EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Standardized Instance‐Level Quantification of CD34‐Positive Vessels in Lymph Node Whole‐Slide Images Using U‐Net

Satomi Omotani, Natsumi Yonemoto, Akifumi Muramoto, Motohiro Kobayashi iD

Pathology International · 2026-05 · 76 (5)

DOI: 10.1111/pin.70125 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pathology International, online erschienen am 11.05.2026. Verfasst von Satomi Omotani und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pathology, Faculty of Medical Sciences, University of Fukui, Eiheiji, Fukui, Japan. Hauptthemen laut MEDLINE: Lymph Nodes, Antigens, CD34, Image Processing, Computer-Assisted. Die Arbeit nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning enhances quantitative analysis of blood vessels in whole‐slide images (WSIs), leading to precise and reliable counting. However, counting vessels in lymph nodes—which contain distinctive high endothelial venules (HEVs)—has not been systematically evaluated. Artificial intelligence (AI) approaches to vessel‐counting fall into two categories: semantic segmentation, which provides a continuous mask, and instance segmentation, which treats each vessel as a separate object; prior work has emphasized the former. To address this gap, we adopted an instance‐level approach to detect and count individual vessels. We developed a convolutional neural network (CNN) to quantify CD34‐positive vessels in lymph‐node WSIs, using U‐Net, a widely used biomedical segmentation architecture. The model was trained over 4.0 million (4.0 M) iterations, followed by a fixed post‐processing procedure to extract vessel instances. At 3.0 M, the model most faithfully captured CD34‐positive vascular morphology. In the validation set, this checkpoint showed the highest morphological similarity. Furthermore, detection performance was robust with minimal variation across lymph nodes and training checkpoints. Using a simple fixed procedure, our method achieves accurate vessel detection and counting in lymph‐node WSIs. This model provides a practical basis for standardized quantification and for studying lymph‐node vascular morphology across normal, inflammatory, and lymphomatous states.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Lymph NodesAntigens, CD34Image Processing, Computer-AssistedHumansConvolutional Neural NetworksDeep Learning

Stichwörter der Autor:innen

AICD34deep learninglymph nodesvessels

Substanzen

Antigens, CD34

Autor:innen und Institutionen

  • Department of Pathology, Faculty of Medical Sciences, University of Fukui, Eiheiji, Fukui, Japan.

ORCID-Profile: Motohiro Kobayashi

Zitieren

APA

Omotani, S., Yonemoto, N., Muramoto, A., & Kobayashi, M. (2026). Standardized Instance‐Level Quantification of CD34‐Positive Vessels in Lymph Node Whole‐Slide Images Using U‐Net. Pathology International, 76(5). https://doi.org/10.1111/pin.70125

Vancouver

Omotani S, Yonemoto N, Muramoto A, Kobayashi M. Standardized Instance‐Level Quantification of CD34‐Positive Vessels in Lymph Node Whole‐Slide Images Using U‐Net. Pathology International. 2026;76(5). doi:10.1111/pin.70125

BibTeX
@article{Omotani2026,
  author = {Omotani, Satomi and Yonemoto, Natsumi and Muramoto, Akifumi and Kobayashi, Motohiro},
  title = {Standardized Instance‐Level Quantification of CD34‐Positive Vessels in Lymph Node Whole‐Slide Images Using U‐Net},
  journal = {Pathology International},
  year = {2026},
  volume = {76},
  number = {5},
  doi = {10.1111/pin.70125}
}
Kostenlos starten →