Efficient Semantic Diffusion Architectures for Model Training on Synthetic Echocardiograms
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910624238272512 |
|---|---|
| author | Stojanovski, David da Silva, Mariana Lamata, Pablo Beqiri, Arian Gomez, Alberto |
| author_facet | Stojanovski, David da Silva, Mariana Lamata, Pablo Beqiri, Arian Gomez, Alberto |
| contents | We investigate the utility of diffusion generative models to efficiently synthesise datasets that effectively train deep learning models for image analysis. Specifically, we propose novel $Γ$-distribution Latent Denoising Diffusion Models (LDMs) designed to generate semantically guided synthetic cardiac ultrasound images with improved computational efficiency. We also investigate the potential of using these synthetic images as a replacement for real data in training deep networks for left-ventricular segmentation and binary echocardiogram view classification tasks. We compared six diffusion models in terms of the computational cost of generating synthetic 2D echo data, the visual realism of the resulting images, and the performance, on real data, of downstream tasks (segmentation and classification) trained using these synthetic echoes. We compare various diffusion strategies and ODE solvers for their impact on segmentation and classification performance. The results show that our propose architectures significantly reduce computational costs while maintaining or improving downstream task performance compared to state-of-the-art methods. While other diffusion models generated more realistic-looking echo images at higher computational cost, our research suggests that for model training, visual realism is not necessarily related to model performance, and considerable compute costs can be saved by using more efficient models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_19371 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Efficient Semantic Diffusion Architectures for Model Training on Synthetic Echocardiograms Stojanovski, David da Silva, Mariana Lamata, Pablo Beqiri, Arian Gomez, Alberto Image and Video Processing Computer Vision and Pattern Recognition We investigate the utility of diffusion generative models to efficiently synthesise datasets that effectively train deep learning models for image analysis. Specifically, we propose novel $Γ$-distribution Latent Denoising Diffusion Models (LDMs) designed to generate semantically guided synthetic cardiac ultrasound images with improved computational efficiency. We also investigate the potential of using these synthetic images as a replacement for real data in training deep networks for left-ventricular segmentation and binary echocardiogram view classification tasks. We compared six diffusion models in terms of the computational cost of generating synthetic 2D echo data, the visual realism of the resulting images, and the performance, on real data, of downstream tasks (segmentation and classification) trained using these synthetic echoes. We compare various diffusion strategies and ODE solvers for their impact on segmentation and classification performance. The results show that our propose architectures significantly reduce computational costs while maintaining or improving downstream task performance compared to state-of-the-art methods. While other diffusion models generated more realistic-looking echo images at higher computational cost, our research suggests that for model training, visual realism is not necessarily related to model performance, and considerable compute costs can be saved by using more efficient models. |
| title | Efficient Semantic Diffusion Architectures for Model Training on Synthetic Echocardiograms |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.19371 |