Artifact Reduction in Undersampled 3D Cone-Beam CTs Using a Hybrid 2D-3D CNN Framework

2025-11-01

2025 IEEE Nuclear Science Symposium (NSS), Medical Imaging Conference (MIC) and Room Temperature Semiconductor Detector Conference (RTSD)

AI Summary

This work addresses the severe artifacts in undersampled 3D cone-beam CT images, which arise from reduced scan time and lower radiation dose, thereby compromising image quality and diagnostic reliability. To tackle this challenge, the authors propose a hybrid 2D–3D convolutional neural network architecture that first employs a 2D U-Net to efficiently extract features from individual axial slices and subsequently leverages a 3D decoder to model volumetric contextual information, ensuring consistent reconstruction across the entire volume. By combining the computational efficiency of 2D networks with the spatial coherence of 3D modeling, the method significantly enhances inter-slice consistency in coronal and sagittal views while improving overall visual quality, all at a relatively low computational cost. This approach offers an efficient and robust solution for artifact correction in clinical CT post-processing.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Constraint Satisfaction and Optimization: Constraint Satisfaction

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Undersampled CT volumes minimize acquisition time and radiation exposure but introduce artifacts degrading image quality and diagnostic utility. Reducing these artifacts is critical for high-quality imaging. We propose a computationally efficient hybrid deep-learning framework that combines the strengths of 2D and 3D models. First, a 2D U-Net operates on individual slices of undersampled CT volumes to extract feature maps. These slice-wise feature maps are then stacked across the volume and used as input to a 3D decoder, which utilizes contextual information across slices to predict an artifact-free 3D CT volume. The proposed two-stage approach balances the computational efficiency of 2D processing with the volumetric consistency provided by 3D modeling. The results show substantial improvements in inter-slice consistency in coronal and sagittal direction with low computational overhead. This hybrid framework presents a robust and efficient solution for high-quality 3D CT image post-processing.

Problem

• Artifact Reduction
• Undersampled CT
• 3D Cone-Beam CT
• Image Quality
• Diagnostic Utility

Innovation

• hybrid 2D-3D CNN
• artifact reduction
• undersampled CT
• inter-slice consistency
• cone-beam CT