# Multimodal Representation Learning of Cardiovascular Magnetic Resonance Imaging

arXiv: https://arxiv.org/abs/2304.07675 · HTML: https://mlsanity.com/paper/2304.07675/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 78 references that are in the map.
- First posted on arXiv 16 Apr 2023.

## Builds on (most cited first, 30 of 38)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [Contrastive Learning of Medical Visual Representations from Paired Images and Text](https://mlsanity.com/paper/2010.00747/) (2020)
- [VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding](https://mlsanity.com/paper/2109.14084/) (2021)
- [MedCLIP: Contrastive Learning from Unpaired Medical Images and Text](https://mlsanity.com/paper/2210.10163/) (2022)
- [End-to-End Learning of Visual Representations from Uncurated Instructional Videos](https://mlsanity.com/paper/1912.06430/) (2019)
- [Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling](https://mlsanity.com/paper/2102.06183/) (2021)
- [Multi-modal Transformer for Video Retrieval](https://mlsanity.com/paper/2007.10639/) (2020)
- [Large-Scale Adversarial Training for Vision-and-Language Representation Learning](https://mlsanity.com/paper/2006.06195/) (2020)
- [Big Self-Supervised Models Advance Medical Image Classification](https://mlsanity.com/paper/2101.05224/) (2021)
- [Temporal Segment Networks for Action Recognition in Videos](https://mlsanity.com/paper/1705.02953/) (2017)
- [Self-Supervised MultiModal Versatile Networks](https://mlsanity.com/paper/2006.16228/) (2020)
- [An Empirical Study of Training End-to-End Vision-and-Language Transformers](https://mlsanity.com/paper/2111.02387/) (2021)
- [Revisiting the "Video" in Video-Language Understanding](https://mlsanity.com/paper/2206.01720/) (2022)
- [Learning a Text-Video Embedding from Incomplete and Heterogeneous Data](https://mlsanity.com/paper/1804.02516/) (2018)
- [Self-Supervised Learning for Cardiac MR Image Segmentation by Anatomical Position Prediction](https://mlsanity.com/paper/1907.02757/) (2019)
- [Grouped Spatial-Temporal Aggregation for Efficient Action Recognition](https://mlsanity.com/paper/1909.13130/) (2019)

## Built on by (most cited first, 4 of 4)

- [Towards Cardiac MRI Foundation Models: Comprehensive Visual-Tabular Representations for Whole-Heart Assessment and Beyond](https://mlsanity.com/paper/2504.13037/) (2025)
- [MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos](https://mlsanity.com/paper/2306.04216/) (2023)
- [Whole Heart 3D+T Representation Learning Through Sparse 2D Cardiac MR Images](https://mlsanity.com/paper/2406.00329/) (2024)
- [Large Language Model-informed ECG Dual Attention Network for Heart Failure Risk Prediction](https://mlsanity.com/paper/2403.10581/) (2024)

## Abstract (arXiv)

Self-supervised learning is crucial for clinical imaging applications, given the lack of explicit labels in healthcare. However, conventional approaches that rely on precise vision-language alignment are not always feasible in complex clinical imaging modalities, such as cardiac magnetic resonance (CMR). CMR provides a comprehensive visualization of cardiac anatomy, physiology, and microstructure, making it challenging to interpret. Additionally, CMR reports require synthesizing information from sequences of images and different views, resulting in potentially weak alignment between the study and diagnosis report pair. To overcome these challenges, we propose CMRformer, a multimodal learning framework to jointly learn sequences of CMR images and associated cardiologist's reports. Moreover, one of the major obstacles to improving CMR study is the lack of large, publicly available datasets. To bridge this gap, we collected a large CMR dataset, which consists of 13,787 studies from clinical cases. By utilizing our proposed CMRformer and our collected dataset, we achieved remarkable performance in real-world clinical tasks, such as CMR image retrieval and diagnosis report retrieval. Furthermore, the learned representations are evaluated to be practically helpful for downstream applications, such as disease classification. Our work could potentially expedite progress in the CMR study and lead to more accurate and effective diagnosis and treatment.