AI-based glioma grading for a trustworthy diagnosis: an analytical pipeline for improved reliability

Glioma is the most common type of tumor in humans originating in the brain. According to the World Health Organization, gliomas can be graded on a four-stage scale, ranging from the most benign to the most malignant. The grading of these tumors from image information is a far from trivial task for r...

Descripción completa

Detalles Bibliográficos
Autores: Pitarch i Abaigar, Carla|||0000-0002-6015-244X, Ribas Ripoll, Vicente Jorge, Vellido Alcacena, Alfredo|||0000-0002-9843-1911
Tipo de recurso: artículo
Fecha de publicación:2023
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/390777
Acceso en línea:https://hdl.handle.net/2117/390777
https://dx.doi.org/10.3390/cancers15133369
Access Level:acceso abierto
Palabra clave:Gliomas
Tumors -- Classification
Machine learning
Glioma
Tumor grading
Decision support
Neuro-oncology
Radiology
Trustworthiness
Model certainty
Model robustness
Reliability
Gliomes
Tumors -- Classificació
Aprenentatge automàtic
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
Àrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica::Bioinformàtica
id ES_5663dc84c19b3a47e4465e96dc4d990b
oai_identifier_str oai:upcommons.upc.edu:2117/390777
network_acronym_str ES
network_name_str España
repository_id_str
spelling AI-based glioma grading for a trustworthy diagnosis: an analytical pipeline for improved reliabilityPitarch i Abaigar, Carla|||0000-0002-6015-244XRibas Ripoll, Vicente JorgeVellido Alcacena, Alfredo|||0000-0002-9843-1911GliomasTumors -- ClassificationMachine learningGliomaTumor gradingDecision supportNeuro-oncologyRadiologyTrustworthinessModel certaintyModel robustnessReliabilityGliomesTumors -- ClassificacióAprenentatge automàticÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàticÀrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica::BioinformàticaGlioma is the most common type of tumor in humans originating in the brain. According to the World Health Organization, gliomas can be graded on a four-stage scale, ranging from the most benign to the most malignant. The grading of these tumors from image information is a far from trivial task for radiologists and one in which they could be assisted by machine-learning-based decision support. However, the machine learning analytical pipeline is also fraught with perils stemming from different sources, such as inadvertent data leakage, adequacy of 2D image sampling, or classifier assessment biases. In this paper, we analyze a glioma database sourced from multiple datasets using a simple classifier, aiming to obtain a reliable tumor grading and, on the way, we provide a few guidelines to ensure such reliability. Our results reveal that by focusing on the tumor region of interest and using data augmentation techniques we significantly enhanced the accuracy and confidence in tumor classifications. Evaluation on an independent test set resulted in an AUC-ROC of 0.932 in the discrimination of low-grade gliomas from high-grade gliomas, and an AUC-ROC of 0.893 in the classification of grades 2, 3, and 4. The study also highlights the importance of providing, beyond generic classification performance, measures of how reliable and trustworthy the model’s output is, thus assessing the model’s certainty and robustness.Carla Pitarch is a fellow of Eurecat’s “Vicente López” PhD grant program.Peer Reviewed20232023-06-2720232023-07-13journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/2117/390777https://dx.doi.org/10.3390/cancers15133369reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2Attribution 4.0 Internationalhttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/3907772026-05-27T15:37:01Z
dc.title.none.fl_str_mv AI-based glioma grading for a trustworthy diagnosis: an analytical pipeline for improved reliability
title AI-based glioma grading for a trustworthy diagnosis: an analytical pipeline for improved reliability
spellingShingle AI-based glioma grading for a trustworthy diagnosis: an analytical pipeline for improved reliability
Pitarch i Abaigar, Carla|||0000-0002-6015-244X
Gliomas
Tumors -- Classification
Machine learning
Glioma
Tumor grading
Decision support
Neuro-oncology
Radiology
Trustworthiness
Model certainty
Model robustness
Reliability
Gliomes
Tumors -- Classificació
Aprenentatge automàtic
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
Àrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica::Bioinformàtica
title_short AI-based glioma grading for a trustworthy diagnosis: an analytical pipeline for improved reliability
title_full AI-based glioma grading for a trustworthy diagnosis: an analytical pipeline for improved reliability
title_fullStr AI-based glioma grading for a trustworthy diagnosis: an analytical pipeline for improved reliability
title_full_unstemmed AI-based glioma grading for a trustworthy diagnosis: an analytical pipeline for improved reliability
title_sort AI-based glioma grading for a trustworthy diagnosis: an analytical pipeline for improved reliability
dc.creator.none.fl_str_mv Pitarch i Abaigar, Carla|||0000-0002-6015-244X
Ribas Ripoll, Vicente Jorge
Vellido Alcacena, Alfredo|||0000-0002-9843-1911
author Pitarch i Abaigar, Carla|||0000-0002-6015-244X
author_facet Pitarch i Abaigar, Carla|||0000-0002-6015-244X
Ribas Ripoll, Vicente Jorge
Vellido Alcacena, Alfredo|||0000-0002-9843-1911
author_role author
author2 Ribas Ripoll, Vicente Jorge
Vellido Alcacena, Alfredo|||0000-0002-9843-1911
author2_role author
author
dc.subject.none.fl_str_mv Gliomas
Tumors -- Classification
Machine learning
Glioma
Tumor grading
Decision support
Neuro-oncology
Radiology
Trustworthiness
Model certainty
Model robustness
Reliability
Gliomes
Tumors -- Classificació
Aprenentatge automàtic
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
Àrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica::Bioinformàtica
topic Gliomas
Tumors -- Classification
Machine learning
Glioma
Tumor grading
Decision support
Neuro-oncology
Radiology
Trustworthiness
Model certainty
Model robustness
Reliability
Gliomes
Tumors -- Classificació
Aprenentatge automàtic
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
Àrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica::Bioinformàtica
description Glioma is the most common type of tumor in humans originating in the brain. According to the World Health Organization, gliomas can be graded on a four-stage scale, ranging from the most benign to the most malignant. The grading of these tumors from image information is a far from trivial task for radiologists and one in which they could be assisted by machine-learning-based decision support. However, the machine learning analytical pipeline is also fraught with perils stemming from different sources, such as inadvertent data leakage, adequacy of 2D image sampling, or classifier assessment biases. In this paper, we analyze a glioma database sourced from multiple datasets using a simple classifier, aiming to obtain a reliable tumor grading and, on the way, we provide a few guidelines to ensure such reliability. Our results reveal that by focusing on the tumor region of interest and using data augmentation techniques we significantly enhanced the accuracy and confidence in tumor classifications. Evaluation on an independent test set resulted in an AUC-ROC of 0.932 in the discrimination of low-grade gliomas from high-grade gliomas, and an AUC-ROC of 0.893 in the classification of grades 2, 3, and 4. The study also highlights the importance of providing, beyond generic classification performance, measures of how reliable and trustworthy the model’s output is, thus assessing the model’s certainty and robustness.
publishDate 2023
dc.date.none.fl_str_mv 2023
2023-06-27
2023
2023-07-13
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/390777
https://dx.doi.org/10.3390/cancers15133369
url https://hdl.handle.net/2117/390777
https://dx.doi.org/10.3390/cancers15133369
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869408376205606912
score 15,300724

Similares en LA Referencia