Self-supervised pre-training with diffusion model for few-shot landmark detection in x-ray images

2024-07-25

arXiv.org

AI Summary

To address the severe scarcity of annotated data (only 50 images) hindering deep learning performance in X-ray landmark detection, this paper introduces, for the first time, Denoising Diffusion Probabilistic Models (DDPMs) into keypoint detection. We propose a DDPM-based self-supervised pre-training framework that requires no manual annotations: it learns robust representations via X-ray-specific data augmentation and physics-informed noise modeling, followed by lightweight fine-tuning for downstream detection. Evaluated on three major X-ray benchmarks, our method significantly outperforms both ImageNet-supervised pre-training and classical self-supervised baselines—including SimCLR and MoCo—achieving high-accuracy, robust keypoint localization under few-shot settings. This work establishes a novel paradigm for medical imaging analysis under extreme data scarcity.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Unsupervised & Self-Supervised Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Deep neural networks have been extensively applied in the medical domain for various tasks, including image classification, segmentation, and landmark detection. However, their application is often hindered by data scarcity, both in terms of available annotations and images. This study introduces a novel application of denoising diffusion probabilistic models (DDPMs) to the landmark detection task, specifically addressing the challenge of limited annotated data in x-ray imaging. Our key innovation lies in leveraging DDPMs for self-supervised pre-training in landmark detection, a previously unexplored approach in this domain. This method enables accurate landmark detection with minimal annotated training data (as few as 50 images), surpassing both ImageNet supervised pre-training and traditional self-supervised techniques across three popular x-ray benchmark datasets. To our knowledge, this work represents the first application of diffusion models for self-supervised learning in landmark detection, which may offer a valuable pre-training approach in few-shot regimes, for mitigating data scarcity.

Problem

• Addresses limited annotated data in x-ray landmark detection.
• Proposes self-supervised pre-training using diffusion models.
• Enables accurate detection with minimal training data.

Innovation

• Self-supervised pre-training with diffusion models
• Few-shot landmark detection in X-ray images
• Denoising diffusion probabilistic models (DDPMs)