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

Constraint Latent Space Matters: An Anti-anomalous Waveform Transformation Solution from Photoplethysmography to Arterial Blood Pressure (2402.17780v1)

Published 23 Feb 2024 in eess.SP, cs.LG, and physics.med-ph

Abstract: Arterial blood pressure (ABP) holds substantial promise for proactive cardiovascular health management. Notwithstanding its potential, the invasive nature of ABP measurements confines their utility primarily to clinical environments, limiting their applicability for continuous monitoring beyond medical facilities. The conversion of photoplethysmography (PPG) signals into ABP equivalents has garnered significant attention due to its potential in revolutionizing cardiovascular disease management. Recent strides in PPG-to-ABP prediction encompass the integration of generative and discriminative models. Despite these advances, the efficacy of these models is curtailed by the latent space shift predicament, stemming from alterations in PPG data distribution across disparate hardware and individuals, potentially leading to distorted ABP waveforms. To tackle this problem, we present an innovative solution named the Latent Space Constraint Transformer (LSCT), leveraging a quantized codebook to yield robust latent spaces by employing multiple discretizing bases. To facilitate improved reconstruction, the Correlation-boosted Attention Module (CAM) is introduced to systematically query pertinent bases on a global scale. Furthermore, to enhance expressive capacity, we propose the Multi-Spectrum Enhancement Knowledge (MSEK), which fosters local information flow within the channels of latent code and provides additional embedding for reconstruction. Through comprehensive experimentation on both publicly available datasets and a private downstream task dataset, the proposed approach demonstrates noteworthy performance enhancements compared to existing methods. Extensive ablation studies further substantiate the effectiveness of each introduced module.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (56)
  1. An estimation method of continuous non-invasive arterial blood pressure waveform using photoplethysmography: A U-Net architecture-based approach. Sensors, 21(5): 1867.
  2. Arterial blood pressure measurement and pulse wave analysis—their role in enhancing cardiovascular assessment. Physiological measurement, 31(1): R1.
  3. Toward IoT-Based Medical Edge Devices: PPG-Based Blood Pressure Estimation Application. IEEE Internet of Things Journal, 10(6): 5240–5255.
  4. All grains, one scheme (AGOS): Learning multigrain instance representation for aerial scene classification. IEEE Transactions on Geoscience and Remote Sensing, 60: 1–17.
  5. Domain adaptation meets zero-shot learning: an annotation-efficient approach to multi-modality medical image segmentation. IEEE Transactions on Medical Imaging, 41(5): 1043–1056.
  6. Uncertainty-aware domain alignment for anatomical structure segmentation. Medical Image Analysis, 64: 101732.
  7. Estimation of continuous blood pressure from PPG via a federated learning approach. Sensors, 21(18): 6311.
  8. Generative pretraining from pixels. In ICML, 1691–1703. PMLR.
  9. Chen, Y. 2022. Estimating Cuff-less Continuous Blood Pressure from Fingertip Photoplethysmogram Signals with Deep Neural Network Model. medRxiv, 2022–03.
  10. Non-invasive arterial blood pressure measurement and SpO2 estimation using PPG signal: a deep learning framework. BMC Medical Informatics and Decision Making, 23(1): 131.
  11. Coatnet: Marrying convolution and attention for all data sizes. Advances in neural information processing systems, 34: 3965–3977.
  12. Computing discrete Fréchet distance.
  13. Real-valued (medical) time series generation with recurrent conditional gans. arXiv preprint arXiv:1706.02633.
  14. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. circulation, 101(23): e215–e220.
  15. Generative adversarial nets. Advances in neural information processing systems, 27.
  16. Continuous blood pressure estimation using exclusively photopletysmography by LSTM-based signal-to-signal translation. Sensors, 21(9): 2952.
  17. Denoising diffusion probabilistic models. Advances in neural information processing systems, 33: 6840–6851.
  18. PPG2ABP: Translating photoplethysmogram (PPG) signals to arterial blood pressure (ABP) waveforms. Bioengineering, 9(11): 692.
  19. Inceptiontime: Finding alexnet for time series classification. Data Mining and Knowledge Discovery, 34(6): 1936–1962.
  20. SemanticRT: A Large-Scale Dataset and Method for Robust Semantic Segmentation in Multispectral Images. In Proceedings of the 31st ACM International Conference on Multimedia, 3307–3316.
  21. Multispectral Video Semantic Segmentation: A Benchmark Dataset and Baseline. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1094–1104.
  22. Learning calibrated medical image segmentation via multi-rater agreement modeling. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 12341–12351.
  23. MIMIC-III clinical database (version 1.4). PhysioNet, 10(C2XW26): 2.
  24. MIMIC-III, a freely accessible critical care database. Scientific data, 3(1): 1–9.
  25. Adam: A method for stochastic optimization in: Proceedings of the 3rd international conference for learning representations (iclr’15). San Diego, 500.
  26. K-nearest neighbors. Dimensionality reduction with unsupervised nearest neighbors, 13–23.
  27. Lan, E. 2023. Performer: A Novel PPG-to-ECG Reconstruction Transformer for a Digital Biomarker of Cardiovascular Disease Detection. In WACV, 1991–1999.
  28. Vector Quantized Time Series Generation with a Bidirectional Prior Model. arXiv preprint arXiv:2303.04743.
  29. VitalDB, a high-fidelity multi-parameter vital signs database in surgical patients. Scientific Data, 9(1): 279.
  30. Magneto-plethysmographic sensor for peripheral blood flow velocity. IEEE Sensors journal, 14(5): 1341–1342.
  31. Tts-cgan: A transformer time-series conditional gan for biosignal data augmentation. arXiv preprint arXiv:2206.13676.
  32. Swin transformer: Hierarchical vision transformer using shifted windows. In ICCV, 10012–10022.
  33. Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983.
  34. Novel blood pressure waveform reconstruction from photoplethysmography using cycle generative adversarial networks. In EMBC, 1906–1909. IEEE.
  35. Multi-sensor fusion approach for cuff-less blood pressure measurement. IEEE journal of biomedical and health informatics, 24(1): 79–91.
  36. Noninvasive assessment of the digital volume pulse: comparison with the peripheral pressure pulse. Hypertension, 36(6): 952–956.
  37. Continuous cardiac output monitoring by peripheral blood pressure waveform analysis. IEEE Transactions on Biomedical Engineering, 53(3): 459–467.
  38. Cuffless blood pressure measurement. Annual Review of Biomedical Engineering, 24: 203–230.
  39. Conditional sig-wasserstein gans for time series generation. arXiv preprint arXiv:2006.05421.
  40. Principles and techniques of blood pressure measurement. Cardiology clinics, 28(4): 571–586.
  41. Label-efficient hybrid-supervised learning for medical image segmentation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, 2026–2034.
  42. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32.
  43. Deep generative model with domain adversarial training for predicting arterial blood pressure waveform from photoplethysmogram signal. Biomedical Signal Processing and Control, 70: 102972.
  44. Utility of the photoplethysmogram in circulatory monitoring. The Journal of the American Society of Anesthesiologists, 108(5): 950–958.
  45. Cardiogan: Attentive generative adversarial network with dual discriminators for synthesis of ecg from ppg. In AAAI, volume 35, 488–496.
  46. Calibration of the photoplethysmogram to arterial blood pressure: capabilities and limitations for continuous pressure monitoring. In 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference, 3970–3973. IEEE.
  47. Wearable, cuff-less PPG-based blood pressure monitor with novel height sensor. In 2006 International Conference of the IEEE Engineering in Medicine and Biology Society, 908–911. IEEE.
  48. Features extraction for cuffless blood pressure estimation by autoencoder from photoplethysmography. In 2018 40Th annual international conference of the IEEE engineering in medicine and biology society (EMBC), 2857–2860. IEEE.
  49. Neural discrete representation learning. Advances in neural information processing systems, 30.
  50. 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.
  51. Predicting systolic blood pressure using machine learning. In 7th international conference on information and automation for sustainability, 1–6. IEEE.
  52. Aggregated residual transformations for deep neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, 1492–1500.
  53. Time-series generative adversarial networks. Advances in neural information processing systems, 32.
  54. Deconvolutional networks. In 2010 IEEE Computer Society Conference on computer vision and pattern recognition, 2528–2535. IEEE.
  55. Style transfer for anime sketches with enhanced residual u-net and auxiliary classifier gan. In ACPR, 506–511. IEEE.
  56. Electrocardiogram generation with a bidirectional LSTM-CNN generative adversarial network. Scientific reports, 9(1): 6734.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (8)
  1. Cheng Bian (21 papers)
  2. Xiaoyu Li (348 papers)
  3. Qi Bi (22 papers)
  4. Guangpu Zhu (8 papers)
  5. Jiegeng Lyu (1 paper)
  6. Weile Zhang (14 papers)
  7. Yelei Li (2 papers)
  8. Zijing Zeng (3 papers)