Atten‐SEVNETR for volumetric segmentation of glioblastoma and interactive refinement to limit over‐segmentation

Abstract Precise localization and volumetric segmentation of glioblastoma before and after surgery are crucial for various clinical purposes, including post‐surgery treatment planning, monitoring tumour recurrence, and creating radiotherapy maps. Manual delineation is time‐consuming and prone to err...

Full description

Saved in:
Bibliographic Details
Main Authors: Swagata Kundu, Dimitrios Toumpanakis, Johan Wikstrom, Robin Strand, Ashis Kumar Dhara
Format: Article
Language:English
Published: Wiley 2024-12-01
Series:IET Image Processing
Subjects:
Online Access:https://doi.org/10.1049/ipr2.13218
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850118439921778688
author Swagata Kundu
Dimitrios Toumpanakis
Johan Wikstrom
Robin Strand
Ashis Kumar Dhara
author_facet Swagata Kundu
Dimitrios Toumpanakis
Johan Wikstrom
Robin Strand
Ashis Kumar Dhara
author_sort Swagata Kundu
collection DOAJ
description Abstract Precise localization and volumetric segmentation of glioblastoma before and after surgery are crucial for various clinical purposes, including post‐surgery treatment planning, monitoring tumour recurrence, and creating radiotherapy maps. Manual delineation is time‐consuming and prone to errors, hence the adoption of automated 3D quantification methods using deep learning algorithms from MRI scans in recent times. However, automated segmentation often leads to over‐segmentation or under‐segmentation of tumour regions. Introducing an interactive deep‐learning tool would empower radiologists to rectify these inaccuracies by adjusting the over‐segmented and under‐segmented voxels as needed. This paper proposes a network named Atten‐SEVNETR, that has a combined architecture of vision transformers and convolutional neural networks (CNN). This hybrid architecture helps to learn the input volume representation in sequences and focuses on the global multi‐scale information. An interactive graphical user interface is also developed where the initial 3D segmentation of glioblastoma can be interactively corrected to remove falsely detected spurious tumour regions. Atten‐SEVNETR is trained on BraTS training dataset and tested on BraTS validation dataset and on Uppsala University post‐operative glioblastoma dataset. The methodology outperformed state‐of‐the‐art networks like nnFormer, SwinUNet, and SwinUNETR. The mean dice score achieved is 0.7302, and the mean Hausdorff distance‐95 got is 7.78 mm for the Uppsala University dataset.
format Article
id doaj-art-94a285fc57444cabbcf8491dc28fc6e2
institution OA Journals
issn 1751-9659
1751-9667
language English
publishDate 2024-12-01
publisher Wiley
record_format Article
series IET Image Processing
spelling doaj-art-94a285fc57444cabbcf8491dc28fc6e22025-08-20T02:35:53ZengWileyIET Image Processing1751-96591751-96672024-12-0118144928494310.1049/ipr2.13218Atten‐SEVNETR for volumetric segmentation of glioblastoma and interactive refinement to limit over‐segmentationSwagata Kundu0Dimitrios Toumpanakis1Johan Wikstrom2Robin Strand3Ashis Kumar Dhara4Electrical Engineering Department National Institute of Technology Durgapur Durgapur West Bengal IndiaDepartment of Surgical Sciences Neuroradiology Uppsala University Uppsala SwedenDepartment of Surgical Sciences Neuroradiology Uppsala University Uppsala SwedenDepartment of Information Technology Centre for Image Analysis Uppsala University Uppsala SwedenElectrical Engineering Department National Institute of Technology Durgapur Durgapur West Bengal IndiaAbstract Precise localization and volumetric segmentation of glioblastoma before and after surgery are crucial for various clinical purposes, including post‐surgery treatment planning, monitoring tumour recurrence, and creating radiotherapy maps. Manual delineation is time‐consuming and prone to errors, hence the adoption of automated 3D quantification methods using deep learning algorithms from MRI scans in recent times. However, automated segmentation often leads to over‐segmentation or under‐segmentation of tumour regions. Introducing an interactive deep‐learning tool would empower radiologists to rectify these inaccuracies by adjusting the over‐segmented and under‐segmented voxels as needed. This paper proposes a network named Atten‐SEVNETR, that has a combined architecture of vision transformers and convolutional neural networks (CNN). This hybrid architecture helps to learn the input volume representation in sequences and focuses on the global multi‐scale information. An interactive graphical user interface is also developed where the initial 3D segmentation of glioblastoma can be interactively corrected to remove falsely detected spurious tumour regions. Atten‐SEVNETR is trained on BraTS training dataset and tested on BraTS validation dataset and on Uppsala University post‐operative glioblastoma dataset. The methodology outperformed state‐of‐the‐art networks like nnFormer, SwinUNet, and SwinUNETR. The mean dice score achieved is 0.7302, and the mean Hausdorff distance‐95 got is 7.78 mm for the Uppsala University dataset.https://doi.org/10.1049/ipr2.13218interactive correctionpost‐operative glioblastomavision transformervolumetric segmentation
spellingShingle Swagata Kundu
Dimitrios Toumpanakis
Johan Wikstrom
Robin Strand
Ashis Kumar Dhara
Atten‐SEVNETR for volumetric segmentation of glioblastoma and interactive refinement to limit over‐segmentation
IET Image Processing
interactive correction
post‐operative glioblastoma
vision transformer
volumetric segmentation
title Atten‐SEVNETR for volumetric segmentation of glioblastoma and interactive refinement to limit over‐segmentation
title_full Atten‐SEVNETR for volumetric segmentation of glioblastoma and interactive refinement to limit over‐segmentation
title_fullStr Atten‐SEVNETR for volumetric segmentation of glioblastoma and interactive refinement to limit over‐segmentation
title_full_unstemmed Atten‐SEVNETR for volumetric segmentation of glioblastoma and interactive refinement to limit over‐segmentation
title_short Atten‐SEVNETR for volumetric segmentation of glioblastoma and interactive refinement to limit over‐segmentation
title_sort atten sevnetr for volumetric segmentation of glioblastoma and interactive refinement to limit over segmentation
topic interactive correction
post‐operative glioblastoma
vision transformer
volumetric segmentation
url https://doi.org/10.1049/ipr2.13218
work_keys_str_mv AT swagatakundu attensevnetrforvolumetricsegmentationofglioblastomaandinteractiverefinementtolimitoversegmentation
AT dimitriostoumpanakis attensevnetrforvolumetricsegmentationofglioblastomaandinteractiverefinementtolimitoversegmentation
AT johanwikstrom attensevnetrforvolumetricsegmentationofglioblastomaandinteractiverefinementtolimitoversegmentation
AT robinstrand attensevnetrforvolumetricsegmentationofglioblastomaandinteractiverefinementtolimitoversegmentation
AT ashiskumardhara attensevnetrforvolumetricsegmentationofglioblastomaandinteractiverefinementtolimitoversegmentation