Brain deformation modeling for neurosurgery reviewed: learning methods show promise but face clinical hurdles

This systematic review examines data-driven methods for brain deformation registration and modeling in image-guided neurosurgery, focusing on learning-based approaches developed between 2020 and 2025. Researchers analyzed 46 eligible studies from major databases, categorizing methodologies such as deep learning for image registration, direct deformation field regression, and hybrid models. While these methods show promise in accuracy and efficiency, challenges remain in robustness, standardized benchmarking, interpretability, and clinical readiness. AI

IMPACT Highlights advancements in AI for medical imaging and surgical guidance, while noting limitations for clinical adoption.

RANK_REASON The item is a systematic review paper published on arXiv. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• alphaXiv
• CatalyzeX Code Finder for Papers
• Connected Papers
• DagsHub
• Gotit.pub
• IEEE Xplore
• Litmaps
• PubMed
• scite Smart Citations
• Scopus
• Tiago Assis
• Web of Science

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →