# Echo from noise: synthetic ultrasound image generation using diffusion models for real image segmentation

arXiv: https://arxiv.org/abs/2305.05424 · HTML: https://mlsanity.com/paper/2305.05424/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 12 of its 23 references that are in the map.
- First posted on arXiv 9 May 2023.

## Placed in

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

## Builds on (most cited first, 12 of 12)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Brain Imaging Generation with Latent Diffusion Models](https://mlsanity.com/paper/2209.07162/) (2022)
- [Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiography](https://mlsanity.com/paper/1908.06948/) (2019)
- [TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning](https://mlsanity.com/paper/2003.04696/) (2020)
- [Semantic Image Synthesis via Diffusion Models](https://mlsanity.com/paper/2207.00050/) (2022)
- [Conversion Between CT and MRI Images Using Diffusion and Score-Matching Models](https://mlsanity.com/paper/2209.12104/) (2022)
- [Unsupervised Medical Image Translation Using Cycle-MedGAN](https://mlsanity.com/paper/1903.03374/) (2019)
- [Efficient Pix2Vox++ for 3D Cardiac Reconstruction from 2D echo views](https://mlsanity.com/paper/2207.13424/) (2022)

## Built on by (most cited first, 30 of 34)

- [Flow Matching for Medical Image Synthesis: Bridging the Gap Between Speed and Quality](https://mlsanity.com/paper/2503.00266/) (2025)
- [Generative AI for Synthetic Data Across Multiple Medical Modalities: A Systematic Review of Recent Developments and Challenges](https://mlsanity.com/paper/2407.00116/) (2024)
- [Dehazing Ultrasound using Diffusion Models](https://mlsanity.com/paper/2307.11204/) (2023)
- [EchoWorld: Learning Motion-Aware World Models for Echocardiography Probe Guidance](https://mlsanity.com/paper/2504.13065/) (2025)
- [Ultrasound Image-to-Video Synthesis via Latent Dynamic Diffusion Models](https://mlsanity.com/paper/2503.14966/) (2025)
- [Diffusion as Sound Propagation: Physics-inspired Model for Ultrasound Image Generation](https://mlsanity.com/paper/2407.05428/) (2024)
- [XReal: Realistic Anatomy and Pathology-Aware X-ray Generation via Controllable Diffusion Model](https://mlsanity.com/paper/2403.09240/) (2024)
- [Echocardiography video synthesis from end diastolic semantic map via diffusion model](https://mlsanity.com/paper/2310.07131/) (2023)
- [Synthetic Data in Radiological Imaging: Current State and Future Outlook](https://mlsanity.com/paper/2407.01561/) (2024)
- [Sequential Posterior Sampling with Diffusion Models](https://mlsanity.com/paper/2409.05399/) (2024)
- [Ultrasound Image Generation using Latent Diffusion Models](https://mlsanity.com/paper/2502.08580/) (2025)
- [Synthetic Boost: Leveraging Synthetic Data for Enhanced Vision-Language Segmentation in Echocardiography](https://mlsanity.com/paper/2309.12829/) (2023)
- [Vision-Language Synthetic Data Enhances Echocardiography Downstream Tasks](https://mlsanity.com/paper/2403.19880/) (2024)
- [Training-Free Condition Video Diffusion Models for single frame Spatial-Semantic Echocardiogram Synthesis](https://mlsanity.com/paper/2408.03035/) (2024)
- [Toward Medical Deepfake Detection: A Comprehensive Dataset and Novel Method](https://mlsanity.com/paper/2509.15711/) (2025)
- [CT Synthesis with Conditional Diffusion Models for Abdominal Lymph Node Segmentation](https://mlsanity.com/paper/2403.17770/) (2024)
- [EchoFlow: A Foundation Model for Cardiac Ultrasound Image and Video Generation](https://mlsanity.com/paper/2503.22357/) (2025)
- [Cardiac ultrasound simulation for autonomous ultrasound navigation](https://mlsanity.com/paper/2402.06463/) (2024)
- [Discriminative Hamiltonian Variational Autoencoder for Accurate Tumor Segmentation in Data-Scarce Regimes](https://mlsanity.com/paper/2406.11659/) (2024)
- [Generative augmentations for improved cardiac ultrasound segmentation using diffusion models](https://mlsanity.com/paper/2502.20100/) (2025)
- [MEDDAP: Medical Dataset Enhancement via Diversified Augmentation Pipeline](https://mlsanity.com/paper/2403.16335/) (2024)
- [S-CycleGAN: Semantic Segmentation Enhanced CT-Ultrasound Image-to-Image Translation for Robotic Ultrasonography](https://mlsanity.com/paper/2406.01191/) (2024)
- [High Volume Rate 3D Ultrasound Reconstruction with Diffusion Models](https://mlsanity.com/paper/2505.22090/) (2025)
- [From Transthoracic to Transesophageal: Cross-Modality Generation using LoRA Diffusion](https://mlsanity.com/paper/2508.13077/) (2025)
- [Efficient Semantic Diffusion Architectures for Model Training on Synthetic Echocardiograms](https://mlsanity.com/paper/2409.19371/) (2024)
- [PCA for Enhanced Cross-Dataset Generalizability in Breast Ultrasound Tumor Segmentation](https://mlsanity.com/paper/2505.23587/) (2025)
- [Synthetic Simplicity: Unveiling Bias in Medical Data Augmentation](https://mlsanity.com/paper/2407.21674/) (2024)
- [DeepSPV: A Deep Learning Pipeline for 3D Spleen Volume Estimation from 2D Ultrasound Images](https://mlsanity.com/paper/2411.11190/) (2024)
- [Generative deep learning for foundational video translation in ultrasound](https://mlsanity.com/paper/2511.03255/) (2025)
- [Label-free Motion-Conditioned Diffusion Model for Cardiac Ultrasound Synthesis](https://mlsanity.com/paper/2512.09418/) (2025)

## Abstract (arXiv)

We propose a novel pipeline for the generation of synthetic ultrasound images via Denoising Diffusion Probabilistic Models (DDPMs) guided by cardiac semantic label maps. We show that these synthetic images can serve as a viable substitute for real data in the training of deep-learning models for ultrasound image analysis tasks such as cardiac segmentation. To demonstrate the effectiveness of this approach, we generated synthetic 2D echocardiograms and trained a neural network for segmenting the left ventricle and left atrium. The performance of the network trained on exclusively synthetic images was evaluated on an unseen dataset of real images and yielded mean Dice scores of 88.6 ± 4.91 , 91.9 ± 4.22, 85.2 ± 4.83 % for left ventricular endocardium, epicardium and left atrial segmentation respectively. This represents a relative increase of 9.2, 3.3 and 13.9 % in Dice scores compared to the previous state-of-the-art. The proposed pipeline has potential for application to a wide range of other tasks across various medical imaging modalities.