mlsanityData to 14 Oct 2026

Synthetic Boost: Leveraging Synthetic Data for Enhanced Vision-Language Segmentation in Echocardiography

arXiv 2309.12829 ↗First posted 22 Sep 2023cs.CV cs.AI cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Accurate segmentation is essential for echocardiography-based assessment of cardiovascular diseases (CVDs). However, the variability among sonographers and the inherent challenges of ultrasound images hinder precise segmentation. By leveraging the joint representation of image and text modalities, Vision-Language Segmentation Models (VLSMs) can incorporate rich contextual information, potentially aiding in accurate and explainable segmentation. However, the lack of readily available data in echocardiography hampers the training of VLSMs. In this study, we explore using synthetic datasets from Semantic Diffusion Models (SDMs) to enhance VLSMs for echocardiography segmentation. We evaluate results for two popular VLSMs (CLIPSeg and CRIS) using seven different kinds of language prompts derived from several attributes, automatically extracted from echocardiography images, segmentation masks, and their metadata. Our results show improved metrics and faster convergence when pretraining VLSMs on SDM-generated synthetic images before finetuning on real images. The code, configs, and prompts are available at https://github.com/naamiinepal/synthetic-boost.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 21 of its 30 references that are in the map. First posted on arXiv 22 Sep 2023.

Builds on

21 of 30 references.

References · 21

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  6. 2021UNETR: Transformers for 3D Medical Image Segmentationcited by 959
  7. 2022OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Frameworkcited by 745
  8. 2021FLAVA: A Foundational Language And Vision Alignment Modelcited by 649
  9. 2021LiT: Zero-Shot Transfer with Locked-image text Tuningcited by 577
  10. 2021DenseCLIP: Language-Guided Dense Prediction with Context-Aware Promptingcited by 532
  11. 2021Image Segmentation Using Text and Image Promptscited by 512
  12. 2021Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigmcited by 405
9 more
  1. 2021CRIS: CLIP-Driven Referring Image Segmentationcited by 353
  2. 2020Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformerscited by 288
  3. 2019Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiographycited by 244
  4. 2022Semantic Image Synthesis via Diffusion Modelscited by 132
  5. 2020PhraseCut: Language-based Image Segmentation in the Wildcited by 116
  6. 2021CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIPcited by 89
  7. 2022Medical Image Understanding with Pretrained Vision Language Models: A Comprehensive Studycited by 66
  8. 2023Echo from noise: synthetic ultrasound image generation using diffusion models for real image segmentationcited by 34
  9. 2023Exploring Transfer Learning in Medical Image Segmentation using Vision-Language Modelscited by 28

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 3; 2025: 2.

6 papers.

  1. 2024A Comprehensive Survey of Foundation Models in Medicinecited by 56
  2. 2023CLIP in Medical Imaging: A Surveycited by 40
  3. 2024VLSM-Adapter: Finetuning Vision-Language Segmentation Efficiently with Lightweight Blockscited by 11
  4. 2024Vision-Language Synthetic Data Enhances Echocardiography Downstream Taskscited by 6
  5. 2025Adversarial Robustness Analysis of Vision-Language Models in Medical Image Segmentationcited by 2
  6. 2025TAGS: 3D Tumor-Adaptive Guidance for SAMcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Efficient Semantic Diffusion Architectures for Model Training on Synthetic Echocardiograms
  2. 2025EchoVLM: Measurement-Grounded Multimodal Learning for Echocardiography
  3. 2023Utilizing Synthetic Data for Medical Vision-Language Pre-training: Bypassing the Need for Real Images
  4. 2024EchoDFKD: Data-Free Knowledge Distillation for Cardiac Ultrasound Segmentation using Synthetic Data
  5. 2024Training-Free Condition Video Diffusion Models for single frame Spatial-Semantic Echocardiogram Synthesis
  6. 2025VLSM-Ensemble: Ensembling CLIP-based Vision-Language Models for Enhanced Medical Image Segmentation
  7. 2024TuneVLSeg: Prompt Tuning Benchmark for Vision-Language Segmentation Models
  8. 2024Can Medical Vision-Language Pre-training Succeed with Purely Synthetic Data?