Hybrid Machine Learning Model for Classifying Traumatic Brain Injury (TBI): CT Scan Analysis

View Sample PDF

Author(s): Sabrina Tang (Taylor's University, Malaysia), Ashley Teong Ling Kuan (Taylor's University, Malaysia), Lee Yee Jeen (Taylor's University, Malaysia), Tia'a Faang Der (Taylor's University, Malaysia)and Harrel Xu Hao Yang (Taylor's University, Malaysia)
Copyright: 2026
Pages: 34
Source title: Precision in CT Imaging for Personalized Implants and Surgical Planning
Source Author(s)/Editor(s): Soobia Saeed (Taylor's University, Malaysia)and Mohsin Qadeer (National Medical Center, Pakistan)
DOI: 10.4018/979-8-3373-2807-2.ch008

Keywords: Knowledge Management and Library Science / Medical Imaging / Medical Information Science Reference / Surgery and Surgical Specialties

Purchase

View Hybrid Machine Learning Model for Classifying Traumatic Brain Injury (TBI): CT Scan Analysis on the publisher's website for pricing and purchasing information.

Abstract

Traumatic Brain Injury, commonly referred to as TBI, is an important issue that concerns worldwide health; it generates permanent disabilities or death, depending on its severity and treatment delay. In any case, early diagnosis and accurate diagnosis are vital for an intervention outcome. This research project, BrainView AI, is an ML-based solution to classify TBI from brain CT scans as an adjunct to fast-tracking clinical decision-making. The Mixed ML approach utilized Support Vector Machines, K-means Clustering, as well as Convolutional Neural Networks to ensure flexible and performant classification methods. The TBI research project is that the researchers also develop UI and user acceptance testing of their web-based prototype with complete stack operating in full functional mode covering backend logic, user-friendly front-end interface, and orderly manage data system.

The IRMA Community

Research IRM

Hybrid Machine Learning Model for Classifying Traumatic Brain Injury (TBI): CT Scan Analysis

Purchase

Abstract

Related Content

IRMA Sponsors