# From Transthoracic to Transesophageal: Cross-Modality Generation using LoRA Diffusion

arXiv: https://arxiv.org/abs/2508.13077 · HTML: https://mlsanity.com/paper/2508.13077/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 13 of its 26 references that are in the map.
- First posted on arXiv 18 Aug 2025.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 13 of 13)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiography](https://mlsanity.com/paper/1908.06948/) (2019)
- [Diffusion Models for Medical Anomaly Detection](https://mlsanity.com/paper/2203.04306/) (2022)
- [Echo from noise: synthetic ultrasound image generation using diffusion models for real image segmentation](https://mlsanity.com/paper/2305.05424/) (2023)
- [Feature-Conditioned Cascaded Video Diffusion Models for Precise Echocardiogram Synthesis](https://mlsanity.com/paper/2303.12644/) (2023)
- [Cascaded Multi-path Shortcut Diffusion Model for Medical Image Translation](https://mlsanity.com/paper/2405.12223/) (2024)
- [Training-Free Condition Video Diffusion Models for single frame Spatial-Semantic Echocardiogram Synthesis](https://mlsanity.com/paper/2408.03035/) (2024)
- [Transesophageal Echocardiography Generation using Anatomical Models](https://mlsanity.com/paper/2410.06781/) (2024)

## Built on by (most cited first, 2 of 2)

- [EchoLVFM: One-Step Video Generation via Latent Flow Matching for Echocardiogram Synthesis](https://mlsanity.com/paper/2603.13967/) (2026)
- [AortaDiff: A Unified Multitask Diffusion Framework For Contrast-Free AAA Imaging](https://mlsanity.com/paper/2510.01498/) (2025)

## Abstract (arXiv)

Deep diffusion models excel at realistic image synthesis but demand large training sets-an obstacle in data-scarce domains like transesophageal echocardiography (TEE). While synthetic augmentation has boosted performance in transthoracic echo (TTE), TEE remains critically underrepresented, limiting the reach of deep learning in this high-impact modality. We address this gap by adapting a TTE-trained, mask-conditioned diffusion backbone to TEE with only a limited number of new cases and adapters as small as 105 parameters. Our pipeline combines Low-Rank Adaptation with MaskR2, a lightweight remapping layer that aligns novel mask formats with the pretrained model's conditioning channels. This design lets users adapt models to new datasets with a different set of anatomical structures to the base model's original set. Through a targeted adaptation strategy, we find that adapting only MLP layers suffices for high-fidelity TEE synthesis. Finally, mixing less than 200 real TEE frames with our synthetic echoes improves the dice score on a multiclass segmentation task, particularly boosting performance on underrepresented right-heart structures. Our results demonstrate that (1) semantically controlled TEE images can be generated with low overhead, (2) MaskR2 effectively transforms unseen mask formats into compatible formats without damaging downstream task performance, and (3) our method generates images that are effective for improving performance on a downstream task of multiclass segmentation.