Brain Tumour Image Segmentation Using Deep Networks
Automated segmentation of brain tumour from multimodal MR images is pivotal for the analysis and monitoring of disease progression. As gliomas are malignant and heterogeneous, efficient and accurate segmentation techniques are used for the successful delineation of tumours into intra-tumoural classe...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9171998/ |
id |
doaj-c0e8389b6f194f9b992c3203f8851fef |
---|---|
record_format |
Article |
spelling |
doaj-c0e8389b6f194f9b992c3203f8851fef2021-03-30T01:52:54ZengIEEEIEEE Access2169-35362020-01-01815358915359810.1109/ACCESS.2020.30181609171998Brain Tumour Image Segmentation Using Deep NetworksMahnoor Ali0https://orcid.org/0000-0003-0702-047XSyed Omer Gilani1https://orcid.org/0000-0001-5654-7863Asim Waris2https://orcid.org/0000-0002-0190-0700Kashan Zafar3https://orcid.org/0000-0001-9797-4810Mohsin Jamil4https://orcid.org/0000-0002-8835-2451Department of Biomedical Engineering and Sciences, School of Mechanical and Manufacturing Engineering, National University of Sciences and Technology, Islamabad, PakistanDepartment of Biomedical Engineering and Sciences, School of Mechanical and Manufacturing Engineering, National University of Sciences and Technology, Islamabad, PakistanDepartment of Biomedical Engineering and Sciences, School of Mechanical and Manufacturing Engineering, National University of Sciences and Technology, Islamabad, PakistanDepartment of Biomedical Engineering and Sciences, School of Mechanical and Manufacturing Engineering, National University of Sciences and Technology, Islamabad, PakistanDepartment of Biomedical Engineering and Sciences, School of Mechanical and Manufacturing Engineering, National University of Sciences and Technology, Islamabad, PakistanAutomated segmentation of brain tumour from multimodal MR images is pivotal for the analysis and monitoring of disease progression. As gliomas are malignant and heterogeneous, efficient and accurate segmentation techniques are used for the successful delineation of tumours into intra-tumoural classes. Deep learning algorithms outperform on tasks of semantic segmentation as opposed to the more conventional, context-based computer vision approaches. Extensively used for biomedical image segmentation, Convolutional Neural Networks have significantly improved the state-of-the-art accuracy on the task of brain tumour segmentation. In this paper, we propose an ensemble of two segmentation networks: a 3D CNN and a U-Net, in a significant yet straightforward combinative technique that results in better and accurate predictions. Both models were trained separately on the BraTS-19 challenge dataset and evaluated to yield segmentation maps which considerably differed from each other in terms of segmented tumour sub-regions and were ensembled variably to achieve the final prediction. The suggested ensemble achieved dice scores of 0.750, 0.906 and 0.846 for enhancing tumour, whole tumour, and tumour core, respectively, on the validation set, performing favourably in comparison to the state-of-the-art architectures currently available.https://ieeexplore.ieee.org/document/9171998/Deep learningBraTSmedical imagingsegmentationU-NetCNN |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Mahnoor Ali Syed Omer Gilani Asim Waris Kashan Zafar Mohsin Jamil |
spellingShingle |
Mahnoor Ali Syed Omer Gilani Asim Waris Kashan Zafar Mohsin Jamil Brain Tumour Image Segmentation Using Deep Networks IEEE Access Deep learning BraTS medical imaging segmentation U-Net CNN |
author_facet |
Mahnoor Ali Syed Omer Gilani Asim Waris Kashan Zafar Mohsin Jamil |
author_sort |
Mahnoor Ali |
title |
Brain Tumour Image Segmentation Using Deep Networks |
title_short |
Brain Tumour Image Segmentation Using Deep Networks |
title_full |
Brain Tumour Image Segmentation Using Deep Networks |
title_fullStr |
Brain Tumour Image Segmentation Using Deep Networks |
title_full_unstemmed |
Brain Tumour Image Segmentation Using Deep Networks |
title_sort |
brain tumour image segmentation using deep networks |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Automated segmentation of brain tumour from multimodal MR images is pivotal for the analysis and monitoring of disease progression. As gliomas are malignant and heterogeneous, efficient and accurate segmentation techniques are used for the successful delineation of tumours into intra-tumoural classes. Deep learning algorithms outperform on tasks of semantic segmentation as opposed to the more conventional, context-based computer vision approaches. Extensively used for biomedical image segmentation, Convolutional Neural Networks have significantly improved the state-of-the-art accuracy on the task of brain tumour segmentation. In this paper, we propose an ensemble of two segmentation networks: a 3D CNN and a U-Net, in a significant yet straightforward combinative technique that results in better and accurate predictions. Both models were trained separately on the BraTS-19 challenge dataset and evaluated to yield segmentation maps which considerably differed from each other in terms of segmented tumour sub-regions and were ensembled variably to achieve the final prediction. The suggested ensemble achieved dice scores of 0.750, 0.906 and 0.846 for enhancing tumour, whole tumour, and tumour core, respectively, on the validation set, performing favourably in comparison to the state-of-the-art architectures currently available. |
topic |
Deep learning BraTS medical imaging segmentation U-Net CNN |
url |
https://ieeexplore.ieee.org/document/9171998/ |
work_keys_str_mv |
AT mahnoorali braintumourimagesegmentationusingdeepnetworks AT syedomergilani braintumourimagesegmentationusingdeepnetworks AT asimwaris braintumourimagesegmentationusingdeepnetworks AT kashanzafar braintumourimagesegmentationusingdeepnetworks AT mohsinjamil braintumourimagesegmentationusingdeepnetworks |
_version_ |
1724186256286416896 |