Key result
A semi-supervised active transfer learning approach achieved 92% accuracy for fetal ECG arrhythmia detection using only 399 training samples, outperforming traditional methods.
Why the study?
Deep learning anomaly detection requires thousands of manually annotated samples, but publicly available fetal ECG datasets annotated for each beat are lacking.
A novel semi-supervised active transfer learning approach significantly reduces the number of annotated samples required for accurate fetal ECG arrhythmia detection.
Answers are grounded in this paper and cite their sources.
May ease annotation burden for fetal ECG anomaly detection; leaves open prospective clinical validation.
Deep learning has demonstrated excellent results for ECG anomaly detection, wherein most approaches used supervised learning. The requirement of thousands of manually annotated samples is a concern for state-of-the-art anomaly detection systems, especially for fetal ECG (FECG), and currently, there is not a publicly available FECG dataset annotated for each FECG beat. In this paper, we offer a modified active learning technique based on transfer learning, calibration probability, and autoencoder-based sampling to reduce number of samples requires to annotate. In this regard, we used 25,000 s of recording from 47 patients from the MIT-BIH Arrhythmia Database to train a deep learning model to detect anomalies in non-fetus subjects. Then we used the unlabeled Non-Invasive Fetal ECG Arrhythmia Database (NIFEA DB) of 26 subjects to fine-tune the trained model to fine-tune the trained model based on active learning to detect anomalies in binary form for fetal. A variational autoencoder is trained on all data (adult and fetal ECG), and clustering is applied to latent features extracted from data after dimension reduction. Then, the sampling process of active learning selected samples from different clusters with low confidence to cover all data distribution. Moreover, a probability calibration based on mc-dropout and isotonic regression is used to calibrate confidences, helping to select reliable low-confidence samples. Various ablation studies were performed to show the influence of autoencoder-based sampling, calibration, and transfer learning, which showed that the proposed method could achieve 92% accuracy using 399 training samples. In contrast, other methods required more training samples to reach the same level of accuracy without calibration or an autoencoder and clustering approach or training without active learning. The study also found that transfer learning significantly impacted faster convergence and that the proposed active learning approach was more effective than traditional methods.
No takes yet. Share an insight, caveat, or question.
Mohebbian et al. (2023) studied Fetal ECG arrhythmia (n=73). Semi-supervised active transfer learning with autoencoder-based sampling and calibration vs. Traditional methods without calibration, autoencoder, clustering, or active learning was evaluated on Accuracy of fetal ECG anomaly detection. A semi-supervised active transfer learning approach achieved 92% accuracy for fetal ECG arrhythmia detection using only 399 training samples, outperforming traditional methods.
Synapse has enriched 10 related papers. Consider them for comparative context: