Brain tumor segmentation based on optimized convolutional neural network and improved chimp optimization algorithm

dc.authoridTirkolaee, Erfan Babaee/0000-0003-1664-9210
dc.authoridRanjbarzadeh, Ramin/0000-0001-7065-9060
dc.authorwosidTirkolaee, Erfan Babaee/U-3676-2017
dc.authorwosidRanjbarzadeh, Ramin/E-7289-2019
dc.contributor.authorRanjbarzadeh, Ramin
dc.contributor.authorZarbakhsh, Payam
dc.contributor.authorCaputo, Annalina
dc.contributor.authorTirkolaee, Erfan Babaee
dc.contributor.authorBendechache, Malika
dc.date.accessioned2024-05-19T14:39:34Z
dc.date.available2024-05-19T14:39:34Z
dc.date.issued2024
dc.departmentİstinye Üniversitesien_US
dc.description.abstractReliable and accurate brain tumor segmentation is a challenging task even with the appropriate acquisition of brain images. Tumor grading and segmentation utilizing Magnetic Resonance Imaging (MRI) are necessary steps for correct diagnosis and treatment planning. There are different MRI sequence images (T1, Flair, T1ce, T2, etc.) for identifying different parts of the tumor. Due to the diversity in the illumination of each brain imaging modality, different information and details can be obtained from each input modality. Therefore, by using various MRI modalities, the diagnosis system is capable of finding more unique details that lead to a better segmentation result, especially in fuzzy borders. In this study, to achieve an automatic and robust brain tumor segmentation framework using four MRI sequence images, an optimized Convolutional Neural Network (CNN) is proposed. All weight and bias values of the CNN model are adjusted using an Improved Chimp Optimization Algorithm (IChOA). In the first step, all four input images are normalized to find some potential areas of the existing tumor. Next, by employing the IChOA, the best features are selected using a Support Vector Machine (SVM) classifier. Finally, the best-extracted features are fed to the optimized CNN model to classify each object for brain tumor segmentation. Accordingly, the proposed IChOA is utilized for feature selection and optimizing Hyperparameters in the CNN model. The experimental outcomes conducted on the BRATS 2018 dataset demonstrate superior performance (Precision of 97.41 %, Recall of 95.78 %, and Dice Score of 97.04 %) compared to the existing frameworks.en_US
dc.description.sponsorshipScience Foundation Ireland [18/CRT/6183, 13/RC/2106_P2, 13/RC/2094_P2]en_US
dc.description.sponsorshipThis research was supported by Science Foundation Ireland under Grant numbers 18/CRT/6183 (SFI Center for Research Training in Machine Learning) , 13/RC/2106_P2 (ADAPT Center for Digital Content Technology) , and 13/RC/2094_P2 (Lero SFI Center for Software) . For the purpose of Open Access, the author has applied a CC BY public copyright license to any Author Accepted Manuscript version arising from this submission.en_US
dc.identifier.doi10.1016/j.compbiomed.2023.107723
dc.identifier.issn0010-4825
dc.identifier.issn1879-0534
dc.identifier.pmid38000242en_US
dc.identifier.scopus2-s2.0-85177867989en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.urihttps://doi.org10.1016/j.compbiomed.2023.107723
dc.identifier.urihttps://hdl.handle.net/20.500.12713/4805
dc.identifier.volume168en_US
dc.identifier.wosWOS:001125006500001en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherPergamon-Elsevier Science Ltden_US
dc.relation.ispartofComputers In Biology and Medicineen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.snmz20240519_kaen_US
dc.subjectBrain Tumoren_US
dc.subjectDeep Learningen_US
dc.subjectImproved Chimp Optimization Algorithmen_US
dc.subjectConvolutional Neural Networken_US
dc.subjectFeature Selectionen_US
dc.titleBrain tumor segmentation based on optimized convolutional neural network and improved chimp optimization algorithmen_US
dc.typeArticleen_US

Dosyalar