Brain Tumour Segmentation Using Choquet Integrals and Coalition Game

Artificial Intelligence (AI) and computer-aided diagnosis (CAD) have revolutionised various aspects of modern life, particularly in the medical domain. These technologies enable efficient solutions for complex challenges, such as accurately segmenting brain tumour regions, which significantly aid me...

Full description

Saved in:
Bibliographic Details
Main Authors: Makhlouf Derdour, Mohammed El Bachir Yahiaoui, Moustafa Sadek Kahil, Mohamed Gasmi, Mohamed Chahine Ghanem
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Information
Subjects:
Online Access:https://www.mdpi.com/2078-2489/16/7/615
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850077124324491264
author Makhlouf Derdour
Mohammed El Bachir Yahiaoui
Moustafa Sadek Kahil
Mohamed Gasmi
Mohamed Chahine Ghanem
author_facet Makhlouf Derdour
Mohammed El Bachir Yahiaoui
Moustafa Sadek Kahil
Mohamed Gasmi
Mohamed Chahine Ghanem
author_sort Makhlouf Derdour
collection DOAJ
description Artificial Intelligence (AI) and computer-aided diagnosis (CAD) have revolutionised various aspects of modern life, particularly in the medical domain. These technologies enable efficient solutions for complex challenges, such as accurately segmenting brain tumour regions, which significantly aid medical professionals in monitoring and treating patients. This research focuses on segmenting glioma brain tumour lesions in MRI images by analysing them at the pixel level. The aim is to develop a deep learning-based approach that enables ensemble learning to achieve precise and consistent segmentation of brain tumours. While many studies have explored ensemble learning techniques in this area, most rely on aggregation functions like the Weighted Arithmetic Mean (WAM) without accounting for the interdependencies between classifier subsets. To address this limitation, the Choquet integral is employed for ensemble learning, along with a novel evaluation framework for fuzzy measures. This framework integrates coalition game theory, information theory, and Lambda fuzzy approximation. Three distinct fuzzy measure sets are computed using different weighting strategies informed by these theories. Based on these measures, three Choquet integrals are calculated for segmenting different components of brain lesions, and their outputs are subsequently combined. The BraTS-2020 online validation dataset is used to validate the proposed approach. Results demonstrate superior performance compared with several recent methods, achieving Dice Similarity Coefficients of 0.896, 0.851, and 0.792 and 95% Hausdorff distances of 5.96 mm, 6.65 mm, and 20.74 mm for the whole tumour, tumour core, and enhancing tumour core, respectively.
format Article
id doaj-art-ca5ffa3b0e1a44939c5dfc35dcb40326
institution DOAJ
issn 2078-2489
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Information
spelling doaj-art-ca5ffa3b0e1a44939c5dfc35dcb403262025-08-20T02:45:52ZengMDPI AGInformation2078-24892025-07-0116761510.3390/info16070615Brain Tumour Segmentation Using Choquet Integrals and Coalition GameMakhlouf Derdour0Mohammed El Bachir Yahiaoui1Moustafa Sadek Kahil2Mohamed Gasmi3Mohamed Chahine Ghanem4Artificial Intelligence and Autonomous Things Laboratory, Larbi Ben M’hidi University of Oum El Bouaghi, Oum el Bouaghi 04000, AlgeriaLaboratory of Mathematics, Informatics and Systems, Larbi Tebessi University of Tebessa, Tebessa 12022, AlgeriaArtificial Intelligence and Autonomous Things Laboratory, Larbi Ben M’hidi University of Oum El Bouaghi, Oum el Bouaghi 04000, AlgeriaLaboratory of Mathematics, Informatics and Systems, Larbi Tebessi University of Tebessa, Tebessa 12022, AlgeriaDepartment of Computer Science, University of Liverpool, Liverpool L69 7ZX, UKArtificial Intelligence (AI) and computer-aided diagnosis (CAD) have revolutionised various aspects of modern life, particularly in the medical domain. These technologies enable efficient solutions for complex challenges, such as accurately segmenting brain tumour regions, which significantly aid medical professionals in monitoring and treating patients. This research focuses on segmenting glioma brain tumour lesions in MRI images by analysing them at the pixel level. The aim is to develop a deep learning-based approach that enables ensemble learning to achieve precise and consistent segmentation of brain tumours. While many studies have explored ensemble learning techniques in this area, most rely on aggregation functions like the Weighted Arithmetic Mean (WAM) without accounting for the interdependencies between classifier subsets. To address this limitation, the Choquet integral is employed for ensemble learning, along with a novel evaluation framework for fuzzy measures. This framework integrates coalition game theory, information theory, and Lambda fuzzy approximation. Three distinct fuzzy measure sets are computed using different weighting strategies informed by these theories. Based on these measures, three Choquet integrals are calculated for segmenting different components of brain lesions, and their outputs are subsequently combined. The BraTS-2020 online validation dataset is used to validate the proposed approach. Results demonstrate superior performance compared with several recent methods, achieving Dice Similarity Coefficients of 0.896, 0.851, and 0.792 and 95% Hausdorff distances of 5.96 mm, 6.65 mm, and 20.74 mm for the whole tumour, tumour core, and enhancing tumour core, respectively.https://www.mdpi.com/2078-2489/16/7/615brain cancerMRIChoquet integralcoalition game theorydeep learningmedical imaging
spellingShingle Makhlouf Derdour
Mohammed El Bachir Yahiaoui
Moustafa Sadek Kahil
Mohamed Gasmi
Mohamed Chahine Ghanem
Brain Tumour Segmentation Using Choquet Integrals and Coalition Game
Information
brain cancer
MRI
Choquet integral
coalition game theory
deep learning
medical imaging
title Brain Tumour Segmentation Using Choquet Integrals and Coalition Game
title_full Brain Tumour Segmentation Using Choquet Integrals and Coalition Game
title_fullStr Brain Tumour Segmentation Using Choquet Integrals and Coalition Game
title_full_unstemmed Brain Tumour Segmentation Using Choquet Integrals and Coalition Game
title_short Brain Tumour Segmentation Using Choquet Integrals and Coalition Game
title_sort brain tumour segmentation using choquet integrals and coalition game
topic brain cancer
MRI
Choquet integral
coalition game theory
deep learning
medical imaging
url https://www.mdpi.com/2078-2489/16/7/615
work_keys_str_mv AT makhloufderdour braintumoursegmentationusingchoquetintegralsandcoalitiongame
AT mohammedelbachiryahiaoui braintumoursegmentationusingchoquetintegralsandcoalitiongame
AT moustafasadekkahil braintumoursegmentationusingchoquetintegralsandcoalitiongame
AT mohamedgasmi braintumoursegmentationusingchoquetintegralsandcoalitiongame
AT mohamedchahineghanem braintumoursegmentationusingchoquetintegralsandcoalitiongame