Cargando…

Target area distillation and section attention segmentation network for accurate 3D medical image segmentation

3D medical image segmentation has an essential role in medical image analysis, while attention mechanism has improved the performance by a large margin. However, existing methods obtained the attention coefficient in a small receptive field, resulting in possible performance limitations. Radiologist...

Descripción completa

Detalles Bibliográficos
Autores principales: Xie, Ruiwei, Pan, Dan, Zeng, An, Xu, Xiaowei, Wang, Tianchen, Ullah, Najeeb, Ji, Yuzhu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer International Publishing 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9884720/
https://www.ncbi.nlm.nih.gov/pubmed/36721638
http://dx.doi.org/10.1007/s13755-022-00200-z
_version_ 1784879780249731072
author Xie, Ruiwei
Pan, Dan
Zeng, An
Xu, Xiaowei
Wang, Tianchen
Ullah, Najeeb
Ji, Yuzhu
author_facet Xie, Ruiwei
Pan, Dan
Zeng, An
Xu, Xiaowei
Wang, Tianchen
Ullah, Najeeb
Ji, Yuzhu
author_sort Xie, Ruiwei
collection PubMed
description 3D medical image segmentation has an essential role in medical image analysis, while attention mechanism has improved the performance by a large margin. However, existing methods obtained the attention coefficient in a small receptive field, resulting in possible performance limitations. Radiologists usually scan all the slices first to have an overall idea of the target, and then analyze regions of interest in multiple 2D views in clinic practice. We simulate radiologists’ recognition process and propose to exploit the 3D context information in a deeper manner for accurate 3D medical images segmentation. Due to the similarity of human body structure, medical images of different populations have highly similar shape and location information, so we use target region distillation to extract the common segmented region information. Particularly, we proposed two optimizations including Target Area Distillation and Section Attention. Target Area Distillation adds positions information to the original input to let the network has an initial attention of the target, while section attention performs attention extraction in three 2D sections thus with large range of receptive field. We compare our method against several popular networks in two public datasets including ImageCHD and COVID-19. Experimental results show that our proposed method improves the segmentation Dice score by 2–4% over the state-of-the-art methods. Our code has been released to the public (Anonymous link).
format Online
Article
Text
id pubmed-9884720
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Springer International Publishing
record_format MEDLINE/PubMed
spelling pubmed-98847202023-01-30 Target area distillation and section attention segmentation network for accurate 3D medical image segmentation Xie, Ruiwei Pan, Dan Zeng, An Xu, Xiaowei Wang, Tianchen Ullah, Najeeb Ji, Yuzhu Health Inf Sci Syst Research 3D medical image segmentation has an essential role in medical image analysis, while attention mechanism has improved the performance by a large margin. However, existing methods obtained the attention coefficient in a small receptive field, resulting in possible performance limitations. Radiologists usually scan all the slices first to have an overall idea of the target, and then analyze regions of interest in multiple 2D views in clinic practice. We simulate radiologists’ recognition process and propose to exploit the 3D context information in a deeper manner for accurate 3D medical images segmentation. Due to the similarity of human body structure, medical images of different populations have highly similar shape and location information, so we use target region distillation to extract the common segmented region information. Particularly, we proposed two optimizations including Target Area Distillation and Section Attention. Target Area Distillation adds positions information to the original input to let the network has an initial attention of the target, while section attention performs attention extraction in three 2D sections thus with large range of receptive field. We compare our method against several popular networks in two public datasets including ImageCHD and COVID-19. Experimental results show that our proposed method improves the segmentation Dice score by 2–4% over the state-of-the-art methods. Our code has been released to the public (Anonymous link). Springer International Publishing 2023-01-30 /pmc/articles/PMC9884720/ /pubmed/36721638 http://dx.doi.org/10.1007/s13755-022-00200-z Text en © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2022, Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
spellingShingle Research
Xie, Ruiwei
Pan, Dan
Zeng, An
Xu, Xiaowei
Wang, Tianchen
Ullah, Najeeb
Ji, Yuzhu
Target area distillation and section attention segmentation network for accurate 3D medical image segmentation
title Target area distillation and section attention segmentation network for accurate 3D medical image segmentation
title_full Target area distillation and section attention segmentation network for accurate 3D medical image segmentation
title_fullStr Target area distillation and section attention segmentation network for accurate 3D medical image segmentation
title_full_unstemmed Target area distillation and section attention segmentation network for accurate 3D medical image segmentation
title_short Target area distillation and section attention segmentation network for accurate 3D medical image segmentation
title_sort target area distillation and section attention segmentation network for accurate 3d medical image segmentation
topic Research
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9884720/
https://www.ncbi.nlm.nih.gov/pubmed/36721638
http://dx.doi.org/10.1007/s13755-022-00200-z
work_keys_str_mv AT xieruiwei targetareadistillationandsectionattentionsegmentationnetworkforaccurate3dmedicalimagesegmentation
AT pandan targetareadistillationandsectionattentionsegmentationnetworkforaccurate3dmedicalimagesegmentation
AT zengan targetareadistillationandsectionattentionsegmentationnetworkforaccurate3dmedicalimagesegmentation
AT xuxiaowei targetareadistillationandsectionattentionsegmentationnetworkforaccurate3dmedicalimagesegmentation
AT wangtianchen targetareadistillationandsectionattentionsegmentationnetworkforaccurate3dmedicalimagesegmentation
AT ullahnajeeb targetareadistillationandsectionattentionsegmentationnetworkforaccurate3dmedicalimagesegmentation
AT jiyuzhu targetareadistillationandsectionattentionsegmentationnetworkforaccurate3dmedicalimagesegmentation