# Efficient Semantic Diffusion Architectures for Model Training on Synthetic Echocardiograms

arXiv: https://arxiv.org/abs/2409.19371 · HTML: https://mlsanity.com/paper/2409.19371/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 26 of its 49 references that are in the map.
- First posted on arXiv 28 Sep 2024.

## Placed in

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

## Builds on (most cited first, 26 of 26)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [Guiding a Diffusion Model with a Bad Version of Itself](https://mlsanity.com/paper/2406.02507/) (2024)
- [Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization](https://mlsanity.com/paper/1804.06516/) (2018)
- [Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiography](https://mlsanity.com/paper/1908.06948/) (2019)
- [SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining](https://mlsanity.com/paper/2107.09559/) (2021)
- [Scalable Adaptive Computation for Iterative Generation](https://mlsanity.com/paper/2212.11972/) (2022)
- [Anatomically Constrained Neural Networks (ACNN): Application to Cardiac Image Enhancement and Segmentation](https://mlsanity.com/paper/1705.08302/) (2017)
- [The rising costs of training frontier AI models](https://mlsanity.com/paper/2405.21015/) (2024)
- [Deep MR to CT Synthesis using Unpaired Data](https://mlsanity.com/paper/1708.01155/) (2017)
- [Generative Adversarial Networks (GANs Survey): Challenges, Solutions, and Future Directions](https://mlsanity.com/paper/2005.00065/) (2020)
- [A Lifelong Learning Approach to Brain MR Segmentation Across Scanners and Protocols](https://mlsanity.com/paper/1805.10170/) (2018)
- [Unsupervised Medical Image Translation Using Cycle-MedGAN](https://mlsanity.com/paper/1903.03374/) (2019)
- [Echo from noise: synthetic ultrasound image generation using diffusion models for real image segmentation](https://mlsanity.com/paper/2305.05424/) (2023)
- [3D U2-Net: A 3D Universal U-Net for Multi-Domain Medical Image Segmentation](https://mlsanity.com/paper/1909.06012/) (2019)
- [A systematic study of race and sex bias in CNN-based cardiac MR segmentation](https://mlsanity.com/paper/2209.01627/) (2022)
- [Rare Disease Detection by Sequence Modeling with Generative Adversarial Networks](https://mlsanity.com/paper/1907.01022/) (2019)
- [CNN-Based Ultrasound Image Reconstruction for Ultrafast Displacement Tracking](https://mlsanity.com/paper/2009.01816/) (2020)

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

- [Diffusion-empowered AutoPrompt MedSAM](https://mlsanity.com/paper/2502.06817/) (2025)

## Abstract (arXiv)

We investigate the utility of diffusion generative models to efficiently synthesise datasets that effectively train deep learning models for image analysis. Specifically, we propose novel Gamma-distribution Latent Denoising Diffusion Models (LDMs) designed to generate semantically guided synthetic cardiac ultrasound images with improved computational efficiency. We also investigate the potential of using these synthetic images as a replacement for real data in training deep networks for left-ventricular segmentation and binary echocardiogram view classification tasks. We compared six diffusion models in terms of the computational cost of generating synthetic 2D echo data, the visual realism of the resulting images, and the performance, on real data, of downstream tasks (segmentation and classification) trained using these synthetic echoes. We compare various diffusion strategies and ODE solvers for their impact on segmentation and classification performance. The results show that our propose architectures significantly reduce computational costs while maintaining or improving downstream task performance compared to state-of-the-art methods. While other diffusion models generated more realistic-looking echo images at higher computational cost, our research suggests that for model training, visual realism is not necessarily related to model performance, and considerable compute costs can be saved by using more efficient models.