Open Access

ARTICLE

Advanced Computational Modeling for Brain Tumor Detection: Enhancing Segmentation Accuracy Using ICA-I and ICA-II Techniques

Abdullah A. Asiri¹, Toufique A. Soomro^2,3,*, Ahmed Ali⁴, Faisal Bin Ubaid⁵, Muhammad Irfan^6,*, Khlood M. Mehdar⁷, Magbool Alelyani⁸, Mohammed S. Alshuhri⁹, Ahmad Joman Alghamdi¹⁰, Sultan Alamri¹⁰

1 Radiological Sciences Department, College of Applied Medical Sciences, Najran University, Najran, 61441, Saudi Arabia
2 Artificial Intelligence and Cyber Futures Institute, Charles University, Bathurst, NSW 2795, Australia
3 Department of Electronic Engineering, The University of Larkano, Larkana, 75660, Pakistan
4 Electrical Engineering Department, Sukkur IBA University, Sukkur, 65200, Pakistan
5 Computer Science Department, Sukkur IBA University, Sukkur, 65200, Pakistan
6 Electrical Engineering Department, College of Engineering, Najran University, Najran, 61441, Saudi Arabia
7 Anatomy Department, Medicine College, Najran University, Najran, 61441, Saudi Arabia
8 Department of Radiological Sciences, College of Applied Medical Science, King Khalid University, Guraiger, Abha, 62521, Saudi Arabia
9 Radiology and Medical Imaging Department, College of Applied Medical Sciences, Prince Sattam bin Abdulaziz University, Kharj, 11942, Saudi Arabia
10 Radiological Sciences Department, College of Applied Medical Sciences, Taif University, Taif, 21944, Saudi Arabia

* Corresponding Authors: Toufique A. Soomro. Email: ; Muhammad Irfan. Email:

Computer Modeling in Engineering & Sciences 2025, 143(1), 255-287. https://doi.org/10.32604/cmes.2025.061683

Received 30 November 2024; Accepted 07 March 2025; Issue published 11 April 2025

Abstract

Global mortality rates are greatly impacted by malignancies of the brain and nervous system. Although, Magnetic Resonance Imaging (MRI) plays a pivotal role in detecting brain tumors; however, manual assessment is time-consuming and susceptible to human error. To address this, we introduce ICA2-SVM, an advanced computational framework integrating Independent Component Analysis Architecture-2 (ICA2) and Support Vector Machine (SVM) for automated tumor segmentation and classification. ICA2 is utilized for image preprocessing and optimization, enhancing MRI consistency and contrast. The Fast-Marching Method (FMM) is employed to delineate tumor regions, followed by SVM for precise classification. Validation on the Contrast-Enhanced Magnetic Resonance Imaging (CE-MRI) dataset demonstrates the superior performance of ICA2-SVM, achieving a Dice Similarity Coefficient (DSC) of 0.974, accuracy of 0.992, specificity of 0.99, and sensitivity of 0.99. Additionally, the model surpasses existing approaches in computational efficiency, completing analysis within 0.41 s. By integrating state-of-the-art computational techniques, ICA2-SVM advances biomedical imaging, offering a highly accurate and efficient solution for brain tumor detection. Future research aims to incorporate multi-physics modeling and diverse classifiers to further enhance the adaptability and applicability of brain tumor diagnostic systems.

---

Keywords

---