Transfer learning for ECG classification.
TL;DR: Kweimann et al. as mentioned in this paper used transfer learning to train deep convolutional neural networks (CNNs) to classify raw ECG recordings and finetune the networks on a small data set for classification of Atrial Fibrillation, which is the most common heart arrhythmia.
Abstract: Remote monitoring devices, which can be worn or implanted, have enabled a more effective healthcare for patients with periodic heart arrhythmia due to their ability to constantly monitor heart activity. However, these devices record considerable amounts of electrocardiogram (ECG) data that needs to be interpreted by physicians. Therefore, there is a growing need to develop reliable methods for automatic ECG interpretation to assist the physicians. Here, we use deep convolutional neural networks (CNN) to classify raw ECG recordings. However, training CNNs for ECG classification often requires a large number of annotated samples, which are expensive to acquire. In this work, we tackle this problem by using transfer learning. First, we pretrain CNNs on the largest public data set of continuous raw ECG signals. Next, we finetune the networks on a small data set for classification of Atrial Fibrillation, which is the most common heart arrhythmia. We show that pretraining improves the performance of CNNs on the target task by up to [Formula: see text], effectively reducing the number of annotations required to achieve the same performance as CNNs that are not pretrained. We investigate both supervised as well as unsupervised pretraining approaches, which we believe will increase in relevance, since they do not rely on the expensive ECG annotations. The code is available on GitHub at https://github.com/kweimann/ecg-transfer-learning .
Citations
More filters
Abstract: Accurate state of charge (SOC) estimation of lithium-ion (Li-ion) batteries is crucial in prolonging cell lifespan and ensuring its safe operation for electric vehicle applications. In this article, we propose the deep learning-based transformer model trained with self-supervised learning (SSL) for end-to-end SOC estimation without the requirements of feature engineering or adaptive filtering. We demonstrate that with the SSL framework, the proposed deep learning transformer model achieves the lowest root-mean-square-error (RMSE) of 0.90% and a mean-absolute-error (MAE) of 0.44% at constant ambient temperature, and RMSE of 1.19% and a MAE of 0.7% at varying ambient temperature. With SSL, the proposed model can be trained with as few as 5 epochs using only 20% of the total training data and still achieves less than 1.9% RMSE on the test data. Finally, we also demonstrate that the learning weights during the SSL training can be transferred to a new Li-ion cell with different chemistry and still achieve on-par performance compared to the models trained from scratch on the new cell.
24 citations
TL;DR: An ECG dataset containing more than 10,000 subject records was used to train and diagnose arrhythmia and important finding of fusion of deep features and shallow classifiers to improve the performance of the proposed system was presented.
Abstract: Arrhythmia is a condition characterized by perturbation of the regular rhythm of the heart. The development of computerized self-diagnostic systems for the detection of these arrhythmias is very popular, thanks to the machine learning models included in these systems, which eliminate the need for visual inspection of long electrocardiogram (ECG) recordings. In order to design a reliable, generalizable and highly accurate model, large number of subjects and arrhythmia classes are included in the training and testing phases of the model. In this study, an ECG dataset containing more than 10,000 subject records was used to train and diagnose arrhythmia. A deep neural network (DNN) model was used on the data set during the extraction of the features of the ECG inputs. Feature maps obtained from hierarchically placed layers in DNN were fed to various shallow classifiers. Principal component analysis (PCA) technique was used to reduce the high dimensions of feature maps. In addition to the morphological features obtained with DNN, various ECG features obtained from lead-II for rhythmic information are fused to increase the performance. Using the ECG features, an accuracy of 90.30% has been achieved. Using only deep features, this accuracy was increased to 97.26%. However, the accuracy was increased to 98.00% by fusing both deep and ECG-based features. Another important research subject of the study is the examination of the features obtained from DNN network both on a layer basis and at each training step. The findings show that the more abstract features obtained from the last layers of the DNN network provide high performance in shallow classifiers, and weight updates of DNN network also increases the performance of these classifiers. Hence, the study presents important findings on the fusion of deep features and shallow classifiers to improve the performance of the proposed system.
20 citations
TL;DR: Wang et al. as discussed by the authors proposed a multi-defect detection system based on StyleGAN-SDM and fusion CNN for sewer pipelines, which integrates StyleGAN v2 and sharpness discrimination model (SDM) to automatically select clear images.
15 citations
13 Oct 2021
TL;DR: The center tasks of AECG signal processing include signal preprocessing, beat detection and classification, event detection, and event prediction, which are the topics most relevant and of greatest concern to the people working in this area.
Abstract: The ambulatory ECG (AECG) is an important diagnostic tool for many heart electrophysiology-related cases. AECG covers a wide spectrum of devices and applications. At the core of these devices and applications are the algorithms responsible for signal conditioning, ECG beat detection and classification, and event detections. Over the years, there has been huge progress for algorithm development and implementation thanks to great efforts by researchers, engineers, and physicians, alongside the rapid development of electronics and signal processing, especially machine learning (ML). The current efforts and progress in machine learning fields are unprecedented, and many of these ML algorithms have also been successfully applied to AECG applications. This review covers some key AECG applications of ML algorithms. However, instead of doing a general review of ML algorithms, we are focusing on the central tasks of AECG and discussing what ML can bring to solve the key challenges AECG is facing. The center tasks of AECG signal processing listed in the review include signal preprocessing, beat detection and classification, event detection, and event prediction. Each AECG device/system might have different portions and forms of those signal components depending on its application and the target, but these are the topics most relevant and of greatest concern to the people working in this area.
10 citations
TL;DR: Transfer learning is a form of machine learning where a pre-trained model trained on a specific task is reused as a starting point and tailored to another task in a different dataset.
Abstract: Background Transfer learning is a form of machine learning where a pre-trained model trained on a specific task is reused as a starting point and tailored to another task in a different dataset. While transfer learning has garnered considerable attention in medical image analysis, its use for clinical non-image data is not well studied. Therefore, the objective of this scoping review was to explore the use of transfer learning for non-image data in the clinical literature. Methods and Findings We systematically searched medical databases (PubMed, EMBASE, CINAHL) for peer-reviewed clinical studies that used transfer learning on human non-image data. We included 83 studies in the review. More than half of the studies (63%) were published within 12 months of the search. Transfer learning was most often applied to time series data (61%), followed by tabular data (18%), audio (12%) and text (8%). Thirty-three (40%) studies applied an image-based model to non-image data after transforming data into images (e.g. spectrograms). Twenty-nine (35%) studies did not have any authors with a health-related affiliation. Many studies used publicly available datasets (66%) and models (49%), but fewer shared their code (27%). Conclusions In this scoping review, we have described current trends in the use of transfer learning for non-image data in the clinical literature. We found that the use of transfer learning has grown rapidly within the last few years. We have identified studies and demonstrated the potential of transfer learning in clinical research in a wide range of medical specialties. More interdisciplinary collaborations and the wider adaption of reproducible research principles are needed to increase the impact of transfer learning in clinical research.
10 citations
References
More filters
20 Jun 2009
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Abstract: The explosion of image data on the Internet has the potential to foster more sophisticated and robust models and algorithms to index, retrieve, organize and interact with images and multimedia data. But exactly how such data can be harnessed and organized remains a critical problem. We introduce here a new database called “ImageNet”, a large-scale ontology of images built upon the backbone of the WordNet structure. ImageNet aims to populate the majority of the 80,000 synsets of WordNet with an average of 500-1000 clean and full resolution images. This will result in tens of millions of annotated images organized by the semantic hierarchy of WordNet. This paper offers a detailed analysis of ImageNet in its current state: 12 subtrees with 5247 synsets and 3.2 million images in total. We show that ImageNet is much larger in scale and diversity and much more accurate than the current image datasets. Constructing such a large-scale database is a challenging task. We describe the data collection scheme with Amazon Mechanical Turk. Lastly, we illustrate the usefulness of ImageNet through three simple applications in object recognition, image classification and automatic object clustering. We hope that the scale, accuracy, diversity and hierarchical structure of ImageNet can offer unparalleled opportunities to researchers in the computer vision community and beyond.
49,639 citations
Posted Content•
TL;DR: In this article, the adaptive estimates of lower-order moments are used for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimate of lowerorder moments.
Abstract: We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has little memory requirements, is invariant to diagonal rescaling of the gradients, and is well suited for problems that are large in terms of data and/or parameters. The method is also appropriate for non-stationary objectives and problems with very noisy and/or sparse gradients. The hyper-parameters have intuitive interpretations and typically require little tuning. Some connections to related algorithms, on which Adam was inspired, are discussed. We also analyze the theoretical convergence properties of the algorithm and provide a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework. Empirical results demonstrate that Adam works well in practice and compares favorably to other stochastic optimization methods. Finally, we discuss AdaMax, a variant of Adam based on the infinity norm.
23,486 citations
Proceedings Article•
01 Jan 2015TL;DR: It is conjecture that the use of a fixed-length vector is a bottleneck in improving the performance of this basic encoder-decoder architecture, and it is proposed to extend this by allowing a model to automatically (soft-)search for parts of a source sentence that are relevant to predicting a target word, without having to form these parts as a hard segment explicitly.
Abstract: Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to maximize the translation performance. The models proposed recently for neural machine translation often belong to a family of encoder-decoders and consists of an encoder that encodes a source sentence into a fixed-length vector from which a decoder generates a translation. In this paper, we conjecture that the use of a fixed-length vector is a bottleneck in improving the performance of this basic encoder-decoder architecture, and propose to extend this by allowing a model to automatically (soft-)search for parts of a source sentence that are relevant to predicting a target word, without having to form these parts as a hard segment explicitly. With this new approach, we achieve a translation performance comparable to the existing state-of-the-art phrase-based system on the task of English-to-French translation. Furthermore, qualitative analysis reveals that the (soft-)alignments found by the model agree well with our intuition.
20,027 citations
TL;DR: The newly inaugurated Research Resource for Complex Physiologic Signals (RRSPS) as mentioned in this paper was created under the auspices of the National Center for Research Resources (NCR Resources).
Abstract: —The newly inaugurated Research Resource for Complex Physiologic Signals, which was created under the auspices of the National Center for Research Resources of the National Institutes of He...
11,407 citations
TL;DR: A real-time algorithm that reliably recognizes QRS complexes based upon digital analyses of slope, amplitude, and width of ECG signals and automatically adjusts thresholds and parameters periodically to adapt to such ECG changes as QRS morphology and heart rate.
Abstract: We have developed a real-time algorithm for detection of the QRS complexes of ECG signals. It reliably recognizes QRS complexes based upon digital analyses of slope, amplitude, and width. A special digital bandpass filter reduces false detections caused by the various types of interference present in ECG signals. This filtering permits use of low thresholds, thereby increasing detection sensitivity. The algorithm automatically adjusts thresholds and parameters periodically to adapt to such ECG changes as QRS morphology and heart rate. For the standard 24 h MIT/BIH arrhythmia database, this algorithm correctly detects 99.3 percent of the QRS complexes.
6,686 citations