Academic Journal

A novel RSCA-YOLOv8s network for automatic diagnosis and graduation in pressure injury.

Bibliographic Details
Title: A novel RSCA-YOLOv8s network for automatic diagnosis and graduation in pressure injury.
Authors: Hu C; The Affiliated Hospital of Jiaxing University, Jiaxing, China., Sheng H; The Affiliated Hospital of Jiaxing University, Jiaxing, China., Zhang D; The Affiliated Hospital of Jiaxing University, Jiaxing, China., Zhu Z; The Affiliated Hospital of Jiaxing University, Jiaxing, China. Electronic address: zzh2025zszq@163.com., Xu D; Tongji Zhejiang College, Jiaxing, China., Ye M; The Third Affiliated Hospital of Jiaxing University, Jiaxing, China.
Source: Geriatric nursing (New York, N.Y.) [Geriatr Nurs] 2026 Jul; Vol. 71, pp. 104084. Date of Electronic Publication: 2026 May 22.
Publication Type: Journal Article
Language: English
Journal Info: Publisher: Mosby-Yearbook Country of Publication: United States NLM ID: 8309633 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1528-3984 (Electronic) Linking ISSN: 01974572 NLM ISO Abbreviation: Geriatr Nurs Subsets: MEDLINE
Imprint Name(s): Publication: St Louis Mo : Mosby-Yearbook
Original Publication: [New York : American Journal of Nursing Co.
MeSH Terms: Pressure Ulcer*/diagnosis , Detection Algorithms*, Humans
Abstract: To enhance the accuracy and objectivity in PI diagnosis, this study proposes an improved PI recognition method based on YOLOv8s, which introduces a spatial and channel synergistic attention mechanism in the C2f module to enhance the feature extraction capability and embeds a multi-scale fusion module to improve the model's ability to recognize PI varying scales. This study was conducted from January 2024 to December 2024, during which 366 PI images were collected by standardized trained nurses from two tertiary Grade A hospitals in Jiaxing. The dataset was divided into a training set and a validation set in an 8:2 ratio. The improved YOLOv8s, YOLOv5, TPH-YOLO, YOLOv7, YOLOv8s, and Swin Transformer models were employed for training. Model performance was evaluated using precision, recall, F1-score, mean average precision(mAP50), and mean average precision(mAP50:95). The results show that the improved YOLOv8s outperforms the algorithms of YOLOv5, TPH-YOLO, YOLOv7, and Swin transformer in the PI staging task, with an mean average precision (mAP50) of 92.0%, and precision(P) of 86.7%, which are significantly better than those of the other models; moreover, compared with the original YOLOv8s, the improved YOLOv8s algorithm precision increased by 6.5%, mAP50 and mAP50:95 increased by 14% and 14.9%, respectively, and the recognition accuracy in each stage of PI (stage 1-4) was 89.3%, 84.3%, 73.2% and 100%, respectively. These results indicate that the improved YOLOv8s in this study can effectively recognize PI with different stages and provide an objective and reliable auxiliary tool for clinical diagnosis.(ChiCTR:250,289).
(Copyright © 2026 Elsevier Inc. All rights reserved.)
Competing Interests: Declaration of competing interest Author Chen Hu declares that she has no conflict of interest; Author Han Sheng declares that she has no conflict of interest; Author Danying Zhang declares that she has no conflict of interest; Author Zhihong Zhu declares that she has no conflict of interest; Author Dong xu declares that he has no conflict of interest; Author Min Ye declares that she has no conflict of interest. This article contains no studies with human participants performed by any authors.
Contributed Indexing: Keywords: Automatic diagnosis; Graduation; Pressure injuries; YOLOv8s
Entry Date(s): Date Created: 20260521 Date Completed: 20260716 Latest Revision: 20260716
Update Code: 20260717
DOI: 10.1016/j.gerinurse.2026.104084
PMID: 42167079
Database: MEDLINE
Description
ISSN:1528-3984
DOI:10.1016/j.gerinurse.2026.104084