Citation

Anaam, Elham Abdulwahab and Haw, Su Cheng and Al Hashimi, Omar (2025) AI-Enhanced Mixed Reality: Transforming Real-Time Medical Data Collaboration among Physicians and Trainees. In: 2025 3rd International Conference on Big Data and Privacy Computing (BDPC), 30 May 2025 - 01 June 2025, Fuzhou, China.

Text 1.pdf - Published Version Restricted to Repository staff only Download (2MB)

Abstract

Artificial Intelligence (AI) involves the development of sophisticated computer algorithms designed to process, interpret, and autonomously act on vast datasets. These AI algorithms continuously refine their logic and decision-making capabilities, becoming progressively more accurate and efficient. The recent advancements in computational hardware, enabling the collection, storage, and analysis of substantial volumes of data, have significantly broadened AI’s applications in fields such as augmented reality (AR) and virtual reality (VR). Healthcare has emerged as a sector where AI and immersive technologies can provide transformative solutions. AI technologies are increasingly integrated with mixed reality (MR) environments, offering promising medical diagnostics and treatment planning enhancements by improving accuracy, efficiency, and accessibility. This study addresses the pressing need for a novel, AI-driven approach to MR within the healthcare sector. Specifically, it explores the potential of MR for supporting real-time, collaborative diagnostic processes by enabling the seamless sharing of critical medical data among physicians, specialists, and medical trainees across geographically dispersed locations. This study aims to illustrate MR's functional capabilities in creating a collaborative medical training environment and advancing diagnostic practices. This approach facilitates enhanced interactivity and accessibility, thereby promoting an inclusive and continuous learning process for medical professionals. The study employed the Region-Enhanced-Weight-and-Perturb Iterative Closest-Point (PICP) algorithm, a cutting-edge technique to align patient-specific medical data accurately within physical settings. This algorithm focuses on facial recognition to achieve precise and meaningful data overlay, allowing healthcare professionals to interact with patient data. The findings reveal that MR technology facilitates the sharing of detailed 3D digital models—such as those representing intracerebral vascular structures—in a collaborative, multi-viewer environment. This interactive approach enables clinicians and trainees to access and manipulate these models remotely, anytime, and from any location. This study comprehensively analyses MR’s capabilities in fostering real-time, collaborative learning experiences, ultimately transforming how medical data is visualized, shared, and utilized in the healthcare domain.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Artificial Intelligence AI, Mixed Reality, Augmented Reality, Virtual Reality, Telemedicine, 3D modelling, Healthcare Technology, Remote Medical Collaboration.
Subjects:	Q Science > QC Physics > QC350-467 Optics. Light
Divisions:	Faculty of Computing and Informatics (FCI)
Depositing User:	Ms Suzilawati Abu Samah
Date Deposited:	30 Sep 2025 00:38
Last Modified:	04 Oct 2025 08:04
URII:	http://shdl.mmu.edu.my/id/eprint/14517

Downloads

Edit (login required)