Real-Time Identification of Look-Alike Medical Vials Using Mixed Reality-Enabled Deep Learning

The accurate identification of look-alike medical vials is essential for patient safety, particularly when similar vials contain different substances, volumes, or concentrations. Traditional methods, such as manual selection or barcode-based identification, are prone to human error or face reliabili...

Full description

Saved in:
Bibliographic Details
Main Authors: Bahar Uddin Mahmud, Guanyue Hong, Virinchi Ravindrakumar Lalwani, Nicholas Brown, Zachary D. Asher
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Future Internet
Subjects:
Online Access:https://www.mdpi.com/1999-5903/17/5/223
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850126827459182592
author Bahar Uddin Mahmud
Guanyue Hong
Virinchi Ravindrakumar Lalwani
Nicholas Brown
Zachary D. Asher
author_facet Bahar Uddin Mahmud
Guanyue Hong
Virinchi Ravindrakumar Lalwani
Nicholas Brown
Zachary D. Asher
author_sort Bahar Uddin Mahmud
collection DOAJ
description The accurate identification of look-alike medical vials is essential for patient safety, particularly when similar vials contain different substances, volumes, or concentrations. Traditional methods, such as manual selection or barcode-based identification, are prone to human error or face reliability issues under varying lighting conditions. This study addresses these challenges by introducing a real-time deep learning-based vial identification system, leveraging a Lightweight YOLOv4 model optimized for edge devices. The system is integrated into a Mixed Reality (MR) environment, enabling the real-time detection and annotation of vials with immediate operator feedback. Compared to standard barcode-based methods and the baseline YOLOv4-Tiny model, the proposed approach improves identification accuracy while maintaining low computational overhead. The experimental evaluations demonstrate a mean average precision (mAP) of 98.76 percent, with an inference speed of 68 milliseconds per frame on HoloLens 2, achieving real-time performance. The results highlight the model’s robustness in diverse lighting conditions and its ability to mitigate misclassifications of visually similar vials. By combining deep learning with MR, this system offers a more reliable and efficient alternative for pharmaceutical and medical applications, paving the way for AI-driven MR-assisted workflows in critical healthcare environments.
format Article
id doaj-art-02f1bc2f851a41d69c47d6a7fb21823f
institution OA Journals
issn 1999-5903
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Future Internet
spelling doaj-art-02f1bc2f851a41d69c47d6a7fb21823f2025-08-20T02:33:50ZengMDPI AGFuture Internet1999-59032025-05-0117522310.3390/fi17050223Real-Time Identification of Look-Alike Medical Vials Using Mixed Reality-Enabled Deep LearningBahar Uddin Mahmud0Guanyue Hong1Virinchi Ravindrakumar Lalwani2Nicholas Brown3Zachary D. Asher4Department of Computer Science, Western Michigan University, Kalamazoo, MI 49008, USADepartment of Computer Science, Western Michigan University, Kalamazoo, MI 49008, USADepartment of Computer Science, Western Michigan University, Kalamazoo, MI 49008, USAEnergy Efficient and Autonomous Vehicle (EEAV) Lab, Western Michigan University, Kalamazoo, MI 49008, USAEnergy Efficient and Autonomous Vehicle (EEAV) Lab, Western Michigan University, Kalamazoo, MI 49008, USAThe accurate identification of look-alike medical vials is essential for patient safety, particularly when similar vials contain different substances, volumes, or concentrations. Traditional methods, such as manual selection or barcode-based identification, are prone to human error or face reliability issues under varying lighting conditions. This study addresses these challenges by introducing a real-time deep learning-based vial identification system, leveraging a Lightweight YOLOv4 model optimized for edge devices. The system is integrated into a Mixed Reality (MR) environment, enabling the real-time detection and annotation of vials with immediate operator feedback. Compared to standard barcode-based methods and the baseline YOLOv4-Tiny model, the proposed approach improves identification accuracy while maintaining low computational overhead. The experimental evaluations demonstrate a mean average precision (mAP) of 98.76 percent, with an inference speed of 68 milliseconds per frame on HoloLens 2, achieving real-time performance. The results highlight the model’s robustness in diverse lighting conditions and its ability to mitigate misclassifications of visually similar vials. By combining deep learning with MR, this system offers a more reliable and efficient alternative for pharmaceutical and medical applications, paving the way for AI-driven MR-assisted workflows in critical healthcare environments.https://www.mdpi.com/1999-5903/17/5/223look-alike vialreal time detectionAIdeep learningAI in healthcareobject detection
spellingShingle Bahar Uddin Mahmud
Guanyue Hong
Virinchi Ravindrakumar Lalwani
Nicholas Brown
Zachary D. Asher
Real-Time Identification of Look-Alike Medical Vials Using Mixed Reality-Enabled Deep Learning
Future Internet
look-alike vial
real time detection
AI
deep learning
AI in healthcare
object detection
title Real-Time Identification of Look-Alike Medical Vials Using Mixed Reality-Enabled Deep Learning
title_full Real-Time Identification of Look-Alike Medical Vials Using Mixed Reality-Enabled Deep Learning
title_fullStr Real-Time Identification of Look-Alike Medical Vials Using Mixed Reality-Enabled Deep Learning
title_full_unstemmed Real-Time Identification of Look-Alike Medical Vials Using Mixed Reality-Enabled Deep Learning
title_short Real-Time Identification of Look-Alike Medical Vials Using Mixed Reality-Enabled Deep Learning
title_sort real time identification of look alike medical vials using mixed reality enabled deep learning
topic look-alike vial
real time detection
AI
deep learning
AI in healthcare
object detection
url https://www.mdpi.com/1999-5903/17/5/223
work_keys_str_mv AT baharuddinmahmud realtimeidentificationoflookalikemedicalvialsusingmixedrealityenableddeeplearning
AT guanyuehong realtimeidentificationoflookalikemedicalvialsusingmixedrealityenableddeeplearning
AT virinchiravindrakumarlalwani realtimeidentificationoflookalikemedicalvialsusingmixedrealityenableddeeplearning
AT nicholasbrown realtimeidentificationoflookalikemedicalvialsusingmixedrealityenableddeeplearning
AT zacharydasher realtimeidentificationoflookalikemedicalvialsusingmixedrealityenableddeeplearning