Brain tumor magnetic resonance images classification based machine learning paradigms

Baby Pattanaik; Komma Anitha; Shanti Rathore; Preesat Biswas; Prabira Sethy; Santi Behera

doi:10.5114/wo.2023.124612

eISSN: 1897-4309
ISSN: 1428-2526

Contemporary Oncology/Współczesna Onkologia

Current issue Archive Manuscripts accepted About the journal Supplements Addendum Special Issues Editorial board Reviewers Abstracting and indexing Subscription Contact Instructions for authors Publication charge Ethical standards and procedures

Editorial System

Submit your Manuscript

Editorial Policies

Sarajevo Declaration on Integrity and Visibility of Scholarly Publications

4/2022
vol. 26

Send email

Copy url:

abstract:

Original paper

Brain tumor magnetic resonance images classification based machine learning paradigms

Baby Barnali Pattanaik

¹

,

Komma Anitha

²

,

Shanti Rathore

³

,

Preesat Biswas

⁴

,

Prabira Kumar Sethy

¹

,

Santi Kumari Behera

⁵

Department of Electronics, Sambalpur University, Burla, India
ECE Department, PVP Siddhartha Institute of Technology, Vijayawada, India
Department of ET and T, Dr. C. V. Raman University Bilaspur Chhattisgarh, India
Department of ET and T, GEC Jagdalpur, Chhattisgarh,India
Department of Computer Science and Engineering, VSSUT Burla, India

Contemp Oncol (Pozn) 2022; 26 (4): 268–274

DOI: https://doi.org/10.5114/wo.2023.124612

Online publish date: 2023/01/30

View full text Get citation

PlumX metrics:

Introduction
Cancer of the nervous system is one of the most common types of cancer in the world and mostly due to presence of a tumour in the brain. The symptoms and severity of the brain tumour depend on its location. The tumour within the brain may develop from nerves, dura (meningioma), pituitary gland (pituitary adenoma), or from the brain tissue itself (glioma).

Material and methods
In this study we proposed a feature engineering approach for classification magnetic resonance imaging (MRI) of 3 kinds of most common brain tumour, i.e. glioma, meningioma, pituitary, and no-tumour. Here 5 machine learning classifiers were used, i.e. support vector machine, K-nearest neighbour (KNN), Naive Bayes, Decision Tree, and Ensemble classifier with their paradigms.

Results
The handcrafted features such as histogram of oriented gradients, local binary pattern features, and grey level co-occurrence matrix are extracted from the MRI, and the feature fusion technique is adopted to enhance the dimension of feature vector. The Fine KNN outperforms among the classifiers for recognition of 4 kinds of MRI: glioma, meningioma, pituitary, and no tumour, and achieved 91.1% accuracy and 0.95 area under the curve (AUC).

Conclusions
The proposed method, i.e. Fine KNN, achieved 91.1% accuracy and 0.96 AUC. Furthermore, this model has the possibility to integrate in low-end devices unlike deep learning, which required a complex system.

keywords:

Brain tumor magnetic resonance images classification based machine learning paradigms

Baby Barnali Pattanaik 1 , Komma Anitha 2 , Shanti Rathore 3 , Preesat Biswas 4 , Prabira Kumar Sethy 1 , Santi Kumari Behera 5

brain tumour, machine learning, feature extraction, feature fusion, classification

Baby Barnali Pattanaik

¹

,

Komma Anitha

²

,

Shanti Rathore

³

,

Preesat Biswas

⁴

,

Prabira Kumar Sethy

¹

,

Santi Kumari Behera

⁵