Performance Analysis of Several CNN Based Models for Brain MRI in Tumor Classification

Title

Performance Analysis of Several CNN Based Models for Brain MRI in Tumor Classification

Creator

Wahlang I.; Pohrmen F.H.

Description

Classification is one of the primary tasks in data mining and machine learning which is used for categorizing data into classes. In this paper, brain MRI images are used for classification of tumors into three categories namely, Meningioma, Glioma, and Pituitary Tumor. These methodologies used are spatial based, depth based, feature map based and depth based CNN showcasing the power of deep learning in automating the tumor detection process. To evaluate the performance of several deep learning models, data is divided into training and testing data where a generalization method is used for comparison. The experimental results demonstrate promising accuracy, showing that a few techniques are valuable tools for radiologists and physicians, along with further analysis. The best accuracy obtained is 96% using MobileNet and ResNet50 in comparison to other CNN methodologies used in this paper. 2024 IEEE.

Source

2024 IEEE 8th International Conference on Signal and Image Processing Applications, ICSIPA 2024

Date

2024-01-01

Publisher

Institute of Electrical and Electronics Engineers Inc.

Subject

brain tumor; classification; Deep learning; MRI

Coverage

Wahlang I., Ghani Khan Choudhury Institute of Engineering and Technology, Department of Computer Science and Engineering, Malda, India; Pohrmen F.H., Christ University, Department of Computer Science, Bangalore, India

Rights

Restricted Access

Relation

ISBN: 979-835035236-8

Format

Online

Language

English

Type

Conference paper

Identifier

https://doi.org/10.1109/ICSIPA62061.2024.10685883

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85206480084&doi=10.1109%2fICSIPA62061.2024.10685883&partnerID=40&md5=bea5a484da2dd58d7f6a394b7b97b344