<link rel="stylesheet" href="styles.f3b1fba60ec7970c.css">

Optimization of cell annotation process: combining manual and automatic labeling in biomedical data analysis optoelectronic systems

dc.contributor.authorAvrunin, О.en
dc.contributor.authorSamokhina, Yu.en
dc.contributor.authorGromaszekb, К.en
dc.contributor.authorDudenko, V.en
dc.contributor.authorStarkova, I.en
dc.contributor.authorArypzhand, А.en
dc.contributor.authorTiutiunnyk, О.en
dc.contributor.authorVitiuk, А.en
dc.contributor.authorJinqiong, Lіen
dc.contributor.authorВітюк, А. В.en
dc.contributor.authorЦзіньцюн, Ліen
dc.identifier.orcidhttps://orcid.org/0000-0001-5211-4948
dc.identifier.orcidhttps://orcid.org/0000-0002-0505-621X
dc.titleOptimization of cell annotation process: combining manual and automatic labeling in biomedical data analysis optoelectronic systemsen
dc.date.issued2025
dc.publisherSPIEen
dc.identifier.citationAvrunin О., Samokhina Yu., Gromaszekb К., Dudenko V., Starkova I., Arypzhand А., Tiutiunnyk О., Vitiuk А., Jinqiong Lі. Optimization of cell annotation process: combining manual and automatic labeling in biomedical data analysis optoelectronic systems // Proceeding SPIE. Photonics Applications in Astronomy, Communications, Industry, and High Energy Physics Experiments 2025, Lublin, Poland, 30 December 2025. Vol. 14009, № 140090L. DOI: https://doi.org/10.1117/12.3096280.en
dc.relation.ispartofProceeding SPIE. Photonics Applications in Astronomy, Communications, Industry, and High Energy Physics Experiments 2025, Lublin, Poland, 30 December 2025. Vol. 14009, № 140090L.en
dc.relation.urihttps://www.spiedigitallibrary.org/conference-proceedings-of-spie/14009/3096280/Optimization-of-cell-annotation-process--combining-manual-and-automatic/10.1117/12.3096280.full
dc.identifier.doihttps://doi.org/10.1117/12.3096280
dc.identifier.urihttps://ir.lib.vntu.edu.ua/handle/123456789/58491
dc.description.abstractModern biomedical research requires highly accurate and scalable image annotation, especially when working with cryomicroscopic data. One of the key stages in analyzing such images is the annotation of cellular structures, which is essential for training machine learning models. This paper explores an approach to optimizing the process of cell annotation by combining manual and automatic labeling within the CVAT (Computer Vision Annotation Tool) environment. The proposed method integrates the precision of manual annotation with the efficiency of automated segmentation algorithms, significantly reducing labor costs and improving reproducibility. During the study, the capabilities of CVAT were analyzed, built-in automated tools were tested, and scenarios for their combined use with manual corrections were described. The advantages of the hybrid approach, common errors, and ways to minimize them are discussed. The results demonstrate that combined annotation enables faster preparation of training datasets without significant loss of quality, especially when working with large volumes of images. This approach may be beneficial for automated biomedical data analysis systems rapid scaling is required without compromising accuracy.uk
dc.subjectcell annotationen
dc.subjectcryomicroscopyen
dc.subjectCVATen
dc.subjectimage segmentationen
dc.subjectmanual labelingen
dc.subjectautomatic labelingen
dc.subjectmachine learningen
dc.subjectbiomedical imagingen
dc.subjectdata annotation toolsen
dc.typeArticle, Scopus-WoS
dc.language.isoen_US
dc.date.accessioned2026-11-18T08:34:02Z

Файли

Контейнер файлів

Зараз показуємо 1 - 1 з 1
Завантаження...
Ескіз
Назва:
210997.pdf
Розмір:
565,36 KB
Формат:
Adobe Portable Document Format

Зібрання