ORIGINAL RESEARCH article
Front. Oncol.
Sec. Cancer Imaging and Image-directed Interventions
Volume 15 - 2025 | doi: 10.3389/fonc.2025.1564802
This article is part of the Research TopicInnovative imaging in neurological disorders: bridging engineering and medicineView all 8 articles
HETEROGENEITY-AWARE LOCAL BINARY PATTERNS FOR BRAIN TUMOR DETECTION
Provisionally accepted
Gunasundari C1*
Selva Bhuvaneswari K2- 1Roever college of engineering and Technology, Perambalur, India
- 2University College of Engineering Kancheepuram, Kancheepuram, India
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
The use of medical image processing has increased, which has resulted in the need for more precise and faster brain tumor segmentation. Magnetic resonance imaging is a powerful tool for analyzing brain tumors.This paper proposes a framework that can help in performing this process.The analysis of brain tumors using T1-weighted MRI images begins with optimized skull stripping to improve tissue visibility and boundary accuracy. Low contrast is utilized to extract the anomalous brain tissues. These edges are precisely identified.The first step in the process is to perform feature extraction using the Local Binary Pattern and Principal Component Analysis.Classification is then carried out using the support vector machine learning approach. This process involves using various learning methods, such as machine learning. The classification's accuracy, specificity, and sensitivity are then measured and compared. It has an accuracy of 99.81 percent, an error rate of 1.54 percent, a TPR of 98.99 percent, a TNR of 98.12 percent, a precision of 97.63 percent, and an F1-score of 97.82 percent.
Keywords: Magnetic Resonance Imaging, Texture feature analysis, Local binary pattern, Brain tumor detection, Machine learning methods
Received: 20 Mar 2025; Accepted: 27 Aug 2025.
Copyright: © 2025 C and K. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Gunasundari C, Roever college of engineering and Technology, Perambalur, India
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.