AI-Guided Delineation of Gross Tumor Volume for Body Tumors: A Systematic Review

<b>Background</b>: Approximately 50% of all oncological patients undergo radiation therapy, where personalized planning of treatment relies on gross tumor volume (GTV) delineation. Manual delineation of GTV is time-consuming, operator-dependent, and prone to variability. An increasing nu...

Full description

Saved in:
Bibliographic Details
Main Authors: Lea Marie Pehrson, Jens Petersen, Nathalie Sarup Panduro, Carsten Ammitzbøl Lauridsen, Jonathan Frederik Carlsen, Sune Darkner, Michael Bachmann Nielsen, Silvia Ingala
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/15/7/846
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850188255970983936
author Lea Marie Pehrson
Jens Petersen
Nathalie Sarup Panduro
Carsten Ammitzbøl Lauridsen
Jonathan Frederik Carlsen
Sune Darkner
Michael Bachmann Nielsen
Silvia Ingala
author_facet Lea Marie Pehrson
Jens Petersen
Nathalie Sarup Panduro
Carsten Ammitzbøl Lauridsen
Jonathan Frederik Carlsen
Sune Darkner
Michael Bachmann Nielsen
Silvia Ingala
author_sort Lea Marie Pehrson
collection DOAJ
description <b>Background</b>: Approximately 50% of all oncological patients undergo radiation therapy, where personalized planning of treatment relies on gross tumor volume (GTV) delineation. Manual delineation of GTV is time-consuming, operator-dependent, and prone to variability. An increasing number of studies apply artificial intelligence (AI) techniques to automate such delineation processes. <b>Methods</b>: To perform a systematic review comparing the performance of AI models in tumor delineations within the body (thoracic cavity, esophagus, abdomen, and pelvis, or soft tissue and bone). A retrospective search of five electronic databases was performed between January 2017 and February 2025. Original research studies developing and/or validating algorithms delineating GTV in CT, MRI, and/or PET were included. The Checklist for Artificial Intelligence in Medical Imaging (CLAIM) and Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis statement and checklist (TRIPOD) were used to assess the risk, bias, and reporting adherence. <b>Results</b>: After screening 2430 articles, 48 were included. The pooled diagnostic performance from the use of AI algorithms across different tumors and topological areas ranged 0.62–0.92 in dice similarity coefficient (DSC) and 1.33–47.10 mm in Hausdorff distance (HD). The algorithms with the highest DSC deployed an encoder–decoder architecture. <b>Conclusions</b>: AI algorithms demonstrate a high level of concordance with clinicians in GTV delineation. Translation to clinical settings requires the building of trust, improvement in performance and robustness of results, and testing in prospective studies and randomized controlled trials.
format Article
id doaj-art-8830ede9fcd94b9ab0f7ad950f9da1e7
institution OA Journals
issn 2075-4418
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-8830ede9fcd94b9ab0f7ad950f9da1e72025-08-20T02:15:55ZengMDPI AGDiagnostics2075-44182025-03-0115784610.3390/diagnostics15070846AI-Guided Delineation of Gross Tumor Volume for Body Tumors: A Systematic ReviewLea Marie Pehrson0Jens Petersen1Nathalie Sarup Panduro2Carsten Ammitzbøl Lauridsen3Jonathan Frederik Carlsen4Sune Darkner5Michael Bachmann Nielsen6Silvia Ingala7Department of Diagnostic Radiology, Copenhagen University Hospital Rigshospitalet, 2100 Copenhagen, DenmarkDepartment of Computer Science, University of Copenhagen, 2100 Copenhagen, DenmarkDepartment of Diagnostic Radiology, Copenhagen University Hospital Rigshospitalet, 2100 Copenhagen, DenmarkDepartment of Diagnostic Radiology, Copenhagen University Hospital Rigshospitalet, 2100 Copenhagen, DenmarkDepartment of Diagnostic Radiology, Copenhagen University Hospital Rigshospitalet, 2100 Copenhagen, DenmarkDepartment of Computer Science, University of Copenhagen, 2100 Copenhagen, DenmarkDepartment of Diagnostic Radiology, Copenhagen University Hospital Rigshospitalet, 2100 Copenhagen, DenmarkDepartment of Diagnostic Radiology, Copenhagen University Hospital Rigshospitalet, 2100 Copenhagen, Denmark<b>Background</b>: Approximately 50% of all oncological patients undergo radiation therapy, where personalized planning of treatment relies on gross tumor volume (GTV) delineation. Manual delineation of GTV is time-consuming, operator-dependent, and prone to variability. An increasing number of studies apply artificial intelligence (AI) techniques to automate such delineation processes. <b>Methods</b>: To perform a systematic review comparing the performance of AI models in tumor delineations within the body (thoracic cavity, esophagus, abdomen, and pelvis, or soft tissue and bone). A retrospective search of five electronic databases was performed between January 2017 and February 2025. Original research studies developing and/or validating algorithms delineating GTV in CT, MRI, and/or PET were included. The Checklist for Artificial Intelligence in Medical Imaging (CLAIM) and Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis statement and checklist (TRIPOD) were used to assess the risk, bias, and reporting adherence. <b>Results</b>: After screening 2430 articles, 48 were included. The pooled diagnostic performance from the use of AI algorithms across different tumors and topological areas ranged 0.62–0.92 in dice similarity coefficient (DSC) and 1.33–47.10 mm in Hausdorff distance (HD). The algorithms with the highest DSC deployed an encoder–decoder architecture. <b>Conclusions</b>: AI algorithms demonstrate a high level of concordance with clinicians in GTV delineation. Translation to clinical settings requires the building of trust, improvement in performance and robustness of results, and testing in prospective studies and randomized controlled trials.https://www.mdpi.com/2075-4418/15/7/846gross tumor volumesegmentationartificial intelligence
spellingShingle Lea Marie Pehrson
Jens Petersen
Nathalie Sarup Panduro
Carsten Ammitzbøl Lauridsen
Jonathan Frederik Carlsen
Sune Darkner
Michael Bachmann Nielsen
Silvia Ingala
AI-Guided Delineation of Gross Tumor Volume for Body Tumors: A Systematic Review
Diagnostics
gross tumor volume
segmentation
artificial intelligence
title AI-Guided Delineation of Gross Tumor Volume for Body Tumors: A Systematic Review
title_full AI-Guided Delineation of Gross Tumor Volume for Body Tumors: A Systematic Review
title_fullStr AI-Guided Delineation of Gross Tumor Volume for Body Tumors: A Systematic Review
title_full_unstemmed AI-Guided Delineation of Gross Tumor Volume for Body Tumors: A Systematic Review
title_short AI-Guided Delineation of Gross Tumor Volume for Body Tumors: A Systematic Review
title_sort ai guided delineation of gross tumor volume for body tumors a systematic review
topic gross tumor volume
segmentation
artificial intelligence
url https://www.mdpi.com/2075-4418/15/7/846
work_keys_str_mv AT leamariepehrson aiguideddelineationofgrosstumorvolumeforbodytumorsasystematicreview
AT jenspetersen aiguideddelineationofgrosstumorvolumeforbodytumorsasystematicreview
AT nathaliesaruppanduro aiguideddelineationofgrosstumorvolumeforbodytumorsasystematicreview
AT carstenammitzbøllauridsen aiguideddelineationofgrosstumorvolumeforbodytumorsasystematicreview
AT jonathanfrederikcarlsen aiguideddelineationofgrosstumorvolumeforbodytumorsasystematicreview
AT sunedarkner aiguideddelineationofgrosstumorvolumeforbodytumorsasystematicreview
AT michaelbachmannnielsen aiguideddelineationofgrosstumorvolumeforbodytumorsasystematicreview
AT silviaingala aiguideddelineationofgrosstumorvolumeforbodytumorsasystematicreview