# Fake It Till You Make It: Using Synthetic Data and Domain Knowledge for Improved Text-Based Learning for LGE Detection

arXiv: https://arxiv.org/abs/2502.12948 · HTML: https://mlsanity.com/paper/2502.12948/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 39 references that are in the map.
- First posted on arXiv 18 Feb 2025.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [Contrastive Learning of Medical Visual Representations from Paired Images and Text](https://mlsanity.com/paper/2010.00747/) (2020)
- [MedCLIP: Contrastive Learning from Unpaired Medical Images and Text](https://mlsanity.com/paper/2210.10163/) (2022)
- [BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs](https://mlsanity.com/paper/2303.00915/) (2023)
- [Med-Flamingo: a Multimodal Medical Few-shot Learner](https://mlsanity.com/paper/2307.15189/) (2023)
- [Quilt-1M: One Million Image-Text Pairs for Histopathology](https://mlsanity.com/paper/2306.11207/) (2023)
- [SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2211.14813/) (2022)
- [MediCLIP: Adapting CLIP for Few-shot Medical Image Anomaly Detection](https://mlsanity.com/paper/2405.11315/) (2024)
- [Deep Learning methods for automatic evaluation of delayed enhancement-MRI. The results of the EMIDEC challenge](https://mlsanity.com/paper/2108.04016/) (2021)
- [GridCLIP: One-Stage Object Detection by Grid-Level CLIP Representation Learning](https://mlsanity.com/paper/2303.09252/) (2023)
- [Towards a vision foundation model for comprehensive assessment of Cardiac MRI](https://mlsanity.com/paper/2410.01665/) (2024)
- [Cascaded Convolutional Neural Network for Automatic Myocardial Infarction Segmentation from Delayed-Enhancement Cardiac MRI](https://mlsanity.com/paper/2012.14128/) (2020)
- [LatteCLIP: Unsupervised CLIP Fine-Tuning via LMM-Synthetic Texts](https://mlsanity.com/paper/2410.08211/) (2024)
- [CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning](https://mlsanity.com/paper/2410.11963/) (2024)

## Built on by (most cited first, 1 of 1)

- [LGESynthNet: Controlled Scar Synthesis for Improved Scar Segmentation in Cardiac LGE-MRI Imaging](https://mlsanity.com/paper/2603.18356/) (2026)

## Abstract (arXiv)

Detection of hyperenhancement from cardiac LGE MRI images is a complex task requiring significant clinical expertise. Although deep learning-based models have shown promising results for the task, they require large amounts of data with fine-grained annotations. Clinical reports generated for cardiac MR studies contain rich, clinically relevant information, including the location, extent and etiology of any scars present. Although recently developed CLIP-based training enables pretraining models with image-text pairs, it requires large amounts of data and further finetuning strategies on downstream tasks. In this study, we use various strategies rooted in domain knowledge to train a model for LGE detection solely using text from clinical reports, on a relatively small clinical cohort of 965 patients. We improve performance through the use of synthetic data augmentation, by systematically creating scar images and associated text. In addition, we standardize the orientation of the images in an anatomy-informed way to enable better alignment of spatial and text features. We also use a captioning loss to enable fine-grained supervision and explore the effect of pretraining of the vision encoder on performance. Finally, ablation studies are carried out to elucidate the contributions of each design component to the overall performance of the model.