New method infers hidden skeletal landmarks from external soft-tissue geometry

Researchers have developed a novel method for inferring hidden skeletal landmarks from external soft-tissue geometry using computed tomography (CT) scans. This "Surface-to-Skeleton 3D Cephalometry" approach aims to estimate internal skeletal points from visible external surfaces, addressing a gap in current 3D facial landmark localization techniques. The study utilized CT scans from two hospitals, constructing a protocol that pairs external soft-tissue point clouds with 21 skeletal landmarks. An integrated hierarchical point-cloud model achieved a mean radial error of 2.97 mm for skeletal landmarks and 3.03 mm for deep or invisible landmarks in a held-out patient group, demonstrating the feasibility of this inference. AI

IMPACT This research could advance medical imaging analysis by enabling more accurate skeletal landmark identification from external scans.

RANK_REASON The cluster contains a research paper detailing a new method for inferring skeletal landmarks from soft-tissue geometry. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• alphaXiv
• CatalyzeX Code Finder for Papers
• computed tomography
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• Influence Flower
• point cloud
• ScienceCast
• soft-tissue geometry
• Surface-to-Skeleton 3D Cephalometry

• paper
• other

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