Related Experiment Video
Updated: Sep 13, 2025
04:25
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
Published on: December 15, 2023
2.9K
A hybrid M-DbneAlexnet for brain tumour detection using MRI images
Jayasri Kotti1, Vidyadhari Chalasani2, Creesy Rajan3
1Department of Information Technology, GMR Institute of Technology, Rajam, Andhra Pradesh, India.
Archives of Physiology and Biochemistry
|July 29, 2025
Summary
This study introduces a novel hybrid deep learning model, M-DbneAlexnet, for accurate brain tumour detection and segmentation from MRI scans. The model achieves high accuracy, improving early diagnosis and patient survival rates.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Oncology
Background:
- Brain Tumours (BT) present a significant health challenge, with early detection crucial for improving patient survival rates.
- Existing methods for BT detection often suffer from high computational costs, limited feature discrimination, and poor generalization.
- Magnetic Resonance Imaging (MRI) is a key modality for visualizing brain structures and identifying abnormalities.
Purpose of the Study:
- To develop an effective and efficient method for brain tumour detection and segmentation using MRI.
- To address the limitations of existing BT detection techniques, including computational complexity and generalization issues.
- To improve the accuracy and speed of brain tumour diagnosis through advanced deep learning techniques.
Main Methods:
- A hybrid deep learning network, MobileNet- Deep Batch-Normalized eLU AlexNet (M-DbneAlexnet), was developed for BT detection and segmentation.
- Image enhancement was performed using a Piecewise Linear Transformation (PLT) function.
- Brain tumour regions were segmented using Transformer Brain Tumour Segmentation (TransBTSV2), followed by feature extraction and detection via the M-DbneAlexnet model.
Main Results:
- The proposed M-DbneAlexnet model achieved high performance metrics: 92.68% accuracy, 93.02% sensitivity, and 92.85% specificity.
- The model demonstrated effectiveness in distinguishing between tumour and healthy tissues, even with limited datasets.
- The method showed enhanced training speed compared to existing approaches.
Conclusions:
- The M-DbneAlexnet model offers a promising solution for accurate and efficient brain tumour detection and segmentation from MRI.
- The developed method has practical utility in enabling earlier diagnosis, potentially reducing brain tumour mortality rates.
- The model's performance highlights the potential of hybrid deep learning architectures in medical image analysis for oncology.
