# Multi-scale Cross-restoration Framework for Electrocardiogram Anomaly Detection

arXiv: https://arxiv.org/abs/2308.01639 · HTML: https://mlsanity.com/paper/2308.01639/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 30 references that are in the map.
- First posted on arXiv 3 Aug 2023.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy](https://mlsanity.com/paper/2110.02642/) (2021)
- [Graph Neural Network-Based Anomaly Detection in Multivariate Time Series](https://mlsanity.com/paper/2106.06947/) (2021)
- [Diffusion Models for Medical Anomaly Detection](https://mlsanity.com/paper/2203.04306/) (2022)
- [TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data](https://mlsanity.com/paper/2201.07284/) (2022)
- [A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data](https://mlsanity.com/paper/1811.08055/) (2018)
- [MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks](https://mlsanity.com/paper/1901.04997/) (2019)
- [Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signals](https://mlsanity.com/paper/2107.12626/) (2021)
- [Robust, Deep and Inductive Anomaly Detection](https://mlsanity.com/paper/1704.06743/) (2017)
- [Task-oriented Self-supervised Learning for Anomaly Detection in Electroencephalography](https://mlsanity.com/paper/2207.01391/) (2022)

## Built on by (most cited first, 10 of 10)

- [Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images](https://mlsanity.com/paper/2403.12570/) (2024)
- [Conditional diffusion models for guided anomaly detection in brain images using fluid-driven anomaly randomization](https://mlsanity.com/paper/2506.10233/) (2025)
- [TSINR: Capturing Temporal Continuity via Implicit Neural Representations for Time Series Anomaly Detection](https://mlsanity.com/paper/2411.11641/) (2024)
- [Complex Style Image Transformations for Domain Generalization in Medical Images](https://mlsanity.com/paper/2406.00298/) (2024)
- [TSRNet: Simple Framework for Real-time ECG Anomaly Detection with Multimodal Time and Spectrogram Restoration Network](https://mlsanity.com/paper/2312.10187/) (2023)
- [SD-MAD: Sign-Driven Few-shot Multi-Anomaly Detection in Medical Images](https://mlsanity.com/paper/2505.16659/) (2025)
- [CADD: Context aware disease deviations via restoration of brain images using normative conditional diffusion models](https://mlsanity.com/paper/2508.03594/) (2025)
- [Cross-Task Generalization in Handwriting-Based Alzheimer's Screening via Vision Language Adaptation](https://mlsanity.com/paper/2511.05841/) (2025)
- [Beyond Pooling: Matching for Robust Generalization under Data Heterogeneity](https://mlsanity.com/paper/2602.07154/) (2026)
- [Demographic-Aware Self-Supervised Anomaly Detection Pretraining for Equitable Rare Cardiac Diagnosis](https://mlsanity.com/paper/2603.19695/) (2026)

## Abstract (arXiv)

Electrocardiogram (ECG) is a widely used diagnostic tool for detecting heart conditions. Rare cardiac diseases may be underdiagnosed using traditional ECG analysis, considering that no training dataset can exhaust all possible cardiac disorders. This paper proposes using anomaly detection to identify any unhealthy status, with normal ECGs solely for training. However, detecting anomalies in ECG can be challenging due to significant inter-individual differences and anomalies present in both global rhythm and local morphology. To address this challenge, this paper introduces a novel multi-scale cross-restoration framework for ECG anomaly detection and localization that considers both local and global ECG characteristics. The proposed framework employs a two-branch autoencoder to facilitate multi-scale feature learning through a masking and restoration process, with one branch focusing on global features from the entire ECG and the other on local features from heartbeat-level details, mimicking the diagnostic process of cardiologists. Anomalies are identified by their high restoration errors. To evaluate the performance on a large number of individuals, this paper introduces a new challenging benchmark with signal point-level ground truths annotated by experienced cardiologists. The proposed method demonstrates state-of-the-art performance on this benchmark and two other well-known ECG datasets. The benchmark dataset and source code are available at: urlhttps://github.com/MediaBrain-SJTU/ECGAD