Using Super-Resolution for Enhancing Visual Perception and Segmentation Performance in Veterinary Cytology.

Autor:	Caputa J; ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland., Wielgosz M; ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland.; AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Kraków, Poland., Łukasik D; ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland., Russek P; ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland.; AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Kraków, Poland., Grzeszczyk J; ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland., Karwatowski M; ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland.; AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Kraków, Poland., Mazurek S; ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland., Frączek R; ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland.; AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Kraków, Poland., Śmiech A; University of Life Sciences, al. Akademicka 13, 20-950 Lublin, Poland., Jamro E; ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland.; AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Kraków, Poland., Koryciak S; ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland.; AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Kraków, Poland., Dąbrowska-Boruch A; ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland.; AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Kraków, Poland., Pietroń M; ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland.; AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Kraków, Poland., Wiatr K; ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland.; AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Kraków, Poland.
Jazyk:	angličtina
Zdroj:	Life (Basel, Switzerland) [Life (Basel)] 2024 Feb 28; Vol. 14 (3). Date of Electronic Publication: 2024 Feb 28.
DOI:	10.3390/life14030321
Abstrakt:	The primary objective of this research was to enhance the quality of semantic segmentation in cytology images by incorporating super-resolution (SR) architectures. An additional contribution was the development of a novel dataset aimed at improving imaging quality in the presence of inaccurate focus. Our experimental results demonstrate that the integration of SR techniques into the segmentation pipeline can lead to a significant improvement of up to 25% in the mean average precision (mAP) metric. These findings suggest that leveraging SR architectures holds great promise for advancing the state-of-the-art in cytology image analysis.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu Plný text ve formátu PDF Plný text ve formátu HTML
Nepřihlášeným uživatelům se plný text nezobrazuje	K zobrazení výsledku je třeba se přihlásit.