Confident Pseudo-labeled Diffusion Augmentation for Canine Cardiomegaly Detection

2025-01-13

AI Summary

Accurate detection of cardiac enlargement in canine radiographs is hindered by scarce high-quality annotations and poor cross-device generalizability. Method: We propose an iterative semi-supervised learning framework integrating diffusion models with uncertainty-driven pseudo-labeling. To our knowledge, this is the first work to employ diffusion models for controllable synthesis of veterinary radiographs and Vertebral Heart Score (VHS) keypoint annotations. We further introduce a confidence-thresholding mechanism—guided by Monte Carlo Dropout-based uncertainty estimation—to self-refine synthetically generated data. Results: Evaluated on a multi-center canine radiography dataset, our method significantly outperforms existing supervised and semi-supervised approaches, achieving state-of-the-art performance. It effectively alleviates robustness bottlenecks under low-data regimes. The source code is publicly available.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Canine Heart Enlargement
• Low-Quality Images
• Detection Accuracy

Innovation

• Confident Pseudo Labeling
• Synthetic X-ray Generation
• Cardiomegaly Detection in Dogs