Using Super-Resolution for Enhancing Visual Perception and Segmentation Performance in Veterinary Cytology
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...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Life |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1729/14/3/321 |
| _version_ | 1797240293028790272 |
|---|---|
| author | Jakub Caputa Maciej Wielgosz Daria Łukasik Paweł Russek Jakub Grzeszczyk Michał Karwatowski Szymon Mazurek Rafał Frączek Anna Śmiech Ernest Jamro Sebastian Koryciak Agnieszka Dąbrowska-Boruch Marcin Pietroń Kazimierz Wiatr |
| author_facet | Jakub Caputa Maciej Wielgosz Daria Łukasik Paweł Russek Jakub Grzeszczyk Michał Karwatowski Szymon Mazurek Rafał Frączek Anna Śmiech Ernest Jamro Sebastian Koryciak Agnieszka Dąbrowska-Boruch Marcin Pietroń Kazimierz Wiatr |
| author_sort | Jakub Caputa |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-24T18:05:07Z |
| format | Article |
| id | doaj.art-aefea36f497b4297bc0579db5d4342e1 |
| institution | Directory Open Access Journal |
| issn | 2075-1729 |
| language | English |
| last_indexed | 2024-04-24T18:05:07Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Life |
| spelling | doaj.art-aefea36f497b4297bc0579db5d4342e12024-03-27T13:51:08ZengMDPI AGLife2075-17292024-02-0114332110.3390/life14030321Using Super-Resolution for Enhancing Visual Perception and Segmentation Performance in Veterinary CytologyJakub Caputa0Maciej Wielgosz1Daria Łukasik2Paweł Russek3Jakub Grzeszczyk4Michał Karwatowski5Szymon Mazurek6Rafał Frączek7Anna Śmiech8Ernest Jamro9Sebastian Koryciak10Agnieszka Dąbrowska-Boruch11Marcin Pietroń12Kazimierz Wiatr13ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, PolandACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, PolandACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, PolandACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, PolandACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, PolandACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, PolandACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, PolandACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, PolandUniversity of Life Sciences, al. Akademicka 13, 20-950 Lublin, PolandACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, PolandACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, PolandACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, PolandACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, PolandACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, PolandThe 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.https://www.mdpi.com/2075-1729/14/3/321super image resolutioncomputer visiondeep learningcytologymedical imagingsemantic segmentation |
| spellingShingle | Jakub Caputa Maciej Wielgosz Daria Łukasik Paweł Russek Jakub Grzeszczyk Michał Karwatowski Szymon Mazurek Rafał Frączek Anna Śmiech Ernest Jamro Sebastian Koryciak Agnieszka Dąbrowska-Boruch Marcin Pietroń Kazimierz Wiatr Using Super-Resolution for Enhancing Visual Perception and Segmentation Performance in Veterinary Cytology Life super image resolution computer vision deep learning cytology medical imaging semantic segmentation |
| title | Using Super-Resolution for Enhancing Visual Perception and Segmentation Performance in Veterinary Cytology |
| title_full | Using Super-Resolution for Enhancing Visual Perception and Segmentation Performance in Veterinary Cytology |
| title_fullStr | Using Super-Resolution for Enhancing Visual Perception and Segmentation Performance in Veterinary Cytology |
| title_full_unstemmed | Using Super-Resolution for Enhancing Visual Perception and Segmentation Performance in Veterinary Cytology |
| title_short | Using Super-Resolution for Enhancing Visual Perception and Segmentation Performance in Veterinary Cytology |
| title_sort | using super resolution for enhancing visual perception and segmentation performance in veterinary cytology |
| topic | super image resolution computer vision deep learning cytology medical imaging semantic segmentation |
| url | https://www.mdpi.com/2075-1729/14/3/321 |
| work_keys_str_mv | AT jakubcaputa usingsuperresolutionforenhancingvisualperceptionandsegmentationperformanceinveterinarycytology AT maciejwielgosz usingsuperresolutionforenhancingvisualperceptionandsegmentationperformanceinveterinarycytology AT dariałukasik usingsuperresolutionforenhancingvisualperceptionandsegmentationperformanceinveterinarycytology AT pawełrussek usingsuperresolutionforenhancingvisualperceptionandsegmentationperformanceinveterinarycytology AT jakubgrzeszczyk usingsuperresolutionforenhancingvisualperceptionandsegmentationperformanceinveterinarycytology AT michałkarwatowski usingsuperresolutionforenhancingvisualperceptionandsegmentationperformanceinveterinarycytology AT szymonmazurek usingsuperresolutionforenhancingvisualperceptionandsegmentationperformanceinveterinarycytology AT rafałfraczek usingsuperresolutionforenhancingvisualperceptionandsegmentationperformanceinveterinarycytology AT annasmiech usingsuperresolutionforenhancingvisualperceptionandsegmentationperformanceinveterinarycytology AT ernestjamro usingsuperresolutionforenhancingvisualperceptionandsegmentationperformanceinveterinarycytology AT sebastiankoryciak usingsuperresolutionforenhancingvisualperceptionandsegmentationperformanceinveterinarycytology AT agnieszkadabrowskaboruch usingsuperresolutionforenhancingvisualperceptionandsegmentationperformanceinveterinarycytology AT marcinpietron usingsuperresolutionforenhancingvisualperceptionandsegmentationperformanceinveterinarycytology AT kazimierzwiatr usingsuperresolutionforenhancingvisualperceptionandsegmentationperformanceinveterinarycytology |