MMGan: a multimodal MR brain tumor image segmentation method
Computer-aided diagnosis has emerged as a rapidly evolving field, garnering increased attention in recent years. At the forefront of this field is the segmentation of lesions in medical images, which is a critical preliminary stage in subsequent treatment procedures. Among the most challenging tasks...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2023-12-01
|
Series: | Frontiers in Human Neuroscience |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fnhum.2023.1275795/full |
_version_ | 1797404553740550144 |
---|---|
author | Leiyi Gao Jiao Li Ruixin Zhang Hailu Hanna Bekele Junzhu Wang Yining Cheng Hongxia Deng |
author_facet | Leiyi Gao Jiao Li Ruixin Zhang Hailu Hanna Bekele Junzhu Wang Yining Cheng Hongxia Deng |
author_sort | Leiyi Gao |
collection | DOAJ |
description | Computer-aided diagnosis has emerged as a rapidly evolving field, garnering increased attention in recent years. At the forefront of this field is the segmentation of lesions in medical images, which is a critical preliminary stage in subsequent treatment procedures. Among the most challenging tasks in medical image analysis is the accurate and automated segmentation of brain tumors in various modalities of brain tumor MRI. In this article, we present a novel end-to-end network architecture called MMGan, which combines the advantages of residual learning and generative adversarial neural networks inspired by classical generative adversarial networks. The segmenter in the MMGan network, which has a U-Net architecture, is constructed using a deep residual network instead of the conventional convolutional neural network. The dataset used for this study is the BRATS dataset from the Brain Tumor Segmentation Challenge at the Medical Image Computing and Computer Assisted Intervention Society. Our proposed method has been extensively tested, and the results indicate that this MMGan framework is more efficient and stable for segmentation tasks. On BRATS 2019, the segmentation algorithm improved accuracy and sensitivity in whole tumor, tumor core, and enhanced tumor segmentation. Particularly noteworthy is the higher dice score of 0.86 achieved by our proposed method in tumor core segmentation, surpassing those of stateof-the-art models. This study improves the accuracy and sensitivity of the tumor segmentation task, which we believe is significant for medical image analysis. And it should be further improved by replacing different loss functions such as cross-entropy loss function and other methods. |
first_indexed | 2024-03-09T02:56:41Z |
format | Article |
id | doaj.art-0bd9f22df8504793aab65a306a1cf900 |
institution | Directory Open Access Journal |
issn | 1662-5161 |
language | English |
last_indexed | 2024-03-09T02:56:41Z |
publishDate | 2023-12-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Human Neuroscience |
spelling | doaj.art-0bd9f22df8504793aab65a306a1cf9002023-12-05T04:17:23ZengFrontiers Media S.A.Frontiers in Human Neuroscience1662-51612023-12-011710.3389/fnhum.2023.12757951275795MMGan: a multimodal MR brain tumor image segmentation methodLeiyi GaoJiao LiRuixin ZhangHailu Hanna BekeleJunzhu WangYining ChengHongxia DengComputer-aided diagnosis has emerged as a rapidly evolving field, garnering increased attention in recent years. At the forefront of this field is the segmentation of lesions in medical images, which is a critical preliminary stage in subsequent treatment procedures. Among the most challenging tasks in medical image analysis is the accurate and automated segmentation of brain tumors in various modalities of brain tumor MRI. In this article, we present a novel end-to-end network architecture called MMGan, which combines the advantages of residual learning and generative adversarial neural networks inspired by classical generative adversarial networks. The segmenter in the MMGan network, which has a U-Net architecture, is constructed using a deep residual network instead of the conventional convolutional neural network. The dataset used for this study is the BRATS dataset from the Brain Tumor Segmentation Challenge at the Medical Image Computing and Computer Assisted Intervention Society. Our proposed method has been extensively tested, and the results indicate that this MMGan framework is more efficient and stable for segmentation tasks. On BRATS 2019, the segmentation algorithm improved accuracy and sensitivity in whole tumor, tumor core, and enhanced tumor segmentation. Particularly noteworthy is the higher dice score of 0.86 achieved by our proposed method in tumor core segmentation, surpassing those of stateof-the-art models. This study improves the accuracy and sensitivity of the tumor segmentation task, which we believe is significant for medical image analysis. And it should be further improved by replacing different loss functions such as cross-entropy loss function and other methods.https://www.frontiersin.org/articles/10.3389/fnhum.2023.1275795/fullimage segmentationbrain tumormulti-modalitypretreatmentdepth residual structuregenerative adversarial networks |
spellingShingle | Leiyi Gao Jiao Li Ruixin Zhang Hailu Hanna Bekele Junzhu Wang Yining Cheng Hongxia Deng MMGan: a multimodal MR brain tumor image segmentation method Frontiers in Human Neuroscience image segmentation brain tumor multi-modality pretreatment depth residual structure generative adversarial networks |
title | MMGan: a multimodal MR brain tumor image segmentation method |
title_full | MMGan: a multimodal MR brain tumor image segmentation method |
title_fullStr | MMGan: a multimodal MR brain tumor image segmentation method |
title_full_unstemmed | MMGan: a multimodal MR brain tumor image segmentation method |
title_short | MMGan: a multimodal MR brain tumor image segmentation method |
title_sort | mmgan a multimodal mr brain tumor image segmentation method |
topic | image segmentation brain tumor multi-modality pretreatment depth residual structure generative adversarial networks |
url | https://www.frontiersin.org/articles/10.3389/fnhum.2023.1275795/full |
work_keys_str_mv | AT leiyigao mmganamultimodalmrbraintumorimagesegmentationmethod AT jiaoli mmganamultimodalmrbraintumorimagesegmentationmethod AT ruixinzhang mmganamultimodalmrbraintumorimagesegmentationmethod AT hailuhannabekele mmganamultimodalmrbraintumorimagesegmentationmethod AT junzhuwang mmganamultimodalmrbraintumorimagesegmentationmethod AT yiningcheng mmganamultimodalmrbraintumorimagesegmentationmethod AT hongxiadeng mmganamultimodalmrbraintumorimagesegmentationmethod |