HeartBEiT: Vision Transformer for Electrocardiogram Data Improves Diagnostic Performance at Low Sample Sizes

• URL: http://arxiv.org/abs/2212.14040v1
• Date: Tue, 13 Dec 2022 16:39:21 GMT
• Title: HeartBEiT: Vision Transformer for Electrocardiogram Data Improves Diagnostic Performance at Low Sample Sizes
• Authors: Akhil Vaid (1-4), Joy Jiang (1-2), Ashwin Sawant (5), Stamatios Lerakis (6,7), Edgar Argulian (6,7), Yuri Ahuja (8), Joshua Lampert (6,7), Alexander Charney (3,9,10), Hayit Greenspan (11), Benjamin Glicksberg (3,4), Jagat Narula (6,7), Girish Nadkarni (1-4,12) ((1) The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, New York (2) Mount Sinai Clinical Intelligence Center, Icahn School of Medicine at Mount Sinai, New York, New York (3) Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, New York (4) The Hasso Plattner Institute for Digital Health at Mount Sinai, New York, New York. (5) Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, New York, USA (6) Mount Sinai Heart, Icahn School of Medicine at Mount Sinai, New York, NY, USA (7) Department of Cardiology, Icahn School of Medicine at Mount Sinai, New York, NY, USA (8) Department of Medicine, NYU Langone Health, New York, NY, USA. (9) The Pamela Sklar Division of Psychiatric Genomics, Icahn School of Medicine at Mount Sinai, New York, New York. (10) Department of Psychiatry, Icahn School of Medicine at Mount Sinai, New York, New York. (11) Department of Biomedical Engineering, Tel Aviv University, Tel Aviv, Israel. (12) Division of Nephrology, Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, New York)
• Abstract summary: We create the first vision-based transformer model, HeartBEiT, for electrocardiogram waveform analysis. We show that HeartBEiT has significantly higher performance at lower sample sizes compared to other models. We also show that HeartBEiT improves explainability of diagnosis by highlighting biologically relevant regions of the EKG vs. standard CNNs.
• Score: 28.88454028731653
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The electrocardiogram (ECG) is a ubiquitous diagnostic modality. Convolutional neural networks (CNNs) applied towards ECG analysis require large sample sizes, and transfer learning approaches result in suboptimal performance when pre-training is done on natural images. We leveraged masked image modeling to create the first vision-based transformer model, HeartBEiT, for electrocardiogram waveform analysis. We pre-trained this model on 8.5 million ECGs and then compared performance vs. standard CNN architectures for diagnosis of hypertrophic cardiomyopathy, low left ventricular ejection fraction and ST elevation myocardial infarction using differing training sample sizes and independent validation datasets. We show that HeartBEiT has significantly higher performance at lower sample sizes compared to other models. Finally, we also show that HeartBEiT improves explainability of diagnosis by highlighting biologically relevant regions of the EKG vs. standard CNNs. Thus, we present the first vision-based waveform transformer that can be used to develop specialized models for ECG analysis especially at low sample sizes.

Related papers

• CNN Based Detection of Cardiovascular Diseases from ECG Images [0.0]
  The model was built using the InceptionV3 architecture and optimized through transfer learning. The developed model successfully detects MI and other cardiovascular conditions with an accuracy of 93.27%.
  arXiv  Detail & Related papers  (2024-08-29T11:26:07Z)
• ECG Arrhythmia Detection Using Disease-specific Attention-based Deep Learning Model [0.0]
  We propose a disease-specific attention-based deep learning model (DANet) for arrhythmia detection from short ECG recordings. The novel idea is to introduce a soft-coding or hard-coding waveform enhanced module into existing deep neural networks. For the soft-coding DANet, we also develop a learning framework combining self-supervised pre-training with two-stage supervised training.
  arXiv  Detail & Related papers  (2024-07-25T13:27:10Z)
• Improving Diffusion Models for ECG Imputation with an Augmented Template Prior [43.6099225257178]
  noisy and poor-quality recordings are a major issue for signals collected using mobile health systems. Recent studies have explored the imputation of missing values in ECG with probabilistic time-series models. We present a template-guided denoising diffusion probabilistic model (DDPM), PulseDiff, which is conditioned on an informative prior for a range of health conditions.
  arXiv  Detail & Related papers  (2023-10-24T11:34:15Z)
• Classification of lung cancer subtypes on CT images with synthetic pathological priors [41.75054301525535]
  Cross-scale associations exist in the image patterns between the same case's CT images and its pathological images. We propose self-generating hybrid feature network (SGHF-Net) for accurately classifying lung cancer subtypes on CT images.
  arXiv  Detail & Related papers  (2023-08-09T02:04:05Z)
• ElectroCardioGuard: Preventing Patient Misidentification in Electrocardiogram Databases through Neural Networks [0.0]
  In clinical practice, the assignment of captured ECG recordings to incorrect patients can occur inadvertently. We propose a small and efficient neural-network based model for determining whether two ECGs originate from the same patient. Our model achieves state-of-the-art performance in gallery-probe patient identification on PTB-XL while utilizing 760x fewer parameters.
  arXiv  Detail & Related papers  (2023-06-09T18:53:25Z)
• PulseNet: Deep Learning ECG-signal classification using random augmentation policy and continous wavelet transform for canines [46.09869227806991]
  evaluating canine electrocardiograms (ECG) require skilled veterinarians. Current availability of veterinary cardiologists for ECG interpretation and diagnostic support is limited. We implement a deep convolutional neural network (CNN) approach for classifying canine electrocardiogram sequences as either normal or abnormal.
  arXiv  Detail & Related papers  (2023-05-17T09:06:39Z)
• Preservation of High Frequency Content for Deep Learning-Based Medical Image Classification [74.84221280249876]
  An efficient analysis of large amounts of chest radiographs can aid physicians and radiologists. We propose a novel Discrete Wavelet Transform (DWT)-based method for the efficient identification and encoding of visual information.
  arXiv  Detail & Related papers  (2022-05-08T15:29:54Z)
• Optimal Transport based Data Augmentation for Heart Disease Diagnosis and Prediction [16.7288675686184]
  We propose a new method of data augmentation to solve the data imbalance problem within imbalanced ECG datasets. By using Optimal Transport, we augment the ECG disease data from normal ECG beats to balance the data among different categories. Our results demonstrate 1) the classification models' ability to make competitive predictions on five ECG categories; 2) improvements in accuracy and robustness reflecting the effectiveness of our data augmentation method.
  arXiv  Detail & Related papers  (2022-01-25T03:49:28Z)
• ECG-Based Heart Arrhythmia Diagnosis Through Attentional Convolutional Neural Networks [9.410102957429705]
  We propose Attention-Based Convolutional Neural Networks (ABCNN) to work on the raw ECG signals and automatically extract the informative dependencies for accurate arrhythmia detection. Our main task is to find the arrhythmia from normal heartbeats and, at the meantime, accurately recognize the heart diseases from five arrhythmia types. The experimental results show that the proposed ABCNN outperforms the widely used baselines.
  arXiv  Detail & Related papers  (2021-08-18T14:55:46Z)
• ECG-DelNet: Delineation of Ambulatory Electrocardiograms with Mixed Quality Labeling Using Neural Networks [69.25956542388653]
  Deep learning (DL) algorithms are gaining weight in academic and industrial settings. We demonstrate DL can be successfully applied to low interpretative tasks by embedding ECG detection and delineation onto a segmentation framework. The model was trained using PhysioNet's QT database, comprised of 105 ambulatory ECG recordings.
  arXiv  Detail & Related papers  (2020-05-11T16:29:12Z)
• A Global Benchmark of Algorithms for Segmenting Late Gadolinium-Enhanced Cardiac Magnetic Resonance Imaging [90.29017019187282]
  " 2018 Left Atrium Challenge" using 154 3D LGE-MRIs, currently the world's largest cardiac LGE-MRI dataset. Analyse of the submitted algorithms using technical and biological metrics was performed. Results show the top method achieved a dice score of 93.2% and a mean surface to a surface distance of 0.7 mm.
  arXiv  Detail & Related papers  (2020-04-26T08:49:17Z)

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.