Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.21154 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912924109373440 |
|---|---|
| author | Niu, Ziwei Sun, Hao Bian, Shujun Yang, Xihong Lin, Lanfen Liu, Yuxin Jin, Yueming |
| author_facet | Niu, Ziwei Sun, Hao Bian, Shujun Yang, Xihong Lin, Lanfen Liu, Yuxin Jin, Yueming |
| contents | Accurate interpretation of electrocardiogram (ECG) signals is crucial for diagnosing cardiovascular diseases. Recent multimodal approaches that integrate ECGs with accompanying clinical reports show strong potential, but they still face two main concerns from a modality perspective: (1) intra-modality: existing models process ECGs in a lead-agnostic manner, overlooking spatial-temporal dependencies across leads, which restricts their effectiveness in modeling fine-grained diagnostic patterns; (2) inter-modality: existing methods directly align ECG signals with clinical reports, introducing modality-specific biases due to the free-text nature of the reports. In light of these two issues, we propose CG-DMER, a contrastive-generative framework for disentangled multimodal ECG representation learning, powered by two key designs: (1) Spatial-temporal masked modeling is designed to better capture fine-grained temporal dynamics and inter-lead spatial dependencies by applying masking across both spatial and temporal dimensions and reconstructing the missing information. (2) A representation disentanglement and alignment strategy is designed to mitigate unnecessary noise and modality-specific biases by introducing modality-specific and modality-shared encoders, ensuring a clearer separation between modality-invariant and modality-specific representations. Experiments on three public datasets demonstrate that CG-DMER achieves state-of-the-art performance across diverse downstream tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_21154 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CG-DMER: Hybrid Contrastive-Generative Framework for Disentangled Multimodal ECG Representation Learning Niu, Ziwei Sun, Hao Bian, Shujun Yang, Xihong Lin, Lanfen Liu, Yuxin Jin, Yueming Artificial Intelligence Accurate interpretation of electrocardiogram (ECG) signals is crucial for diagnosing cardiovascular diseases. Recent multimodal approaches that integrate ECGs with accompanying clinical reports show strong potential, but they still face two main concerns from a modality perspective: (1) intra-modality: existing models process ECGs in a lead-agnostic manner, overlooking spatial-temporal dependencies across leads, which restricts their effectiveness in modeling fine-grained diagnostic patterns; (2) inter-modality: existing methods directly align ECG signals with clinical reports, introducing modality-specific biases due to the free-text nature of the reports. In light of these two issues, we propose CG-DMER, a contrastive-generative framework for disentangled multimodal ECG representation learning, powered by two key designs: (1) Spatial-temporal masked modeling is designed to better capture fine-grained temporal dynamics and inter-lead spatial dependencies by applying masking across both spatial and temporal dimensions and reconstructing the missing information. (2) A representation disentanglement and alignment strategy is designed to mitigate unnecessary noise and modality-specific biases by introducing modality-specific and modality-shared encoders, ensuring a clearer separation between modality-invariant and modality-specific representations. Experiments on three public datasets demonstrate that CG-DMER achieves state-of-the-art performance across diverse downstream tasks. |
| title | CG-DMER: Hybrid Contrastive-Generative Framework for Disentangled Multimodal ECG Representation Learning |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2602.21154 |