Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
Objective: With the advancement of 3D modeling techniques and visualization devices, augmented reality (AR)-based navigation (AR navigation) is being developed actively. The authors developed a pilot model of their newly developed inside-out tracking AR navigation system.
Methods: The inside-out AR navigation technique was developed based on the visual inertial odometry (VIO) algorithm. The Quick Response (QR) marker was created and used for the image feature-detection algorithm. Inside-out AR navigation works through the steps of visualization device recognition, marker recognition, AR implementation, and registration within the running environment. A virtual 3D patient model for AR rendering and a 3D-printed patient model for validating registration accuracy were created. Inside-out tracking was used for the registration. The registration accuracy was validated by using intuitive, visualization, and quantitative methods for identifying coordinates by matching errors. Fine-tuning and opacity-adjustment functions were developed.
Results: ARKit-based inside-out AR navigation was developed. The fiducial marker of the AR model and those of the 3D-printed patient model were correctly overlapped at all locations without errors. The tumor and anatomical structures of AR navigation and the tumors and structures placed in the intracranial space of the 3D-printed patient model precisely overlapped. The registration accuracy was quantified using coordinates, and the average moving errors of the x-axis and y-axis were 0.52 ± 0.35 and 0.05 ± 0.16 mm, respectively. The gradients from the x-axis and y-axis were 0.35° and 1.02°, respectively. Application of the fine-tuning and opacity-adjustment functions was proven by the videos.
Conclusions: The authors developed a novel inside-out tracking-based AR navigation system and validated its registration accuracy. This technical system could be applied in the novel navigation system for patient-specific neurosurgery.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.3171/2021.5.FOCUS21184 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Development and validation of a machine learning model for predicting immune checkpoint inhibitor efficacy in advanced gastric cancer using dynamic changes in peripheral blood clinlabomics data: a retrospective multicenter cohort study.
Gastric Cancer
September 2025
Department of Medical Oncology, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Jinan, Shandong, China.
Background: Immune checkpoint inhibitors (ICIs) play a pivotal role in the treatment of advanced gastric cancer (GC). However, the biomarkers used to predict ICI efficacy are limited due to their reliance on single or static tumor characteristics. This study aims to develop a machine learning (ML) model that incorporates dynamic changes in clinlabomics data to optimize the predictive accuracy of ICI efficacy.
View Article and Find Full Text PDFDynamic data balancing strategy-based Xception-dual-channel LSTM model for laparoscopic cholecystectomy phase recognition.
Int J Comput Assist Radiol Surg
September 2025
The First Affiliated Hospital of University of Science and Technology of China, Hefei, Anhui, China.
Purpose: To enhance the temporal feature learning capability of the laparoscopic cholecystectomy phase recognition model and address the class imbalance issue in the training data, this paper proposes an Xception-dual-channel LSTM fusion model based on a dynamic data balancing strategy.
Methods: The model dynamically adjusts the undersampling rate for each surgical phase, extracting short video clips from the original data as training samples to balance the data distribution and mitigate biased learning. The Xception model, utilizing depthwise separable convolutions, extracts fundamental visual features frame by frame, which are then passed to a dual-channel LSTM network.
Artificial Intelligence Automation of Echocardiographic Measurements.
J Am Coll Cardiol
August 2025
Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, California, USA; Department of Cardiology, Kaiser Permanente Santa Clara Medical Center, Santa Clara, California, USA. Electronic address:
Background: Accurate measurement of echocardiographic parameters is crucial for the diagnosis of cardiovascular disease and tracking of change over time; however, manual assessment requires time-consuming effort and can be imprecise. Artificial intelligence has the potential to reduce clinician burden by automating the time-intensive task of comprehensive measurement of echocardiographic parameters.
Objectives: The purpose of this study was to develop and validate open-sourced deep learning semantic segmentation models for the automated measurement of 18 anatomic and Doppler measurements in echocardiography.
Patient-Specific 3D-Printed Drill Guides for an Ovine Osteochondral Allograft Transplantation Model.
J Orthop Res
September 2025
Faulty of Applied Science and Engineering, University of Toronto, Toronto, Canada.
Proper alignment between donor and recipient cartilage in osteochondral allograft transplantation supports tissue integration and the formation of a stable articulating surface. This study evaluated the use of patient-specific 3D-printed drill guides to improve alignment in an ovine model of osteochondral allograft transplantation when used in place of a free-hand drilling technique. Fourteen female Arcott sheep underwent bilateral osteochondral allograft transplantation.
View Article and Find Full Text PDFMachine Learning Model for Selection of Cementless Total Knee Arthroplasty Candidates Utilizing Patient and Radiographic Parameters.
J Orthop Res
September 2025
Department of Mechanical Engineering, University of Louisville, Louisville, Kentucky, USA.
The use of cementless total knee arthroplasty (TKA) has significantly increased over the past decade. However, there is no objective criteria or consensus on parameters for patient selection for cementless TKA. The purpose of this study was to develop a machine learning model based on patient and radiographic parameters that could identify patients indicated for cementless TKA.
View Article and Find Full Text PDF