Generative Diffusion Model Bootstraps Zero-shot Classification of Fetal Ultrasound Images In Underrepresented African Populations
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916338871566336 |
|---|---|
| author | Wang, Fangyijie Whelan, Kevin Silvestre, Guénolé Curran, Kathleen M. |
| author_facet | Wang, Fangyijie Whelan, Kevin Silvestre, Guénolé Curran, Kathleen M. |
| contents | Developing robust deep learning models for fetal ultrasound image analysis requires comprehensive, high-quality datasets to effectively learn informative data representations within the domain. However, the scarcity of labelled ultrasound images poses substantial challenges, especially in low-resource settings. To tackle this challenge, we leverage synthetic data to enhance the generalizability of deep learning models. This study proposes a diffusion-based method, Fetal Ultrasound LoRA (FU-LoRA), which involves fine-tuning latent diffusion models using the LoRA technique to generate synthetic fetal ultrasound images. These synthetic images are integrated into a hybrid dataset that combines real-world and synthetic images to improve the performance of zero-shot classifiers in low-resource settings. Our experimental results on fetal ultrasound images from African cohorts demonstrate that FU-LoRA outperforms the baseline method by a 13.73% increase in zero-shot classification accuracy. Furthermore, FU-LoRA achieves the highest accuracy of 82.40%, the highest F-score of 86.54%, and the highest AUC of 89.78%. It demonstrates that the FU-LoRA method is effective in the zero-shot classification of fetal ultrasound images in low-resource settings. Our code and data are publicly accessible on https://github.com/13204942/FU-LoRA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_20072 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Generative Diffusion Model Bootstraps Zero-shot Classification of Fetal Ultrasound Images In Underrepresented African Populations Wang, Fangyijie Whelan, Kevin Silvestre, Guénolé Curran, Kathleen M. Image and Video Processing Developing robust deep learning models for fetal ultrasound image analysis requires comprehensive, high-quality datasets to effectively learn informative data representations within the domain. However, the scarcity of labelled ultrasound images poses substantial challenges, especially in low-resource settings. To tackle this challenge, we leverage synthetic data to enhance the generalizability of deep learning models. This study proposes a diffusion-based method, Fetal Ultrasound LoRA (FU-LoRA), which involves fine-tuning latent diffusion models using the LoRA technique to generate synthetic fetal ultrasound images. These synthetic images are integrated into a hybrid dataset that combines real-world and synthetic images to improve the performance of zero-shot classifiers in low-resource settings. Our experimental results on fetal ultrasound images from African cohorts demonstrate that FU-LoRA outperforms the baseline method by a 13.73% increase in zero-shot classification accuracy. Furthermore, FU-LoRA achieves the highest accuracy of 82.40%, the highest F-score of 86.54%, and the highest AUC of 89.78%. It demonstrates that the FU-LoRA method is effective in the zero-shot classification of fetal ultrasound images in low-resource settings. Our code and data are publicly accessible on https://github.com/13204942/FU-LoRA. |
| title | Generative Diffusion Model Bootstraps Zero-shot Classification of Fetal Ultrasound Images In Underrepresented African Populations |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2407.20072 |