
  We introduce StrokeVision-Bench, the first-ever dedicated dataset of stroke patients performing clinically structured block transfer tasks.<n>StrokeVision-Bench comprises 1,000 annotated videos categorized into four clinically meaningful action classes.<n>We benchmark several state-of-the-art video action recognition and skeleton-based action classification methods to establish performance baselines.
  arXiv  Detail & Related papers  (2025-09-02T18:48:37Z)
• End to End Autoencoder MLP Framework for Sepsis Prediction [10.151360630975482]
  Sepsis is a life threatening condition that requires timely detection in intensive care settings.<n>Traditional machine learning approaches, including Naive Bayes, struggle with irregular, incomplete time-series data.<n>We introduce an end-to-end deep learning framework integrating an unsupervised autoencoder for automatic feature extraction.
  arXiv  Detail & Related papers  (2025-08-26T05:22:48Z)
• Generalised Label-free Artefact Cleaning for Real-time Medical Pulsatile Time Series [3.8195510803972454]
  Artefacts compromise clinical decision-making in the use of medical time series.<n>We introduce a generalised label-free framework, GenClean, for real-time artefact detection.
  arXiv  Detail & Related papers  (2025-04-29T22:28:06Z)
• Flip Learning: Weakly Supervised Erase to Segment Nodules in Breast Ultrasound [40.97115667616978]
  We introduce a novel learning-based WSS framework called Flip Learning, which relies solely on 2D/3D boxes for accurate segmentation.<n>Multiple agents are employed to erase the target from the box to facilitate classification tag flipping, with the erased region serving as the predicted segmentation mask.<n>Our method outperforms state-of-the-art WSS methods and foundation models, and achieves comparable performance as fully-supervised learning algorithms.
  arXiv  Detail & Related papers  (2025-03-26T16:20:02Z)
• Finetuning and Quantization of EEG-Based Foundational BioSignal Models on ECG and PPG Data for Blood Pressure Estimation [46.36100528165335]
  Photoplethysmography and electrocardiography can potentially enable continuous blood pressure (BP) monitoring.<n>Yet accurate and robust machine learning (ML) models remains challenging due to variability in data quality and patient-specific factors.<n>In this work, we investigate whether a model pre-trained on one modality can effectively be exploited to improve the accuracy of a different signal type.<n>Our approach achieves near state-of-the-art accuracy for diastolic BP and surpasses by 1.5x the accuracy of prior works for systolic BP.
  arXiv  Detail & Related papers  (2025-02-10T13:33:12Z)
• Adversarial Vessel-Unveiling Semi-Supervised Segmentation for Retinopathy of Prematurity Diagnosis [9.683492465191241]
  We propose a semi supervised segmentation framework designed to advance ROP studies without the need for extensive manual vessel annotation. Unlike previous methods that rely solely on limited labeled data, our approach integrates uncertainty weighted vessel unveiling module and domain adversarial learning. We validate our approach on public datasets and an in-house ROP dataset, demonstrating its superior performance across multiple evaluation metrics.
  arXiv  Detail & Related papers  (2024-11-14T02:40:34Z)
• Machine learning-based algorithms for at-home respiratory disease monitoring and respiratory assessment [45.104212062055424]
  This work aims to develop machine learning-based algorithms to facilitate at-home respiratory disease monitoring and assessment. Data were collected from 30 healthy adults, encompassing respiratory pressure, flow, and dynamic thoraco-abdominal circumferential measurements. Various machine learning models, including the random forest classifier, logistic regression, and support vector machine (SVM), were trained to predict breathing types.
  arXiv  Detail & Related papers  (2024-09-05T02:14:31Z)
• A Deep Learning Approach to Predicting Collateral Flow in Stroke Patients Using Radiomic Features from Perfusion Images [58.17507437526425]
  Collateral circulation results from specialized anastomotic channels which provide oxygenated blood to regions with compromised blood flow. The actual grading is mostly done through manual inspection of the acquired images. We present a deep learning approach to predicting collateral flow grading in stroke patients based on radiomic features extracted from MR perfusion data.
  arXiv  Detail & Related papers  (2021-10-24T18:58:40Z)
• Detecting Parkinsonian Tremor from IMU Data Collected In-The-Wild using Deep Multiple-Instance Learning [59.74684475991192]
  Parkinson's Disease (PD) is a slowly evolving neuro-logical disease that affects about 1% of the population above 60 years old. PD symptoms include tremor, rigidity and braykinesia. We present a method for automatically identifying tremorous episodes related to PD, based on IMU signals captured via a smartphone device.
  arXiv  Detail & Related papers  (2020-05-06T09:02:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.