Predicting Regions of Local Recurrence in Glioblastomas Using Voxel-Based Radiomic Features of Multiparametric Postoperative MRI

The globally accepted surgical strategy in glioblastomas is removing the enhancing tumor. However, the peritumoral region harbors infiltration areas responsible for future tumor recurrence. This study aimed to evaluate a predictive model that identifies areas of future recurrence using a voxel-based...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cepeda, Santiago, Luppino, Luigi Tommaso, Pérez-Núñez, Angel, Solheim, Ole Skeidsvoll, García-García, Sergio, Velasco-Casares, María, Karlberg, Anna Maria, Eikenes, Live, Sarabia, Rosario, Arrese, Ignacio, Zamora, Tomás, Gonzalez, Pedro, Jiménez-Roldán, Luis, Kuttner, Samuel
Format: Artikel
Sprache:eng
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Cepeda, Santiago
Luppino, Luigi Tommaso
Pérez-Núñez, Angel
Solheim, Ole Skeidsvoll
García-García, Sergio
Velasco-Casares, María
Karlberg, Anna Maria
Eikenes, Live
Sarabia, Rosario
Arrese, Ignacio
Zamora, Tomás
Gonzalez, Pedro
Jiménez-Roldán, Luis
Kuttner, Samuel
description The globally accepted surgical strategy in glioblastomas is removing the enhancing tumor. However, the peritumoral region harbors infiltration areas responsible for future tumor recurrence. This study aimed to evaluate a predictive model that identifies areas of future recurrence using a voxel-based radiomics analysis of magnetic resonance imaging (MRI) data. This multi-institutional study included a retrospective analysis of patients diagnosed with glioblastoma who underwent surgery with complete resection of the enhancing tumor. Fifty-five patients met the selection criteria. The study sample was split into training (N = 40) and testing (N = 15) datasets. Follow-up MRI was used for ground truth definition, and postoperative structural multiparametric MRI was used to extract voxel-based radiomic features. Deformable coregistration was used to register the MRI sequences for each patient, followed by segmentation of the peritumoral region in the postoperative scan and the enhancing tumor in the follow-up scan. Peritumoral voxels overlapping with enhancing tumor voxels were labeled as recurrence, while non-overlapping voxels were labeled as nonrecurrence. Voxel-based radiomic features were extracted from the peritumoral region. Four machine learning-based classifiers were trained for recurrence prediction. A region-based evaluation approach was used for model evaluation. The Categorical Boosting (CatBoost) classifier obtained the best performance on the testing dataset with an average area under the curve (AUC) of 0.81 ± 0.09 and an accuracy of 0.84 ± 0.06, using region-based evaluation. There was a clear visual correspondence between predicted and actual recurrence regions. We have developed a method that accurately predicts the region of future tumor recurrence in MRI scans of glioblastoma patients. This could enable the adaptation of surgical and radiotherapy treatment to these areas to potentially prolong the survival of these patients.
format Article
fullrecord <record><control><sourceid>cristin_3HK</sourceid><recordid>TN_cdi_cristin_nora_11250_3079719</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>11250_3079719</sourcerecordid><originalsourceid>FETCH-cristin_nora_11250_30797193</originalsourceid><addsrcrecordid>eNqNjsEKwkAMRHvxIOo_xA8otIqIV8WqYEGKei1xG0tguynZrXj0063iB3gamJk3zDB6nZQqNoFdDQXVLM6D3OEoBm1vmE6VnCFgBzvLcrPogzTo4eI_yFWeZOM1eqqgwIqlYQMZYeiUvkN5ZwO3qNhQ0D47Sc-3pBj4QZAXh3E0uKP1NPnpKJpm2_NmHxtl398qnSiWaTpbJOU8Wa6W6Wr-T-cN8X5InQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Predicting Regions of Local Recurrence in Glioblastomas Using Voxel-Based Radiomic Features of Multiparametric Postoperative MRI</title><source>NORA - Norwegian Open Research Archives</source><creator>Cepeda, Santiago ; Luppino, Luigi Tommaso ; Pérez-Núñez, Angel ; Solheim, Ole Skeidsvoll ; García-García, Sergio ; Velasco-Casares, María ; Karlberg, Anna Maria ; Eikenes, Live ; Sarabia, Rosario ; Arrese, Ignacio ; Zamora, Tomás ; Gonzalez, Pedro ; Jiménez-Roldán, Luis ; Kuttner, Samuel</creator><creatorcontrib>Cepeda, Santiago ; Luppino, Luigi Tommaso ; Pérez-Núñez, Angel ; Solheim, Ole Skeidsvoll ; García-García, Sergio ; Velasco-Casares, María ; Karlberg, Anna Maria ; Eikenes, Live ; Sarabia, Rosario ; Arrese, Ignacio ; Zamora, Tomás ; Gonzalez, Pedro ; Jiménez-Roldán, Luis ; Kuttner, Samuel</creatorcontrib><description>The globally accepted surgical strategy in glioblastomas is removing the enhancing tumor. However, the peritumoral region harbors infiltration areas responsible for future tumor recurrence. This study aimed to evaluate a predictive model that identifies areas of future recurrence using a voxel-based radiomics analysis of magnetic resonance imaging (MRI) data. This multi-institutional study included a retrospective analysis of patients diagnosed with glioblastoma who underwent surgery with complete resection of the enhancing tumor. Fifty-five patients met the selection criteria. The study sample was split into training (N = 40) and testing (N = 15) datasets. Follow-up MRI was used for ground truth definition, and postoperative structural multiparametric MRI was used to extract voxel-based radiomic features. Deformable coregistration was used to register the MRI sequences for each patient, followed by segmentation of the peritumoral region in the postoperative scan and the enhancing tumor in the follow-up scan. Peritumoral voxels overlapping with enhancing tumor voxels were labeled as recurrence, while non-overlapping voxels were labeled as nonrecurrence. Voxel-based radiomic features were extracted from the peritumoral region. Four machine learning-based classifiers were trained for recurrence prediction. A region-based evaluation approach was used for model evaluation. The Categorical Boosting (CatBoost) classifier obtained the best performance on the testing dataset with an average area under the curve (AUC) of 0.81 ± 0.09 and an accuracy of 0.84 ± 0.06, using region-based evaluation. There was a clear visual correspondence between predicted and actual recurrence regions. We have developed a method that accurately predicts the region of future tumor recurrence in MRI scans of glioblastoma patients. This could enable the adaptation of surgical and radiotherapy treatment to these areas to potentially prolong the survival of these patients.</description><language>eng</language><publisher>MDPI</publisher><creationdate>2023</creationdate><rights>info:eu-repo/semantics/openAccess</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,776,881,26544</link.rule.ids><linktorsrc>$$Uhttp://hdl.handle.net/11250/3079719$$EView_record_in_NORA$$FView_record_in_$$GNORA$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Cepeda, Santiago</creatorcontrib><creatorcontrib>Luppino, Luigi Tommaso</creatorcontrib><creatorcontrib>Pérez-Núñez, Angel</creatorcontrib><creatorcontrib>Solheim, Ole Skeidsvoll</creatorcontrib><creatorcontrib>García-García, Sergio</creatorcontrib><creatorcontrib>Velasco-Casares, María</creatorcontrib><creatorcontrib>Karlberg, Anna Maria</creatorcontrib><creatorcontrib>Eikenes, Live</creatorcontrib><creatorcontrib>Sarabia, Rosario</creatorcontrib><creatorcontrib>Arrese, Ignacio</creatorcontrib><creatorcontrib>Zamora, Tomás</creatorcontrib><creatorcontrib>Gonzalez, Pedro</creatorcontrib><creatorcontrib>Jiménez-Roldán, Luis</creatorcontrib><creatorcontrib>Kuttner, Samuel</creatorcontrib><title>Predicting Regions of Local Recurrence in Glioblastomas Using Voxel-Based Radiomic Features of Multiparametric Postoperative MRI</title><description>The globally accepted surgical strategy in glioblastomas is removing the enhancing tumor. However, the peritumoral region harbors infiltration areas responsible for future tumor recurrence. This study aimed to evaluate a predictive model that identifies areas of future recurrence using a voxel-based radiomics analysis of magnetic resonance imaging (MRI) data. This multi-institutional study included a retrospective analysis of patients diagnosed with glioblastoma who underwent surgery with complete resection of the enhancing tumor. Fifty-five patients met the selection criteria. The study sample was split into training (N = 40) and testing (N = 15) datasets. Follow-up MRI was used for ground truth definition, and postoperative structural multiparametric MRI was used to extract voxel-based radiomic features. Deformable coregistration was used to register the MRI sequences for each patient, followed by segmentation of the peritumoral region in the postoperative scan and the enhancing tumor in the follow-up scan. Peritumoral voxels overlapping with enhancing tumor voxels were labeled as recurrence, while non-overlapping voxels were labeled as nonrecurrence. Voxel-based radiomic features were extracted from the peritumoral region. Four machine learning-based classifiers were trained for recurrence prediction. A region-based evaluation approach was used for model evaluation. The Categorical Boosting (CatBoost) classifier obtained the best performance on the testing dataset with an average area under the curve (AUC) of 0.81 ± 0.09 and an accuracy of 0.84 ± 0.06, using region-based evaluation. There was a clear visual correspondence between predicted and actual recurrence regions. We have developed a method that accurately predicts the region of future tumor recurrence in MRI scans of glioblastoma patients. This could enable the adaptation of surgical and radiotherapy treatment to these areas to potentially prolong the survival of these patients.</description><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>3HK</sourceid><recordid>eNqNjsEKwkAMRHvxIOo_xA8otIqIV8WqYEGKei1xG0tguynZrXj0063iB3gamJk3zDB6nZQqNoFdDQXVLM6D3OEoBm1vmE6VnCFgBzvLcrPogzTo4eI_yFWeZOM1eqqgwIqlYQMZYeiUvkN5ZwO3qNhQ0D47Sc-3pBj4QZAXh3E0uKP1NPnpKJpm2_NmHxtl398qnSiWaTpbJOU8Wa6W6Wr-T-cN8X5InQ</recordid><startdate>2023</startdate><enddate>2023</enddate><creator>Cepeda, Santiago</creator><creator>Luppino, Luigi Tommaso</creator><creator>Pérez-Núñez, Angel</creator><creator>Solheim, Ole Skeidsvoll</creator><creator>García-García, Sergio</creator><creator>Velasco-Casares, María</creator><creator>Karlberg, Anna Maria</creator><creator>Eikenes, Live</creator><creator>Sarabia, Rosario</creator><creator>Arrese, Ignacio</creator><creator>Zamora, Tomás</creator><creator>Gonzalez, Pedro</creator><creator>Jiménez-Roldán, Luis</creator><creator>Kuttner, Samuel</creator><general>MDPI</general><scope>3HK</scope></search><sort><creationdate>2023</creationdate><title>Predicting Regions of Local Recurrence in Glioblastomas Using Voxel-Based Radiomic Features of Multiparametric Postoperative MRI</title><author>Cepeda, Santiago ; Luppino, Luigi Tommaso ; Pérez-Núñez, Angel ; Solheim, Ole Skeidsvoll ; García-García, Sergio ; Velasco-Casares, María ; Karlberg, Anna Maria ; Eikenes, Live ; Sarabia, Rosario ; Arrese, Ignacio ; Zamora, Tomás ; Gonzalez, Pedro ; Jiménez-Roldán, Luis ; Kuttner, Samuel</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-cristin_nora_11250_30797193</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><toplevel>online_resources</toplevel><creatorcontrib>Cepeda, Santiago</creatorcontrib><creatorcontrib>Luppino, Luigi Tommaso</creatorcontrib><creatorcontrib>Pérez-Núñez, Angel</creatorcontrib><creatorcontrib>Solheim, Ole Skeidsvoll</creatorcontrib><creatorcontrib>García-García, Sergio</creatorcontrib><creatorcontrib>Velasco-Casares, María</creatorcontrib><creatorcontrib>Karlberg, Anna Maria</creatorcontrib><creatorcontrib>Eikenes, Live</creatorcontrib><creatorcontrib>Sarabia, Rosario</creatorcontrib><creatorcontrib>Arrese, Ignacio</creatorcontrib><creatorcontrib>Zamora, Tomás</creatorcontrib><creatorcontrib>Gonzalez, Pedro</creatorcontrib><creatorcontrib>Jiménez-Roldán, Luis</creatorcontrib><creatorcontrib>Kuttner, Samuel</creatorcontrib><collection>NORA - Norwegian Open Research Archives</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Cepeda, Santiago</au><au>Luppino, Luigi Tommaso</au><au>Pérez-Núñez, Angel</au><au>Solheim, Ole Skeidsvoll</au><au>García-García, Sergio</au><au>Velasco-Casares, María</au><au>Karlberg, Anna Maria</au><au>Eikenes, Live</au><au>Sarabia, Rosario</au><au>Arrese, Ignacio</au><au>Zamora, Tomás</au><au>Gonzalez, Pedro</au><au>Jiménez-Roldán, Luis</au><au>Kuttner, Samuel</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Predicting Regions of Local Recurrence in Glioblastomas Using Voxel-Based Radiomic Features of Multiparametric Postoperative MRI</atitle><date>2023</date><risdate>2023</risdate><abstract>The globally accepted surgical strategy in glioblastomas is removing the enhancing tumor. However, the peritumoral region harbors infiltration areas responsible for future tumor recurrence. This study aimed to evaluate a predictive model that identifies areas of future recurrence using a voxel-based radiomics analysis of magnetic resonance imaging (MRI) data. This multi-institutional study included a retrospective analysis of patients diagnosed with glioblastoma who underwent surgery with complete resection of the enhancing tumor. Fifty-five patients met the selection criteria. The study sample was split into training (N = 40) and testing (N = 15) datasets. Follow-up MRI was used for ground truth definition, and postoperative structural multiparametric MRI was used to extract voxel-based radiomic features. Deformable coregistration was used to register the MRI sequences for each patient, followed by segmentation of the peritumoral region in the postoperative scan and the enhancing tumor in the follow-up scan. Peritumoral voxels overlapping with enhancing tumor voxels were labeled as recurrence, while non-overlapping voxels were labeled as nonrecurrence. Voxel-based radiomic features were extracted from the peritumoral region. Four machine learning-based classifiers were trained for recurrence prediction. A region-based evaluation approach was used for model evaluation. The Categorical Boosting (CatBoost) classifier obtained the best performance on the testing dataset with an average area under the curve (AUC) of 0.81 ± 0.09 and an accuracy of 0.84 ± 0.06, using region-based evaluation. There was a clear visual correspondence between predicted and actual recurrence regions. We have developed a method that accurately predicts the region of future tumor recurrence in MRI scans of glioblastoma patients. This could enable the adaptation of surgical and radiotherapy treatment to these areas to potentially prolong the survival of these patients.</abstract><pub>MDPI</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_cristin_nora_11250_3079719
source NORA - Norwegian Open Research Archives
title Predicting Regions of Local Recurrence in Glioblastomas Using Voxel-Based Radiomic Features of Multiparametric Postoperative MRI
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-04T14%3A25%3A33IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-cristin_3HK&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Predicting%20Regions%20of%20Local%20Recurrence%20in%20Glioblastomas%20Using%20Voxel-Based%20Radiomic%20Features%20of%20Multiparametric%20Postoperative%20MRI&rft.au=Cepeda,%20Santiago&rft.date=2023&rft_id=info:doi/&rft_dat=%3Ccristin_3HK%3E11250_3079719%3C/cristin_3HK%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true