Luffina C. Huang | Searcharxiv

arXiv2024

Greedy-optimized Approach for Interbeat Interval and Heart Rate Variability Daily Monitoring using Wearable PPG

Continuous monitoring of heart rate variability (HRV) provides insights in cardiovascular health. Wearable Photoplethysmography (PPG) assures convenient measurement of HRV. PPG, however, is susceptible to motion artifacts, considerably deteriorating the accuracy in estimation. In this study, a greedy-optimized approach is proposed for attaining high accuracy of interbeat intervals (IBIs) estimation from PPG signals collected during intensive daily activities. Utilizing the fact of continuity in heartbeats, the IBI estimation is converted into the shortest path problem in a directed acyclic graph, where candidate heartbeats from motion-contaminated PPG are regarded as vertices. The approach exploits a convex penalty function to optimize weight assignment in the shortest path calculation and a greedy fusion method to strengthen the selection process of optimal IBIs. Results achieve correlation of 0.96 for IBI estimation with the improvement of 58.4% in percentage error on the single-channel PPG signal from 2015 IEEE Signal Processing Cup. It also achieves correlation of 0.98 with percentage error of 2.2% in the two-channel PPG signal. Estimated and true HRV parameters are highly correlated. The approach is further validated on the PPG-DaLiA dataset with high correlation and low percentage error for IBI and HRV estimation in two daily activities, indicating the robustness of the proposed technique.

eess.SP↗

arXiv2024

Self-Supervised Learning Featuring Small-Scale Image Dataset for Treatable Retinal Diseases Classification

Automated medical diagnosis through image-based neural networks has increased in popularity and matured over years. Nevertheless, it is confined by the scarcity of medical images and the expensive labor annotation costs. Self-Supervised Learning (SSL) is an good alternative to Transfer Learning (TL) and is suitable for imbalanced image datasets. In this study, we assess four pretrained SSL models and two TL models in treatable retinal diseases classification using small-scale Optical Coherence Tomography (OCT) images ranging from 125 to 4000 with balanced or imbalanced distribution for training. The proposed SSL model achieves the state-of-art accuracy of 98.84% using only 4,000 training images. Our results suggest the SSL models provide superior performance under both the balanced and imbalanced training scenarios. The SSL model with MoCo-v2 scheme has consistent good performance under the imbalanced scenario and, especially, surpasses the other models when the training set is less than 500 images.

cs.CV↗