Holographic patient tracking after bed movement for augmented reality neuronavigation using a head-mounted display

Background Holographic neuronavigation has several potential advantages compared to conventional neuronavigation systems. We present the first report of a holographic neuronavigation system with patient-to-image registration and patient tracking with a reference array using an augmented reality head-mounted display (AR-HMD). Methods Three patients undergoing an intracranial neurosurgical procedure were included in this pilot study. The relevant anatomy was first segmented in 3D and then uploaded as holographic scene in our custom neuronavigation software. Registration was performed using point-based matching using anatomical landmarks. We measured the fiducial registration error (FRE) as the outcome measure for registration accuracy. A custom-made reference array with QR codes was integrated in the neurosurgical setup and used for patient tracking after bed movement. Results Six registrations were performed with a mean FRE of 8.5 mm. Patient tracking was achieved with no visual difference between the registration before and after movement. Conclusions This first report shows a proof of principle of intraoperative patient tracking using a standalone holographic neuronavigation system. The navigation accuracy should be further optimized to be clinically applicable. However, it is likely that this technology will be incorporated in future neurosurgical workflows because the system improves spatial anatomical understanding for the surgeon.

Multi-view 3D skin feature recognition and localization for patient tracking in spinal surgery applications

Background Minimally invasive spine surgery is dependent on accurate navigation. Computer-assisted navigation is increasingly used in minimally invasive surgery (MIS), but current solutions require the use of reference markers in the surgical field for both patient and instruments tracking. Purpose To improve reliability and facilitate clinical workflow, this study proposes a new marker-free tracking framework based on skin feature recognition. Methods Maximally Stable Extremal Regions (MSER) and Speeded Up Robust Feature (SURF) algorithms are applied for skin feature detection. The proposed tracking framework is based on a multi-camera setup for obtaining multi-view acquisitions of the surgical area. Features can then be accurately detected using MSER and SURF and afterward localized by triangulation. The triangulation error is used for assessing the localization quality in 3D. Results The framework was tested on a cadaver dataset and in eight clinical cases. The detected features for the entire patient datasets were found to have an overall triangulation error of 0.207 mm for MSER and 0.204 mm for SURF. The localization accuracy was compared to a system with conventional markers, serving as a ground truth. An average accuracy of 0.627 and 0.622 mm was achieved for MSER and SURF, respectively. Conclusions This study demonstrates that skin feature localization for patient tracking in a surgical setting is feasible. The technology shows promising results in terms of detected features and localization accuracy. In the future, the framework may be further improved by exploiting extended feature processing using modern optical imaging techniques for clinical applications where patient tracking is crucial.

Progress Towards Unique Patient Identification and Case-Based Surveillance within the Southern African Development Community (SADC)

Background: Despite significant advances within the South African Development Community (SADC) in making HIV care more accessible through universal prevention, testing, and treatment policies, the mobile nature of the population presents a challenge to tracking and linking of patients to HIV care, and other health services. Case-based surveillance (CBS) through individual-level clinical data linked and tracked with a unique patient identifier (UPI) has been recommended to create a more person-centred health information system, and is an important policy consideration within PEPFAR-supported countries.Methods: We conducted a landscape analysis of UPI and CBS implementation within selected SADC countries through a mixed-methods study design that included the following activities: 1) a literature review to gather evidence around UPI implementation and patient-tracking in the SADC region; 2) an assessment of progress towards UPI and CBS implementation within relatively high HIV prevalence SADC countries; and 3) a case-study of UPI implementation within selected South African primary healthcare (PHC) facilities.Results: Research into UPI implementation and movement towards CBS for the SADC region is lacking. Existing patient identification methods, such as name and surname, may not uniquely identify a patient or guarantee confidentiality. If a UPI has been assigned these are often facility specific, i.e. a patient can be tracked within a facility, but not across facilities. Other challenges include multiple identifiers allocated to one patient, incorrectly captured UPIs, preference for paper-based records and a lack of integration between numerous stand-alone health-information systems, e.g. laboratory databases and electronic health records, resulting in fragmented health information which limits patient-tracking and monitoring. Our analysis revealed that most countries were in the early-middle stages of the shift towards CBS and had challenges with UPI implementation. Our South African case-study found that the required identifier, which is critical for record-linkage and systems-integration, may often not be recorded.Conclusions: Until a fully functional and reliable UPI is in place difficulties tracking patients across prevention and care cascades will continue. Progress towards CBS was lagging in all countries, consistently hampered by a preference for paper-based records and difficulties implementing the UPI, underscoring a need for increased policy efforts and support to address this gap.

Multi-View 3D Skin Feature Recognition and Localization for Patient Tracking in Spinal Surgery Applications

Background: Minimally invasive spine surgery is dependent on accurate navigation. Computer-assisted navigation is increasingly used in minimally invasive surgery (MIS), but current solutions require the use of reference markers in the surgical field for both patient and instruments tracking. Purpose: To improve reliability and facilitate clinical workflow, this study proposes a new marker-free tracking framework based on skin feature recognition. Methods: Maximally Stable Extremal Regions (MSER) and Speeded Up Robust Feature (SURF) algorithms are applied for skin feature detection. The proposed tracking framework is based on a multi-camera setup for obtaining multi-view acquisitions of the surgical area. Features can then be accurately detected using MSER and SURF and afterwards localized by triangulation. The triangulation error is used for assessing the localization quality in 3D. Results: The framework was tested on a cadaver dataset and in eight clinical cases. The detected features for the entire patient datasets were found to have an overall triangulation error of 0.207 mm for MSER and 0.204 mm for SURF. The localization accuracy was compared to a system with conventional markers, serving as a ground truth. An average accuracy of 0.627 and 0.622 mm was achieved for MSER and SURF, respectively. Conclusions: This study demonstrates that skin feature localization for patient tracking in a surgical setting is feasible. The technology shows promising results in terms of detected features and localization accuracy. In the future, the framework may be further improved by exploiting extended feature processing using modern optical imaging techniques for clinical applications where patient tracking is crucial.