Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
126 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Region-Disentangled Diffusion Model for High-Fidelity PPG-to-ECG Translation (2308.13568v2)

Published 25 Aug 2023 in eess.SP and cs.LG

Abstract: The high prevalence of cardiovascular diseases (CVDs) calls for accessible and cost-effective continuous cardiac monitoring tools. Despite Electrocardiography (ECG) being the gold standard, continuous monitoring remains a challenge, leading to the exploration of Photoplethysmography (PPG), a promising but more basic alternative available in consumer wearables. This notion has recently spurred interest in translating PPG to ECG signals. In this work, we introduce Region-Disentangled Diffusion Model (RDDM), a novel diffusion model designed to capture the complex temporal dynamics of ECG. Traditional Diffusion models like Denoising Diffusion Probabilistic Models (DDPM) face challenges in capturing such nuances due to the indiscriminate noise addition process across the entire signal. Our proposed RDDM overcomes such limitations by incorporating a novel forward process that selectively adds noise to specific regions of interest (ROI) such as QRS complex in ECG signals, and a reverse process that disentangles the denoising of ROI and non-ROI regions. Quantitative experiments demonstrate that RDDM can generate high-fidelity ECG from PPG in as few as 10 diffusion steps, making it highly effective and computationally efficient. Additionally, to rigorously validate the usefulness of the generated ECG signals, we introduce CardioBench, a comprehensive evaluation benchmark for a variety of cardiac-related tasks including heart rate and blood pressure estimation, stress classification, and the detection of atrial fibrillation and diabetes. Our thorough experiments show that RDDM achieves state-of-the-art performance on CardioBench. To the best of our knowledge, RDDM is the first diffusion model for cross-modal signal-to-signal translation in the bio-signal domain.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (56)
  1. Synthetic ECG Signal Generation using Probabilistic Diffusion Models. arXiv preprint arXiv:2303.02475.
  2. Diffusion-based conditional ECG generation with structured state space models. Computers in Biology and Medicine, 107115.
  3. Deep learning based atrial fibrillation detection using wearable photoplethysmography sensor. In 2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), 442–445. IEEE.
  4. A digital biomarker of diabetes from smartphone-based vascular signals. Nature medicine, 26(10): 1576–1582.
  5. PhotoECG: Photoplethysmographyto estimate ECG parameters. In 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 4404–4408. IEEE.
  6. Noise detection in electrocardiogram signals for intensive care unit patients. IEEE Access, 7: 88357–88368.
  7. Smart wearable devices in cardiovascular care: where we are and how to move forward. Nature Reviews Cardiology, 18(8): 581–599.
  8. A transformer architecture for stress detection from ecg. In 2021 International Symposium on Wearable Computers, 132–134.
  9. Assessment of hypertension using clinical electrocardiogram features: a first-ever review. Frontiers in Medicine, 7: 583331.
  10. Align your latents: High-resolution video synthesis with latent diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 22563–22575.
  11. Guidelines for the Management of Atrial Fibrillation.
  12. Usefulness of continuous electrocardiographic monitoring for atrial fibrillation. The American journal of cardiology, 110(2): 270–276.
  13. ME-GAN: Learning panoptic electrocardio representations for multi-view ECG synthesis conditioned on heart diseases. In International Conference on Machine Learning, 3360–3370. PMLR.
  14. Diffusion models beat gans on image synthesis. Advances in neural information processing systems, 34: 8780–8794.
  15. The use of photoplethysmography for assessing hypertension. NPJ digital medicine, 2(1): 60.
  16. Pgans: Personalized generative adversarial networks for ecg synthesis to improve patient-specific deep ecg classification. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, 557–564.
  17. Hamilton, P. 2002. Open source ECG analysis. In Computers in cardiology, 101–104. IEEE.
  18. Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nature medicine, 25(1): 65–69.
  19. Denoising diffusion probabilistic models. Advances in neural information processing systems, 33: 6840–6851.
  20. PPG2ABP: Translating photoplethysmogram (PPG) signals to arterial blood pressure (ABP) waveforms. Bioengineering, 9(11): 692.
  21. MIMIC-III, a freely accessible critical care database. Scientific data, 3(1): 1–9.
  22. Cuff-less high-accuracy calibration-free blood pressure estimation using pulse transit time. In 2015 IEEE international symposium on circuits and systems (ISCAS), 1006–1009. IEEE.
  23. Karlen, W. 2021. CapnoBase IEEE TBME respiratory rate benchmark.
  24. Kauffman, D. 2020. Cardiovascular disease burden, deaths are rising around the world. American College of Cardiology, 9.
  25. Stress and heart rate variability: a meta-analysis and review of the literature. Psychiatry investigation, 15(3): 235.
  26. Lan, E. 2023. Performer: A Novel PPG-to-ECG Reconstruction Transformer for a Digital Biomarker of Cardiovascular Disease Detection. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 1991–1999.
  27. A new, short-recorded photoplethysmogram dataset for blood pressure monitoring in China. Scientific data, 5(1): 1–7.
  28. Catching patient’s attention at the right time to help them undergo behavioural change: Stress classification experiment from blood volume pulse. In Artificial Intelligence in Medicine: 19th International Conference on Artificial Intelligence in Medicine, AIME 2021, Virtual Event, June 15–18, 2021, Proceedings, 72–82. Springer.
  29. BPNet: A multi-modal fusion neural network for blood pressure estimation using ECG and PPG. Biomedical Signal Processing and Control, 86: 105287.
  30. Decoupled Weight Decay Regularization. In International Conference on Learning Representations.
  31. NeuroKit2: A Python toolbox for neurophysiological signal processing. Behavior Research Methods, 53(4): 1689–1696.
  32. DiffECG: A Generalized Probabilistic Diffusion Model for ECG Signals Synthesis. arXiv preprint arXiv:2306.01875.
  33. A real-time QRS detection algorithm. IEEE transactions on biomedical engineering, (3): 230–236.
  34. Heart rate–corrected QT interval duration is significantly associated with blood pressure in Chinese hypertensives. Journal of Electrocardiology, 39(2): 206–210.
  35. Toward a robust estimation of respiratory rate from pulse oximeters. IEEE Transactions on Biomedical Engineering, 64(8): 1914–1923.
  36. Deep PPG: large-scale heart rate estimation with convolutional neural networks. Sensors, 19(14): 3079.
  37. Mm-diffusion: Learning multi-modal diffusion models for joint audio and video generation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 10219–10228.
  38. Multiparameter Intelligent Monitoring in Intensive Care II (MIMIC-II): a public-access intensive care unit database. Critical care medicine, 39(5): 952.
  39. Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems, 35: 36479–36494.
  40. Detection of Cardiac Arrhythmias From Varied Length Multichannel Electrocardiogram Recordings Using Deep Convolutional Neural Networks. In 2020 Computing in Cardiology, 1–4. IEEE.
  41. Self-supervised ECG representation learning for emotion recognition. IEEE Transactions on Affective Computing, 13(3): 1541–1554.
  42. Cardiogan: Attentive generative adversarial network with dual discriminators for synthesis of ecg from ppg. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, 488–496.
  43. Schäck, T.; et al. 2017. Computationally efficient heart rate estimation during physical exercise using photoplethysmographic signals. In European Signal Processing Conference, 2478–2481.
  44. Introducing wesad, a multimodal dataset for wearable stress and affect detection. In Proceedings of the 20th ACM international conference on multimodal interaction, 400–408.
  45. Ambulatory atrial fibrillation monitoring using wearable photoplethysmography with deep learning. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 1909–1916.
  46. Deep unsupervised learning using nonequilibrium thermodynamics. In International conference on machine learning, 2256–2265. PMLR.
  47. NAS-PPG: PPG-based heart rate estimation using neural architecture search. IEEE Sensors Journal, 21(13): 14941–14949.
  48. Effect of a home-based wearable continuous ECG monitoring patch on detection of undiagnosed atrial fibrillation: the mSToPS randomized clinical trial. Jama, 320(2): 146–155.
  49. Sympathetic–parasympathetic activity and reactivity in central serous chorioretinopathy: a case–control study. Investigative ophthalmology & visual science, 47(8): 3474–3478.
  50. Cross-domain Joint Dictionary Learning for ECG Inference from PPG. IEEE Internet of Things Journal.
  51. BP-Net: Efficient deep learning for continuous arterial blood pressure estimation using photoplethysmogram. In 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA), 1495–1500. IEEE.
  52. QT interval, cardiovascular risk factors and risk of death in diabetes. Journal of endocrinological investigation, 27: 175–181.
  53. P2E-WGAN: ECG waveform synthesis from PPG with conditional wasserstein generative adversarial networks. In Proceedings of the 36th Annual ACM Symposium on Applied Computing, 1030–1036.
  54. Photoplethysmographic time-domain heart rate measurement algorithm for resource-constrained wearable devices and its implementation. Sensors, 20(6): 1783.
  55. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE international conference on computer vision, 2223–2232.
  56. Learning your heart actions from pulse: ECG waveform reconstruction from PPG. IEEE Internet of Things Journal, 8(23): 16734–16748.
Citations (5)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets