Downloads: 19 | Views: 66 | Weekly Hits: ⮙4 | Monthly Hits: ⮙18
Research Paper | Computer Science and Information Technology | United States of America | Volume 13 Issue 6, June 2024 | Rating: 7.1 / 10
MRI Brain Tumor Segmentation using Cuckoo Optimization and Ensemble CNNs
Kulbir Singh
Abstract: Early identification of brain tumors significantly increases patient survival rates. Traditional methods relying on specialist knowledge are time - consuming and prone to inaccuracies. This paper proposes an automated segmentation technique using Cuckoo - based optimization and Ensemble Convolutional Neural Networks CNNs to enhance the segmentation of MRI brain images. Experimental results on the Leaderboard and Brats Challenge datasets demonstrate that the proposed method achieves superior performance, with Dice Similarity Coefficients DSC, Positive Predictive Values PPV, and Sensitivity metrics outperforming existing methods for High - Grade Glioma HGG and Low - Grade Glioma LGG. The purpose of this article is to propose and validate an automated method for brain tumor segmentation in MRI images using Cuckoo - based optimization and Ensemble Convolutional Neural Networks CNNs.
Keywords: Ensemble Convolutional Neural Networks (ECNN), Segmentation, High - Grade Glioma, Low - Grade Glioma, Dimensionality reduction, MRI
Edition: Volume 13 Issue 6, June 2024,
Pages: 425 - 434