Page 135 - AIH-2-4

Artificial Intelligence in Health

ORIGINAL RESEARCH ARTICLE
Leveraging the smarts in your phone: An

artificial intelligence-driven iOS application for
neurosurgical navigation of external ventricular

drains

Andrew Abumoussa , Benjamin Succop * , Carolyn Quinsey 3 , Yueh Lee 4 ,
1
2
and Sivakumar Jaikumar 1
1 Department of Neurosurgery, School of Medicine, University of North Carolina at Chapel Hill,
Chapel Hill, North Carolina, United States of America
2 Department of Neurosurgery, School of Medicine, Duke University, Durham, North Carolina, United
States of America
3 Department of Neurosurgery, School of Medicine, University of Missouri, Columbia, Missouri,
United States of America
4 Department of Radiology, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina,
United States of America
(This article belongs to the Special Issue: Sensors and circuits for AI in health)

*Corresponding author: Abstract
Benjamin Succop
(ben.succop@duke.edu) External ventricular drain (EVD) placement is a critical neurosurgical procedure
Citation: Abumoussa A, Succop B, traditionally performed freehand, with inherent risks of malposition, infection, and
Quinsey C, Lee Y, Jaikumar S. hemorrhage. Recent advances in artificial intelligence (AI), particularly in medical imaging
Leveraging the smarts in your and real-time computer vision, have enabled the development of portable navigation
phone: An artificial intelligence-
driven iOS application for tools that may enhance accuracy, safety, and bedside accessibility. This study evaluated
neurosurgical navigation of external whether iOS devices equipped with a TrueDepth camera could perform real-time object
ventricular drains. Artif Intell Health. and facial recognition, tracking, and semantic segmentation of computed tomography
2025;2(4):129-138.
doi: 10.36922/aih.8195 (CT) scans for non-immobilized heads to guide EVD placement via a custom AI-driven
application. A custom iOS application was developed to provide a complete, real-time
Received: December 25, 2024
surgical navigation experience on an iPhone or iPad Pro. Three AI models were trained,
1st revised: June 10, 2025 tuned, and validated: a semantic segmentation model for brain anatomy, a semantic
2nd revised: July 27, 2025 segmentation model for facial features, and an object detection model for a custom
EVD stylet attachment. GPU programming accelerated on-device real-time, continuous
Accepted: August 13, 2025
registration while optimizing power consumption. A UNet convolutional neural network
Published online: September 23, trained on eight 1 mm head CTs achieved 98.3% testing and 98.2% validation accuracy
2025 using a 50/50 test–validation split, segmenting a thin-cut CT in 3 s on an iPhone 12
Copyright: © 2025 Author(s). Pro. Point cloud merging of patient anatomy took 4 seconds with an initial depth scan
This is an Open-Access article of 30,000 points, updating in real time with a cumulative error of 1 × 10 cm. Transfer
-8
distributed under the terms of the
Creative Commons Attribution learning-powered EVD tracking, trained for 1,000 epochs, achieved an intersection over
License, permitting distribution, union of 1.0 and 0.98 for the detection model, with inference times of 800 μs on Apple’s
and reproduction in any medium, Neural Engine. This feasibility study demonstrates that iOS devices with TrueDepth
provided the original work is
properly cited. cameras can enable real-time, continuous surgical navigation for EVD stylets.
Publisher’s Note: AccScience
Publishing remains neutral with Keywords: External ventricular drain; Surgical navigation; Artificial intelligence; Machine
regard to jurisdictional claims in
published maps and institutional learning
affiliations.

Volume 2 Issue 4 (2025) 129 doi: 10.36922/aih.8195