AI-Based 3D Radiological Image Reconstruction: A Systematic Review
A systematic review published on arXiv surveys AI-based 3D reconstruction algorithms in radiological imaging. The study organizes algorithms into four representation families: discrete grid, explicit basis expansion, explicit primitive, and implicit neural representations. It highlights radiance field methods as a specialized subtype of implicit neural representations. The review aims to clarify relationships among these forms and improve reconstruction accuracy while reducing acquisition and processing time, ultimately minimizing patient radiation exposure.
Key facts
- The review is published on arXiv with ID 2504.11349.
- It surveys state-of-the-art AI-based 3D reconstruction algorithms in radiological imaging.
- Algorithms are organized into four representation families: discrete grid, explicit basis expansion, explicit primitive, and implicit neural representations.
- Radiance field methods are highlighted as a specialized subtype of implicit neural representations.
- The review clarifies relationships among representation forms.
- AI aims to improve reconstruction accuracy while reducing acquisition and processing time.
- Reduced acquisition and processing time minimizes patient radiation exposure and discomfort.
- The review focuses on 3D image reconstruction in radiological imaging.
Entities
Institutions
- arXiv