Pre-trained Under Noise: A Framework for Robust Bone Fracture Detection in Medical Imaging

2025-07-13

AI Summary

This study addresses the robustness of bone fracture detection in low-quality X-ray imaging conditions. We systematically evaluate the performance degradation of three pre-trained architectures—ResNet50, VGG16, and EfficientNetV2—under controlled noise-induced image degradation, simulating varying clinical device quality. We propose a methodological framework integrating transfer learning with gradient-controllable noise augmentation to quantitatively assess model generalization under realistic imaging impairments. Experimental results reveal a nonlinear decline in diagnostic accuracy with increasing noise intensity, and significant architectural differences in robustness: EfficientNetV2 consistently achieves superior performance at low signal-to-noise ratios. These findings provide empirically grounded, reproducible evaluation protocols and evidence-based guidance for clinical AI model selection and deployment in resource-constrained settings.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Adversarial Learning & Robustness
• Natural Language Processing: Safety and Robustness

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Medical Imagings are considered one of the crucial diagnostic tools for different bones-related diseases, especially bones fractures. This paper investigates the robustness of pre-trained deep learning models for classifying bone fractures in X-ray images and seeks to address global healthcare disparity through the lens of technology. Three deep learning models have been tested under varying simulated equipment quality conditions. ResNet50, VGG16 and EfficientNetv2 are the three pre-trained architectures which are compared. These models were used to perform bone fracture classification as images were progressively degraded using noise. This paper specifically empirically studies how the noise can affect the bone fractures detection and how the pre-trained models performance can be changes due to the noise that affect the quality of the X-ray images. This paper aims to help replicate real world challenges experienced by medical imaging technicians across the world. Thus, this paper establishes a methodological framework for assessing AI model degradation using transfer learning and controlled noise augmentation. The findings provide practical insight into how robust and generalizable different pre-trained deep learning powered computer vision models can be when used in different contexts.

Problem

• Assessing robustness of pre-trained models for bone fracture detection
• Studying noise impact on X-ray image classification accuracy
• Addressing healthcare disparity via transfer learning in medical imaging

Innovation

• Pre-trained deep learning models for fracture detection
• Controlled noise augmentation to simulate real-world conditions
• Transfer learning framework for model robustness assessment