Transformation of WSI images for the detection of cervical cells in the Papanicolau test

Autores
Ricapito, Juan Pablo; Silva Fiezzy, Tomás
Año de publicación
2023
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
The rising use of scanners to digitize medical samples has enabled the application of a great diversity of machine learning algorithms with the objective of simplifying routine tasks for pathologists. These samples are commonly digitized using a technique called Whole Slide Imaging (WSI). Problems arise when these very-high-resolution images are used in object detection models such as YOLO (You Only Look Once). In this paper, we propose a WSI inference pipeline which allows the extraction of overlapping sub-images, inference using the YOLOv7 model, and the reassembly of the original image. Special focus was given to the detection of cervical cells obtained from the conventional Papanicolau test samples. The results demonstrate how this pipeline allows the accurate detection of cells and opens up the possibility for its use in different WSI domains and object recognition models.
Fil: Ricapito, Juan Pablo. Universidad Tecnológica Nacional. Facultad Regional Córdoba. Grupo de Investigación en Inteligencia Artificial; Argentina.
Fil: Silva Fiezzy, Tomás. Universidad Tecnológica Nacional. Facultad Regional Córdoba. Grupo de Investigación en Inteligencia Artificial; Argentina.
Peer Reviewed
Fuente
XI Congreso Nacional de Ingeniería Informática / Sistemas de Información
Materia
WSI
Object detection
Pap test
Cervical cancer
Deep learning
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:20.500.12272/15581
Acceder
id RIAUTN_4e8f91decbe2110bbb6b9ad6e3096230
oai_identifier_str oai:ria.utn.edu.ar:20.500.12272/15581
network_acronym_str RIAUTN
repository_id_str a
network_name_str Repositorio Institucional Abierto (UTN)
spelling Transformation of WSI images for the detection of cervical cells in the Papanicolau testRicapito, Juan PabloSilva Fiezzy, TomásWSIObject detectionPap testCervical cancerDeep learningThe rising use of scanners to digitize medical samples has enabled the application of a great diversity of machine learning algorithms with the objective of simplifying routine tasks for pathologists. These samples are commonly digitized using a technique called Whole Slide Imaging (WSI). Problems arise when these very-high-resolution images are used in object detection models such as YOLO (You Only Look Once). In this paper, we propose a WSI inference pipeline which allows the extraction of overlapping sub-images, inference using the YOLOv7 model, and the reassembly of the original image. Special focus was given to the detection of cervical cells obtained from the conventional Papanicolau test samples. The results demonstrate how this pipeline allows the accurate detection of cells and opens up the possibility for its use in different WSI domains and object recognition models.Fil: Ricapito, Juan Pablo. Universidad Tecnológica Nacional. Facultad Regional Córdoba. Grupo de Investigación en Inteligencia Artificial; Argentina.Fil: Silva Fiezzy, Tomás. Universidad Tecnológica Nacional. Facultad Regional Córdoba. Grupo de Investigación en Inteligencia Artificial; Argentina.Peer ReviewededUTecNe2026-09-15T19:29:49Z2023-11-02info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articulopdfapplication/pdfXI Congreso Nacional de Ingeniería en Informática y Sistemas de Información. CoNaIISI 2023978-987-8992-38-9https://hdl.handle.net/20.500.12272/15581XI Congreso Nacional de Ingeniería Informática / Sistemas de Informaciónreponame:Repositorio Institucional Abierto (UTN)instname:Universidad Tecnológica Nacionalenginfo:eu-repo/semantics/openAccessAttribution-NonCommercial-NoDerivs 2.5 Argentinahttp://creativecommons.org/licenses/by-nc-nd/2.5/ar/Ricapito, Juan Pablo; Silva Fiezzy, Tomáshttps://creativecommons.org/licenses/by-nc-nd/4.0/2026-10-01T12:01:09Zoai:ria.utn.edu.ar:20.500.12272/15581instacron: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:a2026-10-01 12:01:10.376Repositorio Institucional Abierto (UTN) - Universidad Tecnológica Nacionalfalse
dc.title.none.fl_str_mv Transformation of WSI images for the detection of cervical cells in the Papanicolau test
title Transformation of WSI images for the detection of cervical cells in the Papanicolau test
spellingShingle Transformation of WSI images for the detection of cervical cells in the Papanicolau test
Ricapito, Juan Pablo
WSI
Object detection
Pap test
Cervical cancer
Deep learning
title_short Transformation of WSI images for the detection of cervical cells in the Papanicolau test
title_full Transformation of WSI images for the detection of cervical cells in the Papanicolau test
title_fullStr Transformation of WSI images for the detection of cervical cells in the Papanicolau test
title_full_unstemmed Transformation of WSI images for the detection of cervical cells in the Papanicolau test
title_sort Transformation of WSI images for the detection of cervical cells in the Papanicolau test
dc.creator.none.fl_str_mv Ricapito, Juan Pablo
Silva Fiezzy, Tomás
author Ricapito, Juan Pablo
author_facet Ricapito, Juan Pablo
Silva Fiezzy, Tomás
author_role author
author2 Silva Fiezzy, Tomás
author2_role author
dc.subject.none.fl_str_mv WSI
Object detection
Pap test
Cervical cancer
Deep learning
topic WSI
Object detection
Pap test
Cervical cancer
Deep learning
dc.description.none.fl_txt_mv The rising use of scanners to digitize medical samples has enabled the application of a great diversity of machine learning algorithms with the objective of simplifying routine tasks for pathologists. These samples are commonly digitized using a technique called Whole Slide Imaging (WSI). Problems arise when these very-high-resolution images are used in object detection models such as YOLO (You Only Look Once). In this paper, we propose a WSI inference pipeline which allows the extraction of overlapping sub-images, inference using the YOLOv7 model, and the reassembly of the original image. Special focus was given to the detection of cervical cells obtained from the conventional Papanicolau test samples. The results demonstrate how this pipeline allows the accurate detection of cells and opens up the possibility for its use in different WSI domains and object recognition models.
Fil: Ricapito, Juan Pablo. Universidad Tecnológica Nacional. Facultad Regional Córdoba. Grupo de Investigación en Inteligencia Artificial; Argentina.
Fil: Silva Fiezzy, Tomás. Universidad Tecnológica Nacional. Facultad Regional Córdoba. Grupo de Investigación en Inteligencia Artificial; Argentina.
Peer Reviewed
description The rising use of scanners to digitize medical samples has enabled the application of a great diversity of machine learning algorithms with the objective of simplifying routine tasks for pathologists. These samples are commonly digitized using a technique called Whole Slide Imaging (WSI). Problems arise when these very-high-resolution images are used in object detection models such as YOLO (You Only Look Once). In this paper, we propose a WSI inference pipeline which allows the extraction of overlapping sub-images, inference using the YOLOv7 model, and the reassembly of the original image. Special focus was given to the detection of cervical cells obtained from the conventional Papanicolau test samples. The results demonstrate how this pipeline allows the accurate detection of cells and opens up the possibility for its use in different WSI domains and object recognition models.
publishDate 2023
dc.date.none.fl_str_mv 2023-11-02
2026-09-15T19:29:49Z
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 Congreso Nacional de Ingeniería en Informática y Sistemas de Información. CoNaIISI 2023
978-987-8992-38-9
https://hdl.handle.net/20.500.12272/15581
identifier_str_mv XI Congreso Nacional de Ingeniería en Informática y Sistemas de Información. CoNaIISI 2023
978-987-8992-38-9
url https://hdl.handle.net/20.500.12272/15581
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/
Ricapito, Juan Pablo; Silva Fiezzy, Tomás
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/
Ricapito, Juan Pablo; Silva Fiezzy, Tomás
https://creativecommons.org/licenses/by-nc-nd/4.0/
dc.format.none.fl_str_mv pdf
application/pdf
dc.publisher.none.fl_str_mv edUTecNe
publisher.none.fl_str_mv edUTecNe
dc.source.none.fl_str_mv XI Congreso Nacional de Ingeniería Informática / Sistemas de Información
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_ 1877862446088060928
score 12.853507

Publicaciones similares