Validation of a You Only Look Once– LabelMe Hybrid AI Model for Automated Assessment of Pressure Injury Size and Pocket
International Wound Journal · 2026-08 · 23 (8)
DOI: 10.1111/iwj.71012 ↗Kurz gefasst
Validierungsstudie in der Zeitschrift International Wound Journal, online erschienen am 05.08.2026. Verfasst von Kento Ikuta und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Plastic and Reconstructive Surgery, Tottori University Hospital, Yonago, Japan. Hauptthemen laut MEDLINE: Pressure Ulcer, Wound Healing, Artificial Intelligence, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 10 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Tottori University, Japan Society for the Promotion of Science.
Themen: Dekubitus
Abstract (Originalsprache)
Quantitative assessment of the pressure injury size (S) and pocket (P, undermining) is essential for evaluating wound healing. Conventional LabelMe annotations often lead to oversegmentation, whereas object detection with You Only Look Once (YOLO) enables accurate wound localization. Here, we developed a hybrid AI model that combines LabelMe segmentation with YOLO gating. This single‐centre retrospective study compared two models: LabelMe‐Seeded Auto‐Recognition (LSAR) and YOLO‐gated LSAR (YGL). Model performance was evaluated by concordance rate and weighted Cohen's κ for DESIGN‐R staging and by mean absolute error (MAE) and median (interquartile range) for area error. Overall, 1017 wound images (training: 979; testing: 38) were analysed. For S, the YGL model achieved higher concordance (85.7%, κ = 0.969) and smaller area errors than did the LSAR. For P, the YGL model demonstrated higher concordance and smaller area errors than did the LSAR model. The YOLO–LabelMe hybrid model improved the stage concordance and size accuracy compared with LabelMe alone. Despite the residual outliers in P assessment, this approach represents a promising step towards automated, clinically adaptable wound measurements.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Plastic and Reconstructive Surgery, Tottori University Hospital, Yonago, Japan.
- Department of Plastic and Reconstructive Surgery, Japanese Red Cross Tottori Hospital, Tottori, Japan.
- Department of Plastic and Reconstructive Surgery, Nagoya University School of Medicine, Nagoya, Japan.
- Focus Systems Corporation, Tokyo, Japan.
ORCID-Profile: Kento Ikuta, Hiroyuki Nishikawa, Shunjiro Yagi
Förderung
- Tottori University
- Japan Society for the Promotion of Science
Zitieren
APA
Ikuta, K., Fukuoka, K., Nakagaki, M., Ohga, M., Suyama, Y., Kanayama, H., Fujii, N., Konishi, M., Nishikawa, H., & Yagi, S. (2026). Validation of a You Only Look Once– LabelMe Hybrid AI Model for Automated Assessment of Pressure Injury Size and Pocket. International Wound Journal, 23(8). https://doi.org/10.1111/iwj.71012
Vancouver
Ikuta K, Fukuoka K, Nakagaki M, Ohga M, Suyama Y, Kanayama H, et al. Validation of a You Only Look Once– LabelMe Hybrid AI Model for Automated Assessment of Pressure Injury Size and Pocket. International Wound Journal. 2026;23(8). doi:10.1111/iwj.71012
BibTeX
@article{Ikuta2026,
author = {Ikuta, Kento and Fukuoka, Kohei and Nakagaki, Makoto and Ohga, Makoto and Suyama, Yoshiko and Kanayama, Haruka and Fujii, Natsuko and Konishi, Mamoru and Nishikawa, Hiroyuki and Yagi, Shunjiro},
title = {Validation of a You Only Look Once– LabelMe Hybrid AI Model for Automated Assessment of Pressure Injury Size and Pocket},
journal = {International Wound Journal},
year = {2026},
volume = {23},
number = {8},
doi = {10.1111/iwj.71012}
}
EUVIMED