Vision-Language Synthetic Data Enhances Echocardiography Downstream Tasks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911818896637952 |
|---|---|
| author | Ashrafian, Pooria Yazdani, Milad Heidari, Moein Shahriari, Dena Hacihaliloglu, Ilker |
| author_facet | Ashrafian, Pooria Yazdani, Milad Heidari, Moein Shahriari, Dena Hacihaliloglu, Ilker |
| contents | 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 \href{https://github.com/Pooria90/DiffEcho}{GitHub}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_19880 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Vision-Language Synthetic Data Enhances Echocardiography Downstream Tasks Ashrafian, Pooria Yazdani, Milad Heidari, Moein Shahriari, Dena Hacihaliloglu, Ilker Image and Video Processing Computer Vision and Pattern Recognition 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 \href{https://github.com/Pooria90/DiffEcho}{GitHub}. |
| title | Vision-Language Synthetic Data Enhances Echocardiography Downstream Tasks |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.19880 |