Efficient Approach for Brain Tumor Detection and Classification Using Fuzzy Thresholding and Deep Learning Algorithms
Accurate and efficient brain tumor diagnosis remains a critical challenge in medical imaging. This study proposes a novel framework that integrates fuzzy logic-based segmentation with deep learning (DL) techniques to enhance brain tumor detection and classification in magnetic resonance imaging (MRI...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10981713/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Accurate and efficient brain tumor diagnosis remains a critical challenge in medical imaging. This study proposes a novel framework that integrates fuzzy logic-based segmentation with deep learning (DL) techniques to enhance brain tumor detection and classification in magnetic resonance imaging (MRI) scans. In the first stage, a fuzzy thresholding approach is applied to segment MRI images into healthy and abnormal regions, enabling the precise extraction of tumor areas. In the second stage, an optimized convolutional neural network (CNN) model classifies tumors into four categories: glioma, meningioma, pituitary tumor, and no tumor. The proposed method is evaluated across three large public datasets comprising more than 23,000 MRI images. Experimental results demonstrate that the model achieved an accuracy of 98% and a Dice similarity coefficient of 97.97%, confirming its high effectiveness in accurately extracting tumor regions and classifying them correctly. Furthermore, the proposed system outperforms conventional machine learning, deep learning, and transfer learning techniques. In addition to classification, the system accurately estimates tumor size, providing valuable clinical insights. These findings highlight the potential of combining fuzzy logic with DL to improve automated brain tumor diagnostics, enhance diagnostic reliability, and support clinical decision-making. |
|---|---|
| ISSN: | 2169-3536 |