AI advances medical imaging with new 3D radiological reconstruction review

This systematic review categorizes AI-based 3D radiological image reconstruction methods into four primary representation paradigms: discrete grids, explicit basis expansions, explicit primitives, and implicit neural representations. The paper highlights the relationships between these forms, identifying radiance fields as a subset of implicit neural representations. It also outlines common evaluation metrics, benchmark datasets, and discusses current challenges and future research avenues in the field. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Provides a structured overview of AI techniques for medical imaging reconstruction, aiding researchers in understanding current methods and future directions.

RANK_REASON This is a systematic review paper published on arXiv.

Read on arXiv cs.CV →

• arXiv
• Yuezhe Yang
• radiance field

• paper
• other