SSC-UNet: UNet with Self-Supervised Contrastive Learning for Phonocardiography Noise Reduction

• URL: http://arxiv.org/abs/2601.10735v1
• Date: Wed, 07 Jan 2026 17:06:42 GMT
• Title: SSC-UNet: UNet with Self-Supervised Contrastive Learning for Phonocardiography Noise Reduction
• Abstract summary: Congenital Heart Disease (CHD) remains a significant global health concern affecting approximately 1% of births worldwide.<n>This study proposes a self-supervised phonocardiography noise reduction model based on Noise2Noise to enable training without clean data.
• Score: 1.8780017602640042
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Congenital Heart Disease (CHD) remains a significant global health concern affecting approximately 1\% of births worldwide. Phonocardiography has emerged as a supplementary tool to diagnose CHD cost-effectively. However, the performance of these diagnostic models highly depends on the quality of the phonocardiography, thus, noise reduction is particularly critical. Supervised UNet effectively improves noise reduction capabilities, but limited clean data hinders its application. The complex time-frequency characteristics of phonocardiography further complicate finding the balance between effectively removing noise and preserving pathological features. In this study, we proposed a self-supervised phonocardiography noise reduction model based on Noise2Noise to enable training without clean data. Augmentation and contrastive learning are applied to enhance its performance. We obtained an average SNR of 12.98 dB after filtering under 10~dB of hospital noise. Classification sensitivity after filtering was improved from 27\% to 88\%, indicating its promising pathological feature retention capabilities in practical noisy environments.

Related papers

• Autoencoder-Based Denoising of Muscle Artifacts in ECG to Preserve Skin Nerve Activity (SKNA) for Cognitive Stress Detection [2.9710010895451746]
  Skin nerve activity (SKNA) extracted from high-frequency electrocardiogram (ECG) recordings provides a noninvasive window into SNS dynamics.<n>Traditional preprocessing is susceptible to overlapping EMG and SKNA spectral components.<n>We present a denoising approach using a lightweight one-dimensional convolutional autoencoder with a long short-term memory (LSTM) bottleneck.
  arXiv  Detail & Related papers  (2025-09-08T18:51:36Z)
• PRECISE-AS: Personalized Reinforcement Learning for Efficient Point-of-Care Echocardiography in Aortic Stenosis Diagnosis [6.276251898178271]
  Aortic stenosis (AS) is a life-threatening condition caused by a narrowing of the aortic valve, leading to impaired blood flow.<n>Access to echocardiography (echo) is often limited due to resource constraints, particularly in rural and underserved areas.<n>We propose a reinforcement learning (RL)-driven active video acquisition framework that dynamically selects each patient's most informative echo videos.
  arXiv  Detail & Related papers  (2025-09-02T23:47:43Z)
• A Denoising VAE for Intracardiac Time Series in Ischemic Cardiomyopathy [10.70564642401123]
  This work introduces a Variational Autoencoder (VAE) model, aimed at improving the quality of intra-ventricular monophasic action potential (MAP) signal recordings.<n>By constructing representations of clean signals from a dataset of 5706 time series from 42 patients diagnosed with ischemic cardiomyopathy, our approach demonstrates superior denoising performance.<n>VAEs can eliminate diverse sources of noise in single beats, outperforming state-of-the-art denoising techniques and potentially improving treatment efficacy in cardiac EP.
  arXiv  Detail & Related papers  (2025-07-08T08:27:31Z)
• Wavelet Integrated Convolutional Neural Network for ECG Signal Denoising [1.565361244756411]
  Wearable electrocardiogram (ECG) measurement using dry electrodes has a problem with high-intensity noise distortion.<n>This study proposes a convolutional neural network (CNN) model with an additional wavelet transform layer that extracts the specific frequency features in a clean ECG.<n>Testing confirms that the proposed method effectively predicts accurate ECG behavior with reduced noise by accounting for all frequency domains.
  arXiv  Detail & Related papers  (2025-01-12T06:18:46Z)
• Towards Robust Transcription: Exploring Noise Injection Strategies for Training Data Augmentation [55.752737615873464]
  This study investigates the impact of white noise at various Signal-to-Noise Ratio (SNR) levels on state-of-the-art APT models. We hope this research provides valuable insights as preliminary work toward developing transcription models that maintain consistent performance across a range of acoustic conditions.
  arXiv  Detail & Related papers  (2024-10-18T02:31:36Z)
• Brain Imaging-to-Graph Generation using Adversarial Hierarchical Diffusion Models for MCI Causality Analysis [44.45598796591008]
  Brain imaging-to-graph generation (BIGG) framework is proposed to map functional magnetic resonance imaging (fMRI) into effective connectivity for mild cognitive impairment analysis. The hierarchical transformers in the generator are designed to estimate the noise at multiple scales. Evaluations of the ADNI dataset demonstrate the feasibility and efficacy of the proposed model.
  arXiv  Detail & Related papers  (2023-05-18T06:54:56Z)
• A noise-robust acoustic method for recognizing foraging activities of grazing cattle [35.21388806827219]
  We present the operating principle and generalization capability of an acoustic method called Noise-Robust Foraging Activity Recognizer (NRFAR) In noiseless conditions, NRFAR reached an average balanced accuracy of 86.4%, outperforming two previous acoustic methods by more than 7.5%. NRFAR has been shown to be effective in harsh free-ranging environments and could be used as a reliable solution to improve pasture management and monitor the health and welfare of dairy cows.
  arXiv  Detail & Related papers  (2023-04-28T13:06:14Z)
• The role of noise in denoising models for anomaly detection in medical images [62.0532151156057]
  Pathological brain lesions exhibit diverse appearance in brain images. Unsupervised anomaly detection approaches have been proposed using only normal data for training. We show that optimization of the spatial resolution and magnitude of the noise improves the performance of different model training regimes.
  arXiv  Detail & Related papers  (2023-01-19T21:39:38Z)
• RoS-KD: A Robust Stochastic Knowledge Distillation Approach for Noisy Medical Imaging [67.02500668641831]
  Deep learning models trained on noisy datasets are sensitive to the noise type and lead to less generalization on unseen samples. We propose a Robust Knowledge Distillation (RoS-KD) framework which mimics the notion of learning a topic from multiple sources to ensure deterrence in learning noisy information. RoS-KD learns a smooth, well-informed, and robust student manifold by distilling knowledge from multiple teachers trained on overlapping subsets of training data.
  arXiv  Detail & Related papers  (2022-10-15T22:32:20Z)
• Self-supervised contrastive learning of echocardiogram videos enables label-efficient cardiac disease diagnosis [48.64462717254158]
  We developed a self-supervised contrastive learning approach, EchoCLR, to catered to echocardiogram videos. When fine-tuned on small portions of labeled data, EchoCLR pretraining significantly improved classification performance for left ventricular hypertrophy (LVH) and aortic stenosis (AS) EchoCLR is unique in its ability to learn representations of medical videos and demonstrates that SSL can enable label-efficient disease classification from small, labeled datasets.
  arXiv  Detail & Related papers  (2022-07-23T19:17:26Z)
• Heart Sound Classification Considering Additive Noise and Convolutional Distortion [2.63046959939306]
  Automatic analysis of heart sounds for abnormality detection is faced with the challenges of additive noise and sensor-dependent degradation. This paper aims to develop methods to address the cardiac abnormality detection problem when both types of distortions are present in the cardiac auscultation sound. The proposed method paves the way towards developing computer-aided cardiac auscultation systems in noisy environments using low-cost stethoscopes.
  arXiv  Detail & Related papers  (2021-06-03T14:09:04Z)
• On Dynamic Noise Influence in Differentially Private Learning [102.6791870228147]
  Private Gradient Descent (PGD) is a commonly used private learning framework, which noises based on the Differential protocol. Recent studies show that emphdynamic privacy schedules can improve at the final iteration, yet yet theoreticals of the effectiveness of such schedules remain limited. This paper provides comprehensive analysis of noise influence in dynamic privacy schedules to answer these critical questions.
  arXiv  Detail & Related papers  (2021-01-19T02:04:00Z)
• Bulbar ALS Detection Based on Analysis of Voice Perturbation and Vibrato [68.97335984455059]
  The purpose of this work was to verify the sutability of the sustain vowel phonation test for automatic detection of patients with ALS. We proposed enhanced procedure for separation of voice signal into fundamental periods that requires for calculation of measurements.
  arXiv  Detail & Related papers  (2020-03-24T12:49:25Z)

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.