International Journal of Science and Research (IJSR)

International Journal of Science and Research (IJSR)
Call for Papers | Fully Refereed | Open Access | Double Blind Peer Reviewed

ISSN: 2319-7064


Downloads: 1

Research Paper | Computer Science | Volume 15 Issue 3, March 2026 | Pages: 397 - 401 | India


Improving Brain Tumor Detection Accuracy in MRI Using Intelligent Preprocessing and U-Net Segmentation

Dr. Rajshree

Abstract: Accurate detection and segmentation of brain tumors from Magnetic Resonance Imaging (MRI) are essential for early diagnosis and effective treatment planning. However, MRI images are often affected by noise, low contrast, and intensity inhomogeneity, which degrade the performance of automated detection systems. This paper proposes a comprehensive framework that improves brain tumor detection accuracy using intelligent preprocessing techniques combined with U-Net-based segmentation. The preprocessing stage includes advanced noise reduction, skull stripping, intensity normalization, and contrast enhancement to improve image quality before deep learning analysis. A U-Net architecture is employed for precise tumor segmentation due to its ability to preserve spatial features through encoder-decoder pathways and skip connections. Experimental evaluation on benchmark MRI datasets demonstrates that the proposed approach significantly enhances segmentation accuracy and overall detection performance compared to models without intelligent preprocessing.

Keywords: Brain Tumor Detection, MRI, Intelligent Preprocessing, U-Net, Image Segmentation, Deep Learning

How to Cite?: Dr. Rajshree, "Improving Brain Tumor Detection Accuracy in MRI Using Intelligent Preprocessing and U-Net Segmentation", Volume 15 Issue 3, March 2026, International Journal of Science and Research (IJSR), Pages: 397-401, https://www.ijsr.net/getabstract.php?paperid=SR26304163510, DOI: https://dx.dx.doi.org/10.21275/SR26304163510

Download Citation: APA | MLA | BibTeX | EndNote | RefMan


Download Article PDF


Rate This Article!


Top