A Mixed Reality System for Robust Manikin Localization in Childbirth Training

Area of Science:

• Medical Education Technology
• Surgical Simulation
• Mixed Reality Applications

Background:

• Clinical training for vaginal births faces limitations due to reduced rotations and patient availability.
• There is a need for efficient, supervised training methods to enhance medical students' practical skills.

Purpose of the Study:

• To develop and evaluate a mixed reality (MR) system for childbirth training.
• To compare the effectiveness of MR training against virtual reality (VR) training for medical students.

Main Methods:

• Developed an MR system integrating virtual guidance with a tactile manikin, using head-mounted displays (HMDs) and external cameras.
• Implemented a spatial calibration and localization pipeline for accurate registration of virtual elements with the physical manikin.
• Conducted a user study with 83 medical students, comparing MR and VR training, with performance assessed by senior obstetricians.

Main Results:

• The MR system achieved accurate and stable manikin localization on a standalone headset.
• MR training resulted in significantly higher scores in delivery, post-delivery, and overall task performance compared to VR training.
• Trainees consistently preferred the MR training experience over VR training.

Conclusions:

• The developed MR system offers a viable solution for effective and independent childbirth training.
• MR-based simulation shows superior performance and user satisfaction compared to VR for obstetric procedures.
• The system holds potential for expanding manikin-based procedural training across various healthcare education settings.