EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Optimization of whole slide imaging scan settings for computer vision using human lung cancer tissue

Melvin Geubbelmans iD, Jari Claes, Kim Nijsten iD, Pascal Gervois, Simon Appeltans, Sandrina Martens iD, Esther Wolfs iD, Michiel Thomeer, Dirk Valkenborg, Christel Faes iD

PLOS ONE · 2024

DOI: 10.1371/journal.pone.0309740 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, 2024. Verfasst von Melvin Geubbelmans und 9 weiteren Autor:innen. Beteiligte Einrichtung: Data Science Institute, Hasselt University, Hasselt, Belgium. Hauptthemen laut MEDLINE: Lung Neoplasms. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Bijzonder Onderzoeksfonds UHasselt, Onderzoeksprogramma Artificiële Intelligentie Vlaanderen.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Digital pathology has become increasingly popular for research and clinical applications. Using high-quality microscopes to produce Whole Slide Images of tumor tissue enables the discovery of insights into biological aspects invisible to the human eye. These are acquired through downstream analyses using spatial statistics and artificial intelligence. Determination of the quality and consistency of these images is needed to ensure accurate outcomes when identifying clinical and subclinical image features. Additionally, the time-intensive process of generating high-volume images results in a trade-off that needs to be carefully balanced. This study aims to determine optimal instrument settings to generate representative images of pathological tissue using digital microscopy. Using various settings, an H&E stained sample was scanned using the ZEISS Axio Scan.Z1. Next, nucleus segmentation was performed on resulting images using StarDist. Subsequently, detections were compared between scans using a matching algorithm. Finally, nucleus-level information was compared between scans. Results indicated that while general matching percentages were high, similarity between information from replicates was relatively low. Additionally, settings resulting in longer scanning times and increased data volume did not increase similarity between replicates. In conclusion, the scan setting ultimately deemed optimal combined consistent and qualitative performance with low throughput time.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Lung NeoplasmsHumansImage Processing, Computer-AssistedAlgorithmsMicroscopyCell Nucleus

Autor:innen und Institutionen

  • Data Science Institute, Hasselt University, Hasselt, Belgium.
  • UHasselt, Lab for Functional Imaging & Research on Stem Cells (FIERCE Lab), BIOMED, Diepenbeek, Belgium.
  • UHasselt, Limburg Clinical Research Center (LCRC), Hasselt, Belgium.
  • Department of Respiratory Medicine, Ziekenhuis Oost-Limburg, Genk, Belgium.

ORCID-Profile: Melvin Geubbelmans, Kim Nijsten, Sandrina Martens, Esther Wolfs, Christel Faes

Förderung

  • Bijzonder Onderzoeksfonds UHasselt
  • Onderzoeksprogramma Artificiële Intelligentie Vlaanderen

Zitieren

APA

Geubbelmans, M., Claes, J., Nijsten, K., Gervois, P., Appeltans, S., Martens, S., Wolfs, E., Thomeer, M., Valkenborg, D., & Faes, C. (2024). Optimization of whole slide imaging scan settings for computer vision using human lung cancer tissue. PLOS ONE. https://doi.org/10.1371/journal.pone.0309740

Vancouver

Geubbelmans M, Claes J, Nijsten K, Gervois P, Appeltans S, Martens S, et al. Optimization of whole slide imaging scan settings for computer vision using human lung cancer tissue. PLOS ONE. 2024. doi:10.1371/journal.pone.0309740

BibTeX
@article{Geubbelmans2024,
  author = {Geubbelmans, Melvin and Claes, Jari and Nijsten, Kim and Gervois, Pascal and Appeltans, Simon and Martens, Sandrina and Wolfs, Esther and Thomeer, Michiel and Valkenborg, Dirk and Faes, Christel},
  title = {Optimization of whole slide imaging scan settings for computer vision using human lung cancer tissue},
  journal = {PLOS ONE},
  year = {2024},
  doi = {10.1371/journal.pone.0309740}
}
Kostenlos starten →