Reading the Whole Heart: Latent-Attention Masked Autoencoders for Multimodal Cardiac Representation Learning

• URL: http://arxiv.org/abs/2609.12035v1
• Date: Thu, 10 Sep 2026 17:49:44 GMT
• Title: Reading the Whole Heart: Latent-Attention Masked Autoencoders for Multimodal Cardiac Representation Learning
• Abstract summary: We introduce Latent-Attention Masked Autoencoders (LAMAE), a multimodal, structure-aware masked autoencoder.<n>LAMAE exchanges information directly in the latent space through a shared latent-attention module operating over a study-view-entity hierarchy.<n>LAMAE outperforms modality-specific pretraining and strong contrastive and vision-language baselines across multimodal hospital-stay tasks.
• Score: 16.941311033409626
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Cardiovascular diagnosis rests on integrating complementary modalities, like ECG, echocardiography, chest radiographs, and clinical variables, each capturing distinct but correlated aspects of cardiac physiology. Yet most medical foundation models remain modality-specific, combining modalities only for finetuning or post-training. This discards the cross-modal evidence clinicians naturally integrate and ignores the structure within each modality. We introduce Latent-Attention Masked Autoencoders (LAMAE), a multimodal, structure-aware masked autoencoder that jointly learns patient-level representations during self-supervised pretraining. Rather than fusing modalities post hoc, LAMAE exchanges information directly in the latent space through a shared latent-attention module operating over a study-view-entity hierarchy, enabling aggregation of variable observations and graceful handling of missing modalities. Pretrained on over 1.2 million MIMIC-IV hospital stays, LAMAE outperforms modality-specific pretraining and strong contrastive and vision-language baselines across multimodal hospital-stay tasks, such as in-hospital mortality, ICD-10 and DRG coding, and length of stay, while remaining competitive on unimodal tasks. These gains persist even when only a single modality is available at test time, showing that modeling both intra- and inter-modal structure yields more robust, transferable representations.

Related papers

• AdaSurvMamba: Dynamic Fusion and Semantic Scanning for Multimodal Survival Analysis [57.942670844512016]
  We introduce AdaSurvMamba as a novel adaptive framework for multimodal survival analysis.<n>The framework features a Dual-Scale Importance-Aware Reconstruction (DSIR) module to dynamically modulate cross-modal interaction strength.<n>Experiments across five TCGA cohorts demonstrate consistent gains over existing methods.
  arXiv  Detail & Related papers  (2026-06-28T11:36:31Z)
• Beyond Independent Frames: Latent Attention Masked Autoencoders for Multi-View Echocardiography [18.218981066770514]
  We introduce Latent Attention Masked Autocoder (LAMAE), a foundation model architecture tailored to the multi-view nature of medical imaging.<n>LAMAE augments the standard MAE with a latent attention module that enables information exchange across frames and views directly in latent space.
  arXiv  Detail & Related papers  (2026-04-16T14:55:28Z)
• A Language-Signal-Vision Multimodal Framework for Multitask Cardiac Analysis [37.18952260878238]
  Textual Guidance Multimodal fusion for Multiple cardiac tasks (TGMM) was developed.<n>This study systematically explored key features across multiple modalities and elucidated their synergistic contributions in clinical decision-making.
  arXiv  Detail & Related papers  (2025-08-18T16:43:31Z)
• impuTMAE: Multi-modal Transformer with Masked Pre-training for Missing Modalities Imputation in Cancer Survival Prediction [75.43342771863837]
  We introduce impuTMAE, a novel transformer-based end-to-end approach with an efficient multimodal pre-training strategy.<n>It learns inter- and intra-modal interactions while simultaneously imputing missing modalities by reconstructing masked patches.<n>Our model is pre-trained on heterogeneous, incomplete data and fine-tuned for glioma survival prediction using TCGA-GBM/LGG and BraTS datasets.
  arXiv  Detail & Related papers  (2025-08-08T10:01:16Z)
• Multimodal Causal-Driven Representation Learning for Generalizable Medical Image Segmentation [56.52520416420957]
  We propose Multimodal Causal-Driven Representation Learning (MCDRL) to tackle domain generalization in medical image segmentation.<n>MCDRL consistently outperforms competing methods, yielding superior segmentation accuracy and exhibiting robust generalizability.
  arXiv  Detail & Related papers  (2025-08-07T03:41:41Z)
• NEARL-CLIP: Interacted Query Adaptation with Orthogonal Regularization for Medical Vision-Language Understanding [51.63264715941068]
  textbfNEARL-CLIP (iunderlineNteracted quunderlineEry underlineAdaptation with ounderlineRthogonaunderlineL Regularization) is a novel cross-modality interaction VLM-based framework.
  arXiv  Detail & Related papers  (2025-08-06T05:44:01Z)
• Multimodal Masked Autoencoder Pre-training for 3D MRI-Based Brain Tumor Analysis with Missing Modalities [0.0]
  BM-MAE is a masked image modeling pre-training strategy tailored for multimodal MRI data.<n>It seamlessly adapts to any combination of available modalities, extracting rich representations that capture both intra- and inter-modal information.<n>It can quickly and efficiently reconstruct missing modalities, highlighting its practical value.
  arXiv  Detail & Related papers  (2025-05-01T14:51:30Z)
• Foundation Model for Whole-Heart Segmentation: Leveraging Student-Teacher Learning in Multi-Modal Medical Imaging [0.510750648708198]
  Whole-heart segmentation from CT and MRI scans is crucial for cardiovascular disease analysis.<n>Existing methods struggle with modality-specific biases and the need for extensive labeled datasets.<n>We propose a foundation model for whole-heart segmentation using a self-supervised learning framework based on a student-teacher architecture.
  arXiv  Detail & Related papers  (2025-03-24T14:47:54Z)
• PMT: Progressive Mean Teacher via Exploring Temporal Consistency for Semi-Supervised Medical Image Segmentation [51.509573838103854]
  We propose a semi-supervised learning framework, termed Progressive Mean Teachers (PMT), for medical image segmentation. Our PMT generates high-fidelity pseudo labels by learning robust and diverse features in the training process. Experimental results on two datasets with different modalities, i.e., CT and MRI, demonstrate that our method outperforms the state-of-the-art medical image segmentation approaches.
  arXiv  Detail & Related papers  (2024-09-08T15:02:25Z)
• Cross-modality Guidance-aided Multi-modal Learning with Dual Attention for MRI Brain Tumor Grading [47.50733518140625]
  Brain tumor represents one of the most fatal cancers around the world, and is very common in children and the elderly. We propose a novel cross-modality guidance-aided multi-modal learning with dual attention for addressing the task of MRI brain tumor grading.
  arXiv  Detail & Related papers  (2024-01-17T07:54:49Z)
• Intra-Inter Subject Self-supervised Learning for Multivariate Cardiac Signals [5.344233761474541]
  We propose an Intra-inter Subject self-supervised Learning (ISL) model that is customized for multivariate cardiac signals. Our proposed ISL model integrates medical knowledge into self-supervision to effectively learn from intra-inter subject differences. In a semi-supervised transfer learning scenario, our pre-trained ISL model leads about 10% improvement over supervised training when only 1% labeled data is available.
  arXiv  Detail & Related papers  (2021-09-18T11:37:10Z)
• Towards Cross-modality Medical Image Segmentation with Online Mutual Knowledge Distillation [71.89867233426597]
  In this paper, we aim to exploit the prior knowledge learned from one modality to improve the segmentation performance on another modality. We propose a novel Mutual Knowledge Distillation scheme to thoroughly exploit the modality-shared knowledge. Experimental results on the public multi-class cardiac segmentation data, i.e., MMWHS 2017, show that our method achieves large improvements on CT segmentation.
  arXiv  Detail & Related papers  (2020-10-04T10:25:13Z)

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.