Machine learning and transfer learning techniques for accurate brain tumor classification

Brain tumors, resulting from uncontrolled and rapid cell growth, pose significant health risks if not treated early. Despite numerous advancements, accurate segmentation and classification remain challenging. This study leverages machine learning (ML) and transfer learning techniques to classify hea...

Full description

Saved in:
Bibliographic Details
Main Authors: Seyed Matin Malakouti, Mohammad Bagher Menhaj, Amir Abolfazl Suratgar
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2024-12-01
Series:Clinical eHealth
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2588914124000091
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850043577137102848
author Seyed Matin Malakouti
Mohammad Bagher Menhaj
Amir Abolfazl Suratgar
author_facet Seyed Matin Malakouti
Mohammad Bagher Menhaj
Amir Abolfazl Suratgar
author_sort Seyed Matin Malakouti
collection DOAJ
description Brain tumors, resulting from uncontrolled and rapid cell growth, pose significant health risks if not treated early. Despite numerous advancements, accurate segmentation and classification remain challenging. This study leverages machine learning (ML) and transfer learning techniques to classify healthy and sick individuals using numerical data and MRI images. We utilized 3762 MRI images alongside Light Gradient Boosting Machine (LightGBM), AdaBoost, gradient boosting, Random Forest, Quadratic Discriminant Analysis, Linear Discriminant Analysis, logistic regression, and transfer learning algorithms. Numerical data was processed with LightGBM, achieving an accuracy of 95.7 %. Transfer learning applied to image data using a modified GoogLeNet model further enhanced classification accuracy to 99.3 %. These results demonstrate the effectiveness of combining ML and transfer learning techniques for accurate brain tumor classification, addressing limitations of prior approaches and offering improved diagnostic reliability. All coding and model implementations were conducted on the Python platform.
format Article
id doaj-art-7ade14d9b80e457db9b7bf56df40d5b8
institution DOAJ
issn 2588-9141
language English
publishDate 2024-12-01
publisher KeAi Communications Co., Ltd.
record_format Article
series Clinical eHealth
spelling doaj-art-7ade14d9b80e457db9b7bf56df40d5b82025-08-20T02:55:12ZengKeAi Communications Co., Ltd.Clinical eHealth2588-91412024-12-01710611910.1016/j.ceh.2024.08.001Machine learning and transfer learning techniques for accurate brain tumor classificationSeyed Matin Malakouti0Mohammad Bagher Menhaj1Amir Abolfazl Suratgar2Distributed and Intelligent Optimization Research Laboratory, Department of Electrical Engineering, Amirkabir University of Technology, Tehran, IranDistributed and Intelligent Optimization Research Laboratory, Department of Electrical Engineering, Amirkabir University of Technology, Tehran, IranDistributed and Intelligent Optimization Research Laboratory, Department of Electrical Engineering, Amirkabir University of Technology, Tehran, IranBrain tumors, resulting from uncontrolled and rapid cell growth, pose significant health risks if not treated early. Despite numerous advancements, accurate segmentation and classification remain challenging. This study leverages machine learning (ML) and transfer learning techniques to classify healthy and sick individuals using numerical data and MRI images. We utilized 3762 MRI images alongside Light Gradient Boosting Machine (LightGBM), AdaBoost, gradient boosting, Random Forest, Quadratic Discriminant Analysis, Linear Discriminant Analysis, logistic regression, and transfer learning algorithms. Numerical data was processed with LightGBM, achieving an accuracy of 95.7 %. Transfer learning applied to image data using a modified GoogLeNet model further enhanced classification accuracy to 99.3 %. These results demonstrate the effectiveness of combining ML and transfer learning techniques for accurate brain tumor classification, addressing limitations of prior approaches and offering improved diagnostic reliability. All coding and model implementations were conducted on the Python platform.http://www.sciencedirect.com/science/article/pii/S2588914124000091Brain tumorMRI imagesNumerical dataLight gradient boosting machineTransfer learning
spellingShingle Seyed Matin Malakouti
Mohammad Bagher Menhaj
Amir Abolfazl Suratgar
Machine learning and transfer learning techniques for accurate brain tumor classification
Clinical eHealth
Brain tumor
MRI images
Numerical data
Light gradient boosting machine
Transfer learning
title Machine learning and transfer learning techniques for accurate brain tumor classification
title_full Machine learning and transfer learning techniques for accurate brain tumor classification
title_fullStr Machine learning and transfer learning techniques for accurate brain tumor classification
title_full_unstemmed Machine learning and transfer learning techniques for accurate brain tumor classification
title_short Machine learning and transfer learning techniques for accurate brain tumor classification
title_sort machine learning and transfer learning techniques for accurate brain tumor classification
topic Brain tumor
MRI images
Numerical data
Light gradient boosting machine
Transfer learning
url http://www.sciencedirect.com/science/article/pii/S2588914124000091
work_keys_str_mv AT seyedmatinmalakouti machinelearningandtransferlearningtechniquesforaccuratebraintumorclassification
AT mohammadbaghermenhaj machinelearningandtransferlearningtechniquesforaccuratebraintumorclassification
AT amirabolfazlsuratgar machinelearningandtransferlearningtechniquesforaccuratebraintumorclassification