# A Data Augmentation Pipeline to Generate Synthetic Labeled Datasets of 3D Echocardiography Images using a GAN

arXiv: https://arxiv.org/abs/2403.05384 · HTML: https://mlsanity.com/paper/2403.05384/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 45 references that are in the map.
- First posted on arXiv 8 Mar 2024.

## Builds on (most cited first, 15 of 15)

- [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)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [SynSeg-Net: Synthetic Segmentation Without Target Modality Ground Truth](https://mlsanity.com/paper/1810.06498/) (2018)
- [Ensembling with Deep Generative Views](https://mlsanity.com/paper/2104.14551/) (2021)
- [How to Fool Radiologists with Generative Adversarial Networks? A Visual Turing Test for Lung Cancer Diagnosis](https://mlsanity.com/paper/1710.09762/) (2017)
- [Vox2Vox: 3D-GAN for Brain Tumour Segmentation](https://mlsanity.com/paper/2003.13653/) (2020)
- [Freehand Ultrasound Image Simulation with Spatially-Conditioned Generative Adversarial Networks](https://mlsanity.com/paper/1707.05392/) (2017)
- [Memory-efficient GAN-based Domain Translation of High Resolution 3D Medical Images](https://mlsanity.com/paper/2010.03396/) (2020)
- [XCAT-GAN for Synthesizing 3D Consistent Labeled Cardiac MR Images on Anatomically Variable XCAT Phantoms](https://mlsanity.com/paper/2007.13408/) (2020)
- [4D Semantic Cardiac Magnetic Resonance Image Synthesis on XCAT Anatomical Model](https://mlsanity.com/paper/2002.07089/) (2020)
- [Optimized Automated Cardiac MR Scar Quantification with GAN-Based Data Augmentation](https://mlsanity.com/paper/2109.12940/) (2021)

## Built on by (most cited first, 6 of 6)

- [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)
- [EchoNet-Synthetic: Privacy-preserving Video Generation for Safe Medical Data Sharing](https://mlsanity.com/paper/2406.00808/) (2024)
- [EchoFlow: A Foundation Model for Cardiac Ultrasound Image and Video Generation](https://mlsanity.com/paper/2503.22357/) (2025)
- [Generative augmentations for improved cardiac ultrasound segmentation using diffusion models](https://mlsanity.com/paper/2502.20100/) (2025)
- [Evaluating the plausibility of synthetic images for improving automated endoscopic stone recognition](https://mlsanity.com/paper/2409.13409/) (2024)

## Abstract (arXiv)

Due to privacy issues and limited amount of publicly available labeled datasets in the domain of medical imaging, we propose an image generation pipeline to synthesize 3D echocardiographic images with corresponding ground truth labels, to alleviate the need for data collection and for laborious and error-prone human labeling of images for subsequent Deep Learning (DL) tasks. The proposed method utilizes detailed anatomical segmentations of the heart as ground truth label sources. This initial dataset is combined with a second dataset made up of real 3D echocardiographic images to train a Generative Adversarial Network (GAN) to synthesize realistic 3D cardiovascular Ultrasound images paired with ground truth labels. To generate the synthetic 3D dataset, the trained GAN uses high resolution anatomical models from Computed Tomography (CT) as input. A qualitative analysis of the synthesized images showed that the main structures of the heart are well delineated and closely follow the labels obtained from the anatomical models. To assess the usability of these synthetic images for DL tasks, segmentation algorithms were trained to delineate the left ventricle, left atrium, and myocardium. A quantitative analysis of the 3D segmentations given by the models trained with the synthetic images indicated the potential use of this GAN approach to generate 3D synthetic data, use the data to train DL models for different clinical tasks, and therefore tackle the problem of scarcity of 3D labeled echocardiography datasets.