Validating retinaNet for the object detection-based mitosis detection in the MIDOG challenge

García-Salmerón, Jesús; García, José Manuel; Bernabé García, Gregorio; González Férez, Pilar

Publication:
Validating retinaNet for the object detection-based mitosis detection in the MIDOG challenge

dc.contributor.author	García-Salmerón, Jesús
dc.contributor.author	García, José Manuel
dc.contributor.author	Bernabé García, Gregorio
dc.contributor.author	González Férez, Pilar
dc.contributor.department	Ingeniería y Tecnología de Computadores
dc.date.accessioned	2025-05-16T06:44:47Z
dc.date.available	2025-05-16T06:44:47Z
dc.date.issued	2025-04-25
dc.description	© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG.
dc.description.abstract	Mitosis detection is critical in histopathology for accurate diagnosis and prognosis of tumors, a topic of particular interest underscored by recent challenges. In this study, we focus on developing deep learning (DL) solutions to confront this challenge within the framework of the MIDOG challenge. Leveraging the newest MIDOG challenge dataset, the MIDOG++ dataset, we explore the efficacy of object detection models. Specifically, the RetinaNet model using fastai and PyTorch frameworks. We replicate and validate the reference work, RetinaNet, using fastai, and we propose the RetinaNet model using PyTorch. Through rigorous training and evaluation, we analyze the performance of these models in detecting mitotic figures, crucial for automating histopathological analysis and improving diagnostic accuracy. Our study demonstrates the effectiveness of the RetinaNet model in mitosis detection within histopathological images. Obtaining favorable F1 scores across the different scenarios and analyzing the relationship between different tumor types.
dc.format	application/pdf	es
dc.format.extent	10
dc.identifier.doi	https://doi.org/10.1007/978-3-031-87873-2_8
dc.identifier.eissn	Print: 978-3-031-87872-5
dc.identifier.eissn	Electronic: 978-3-031-87873-2
dc.identifier.uri	http://hdl.handle.net/10201/154712
dc.language	eng	es
dc.publisher	Springer Nature
dc.relation	This work has been partially funded by Grant TED2021-129221B-I00 funded by MCIN/AEI/10.13039/501100011033 and by the “European Union NextGenerationEU/PRTR”.	es
dc.relation.ispartof	Practical Applications of Computational Biology and Bioinformatics, 18th International Conference (PACBB 2024), p.p. 71-80	es
dc.relation.publisherversion	https://link.springer.com/chapter/10.1007/978-3-031-87873-2_8
dc.rights	info:eu-repo/semantics/restrictedAccess	es
dc.subject	Mitosis detection
dc.subject	Deep Learning
dc.subject	Object detection
dc.subject	MIDOG Challenge
dc.title	Validating retinaNet for the object detection-based mitosis detection in the MIDOG challenge	es
dc.type	info:eu-repo/semantics/article	es
dspace.entity.type	Publication	es