Evaluation of Performance Using Cross-Validation.

<div><p>Brain tumors are one of the leading diseases imposing a huge morbidity rate across the world every year. Classifying brain tumors accurately plays a crucial role in clinical diagnosis and improves the overall healthcare process. ML techniques have shown promise in accurately clas...

Full description

Saved in:
Bibliographic Details
Main Author: Priyanka Roy (14580479) (author)
Other Authors: Fahim Mohammad Sadique Srijon (19751363) (author), Pankaj Bhowmik (6002078) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1852020783815065600
author Priyanka Roy (14580479)
author2 Fahim Mohammad Sadique Srijon (19751363)
Pankaj Bhowmik (6002078)
author2_role author
author
author_facet Priyanka Roy (14580479)
Fahim Mohammad Sadique Srijon (19751363)
Pankaj Bhowmik (6002078)
author_role author
dc.creator.none.fl_str_mv Priyanka Roy (14580479)
Fahim Mohammad Sadique Srijon (19751363)
Pankaj Bhowmik (6002078)
dc.date.none.fl_str_mv 2025-05-05T16:50:54Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0310748.t006
dc.relation.none.fl_str_mv https://figshare.com/articles/dataset/Evaluation_of_Performance_Using_Cross-Validation_/28931609
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Medicine
Cell Biology
Genetics
Cancer
Space Science
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
world every year
significantly improved precision
significant class imbalance
prioritizing stable performance
planning treatment early
medical image datasets
leading diseases imposing
handling class imbalance
deep learning models
brain tumor classification
medical imaging data
highly imbalanced data
feature extraction techniques
overall healthcare process
overall classification process
improving patient outcomes
explainable ensemble approach
gan mechanism facilitates
classification process
explainable ensemble
gan mechanism
techniques aid
proposed mechanism
ml techniques
overall accuracy
study proposes
study presents
study focuses
specifically designed
shown promise
score demonstrate
research identifies
reliable model
proposed pipeline
original quality
mri scans
informative features
incorporating grad
frequently affected
crucial role
contributing parts
clinical diagnosis
benchmark ml
based pipeline
15 %.
dc.title.none.fl_str_mv Evaluation of Performance Using Cross-Validation.
dc.type.none.fl_str_mv Dataset
info:eu-repo/semantics/publishedVersion
dataset
description <div><p>Brain tumors are one of the leading diseases imposing a huge morbidity rate across the world every year. Classifying brain tumors accurately plays a crucial role in clinical diagnosis and improves the overall healthcare process. ML techniques have shown promise in accurately classifying brain tumors based on medical imaging data such as MRI scans. These techniques aid in detecting and planning treatment early, improving patient outcomes. However, medical image datasets are frequently affected by a significant class imbalance, especially when benign tumors outnumber malignant tumors in number. This study presents an explainable ensemble-based pipeline for brain tumor classification that integrates a Dual-GAN mechanism with feature extraction techniques, specifically designed for highly imbalanced data. This Dual-GAN mechanism facilitates the generation of synthetic minority class samples, addressing the class imbalance issue without compromising the original quality of the data. Additionally, the integration of different feature extraction methods facilitates capturing precise and informative features. This study proposes a novel deep ensemble feature extraction (DeepEFE) framework that surpasses other benchmark ML and deep learning models with an accuracy of 98.15%. This study focuses on achieving high classification accuracy while prioritizing stable performance. By incorporating Grad-CAM, it enhances the transparency and interpretability of the overall classification process. This research identifies the most relevant and contributing parts of the input images toward accurate outcomes enhancing the reliability of the proposed pipeline. The significantly improved Precision, Sensitivity and F1-Score demonstrate the effectiveness of the proposed mechanism in handling class imbalance and improving the overall accuracy. Furthermore, the integration of explainability enhances the transparency of the classification process to establish a reliable model for brain tumor classification, encouraging their adoption in clinical practice promoting trust in decision-making processes.</p></div>
eu_rights_str_mv openAccess
id Manara_008b6509ec8a67b9538871bd8a20fc49
identifier_str_mv 10.1371/journal.pone.0310748.t006
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/28931609
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Evaluation of Performance Using Cross-Validation.Priyanka Roy (14580479)Fahim Mohammad Sadique Srijon (19751363)Pankaj Bhowmik (6002078)MedicineCell BiologyGeneticsCancerSpace ScienceBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedworld every yearsignificantly improved precisionsignificant class imbalanceprioritizing stable performanceplanning treatment earlymedical image datasetsleading diseases imposinghandling class imbalancedeep learning modelsbrain tumor classificationmedical imaging datahighly imbalanced datafeature extraction techniquesoverall healthcare processoverall classification processimproving patient outcomesexplainable ensemble approachgan mechanism facilitatesclassification processexplainable ensemblegan mechanismtechniques aidproposed mechanismml techniquesoverall accuracystudy proposesstudy presentsstudy focusesspecifically designedshown promisescore demonstrateresearch identifiesreliable modelproposed pipelineoriginal qualitymri scansinformative featuresincorporating gradfrequently affectedcrucial rolecontributing partsclinical diagnosisbenchmark mlbased pipeline15 %.<div><p>Brain tumors are one of the leading diseases imposing a huge morbidity rate across the world every year. Classifying brain tumors accurately plays a crucial role in clinical diagnosis and improves the overall healthcare process. ML techniques have shown promise in accurately classifying brain tumors based on medical imaging data such as MRI scans. These techniques aid in detecting and planning treatment early, improving patient outcomes. However, medical image datasets are frequently affected by a significant class imbalance, especially when benign tumors outnumber malignant tumors in number. This study presents an explainable ensemble-based pipeline for brain tumor classification that integrates a Dual-GAN mechanism with feature extraction techniques, specifically designed for highly imbalanced data. This Dual-GAN mechanism facilitates the generation of synthetic minority class samples, addressing the class imbalance issue without compromising the original quality of the data. Additionally, the integration of different feature extraction methods facilitates capturing precise and informative features. This study proposes a novel deep ensemble feature extraction (DeepEFE) framework that surpasses other benchmark ML and deep learning models with an accuracy of 98.15%. This study focuses on achieving high classification accuracy while prioritizing stable performance. By incorporating Grad-CAM, it enhances the transparency and interpretability of the overall classification process. This research identifies the most relevant and contributing parts of the input images toward accurate outcomes enhancing the reliability of the proposed pipeline. The significantly improved Precision, Sensitivity and F1-Score demonstrate the effectiveness of the proposed mechanism in handling class imbalance and improving the overall accuracy. Furthermore, the integration of explainability enhances the transparency of the classification process to establish a reliable model for brain tumor classification, encouraging their adoption in clinical practice promoting trust in decision-making processes.</p></div>2025-05-05T16:50:54ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.1371/journal.pone.0310748.t006https://figshare.com/articles/dataset/Evaluation_of_Performance_Using_Cross-Validation_/28931609CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/289316092025-05-05T16:50:54Z
spellingShingle Evaluation of Performance Using Cross-Validation.
Priyanka Roy (14580479)
Medicine
Cell Biology
Genetics
Cancer
Space Science
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
world every year
significantly improved precision
significant class imbalance
prioritizing stable performance
planning treatment early
medical image datasets
leading diseases imposing
handling class imbalance
deep learning models
brain tumor classification
medical imaging data
highly imbalanced data
feature extraction techniques
overall healthcare process
overall classification process
improving patient outcomes
explainable ensemble approach
gan mechanism facilitates
classification process
explainable ensemble
gan mechanism
techniques aid
proposed mechanism
ml techniques
overall accuracy
study proposes
study presents
study focuses
specifically designed
shown promise
score demonstrate
research identifies
reliable model
proposed pipeline
original quality
mri scans
informative features
incorporating grad
frequently affected
crucial role
contributing parts
clinical diagnosis
benchmark ml
based pipeline
15 %.
status_str publishedVersion
title Evaluation of Performance Using Cross-Validation.
title_full Evaluation of Performance Using Cross-Validation.
title_fullStr Evaluation of Performance Using Cross-Validation.
title_full_unstemmed Evaluation of Performance Using Cross-Validation.
title_short Evaluation of Performance Using Cross-Validation.
title_sort Evaluation of Performance Using Cross-Validation.
topic Medicine
Cell Biology
Genetics
Cancer
Space Science
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
world every year
significantly improved precision
significant class imbalance
prioritizing stable performance
planning treatment early
medical image datasets
leading diseases imposing
handling class imbalance
deep learning models
brain tumor classification
medical imaging data
highly imbalanced data
feature extraction techniques
overall healthcare process
overall classification process
improving patient outcomes
explainable ensemble approach
gan mechanism facilitates
classification process
explainable ensemble
gan mechanism
techniques aid
proposed mechanism
ml techniques
overall accuracy
study proposes
study presents
study focuses
specifically designed
shown promise
score demonstrate
research identifies
reliable model
proposed pipeline
original quality
mri scans
informative features
incorporating grad
frequently affected
crucial role
contributing parts
clinical diagnosis
benchmark ml
based pipeline
15 %.