Related Experiment Video
Updated: Mar 12, 2026
09:41
A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery
Published on: May 20, 2016
12.8K
Robust cascade bidirectional triple capsule network with OOA for deep neural network-based improved brain tumor
Kavitha Thangavel1, Mathivanan Murugavelu2, Selvin Christalin Nelson3
1Department of Computer Applications, Kongu Engineering College, Perundurai, Tamil Nadu, India.
Medical Physics
|March 10, 2026
Summary
This study introduces a new AI model for brain tumor detection, achieving 99.9% recall and 99.8% accuracy. The Robust Triple Extraction with Cascade Bidirectional Capsule Network and Osprey Optimization Algorithm (RT-CBCN-OOA) offers a more reliable solution for medical imaging.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Neurology
Background:
- Brain tumors can cause severe neurological symptoms, necessitating early and accurate diagnosis.
- Current Deep Learning (DL) models for brain tumor detection suffer from low accuracy and high false positive rates.
- Improved diagnostic tools are crucial for better patient prognosis and treatment planning.
Purpose of the Study:
- To propose a Robust Triple Extraction with Cascade Bidirectional Capsule Network and Osprey Optimization Algorithm (RT-CBCN-OOA) for enhanced brain tumor detection and classification.
- To improve the quality, accuracy, and dependability of automated brain tumor diagnosis.
- To address the limitations of existing DL models in terms of accuracy and false positive rates.
Main Methods:
- Pre-processing of MRI images (BraTS and Figshare) using Modified Square Root Sage-Husa Adaptive Kalman Filter (MSRS-HAKF) for noise reduction and clarity enhancement.
- Feature extraction, segmentation, and classification using Dual-Domain Attention CNN (EfficientNet-B3) and Geometric Algebra Transformer-based Robust Cascade Bidirectional Triple Capsule Network with Triple Attention (GAT-RCBTCN-TA).
- Optimization of model weights using the Osprey Optimization Algorithm (OOA).
Main Results:
- The proposed RT-CBCN-OOA model achieved a recall of 99.9% and an accuracy of 99.8%.
- These results surpass the performance of current state-of-the-art models in brain tumor detection.
- The model demonstrates high precision and efficiency in identifying and classifying brain tumors.
Conclusions:
- The RT-CBCN-OOA model offers a powerful, precise, and efficient solution for brain tumor detection.
- The high accuracy and recall indicate significant potential for clinical application in medical imaging and diagnosis.
- This approach represents a promising advancement for improving patient outcomes through early and reliable diagnosis.
