A Method for Automatic Feature Points Extraction of Pelvic Surface Based on PointMLP_RegNet DOI Creative Commons
Wei Kou, Rui Zhou, Hongmiao Zhang

et al.

CAAI Transactions on Intelligence Technology, Journal Year: 2025, Volume and Issue: unknown

Published: March 14, 2025

ABSTRACT The success of robot‐assisted pelvic fracture reduction surgery heavily relies on the accuracy 3D/3D feature‐based registration. This process involves extracting anatomical feature points from pre‐operative 3D images which can be challenging because complex and variable structure pelvis. PointMLP_RegNet, a modified PointMLP, was introduced to address this issue. It retains extraction module PointMLP but replaces classification layer with regression predict coordinates instead conducting regular classification. A flowchart for an automatic method presented, series experiments conducted clinical dataset confirm effectiveness method. PointMLP_RegNet extracted more accurately, 8 out 10 showing less than 4 mm errors remaining two 5 mm. Compared PointNet++ PointNet, it exhibited higher accuracy, robustness space efficiency. proposed will improve extraction, enhance intra‐operative registration precision facilitate widespread application reduction.

Language: Английский

A Method for Automatic Feature Points Extraction of Pelvic Surface Based on PointMLP_RegNet DOI Creative Commons
Wei Kou, Rui Zhou, Hongmiao Zhang

et al.

CAAI Transactions on Intelligence Technology, Journal Year: 2025, Volume and Issue: unknown

Published: March 14, 2025

ABSTRACT The success of robot‐assisted pelvic fracture reduction surgery heavily relies on the accuracy 3D/3D feature‐based registration. This process involves extracting anatomical feature points from pre‐operative 3D images which can be challenging because complex and variable structure pelvis. PointMLP_RegNet, a modified PointMLP, was introduced to address this issue. It retains extraction module PointMLP but replaces classification layer with regression predict coordinates instead conducting regular classification. A flowchart for an automatic method presented, series experiments conducted clinical dataset confirm effectiveness method. PointMLP_RegNet extracted more accurately, 8 out 10 showing less than 4 mm errors remaining two 5 mm. Compared PointNet++ PointNet, it exhibited higher accuracy, robustness space efficiency. proposed will improve extraction, enhance intra‐operative registration precision facilitate widespread application reduction.

Language: Английский

Citations

0