ActiveReg: Information-Driven Active Regional Probing for Partial-to-Full Bone Registration

Key points

• In a common workflow, the surgeon needs to identify and probe a number of prescribed locations on the exposed bone surface to obtain data points for registration, which can be difficult and time-consuming under limited surgical exposure.1
• We present ActiveReg, a closed-loop framework that recommends probing regions rather than individual points, allowing flexibility in the exact contact location.1
• Simulations across four anatomical scenarios demonstrated that ActiveReg can achieve competitive accuracy compared with baseline registration methods while using substantially fewer acquired points.1
• Real phantom experiments with optical and electromagnetic tracking demonstrated comparable mean target registration error to the Gradient-SDF framework, using only 24-28 acquired points instead of 771-1263.1

Sources (1)

• [1]ActiveReg: Information-Driven Active Regional Probing for Partial-to-Full Bone Registration
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 11:36 PM

  Accurate bone registration is essential for orthopedic surgical navigation and robotic assistance.

  In a common workflow, the surgeon needs to identify and probe a number of prescribed locations on the exposed bone surface to obtain data points for registration, which can be difficult and time-consuming under limited surgical exposure.

Extractive summary: sentences quoted from the sources.