A Projector-Based Augmented Reality Navigation System for Computer-Assisted Surgery

3D human anatomy augmentation over a mannequin for the training of nursing skills

BACKGROUND

The in-depth understanding of human anatomy is the foundation for safety in nursing practice. Augmented reality is an emerging technology that can be used for integrative learning in nursing education.

OBJECTIVE

The study aimed to develop a human anatomy-based skill training system and pilot test its usability and feasibility.

METHODS

Twenty-seven nursing students participated in 3D anatomy-based skill training for intramuscular injection and Levin tube feeding using HoloLens 2. Various user interfaces including pictures, videos, animation graphics, and annotation boxes assisted users with a comprehensive understanding of the step-by-step procedures for these techniques. A one-group pre-post test was conducted to observe changes in skill performance competency, usability, and learning satisfaction.

RESULTS

After study participation, a statistically significant improvement in skill performance competency (p< 0.05) was observed. The usability results showed that students were satisfied with the usefulness of the program (9.55 ± 0.49) and scored highly for the intention to participate in other educational programs (9.62 ± 0.59). A high level of learning satisfaction was achieved (9.55 ± 0.49), with positive responses in fostering students' engagement and excitement in the application of cutting-edge technology.

CONCLUSION

The 3D anatomy-based nursing skill training demonstrated good potential to improve learning outcomes and facilitate engagement in self-directed practice. This can be integrated into undergraduate nursing education as an assistant teaching tool, contributing to the combination of knowledge and practice.

Research on augmented reality navigation of in vitro fenestration of stent-graft based on deep learning and virtual-real registration

OBJECTIVES

In vitro fenestration of stent-graft (IVFS) demands high-precision navigation methods to achieve optimal surgical outcomes. This study aims to propose an augmented reality (AR) navigation method for IVFS, which can provide in situ overlay display to locate fenestration positions.

METHODS

We propose an AR navigation method to assist doctors in performing IVFS. A deep learning-based aorta segmentation algorithm is used to achieve automatic and rapid aorta segmentation. The Vuforia-based virtual-real registration and marker recognition algorithm are integrated to ensure accurate in situ AR image.

RESULTS

The proposed method can provide three-dimensional in situ AR image, and the fiducial registration error after virtual-real registration is 2.070 mm. The aorta segmentation experiment obtains dice similarity coefficient of 91.12% and Hausdorff distance of 2.59, better than conventional algorithms before improvement.

CONCLUSIONS

The proposed method can intuitively and accurately locate fenestration positions, and therefore can assist doctors in performing IVFS.

Head-Mounted Projector for Manual Precision Tasks: Performance Assessment

The growing interest in augmented reality applications has led to an in-depth look at the performance of head-mounted displays and their testing in numerous domains. Other devices for augmenting the real world with virtual information are presented less frequently and usually focus on the description of the device rather than on its performance analysis. This is the case of projected augmented reality, which, compared to head-worn AR displays, offers the advantages of being simultaneously accessible by multiple users whilst preserving user awareness of the environment and feeling of immersion. This work provides a general evaluation of a custom-made head-mounted projector for the aid of precision manual tasks through an experimental protocol designed for investigating spatial and temporal registration and their combination. The results of the tests show that the accuracy (0.6±0.1 mm of spatial registration error) and motion-to-photon latency (113±12 ms) make the proposed solution suitable for guiding precision tasks.

Visualization, registration and tracking techniques for augmented reality guided surgery: a review

Augmented reality (AR) surgical navigation has developed rapidly in recent years. This paper reviews and analyzes the visualization, registration, and tracking techniques used in AR surgical navigation systems, as well as the application of these AR systems in different surgical fields. The types of AR visualization are divided into two categories ofin situvisualization and nonin situvisualization. The rendering contents of AR visualization are various. The registration methods include manual registration, point-based registration, surface registration, marker-based registration, and calibration-based registration. The tracking methods consist of self-localization, tracking with integrated cameras, external tracking, and hybrid tracking. Moreover, we describe the applications of AR in surgical fields. However, most AR applications were evaluated through model experiments and animal experiments, and there are relatively few clinical experiments, indicating that the current AR navigation methods are still in the early stage of development. Finally, we summarize the contributions and challenges of AR in the surgical fields, as well as the future development trend. Despite the fact that AR-guided surgery has not yet reached clinical maturity, we believe that if the current development trend continues, it will soon reveal its clinical utility.

Ultrasound Probe and Hand-Eye Calibrations for Robot-Assisted Needle Biopsy

In robot-assisted ultrasound-guided needle biopsy, it is essential to conduct calibration of the ultrasound probe and to perform hand-eye calibration of the robot in order to establish a link between intra-operatively acquired ultrasound images and robot-assisted needle insertion. Based on a high-precision optical tracking system, novel methods for ultrasound probe and robot hand-eye calibration are proposed. Specifically, we first fix optically trackable markers to the ultrasound probe and to the robot, respectively. We then design a five-wire phantom to calibrate the ultrasound probe. Finally, an effective method taking advantage of steady movement of the robot but without an additional calibration frame or the need to solve the AX=XB equation is proposed for hand-eye calibration. After calibrations, our system allows for in situ definition of target lesions and aiming trajectories from intra-operatively acquired ultrasound images in order to align the robot for precise needle biopsy. Comprehensive experiments were conducted to evaluate accuracy of different components of our system as well as the overall system accuracy. Experiment results demonstrated the efficacy of the proposed methods.

Calibration of a Catadioptric System and 3D Reconstruction Based on Surface Structured Light

In response to the problem of the small field of vision in 3D reconstruction, a 3D reconstruction system based on a catadioptric camera and projector was built by introducing a traditional camera to calibrate the catadioptric camera and projector system. Firstly, the intrinsic parameters of the camera and the traditional camera are calibrated separately. Then, the calibration of the projection system is accomplished by the traditional camera. Secondly, the coordinate system is introduced to calculate, respectively, the position of the catadioptric camera and projector in the coordinate system, and the position relationship between the coordinate systems of the catadioptric camera and the projector is obtained. Finally, the projector is used to project the structured light fringe to realize the reconstruction using a catadioptric camera. The experimental results show that the reconstruction error is 0.75 mm and the relative error is 0.0068 for a target of about 1 m. The calibration method and reconstruction method proposed in this paper can guarantee the ideal geometric reconstruction accuracy.

A Multi-User Collaborative AR System for Industrial Applications

Augmented reality (AR) applications are increasingly being used in various fields (e.g., design, maintenance, assembly, repair, training, etc.), as AR techniques help improve efficiency and reduce costs. Moreover, collaborative AR systems extend applicability, allowing for collaborative environments for different roles. In this paper, we propose a multi-user collaborative AR system (aptly called the “multi-user collaborative system”, or MUCSys); it is composed of three ends—MUCStudio, MUCView, and MUCServer. MUCStudio aims to construct industrial content with CAD model transformation, simplification, database update, marker design, scene editing, and exportation, while MUCView contains sensor data analysis, real-time localization, scene loading, annotation editing, and virtual–real rendering. MUCServer—as the bridge between MUCStudio and MUCView—presents collaborative and database services. To achieve this, we implemented the algorithms of local map establishment, global map registration, optimization, and network synchronization. The system provides AR services for diverse industrial processes via three collaborative ways—remote support, collaborative annotation, and editing. According to the system, applications for cutting machines were presented to improve efficiency and reduce costs, covering cutting head designs, production line sales, and cutting machine inspections. Finally, a user study was performed to prove the usage experience of the system.