Confident Pseudo-labeled Diffusion Augmentation for Canine Cardiomegaly Detection

TL;DR

This paper introduces a novel diffusion-based data augmentation and pseudo-labeling approach to improve the accuracy of canine cardiomegaly detection from X-ray images, addressing data scarcity and annotation challenges.

Contribution

The proposed CDA model combines diffusion-generated synthetic images with pseudo-labeling to enhance detection accuracy beyond existing methods.

Findings

Achieves state-of-the-art accuracy in canine cardiomegaly detection

Effectively expands training data with synthetic images and high-confidence labels

Outperforms traditional detection models in diverse imaging conditions

Abstract

Canine cardiomegaly, marked by an enlarged heart, poses serious health risks if undetected, requiring accurate diagnostic methods. Current detection models often rely on small, poorly annotated datasets and struggle to generalize across diverse imaging conditions, limiting their real-world applicability. To address these issues, we propose a Confident Pseudo-labeled Diffusion Augmentation (CDA) model for identifying canine cardiomegaly. Our approach addresses the challenge of limited high-quality training data by employing diffusion models to generate synthetic X-ray images and annotate Vertebral Heart Score key points, thereby expanding the dataset. We also employ a pseudo-labeling strategy with Monte Carlo Dropout to select high-confidence labels, refine the synthetic dataset, and improve accuracy. Iteratively incorporating these labels enhances the model's performance, overcoming the limitations of existing approaches. Experimental results show that the CDA model outperforms traditional methods, achieving state-of-the-art accuracy in canine cardiomegaly detection. The code implementation is available at https://github.com/Shira7z/CDA.