Towards the target and not beyond: 2d vs 3d visual aids in mr-based neurosurgical simulation

2025-06-05

AI Summary

Neurosurgeons frequently perform three-dimensional anatomical reconstruction from two-dimensional (2D) medical images alone—without mixed reality (MR)—compromising procedural accuracy in critical interventions such as external ventricular drain (EVD) placement. To address this, we developed NeuroMix, a simulation-based training platform evaluating the transfer effect of three visual assistance paradigms—no assistance, 2D-only, and combined 2D+3D visualization—on task accuracy under MR-free conditions. Our study provides the first empirical evidence that trainees in the 2D+3D group achieved a 44% improvement in accuracy during unassisted testing (p < 0.01), without a significant increase in cognitive load as measured by the NASA-TLX. Furthermore, Technology Acceptance Model (TAM) surveys and phantom-based performance assessments confirmed high usability, user acceptance, and functional equivalence to conventional methods. These findings establish a novel, low-cost, high-transfer paradigm for neurosurgical visualization training.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Neuro-Symbolic Learning
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Web Mining and Content Analysis: Web data generation and simulation
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Neurosurgery increasingly uses Mixed Reality (MR) technologies for intraoperative assistance. The greatest challenge in this area is mentally reconstructing complex 3D anatomical structures from 2D slices with millimetric precision, which is required in procedures like External Ventricular Drain (EVD) placement. MR technologies have shown great potential in improving surgical performance, however, their limited availability in clinical settings underscores the need for training systems that foster skill retention in unaided conditions. In this paper, we introduce NeuroMix, an MR-based simulator for EVD placement. We conduct a study with 48 participants to assess the impact of 2D and 3D visual aids on usability, cognitive load, technology acceptance, and procedure precision and execution time. Three training modalities are compared: one without visual aids, one with 2D aids only, and one combining both 2D and 3D aids. The training phase takes place entirely on digital objects, followed by a freehand EVD placement testing phase performed with a physical catherer and a physical phantom without MR aids. We then compare the participants performance with that of a control group that does not undergo training. Our findings show that participants trained with both 2D and 3D aids achieve a 44% improvement in precision during unaided testing compared to the control group, substantially higher than the improvement observed in the other groups. All three training modalities receive high usability and technology acceptance ratings, with significant equivalence across groups. The combination of 2D and 3D visual aids does not significantly increase cognitive workload, though it leads to longer operation times during freehand testing compared to the control group.

Problem

• Comparing 2D and 3D visual aids in MR-based neurosurgical simulation.
• Assessing impact of visual aids on precision and cognitive load in EVD placement.
• Evaluating skill retention in unaided conditions after MR-based training.

Innovation

• MR-based simulator for neurosurgical training
• Combines 2D and 3D visual aids
• Improves precision in unaided conditions