Intermediate Task Transfer Learning and Weakly Supervised Training in Histopathology

Autores
Gramática, Martín Nicolás; García, Mario Alejandro; Ricapito, Juan Pablo
Año de publicación
2023
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Reducing the amount of annotated data required to train predictive models is one of the main challenges in applying artificial intelligence to histopathology. In this paper, we propose a method to enhance the performance of deep learning models trained with limited data in the field of digital pathology. The method relies on a two-stage transfer learning process, where an intermediate model serves as a bridge between a pre-trained model on ImageNet and the final cancer classification model. The intermediate model is fine-tuned with a dataset of over 4,000,000 images weakly labeled with clinical data extracted from the TCGA program. The model obtained through the proposed method significantly outperforms a model trained with a traditional transfer learning process.
Fil: Gramática, Martín Nicolás . Universidad Tecnológica Nacional. Facultad Regional Córdoba. Grupo de Investigación en Inteligencia Artificial; Argentina.
Fil: García, Mario Alejandro. Universidad Tecnológica Nacional. Facultad Regional Córdoba. Grupo de Investigación en Inteligencia Artificial; Argentina.
Fil: Ricapito, Juan Pablo. Universidad Tecnológica Nacional. Facultad Regional Córdoba. Grupo de Investigación en Inteligencia Artificial; Argentina.
Peer Reviewed
Materia
Histopathology
Digital pathology
Deep learning
Transfer learning
Tcga
Nivel de accesibilidad
acceso abierto
Condiciones de uso
Attribution-NonCommercial-NoDerivs 2.5 Argentina
Repositorio
Repositorio Institucional Abierto (UTN)
Institución
Universidad Tecnológica Nacional
OAI Identificador
oai:ria.utn.edu.ar:20.500.12272/15599
Acceder
id RIAUTN_66a90a885fe63b127f7dfc16e8bddc40
oai_identifier_str oai:ria.utn.edu.ar:20.500.12272/15599
network_acronym_str RIAUTN
repository_id_str a
network_name_str Repositorio Institucional Abierto (UTN)
spelling Intermediate Task Transfer Learning and Weakly Supervised Training in HistopathologyGramática, Martín NicolásGarcía, Mario AlejandroRicapito, Juan PabloHistopathologyDigital pathologyDeep learningTransfer learningTcgaReducing the amount of annotated data required to train predictive models is one of the main challenges in applying artificial intelligence to histopathology. In this paper, we propose a method to enhance the performance of deep learning models trained with limited data in the field of digital pathology. The method relies on a two-stage transfer learning process, where an intermediate model serves as a bridge between a pre-trained model on ImageNet and the final cancer classification model. The intermediate model is fine-tuned with a dataset of over 4,000,000 images weakly labeled with clinical data extracted from the TCGA program. The model obtained through the proposed method significantly outperforms a model trained with a traditional transfer learning process.Fil: Gramática, Martín Nicolás . Universidad Tecnológica Nacional. Facultad Regional Córdoba. Grupo de Investigación en Inteligencia Artificial; Argentina.Fil: García, Mario Alejandro. Universidad Tecnológica Nacional. Facultad Regional Córdoba. Grupo de Investigación en Inteligencia Artificial; Argentina.Fil: Ricapito, Juan Pablo. Universidad Tecnológica Nacional. Facultad Regional Córdoba. Grupo de Investigación en Inteligencia Artificial; Argentina.Peer ReviewedUniversidad Tecnológica Nacional Regional Córdoba.2026-09-16T19:54:13Z2023-06-27info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articulopdfapplication/pdfXI Jornadas de Cloud Computing, Big Data & Emerging Topics, La Plata, Argentina. 2013https://hdl.handle.net/20.500.12272/15599enginfo:eu-repo/semantics/openAccessAttribution-NonCommercial-NoDerivs 2.5 Argentinahttp://creativecommons.org/licenses/by-nc-nd/2.5/ar/Gramática, Martín Nicolás; García, Mario Alejandro; Ricapito, Juan Pablohttps://creativecommons.org/licenses/by-nc-nd/4.0/reponame:Repositorio Institucional Abierto (UTN)instname:Universidad Tecnológica Nacional2026-09-24T12:44:00Zoai:ria.utn.edu.ar:20.500.12272/15599instacron:UTNInstitucionalhttp://ria.utn.edu.ar/Universidad públicaNo correspondehttp://ria.utn.edu.ar/oaigestionria@rec.utn.edu.ar; fsuarez@rec.utn.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:a2026-09-24 12:44:02.119Repositorio Institucional Abierto (UTN) - Universidad Tecnológica Nacionalfalse
dc.title.none.fl_str_mv Intermediate Task Transfer Learning and Weakly Supervised Training in Histopathology
title Intermediate Task Transfer Learning and Weakly Supervised Training in Histopathology
spellingShingle Intermediate Task Transfer Learning and Weakly Supervised Training in Histopathology
Gramática, Martín Nicolás
Histopathology
Digital pathology
Deep learning
Transfer learning
Tcga
title_short Intermediate Task Transfer Learning and Weakly Supervised Training in Histopathology
title_full Intermediate Task Transfer Learning and Weakly Supervised Training in Histopathology
title_fullStr Intermediate Task Transfer Learning and Weakly Supervised Training in Histopathology
title_full_unstemmed Intermediate Task Transfer Learning and Weakly Supervised Training in Histopathology
title_sort Intermediate Task Transfer Learning and Weakly Supervised Training in Histopathology
dc.creator.none.fl_str_mv Gramática, Martín Nicolás
García, Mario Alejandro
Ricapito, Juan Pablo
author Gramática, Martín Nicolás
author_facet Gramática, Martín Nicolás
García, Mario Alejandro
Ricapito, Juan Pablo
author_role author
author2 García, Mario Alejandro
Ricapito, Juan Pablo
author2_role author
author
dc.subject.none.fl_str_mv Histopathology
Digital pathology
Deep learning
Transfer learning
Tcga
topic Histopathology
Digital pathology
Deep learning
Transfer learning
Tcga
dc.description.none.fl_txt_mv Reducing the amount of annotated data required to train predictive models is one of the main challenges in applying artificial intelligence to histopathology. In this paper, we propose a method to enhance the performance of deep learning models trained with limited data in the field of digital pathology. The method relies on a two-stage transfer learning process, where an intermediate model serves as a bridge between a pre-trained model on ImageNet and the final cancer classification model. The intermediate model is fine-tuned with a dataset of over 4,000,000 images weakly labeled with clinical data extracted from the TCGA program. The model obtained through the proposed method significantly outperforms a model trained with a traditional transfer learning process.
Fil: Gramática, Martín Nicolás . Universidad Tecnológica Nacional. Facultad Regional Córdoba. Grupo de Investigación en Inteligencia Artificial; Argentina.
Fil: García, Mario Alejandro. Universidad Tecnológica Nacional. Facultad Regional Córdoba. Grupo de Investigación en Inteligencia Artificial; Argentina.
Fil: Ricapito, Juan Pablo. Universidad Tecnológica Nacional. Facultad Regional Córdoba. Grupo de Investigación en Inteligencia Artificial; Argentina.
Peer Reviewed
description Reducing the amount of annotated data required to train predictive models is one of the main challenges in applying artificial intelligence to histopathology. In this paper, we propose a method to enhance the performance of deep learning models trained with limited data in the field of digital pathology. The method relies on a two-stage transfer learning process, where an intermediate model serves as a bridge between a pre-trained model on ImageNet and the final cancer classification model. The intermediate model is fine-tuned with a dataset of over 4,000,000 images weakly labeled with clinical data extracted from the TCGA program. The model obtained through the proposed method significantly outperforms a model trained with a traditional transfer learning process.
publishDate 2023
dc.date.none.fl_str_mv 2023-06-27
2026-09-16T19:54:13Z
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv XI Jornadas de Cloud Computing, Big Data & Emerging Topics, La Plata, Argentina. 2013
https://hdl.handle.net/20.500.12272/15599
identifier_str_mv XI Jornadas de Cloud Computing, Big Data & Emerging Topics, La Plata, Argentina. 2013
url https://hdl.handle.net/20.500.12272/15599
dc.language.none.fl_str_mv eng
language eng
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
Attribution-NonCommercial-NoDerivs 2.5 Argentina
http://creativecommons.org/licenses/by-nc-nd/2.5/ar/
Gramática, Martín Nicolás; García, Mario Alejandro; Ricapito, Juan Pablo
https://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
rights_invalid_str_mv Attribution-NonCommercial-NoDerivs 2.5 Argentina
http://creativecommons.org/licenses/by-nc-nd/2.5/ar/
Gramática, Martín Nicolás; García, Mario Alejandro; Ricapito, Juan Pablo
https://creativecommons.org/licenses/by-nc-nd/4.0/
dc.format.none.fl_str_mv pdf
application/pdf
dc.publisher.none.fl_str_mv Universidad Tecnológica Nacional Regional Córdoba.
publisher.none.fl_str_mv Universidad Tecnológica Nacional Regional Córdoba.
dc.source.none.fl_str_mv reponame:Repositorio Institucional Abierto (UTN)
instname:Universidad Tecnológica Nacional
reponame_str Repositorio Institucional Abierto (UTN)
collection Repositorio Institucional Abierto (UTN)
instname_str Universidad Tecnológica Nacional
repository.name.fl_str_mv Repositorio Institucional Abierto (UTN) - Universidad Tecnológica Nacional
repository.mail.fl_str_mv gestionria@rec.utn.edu.ar; fsuarez@rec.utn.edu.ar
_version_ 1877230869085683712
score 13.265058

Publicaciones similares