Self-calibrated convolution towards glioma segmentation

Bibliographic Details
Main Author: Salvagnini, Felipe C. R.
Publication Date: 2023
Other Authors: Barbosa, Gerson O., Falcao, Alexandre X. [UNESP], Santos, Cid A. N.
Format: Conference object
Language: eng
Source: Repositório Institucional da UNESP
Download full: http://dx.doi.org/10.1109/SIPAIM56729.2023.10373517
https://hdl.handle.net/11449/308428
Summary: Accurate brain tumor segmentation in the early stages of the disease is crucial for the treatment's effectiveness, avoiding exhaustive visual inspection of a qualified specialist on 3D MR brain images of multiple protocols (e.g., T1, T2, T2-FLAIR, T1-Gd). Several networks exist for Glioma segmentation, being nnU-Net one of the best. In this work, we evaluate self-calibrated convolutions in different parts of the nnU-Net network to demonstrate that self-calibrated modules in skip connections can significantly improve the enhanced-tumor and tumor-core segmentation accuracy while preserving the wholetumor segmentation accuracy.
id UNSP_8b42fb274c835d1f56990361f79bfc0a
oai_identifier_str oai:repositorio.unesp.br:11449/308428
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Self-calibrated convolution towards glioma segmentation3D Image SegmentationMedical Image AnalysisNeural NetworksAccurate brain tumor segmentation in the early stages of the disease is crucial for the treatment's effectiveness, avoiding exhaustive visual inspection of a qualified specialist on 3D MR brain images of multiple protocols (e.g., T1, T2, T2-FLAIR, T1-Gd). Several networks exist for Glioma segmentation, being nnU-Net one of the best. In this work, we evaluate self-calibrated convolutions in different parts of the nnU-Net network to demonstrate that self-calibrated modules in skip connections can significantly improve the enhanced-tumor and tumor-core segmentation accuracy while preserving the wholetumor segmentation accuracy.Eldorado Institute Computational Photography Department (DFC)State University of Campinas (UNICAMP)São Paulo State University (UNESP)São Paulo State University (UNESP)Computational Photography Department (DFC)Universidade Estadual de Campinas (UNICAMP)Universidade Estadual Paulista (UNESP)Salvagnini, Felipe C. R.Barbosa, Gerson O.Falcao, Alexandre X. [UNESP]Santos, Cid A. N.2025-04-29T20:12:32Z2023-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObjecthttp://dx.doi.org/10.1109/SIPAIM56729.2023.10373517Proceedings of the 19th International Symposium on Medical Information Processing and Analysis, SIPAIM 2023.https://hdl.handle.net/11449/30842810.1109/SIPAIM56729.2023.103735172-s2.0-85183465364Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengProceedings of the 19th International Symposium on Medical Information Processing and Analysis, SIPAIM 2023info:eu-repo/semantics/openAccess2025-04-30T13:24:13Zoai:repositorio.unesp.br:11449/308428Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestrepositoriounesp@unesp.bropendoar:29462025-04-30T13:24:13Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Self-calibrated convolution towards glioma segmentation
title Self-calibrated convolution towards glioma segmentation
spellingShingle Self-calibrated convolution towards glioma segmentation
Salvagnini, Felipe C. R.
3D Image Segmentation
Medical Image Analysis
Neural Networks
title_short Self-calibrated convolution towards glioma segmentation
title_full Self-calibrated convolution towards glioma segmentation
title_fullStr Self-calibrated convolution towards glioma segmentation
title_full_unstemmed Self-calibrated convolution towards glioma segmentation
title_sort Self-calibrated convolution towards glioma segmentation
author Salvagnini, Felipe C. R.
author_facet Salvagnini, Felipe C. R.
Barbosa, Gerson O.
Falcao, Alexandre X. [UNESP]
Santos, Cid A. N.
author_role author
author2 Barbosa, Gerson O.
Falcao, Alexandre X. [UNESP]
Santos, Cid A. N.
author2_role author
author
author
dc.contributor.none.fl_str_mv Computational Photography Department (DFC)
Universidade Estadual de Campinas (UNICAMP)
Universidade Estadual Paulista (UNESP)
dc.contributor.author.fl_str_mv Salvagnini, Felipe C. R.
Barbosa, Gerson O.
Falcao, Alexandre X. [UNESP]
Santos, Cid A. N.
dc.subject.por.fl_str_mv 3D Image Segmentation
Medical Image Analysis
Neural Networks
topic 3D Image Segmentation
Medical Image Analysis
Neural Networks
description Accurate brain tumor segmentation in the early stages of the disease is crucial for the treatment's effectiveness, avoiding exhaustive visual inspection of a qualified specialist on 3D MR brain images of multiple protocols (e.g., T1, T2, T2-FLAIR, T1-Gd). Several networks exist for Glioma segmentation, being nnU-Net one of the best. In this work, we evaluate self-calibrated convolutions in different parts of the nnU-Net network to demonstrate that self-calibrated modules in skip connections can significantly improve the enhanced-tumor and tumor-core segmentation accuracy while preserving the wholetumor segmentation accuracy.
publishDate 2023
dc.date.none.fl_str_mv 2023-01-01
2025-04-29T20:12:32Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/conferenceObject
format conferenceObject
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://dx.doi.org/10.1109/SIPAIM56729.2023.10373517
Proceedings of the 19th International Symposium on Medical Information Processing and Analysis, SIPAIM 2023.
https://hdl.handle.net/11449/308428
10.1109/SIPAIM56729.2023.10373517
2-s2.0-85183465364
url http://dx.doi.org/10.1109/SIPAIM56729.2023.10373517
https://hdl.handle.net/11449/308428
identifier_str_mv Proceedings of the 19th International Symposium on Medical Information Processing and Analysis, SIPAIM 2023.
10.1109/SIPAIM56729.2023.10373517
2-s2.0-85183465364
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Proceedings of the 19th International Symposium on Medical Information Processing and Analysis, SIPAIM 2023
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.source.none.fl_str_mv Scopus
reponame:Repositório Institucional da UNESP
instname:Universidade Estadual Paulista (UNESP)
instacron:UNESP
instname_str Universidade Estadual Paulista (UNESP)
instacron_str UNESP
institution UNESP
reponame_str Repositório Institucional da UNESP
collection Repositório Institucional da UNESP
repository.name.fl_str_mv Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)
repository.mail.fl_str_mv repositoriounesp@unesp.br
_version_ 1834482436137811968

Similar Items