Rapid Competency in NIR-Based Neuroimaging: Training Non-Experts for Head Trauma Triage
D'Amario, S.; Lamanna, M. T.; Riley, J. D.; Cook, D. J.
Show abstract
ObjectiveTo evaluate whether novice, non-specialist operators can rapidly learn to use a handheld near-infrared (NIR) head scanner and maintain scan quality after brief training, supporting its use for point-of-care triage when computed tomography is unavailable or delayed. MethodsThirty-two right-handed adults with no prior NIR experience received a brief standardized training session ([~]2 minutes) on the ArcheOptix NIRD(R) device, which detects intracranial hemorrhage by tracking hemoglobin absorption during guided scalp scans. Operators then completed two full-head scans on a healthy volunteer: an initial competency assessment (Scan 1) and a follow-up assessment after one day without refresher training (Scan 2). Performance metrics included total scan time, frequency of repeat scans prompted by loss of contact or light leaks, and mean scanpath time as an index of handling efficiency and consistency. Scan quality was evaluated using Lift on dark and Noise on dark indices. User experience was measured after each scan with the 10-item System Usability Scale (SUS, 0-100). Within-participant changes were analyzed with paired t tests or Wilcoxon signed-rank tests. ResultsAll operators completed both sessions. Median performance improved from Scan 1 to Scan 2, with total scan time decreasing from 5 min 27 s to 2 min 53 s. The proportion of "Excellent" scans (<5 minutes) increased from 50% to 84%, and "Poor" scans (>10 minutes) fell to zero. Repeat scans per session declined from 38 to 24, and mean scanpath time shortened while becoming more consistent. Lift on dark and Noise on dark remained stable, indicating no degradation in signal quality as operators worked faster. SUS scores improved from 69.4 to 76.5, reflecting higher perceived ease of use and confidence. ConclusionsAfter minimal training, novice operators achieved rapid, reliable NIR scans with faster performance, fewer repeat scans, stable signal quality, and improved usability ratings. This work shows that portable NIR can practically complement CT by helping prioritize transport and focus scarce imaging resources in emergency, sideline, and remote head trauma triage.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Designing a computer-assisted diagnosis system for cardiomegaly detection and radiology report generation 91%
- Implementation and prospective real-time evaluation of a generalized system for in-clinic deployment and validation of machine learning models in radiology 91%
- Theory of radiologist interaction with instant messaging decision support tools: a sequential-explanatory study 91%
Similar papers in this journal
- Laser speckle contrast imaging for visualizing blood flow during cerebral aneurysm surgery: A comparison with indocyanine green angiography 94%
- Portable Six-Channel Laser Speckle System for Simultaneous Cerebral Blood Flow and Volume Measurement with Potential Application for Characterization of Brain Injury 93%
- Creating anatomically-derived, standardized, customizable, and three-dimensional printable head caps for functional neuroimaging 92%
Similar papers in this journal
- 3D-Printable Non-invasive Head Immobilization System for Non-Human Primates 92%
- BrainTRACE (Brain Tumor Registration and Cortical Electrocorticography): A Novel Tool for Localizing Electrocorticography Electrodes in Patients with Brain Tumors 92%
- Dynamics of isoflurane-induced vasodilation and blood flow of cerebral vasculature revealed by multi-exposure speckle imaging 92%
Similar papers in this journal
- Inconsistency of AI in Intracranial Aneurysm Detection with Varying Dose and Image Reconstruction 93%
- MyoVision-US: an Artificial Intelligence-Powered Software for Automated Analysis of Skeletal Muscle Ultrasonography 93%
- Content-based image retrieval assists radiologists in diagnosing eye and orbital mass lesions in MRI 92%
Similar papers in this journal
- How AI is used in FDA-authorized medical devices: a taxonomy across 1,016 authorizations 92%
- Bridging the Literacy Gap for Surgical Consents: An AI-Human Expert Collaborative Approach 91%
- The clinician-AI interface: intended use and explainability in FDA-cleared AI devices for medical image interpretation 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.