AttU-NET: attention U-net for brain tumor segmentation
Tumor delineation is critical for the precise diagnosis and treatment of glioma patients. Since manual segmentation is time-consuming and tedious, automatic segmentation is desired. With the advent of convolution neural network (CNN), tremendous CNN models have been proposed for medical image segmen...
Main Authors: | , , |
---|---|
Other Authors: | , |
Format: | Conference Object |
Language: | English |
Published: |
Springer Cham
2022
|
Subjects: | |
Online Access: | https://eprints.soton.ac.uk/488815/ |
id |
ftsouthampton:oai:eprints.soton.ac.uk:488815 |
---|---|
record_format |
openpolar |
spelling |
ftsouthampton:oai:eprints.soton.ac.uk:488815 2024-05-12T08:01:24+00:00 AttU-NET: attention U-net for brain tumor segmentation Wang, Sihan Li, Lei Zhuang, Xiahai Crimi, Alessandro Bakas, Spyridon 2022-07-15 https://eprints.soton.ac.uk/488815/ English eng Springer Cham Wang, Sihan, Li, Lei and Zhuang, Xiahai (2022) AttU-NET: attention U-net for brain tumor segmentation. Crimi, Alessandro and Bakas, Spyridon (eds.) In Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 7th International Workshop, BrainLes 2021, Held in Conjunction with MICCAI 2021, Virtual Event, September 27, 2021, Revised Selected Papers, Part II. vol. 12963, Springer Cham. pp. 302-311 . (doi:10.1007/978-3-031-09002-8_27 <http://dx.doi.org/10.1007/978-3-031-09002-8_27>). Conference or Workshop Item PeerReviewed 2022 ftsouthampton https://doi.org/10.1007/978-3-031-09002-8_27 2024-04-17T14:08:58Z Tumor delineation is critical for the precise diagnosis and treatment of glioma patients. Since manual segmentation is time-consuming and tedious, automatic segmentation is desired. With the advent of convolution neural network (CNN), tremendous CNN models have been proposed for medical image segmentation. However, the small size of kernel limits the shape of the receptive view, omitting the global information. To utilize the intrinsic features of brain anatomical structure, we propose a modified U-Net with an attention block (AttU-Net) to tract the complementary information from the whole image. The proposed attention block can be easily added to any segmentation backbones, which improved the Dice score by 5%. We evaluated our approach on the dataset of BraTS 2021 challenge and achieved promising performance on this dataset. The Dice scores of enhancing tumor, tumor core, and whole tumor segmentation are 0.793, 0.819, and 0.879, respectively. Conference Object Attu University of Southampton: e-Prints Soton 302 311 |
institution |
Open Polar |
collection |
University of Southampton: e-Prints Soton |
op_collection_id |
ftsouthampton |
language |
English |
description |
Tumor delineation is critical for the precise diagnosis and treatment of glioma patients. Since manual segmentation is time-consuming and tedious, automatic segmentation is desired. With the advent of convolution neural network (CNN), tremendous CNN models have been proposed for medical image segmentation. However, the small size of kernel limits the shape of the receptive view, omitting the global information. To utilize the intrinsic features of brain anatomical structure, we propose a modified U-Net with an attention block (AttU-Net) to tract the complementary information from the whole image. The proposed attention block can be easily added to any segmentation backbones, which improved the Dice score by 5%. We evaluated our approach on the dataset of BraTS 2021 challenge and achieved promising performance on this dataset. The Dice scores of enhancing tumor, tumor core, and whole tumor segmentation are 0.793, 0.819, and 0.879, respectively. |
author2 |
Crimi, Alessandro Bakas, Spyridon |
format |
Conference Object |
author |
Wang, Sihan Li, Lei Zhuang, Xiahai |
spellingShingle |
Wang, Sihan Li, Lei Zhuang, Xiahai AttU-NET: attention U-net for brain tumor segmentation |
author_facet |
Wang, Sihan Li, Lei Zhuang, Xiahai |
author_sort |
Wang, Sihan |
title |
AttU-NET: attention U-net for brain tumor segmentation |
title_short |
AttU-NET: attention U-net for brain tumor segmentation |
title_full |
AttU-NET: attention U-net for brain tumor segmentation |
title_fullStr |
AttU-NET: attention U-net for brain tumor segmentation |
title_full_unstemmed |
AttU-NET: attention U-net for brain tumor segmentation |
title_sort |
attu-net: attention u-net for brain tumor segmentation |
publisher |
Springer Cham |
publishDate |
2022 |
url |
https://eprints.soton.ac.uk/488815/ |
genre |
Attu |
genre_facet |
Attu |
op_relation |
Wang, Sihan, Li, Lei and Zhuang, Xiahai (2022) AttU-NET: attention U-net for brain tumor segmentation. Crimi, Alessandro and Bakas, Spyridon (eds.) In Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 7th International Workshop, BrainLes 2021, Held in Conjunction with MICCAI 2021, Virtual Event, September 27, 2021, Revised Selected Papers, Part II. vol. 12963, Springer Cham. pp. 302-311 . (doi:10.1007/978-3-031-09002-8_27 <http://dx.doi.org/10.1007/978-3-031-09002-8_27>). |
op_doi |
https://doi.org/10.1007/978-3-031-09002-8_27 |
container_start_page |
302 |
op_container_end_page |
311 |
_version_ |
1798843533281460224 |