Diffusion-Based Heart Sound Generation: Evaluation with Physiological Signal Metrics, Classifiers, and Expert Listening
Department of Information Science & Engineering, KTH Royal Institute of Technology（信息科学与工程系，皇家理工学院）；Rutherford Appleton Laboratory（拉瑟福德·苹果顿实验室）；Peng Cheng Laboratory（鹏城实验室）；Department of Engineering, King’s College London（工程系，伦敦国王学院）
公开可用的心音图（PCG）数据集在规模和病理多样性方面仍然有限，限制了听诊训练和自动心音分类器的泛化能力。本文在log-mel域上开发了一种用于PCG生成的类别条件扩散模型，并使用互补的（i）生理启发的合理性指标、（ii）下游标签一致性评估和（iii）专家听诊来评估合成保真度。实验使用Phy-sioNet/Computing in Cardiology Challenge 2016数据集（3240条记录）进行记录级划分。经过预处理和质量控制后，将16,749个不重叠的4秒片段映射到归一化的1×128×128 log-mel表示，以训练带有无分类器引导的条件2D U-Net去噪器。使用三个轻量级指标在重建波形上量化信号级合理性：包络自相关节律评分、基于幅度的爆炸评分和主周期滞后。合成片段保留了相似的主周期持续时间，但与真实片段相比，包络周期性降低，瞬态突发性增加。在下游评估中，ResNet-50分类器在保留的真实测试集上达到92.24%的准确率，在类别平衡的合成批次上达到82.8%的准确率，表明生成信号保留了与正常/异常分类相关的判别结构。在一项初步的专家听诊研究（60个片段，两名临床医生）中，大多数合成片段被判断为类似心音，而真实和合成的4秒片段对异常敏感性均较低。总体而言，结果为基于扩散的PCG生成提供了实用基线，同时突出了在保留异常声学线索和减少重建伪影方面的剩余挑战。
英文摘要：
Publicly available phonocardiogram (PCG) datasets remain limited in size and pathological diversity, constraining both auscultation training and the generalisation of automated heart-sound classifiers. A class-conditional diffusion model for PCG generation is developed in the log-mel domain and synthetic fidelity is assessed using complementary (i) physiology-inspired plausibility metrics, (ii) downstream label-consistency evaluation, and (iii) expert listening. Experiments use the Phy-sioNet/Computing in Cardiology Challenge 2016 dataset (3240 recordings) with recording-level splits. After preprocessing and quality control, 16,749 non-overlapping 4 s clips are mapped to a normalised 1 x 128 x 128 log-mel representation to train a conditional 2D U-Net denoiser with classifier-free guidance. Signal-level plausibility is quantified on reconstructed waveforms using three lightweight metrics: an envelope-autocorrelation rhythm score, an amplitude-based explosion score, and the dominant cycle lag. Synthetic clips preserve similar dominant cycle durations but exhibit reduced envelope periodicity and increased transient burstiness relative to real clips. For downstream evaluation, a ResNet-50 classifier achieves 92.24% accuracy on the held-out real test set and 82.8% accuracy on class-balanced synthetic batches, indicating that generated signals retain discriminative structure relevant to normal/abnormal classification. In a pilot expert listening study (60 clips, two clinicians), most synthetic clips are judged as heart-sound-like, while abnormality sensitivity is low for both real and synthetic 4 s excerpts. Overall, the results provide a practical baseline for diffusion-based PCG generation while highlighting remaining challenges in retaining abnormal acoustic cues and reducing reconstruction-induced artefacts.
Towards Generalizable Drowsiness Monitoring with Physiological Sensors: A Preliminary Study
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；University of Toronto（多伦多大学）；The Hong Kong University of Science and Technology（香港科技大学）
Differentiating Physical and Psychological Stress Using Wearable Physiological Signals and Salivary Cortisol
Institute for Manufacturing, Department of Engineering, University of Cambridge（剑桥大学工程学院制造研究所）；Electrical Engineering Division, Department of Engineering, University of Cambridge（剑桥大学工程学院电气工程系）；School of Electrical and Electronic Engineering, University College Dublin（都柏林大学学院电气与电子工程学院）；Division of Anaesthesia, Department of Medicine, University of Cambridge, Addenbrooke’s Hospital（剑桥大学医学院麻醉科阿登布鲁克斯医院）
Self-Supervised Autoencoder Network for Robust Heart Rate Extraction from Noisy Photoplethysmogram: Applying Blind Source Separation to Biosignal Analysis
Mellowing Factory Co. Ltd.（梅洛灵工厂有限公司）；Chungnam National University Hospital（全南国立大学医院）；Department of Radiology, Seoul National University College of Medicine（首尔国立大学医学院放射科）
