Generative Diffusion Model Bootstraps Zero-shot Classification of Fetal Ultrasound Images In Underrepresented African Populations

TL;DR

This paper introduces FU-LoRA, a diffusion-based method that uses synthetic data to improve zero-shot classification of fetal ultrasound images in underrepresented African populations, addressing data scarcity challenges.

Contribution

The study presents a novel diffusion-based approach leveraging LoRA for generating synthetic ultrasound images, enhancing zero-shot classification in low-resource settings.

Findings

13.73% increase in zero-shot classification accuracy

Achieves 82.40% highest accuracy

Demonstrates effectiveness in low-resource environments

Abstract

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.