dc.contributor.author |
Ahmad, Parvez |
|
dc.contributor.author |
Jin, Hai |
|
dc.contributor.author |
Qamar, Saqib |
|
dc.contributor.author |
Zheng, Ran |
|
dc.contributor.author |
Saeed, Adnan |
|
dc.date.accessioned |
2024-06-07T03:25:24Z |
|
dc.date.available |
2024-06-07T03:25:24Z |
|
dc.date.issued |
2021-07 |
|
dc.identifier.citation |
(2021). Multimedia Tools and Applications, 80(18), 27069-27094. |
|
dc.identifier.issn |
1380-7501 |
|
dc.identifier.uri |
https://hdl.handle.net/2292/68696 |
|
dc.description.abstract |
The variations among shapes, sizes, and locations of tumors are obstacles for accurate automatic segmentation. U-Net is a simplified approach for automatic segmentation. Generally, the convolutional or the dilated convolutional layers are used for brain tumor segmentation. However, existing segmentation methods of the significant dilation rates degrade the final accuracy. Moreover, tuning parameters and imbalance ratio between the different tumor classes are the issues for segmentation. The proposed model, known as Residual-Dilated Dense Atrous-Spatial Pyramid Pooling (RD2A) 3D U-Net, is found adequate to solve these issues. The RD2A is the combination of the residual connections, dilation, and dense ASPP to preserve more contextual information of small sizes of tumors at each level encoder path. The multi-scale contextual information minimizes the ambiguities among the tissues of the white matter (WM) and gray matter (GM) of the infant’s brain MRI. The BRATS 2018, BRATS 2019, and iSeg-2019 datasets are used on different evaluation metrics to validate the RD2A. In the BRATS 2018 validation dataset, the proposed model achieves the average dice scores of 90.88, 84.46, and 78.18 for the whole tumor, the tumor core, and the enhancing tumor, respectively. We also evaluated on iSeg-2019 testing set, where the proposed approach achieves the average dice scores of 79.804, 77.925, and 80.569 for the cerebrospinal fluid (CSF), the gray matter (GM), and the white matter (WM), respectively. Furthermore, the presented work also obtains the mean dice scores of 90.35, 82.34, and 71.93 for the whole tumor, the tumor core, and the enhancing tumor, respectively on the BRATS 2019 validation dataset. Experimentally, it is found that the proposed approach is ideal for exploiting the full contextual information of the 3D brain MRI datasets. |
|
dc.language |
en |
|
dc.publisher |
Springer Nature |
|
dc.relation.ispartofseries |
Multimedia Tools and Applications |
|
dc.rights |
Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated. Previously published items are made available in accordance with the copyright policy of the publisher. |
|
dc.rights.uri |
https://researchspace.auckland.ac.nz/docs/uoa-docs/rights.htm |
|
dc.subject |
46 Information and Computing Sciences |
|
dc.subject |
4603 Computer Vision and Multimedia Computation |
|
dc.subject |
Cancer |
|
dc.subject |
Biomedical Imaging |
|
dc.subject |
Neurosciences |
|
dc.subject |
3 Good Health and Well Being |
|
dc.subject |
0801 Artificial Intelligence and Image Processing |
|
dc.subject |
0803 Computer Software |
|
dc.subject |
0805 Distributed Computing |
|
dc.subject |
0806 Information Systems |
|
dc.subject |
4009 Electronics, sensors and digital hardware |
|
dc.subject |
4605 Data management and data science |
|
dc.subject |
4606 Distributed computing and systems software |
|
dc.title |
RD2A: densely connected residual networks using ASPP for brain tumor segmentation |
|
dc.type |
Journal Article |
|
dc.identifier.doi |
10.1007/s11042-021-10915-y |
|
pubs.issue |
18 |
|
pubs.begin-page |
27069 |
|
pubs.volume |
80 |
|
dc.date.updated |
2024-05-31T06:23:47Z |
|
dc.rights.holder |
Copyright: The authors |
en |
pubs.end-page |
27094 |
|
pubs.publication-status |
Published |
|
dc.rights.accessrights |
http://purl.org/eprint/accessRights/RetrictedAccess |
en |
pubs.subtype |
Journal Article |
|
pubs.elements-id |
1029145 |
|
pubs.org-id |
Bioengineering Institute |
|
dc.identifier.eissn |
1573-7721 |
|
pubs.record-created-at-source-date |
2024-05-31 |
|
pubs.online-publication-date |
2021-05-13 |
|