mlsanityData to 7 Oct 2026

Vision-Language Synthetic Data Enhances Echocardiography Downstream Tasks

arXiv 2403.19880 ↗First posted 28 Mar 2024eess.IV cs.CVcited by 6

On the map: Synthetic data and self-improvement for LLMs → Self-improving MLLMs and synthetic data

Abstract (arXiv)

High-quality, large-scale data is essential for robust deep learning models in medical applications, particularly ultrasound image analysis. Diffusion models facilitate high-fidelity medical image generation, reducing the costs associated with acquiring and annotating new images. This paper utilizes recent vision-language models to produce diverse and realistic synthetic echocardiography image data, preserving key features of the original images guided by textual and semantic label maps. Specifically, we investigate three potential avenues: unconditional generation, generation guided by text, and a hybrid approach incorporating both textual and semantic supervision. We show that the rich contextual information present in the synthesized data potentially enhances the accuracy and interpretability of downstream tasks, such as echocardiography segmentation and classification with improved metrics and faster convergence. Our implementation with checkpoints, prompts, and the created synthetic dataset will be publicly available at hrefhttps://github.com/Pooria90/DiffEchoGitHub.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in Self-improving MLLMs and synthetic data, one of 13 directions in Synthetic data and self-improvement for LLMs. Builds on 23 of its 30 references that are in the map. First posted on arXiv 28 Mar 2024.

Builds on

23 of 30 references.

References · 23

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  6. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  7. 2018Demystifying MMD GANscited by 1,268
  8. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  9. 2023UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Modelscited by 441
  10. 2019Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiographycited by 243
  11. 2021Diffusion Models for Implicit Image Segmentation Ensemblescited by 198
  12. 2022Semantic Image Synthesis via Diffusion Modelscited by 131
11 more
  1. 2023Diffusion Models for Time Series Applications: A Surveycited by 72
  2. 2021GANs for Medical Image Synthesis: An Empirical Studycited by 64
  3. 2022Medical Diffusion: Denoising Diffusion Probabilistic Models for 3D Medical Image Generationcited by 54
  4. 2023Echo from noise: synthetic ultrasound image generation using diffusion models for real image segmentationcited by 33
  5. 2023Feature-Conditioned Cascaded Video Diffusion Models for Precise Echocardiogram Synthesiscited by 32
  6. 2022Generating Realistic Brain MRIs via a Conditional Diffusion Probabilistic Modelcited by 28
  7. 2023Unsupervised Anomaly Detection in Medical Images Using Masked Diffusion Modelcited by 25
  8. 2023Dehazing Ultrasound using Diffusion Modelscited by 17
  9. 2023Multi-Level Global Context Cross Consistency Model for Semi-Supervised Ultrasound Image Segmentation with Diffusion Modelcited by 8
  10. 2023Synthetic Boost: Leveraging Synthetic Data for Enhanced Vision-Language Segmentation in Echocardiographycited by 6
  11. 2023SA2-Net: Scale-aware Attention Network for Microscopic Image Segmentationcited by 6

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 4.

6 papers.

  1. 2025Flow Matching for Medical Image Synthesis: Bridging the Gap Between Speed and Qualitycited by 24
  2. 2024ECHOPulse: ECG controlled echocardio-grams video generationcited by 8
  3. 2025Toward Medical Deepfake Detection: A Comprehensive Dataset and Novel Methodcited by 6
  4. 2024Prompt2Perturb (P2P): Text-Guided Diffusion-Based Adversarial Attacks on Breast Ultrasound Imagescited by 4
  5. 2025Text-Printed Image: Bridging the Image-Text Modality Gap for Text-centric Training of Large Vision-Language Modelscited by 1
  6. 2025Recovering Diagnostic Value: Super-Resolution-Aided Echocardiographic Classification in Resource-Constrained Imagingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Efficient Semantic Diffusion Architectures for Model Training on Synthetic Echocardiograms
  2. 2024A Domain Translation Framework with an Adversarial Denoising Diffusion Model to Generate Synthetic Datasets of Echocardiography Images
  3. 2023Utilizing Synthetic Data for Medical Vision-Language Pre-training: Bypassing the Need for Real Images
  4. 2025EchoVLM: Measurement-Grounded Multimodal Learning for Echocardiography
  5. 2024Training-Free Condition Video Diffusion Models for single frame Spatial-Semantic Echocardiogram Synthesis
  6. 2023Echocardiography video synthesis from end diastolic semantic map via diffusion model
  7. 2024Can Medical Vision-Language Pre-training Succeed with Purely Synthetic Data?
  8. 2024EchoPrime: A Multi-Video View-Informed Vision-Language Model for Comprehensive Echocardiography Interpretation