Work

YOLOv7-PSA, an intelligent detection model, is designed for assessing the severity of skin burns

Year: 2025

Type: article

Abstract: We have developed an intelligent burn severity detection model called YOLOv7-PSA based on deep learning techniques and verified its efficiency and accuracy in assessing the severity of burn injuries. First, we collected 492 wound photos from burn patients that met research standards. Burn plastic surgeons used LabelMe to annotate the target wounds in these photos and determine their severity. Subsequently, we expanded the burn patient wound photo dataset to 2952images and divided it into training, validation, and test sets in a 7:2:1 ratio. Through testing, the YOLOv7-PSA model achieved accuracies of 86%, 87%, and 91% for detecting first-degree, second-degree, and third-degree burns, respectively. This model holds promise for improving the diagnostic efficiency and precision of burn specialists and assisting physicians in assessing burn severity.

Source: Regenesis repair rehabilitation.

DOI: 10.1016/j.rerere.2025.03.002

Authors: Yuhong Luo, Kecheng Zhang, Rui Wang, Lei Yi, Zengding Zhou

Institutions: Shanghai Jiao Tong University, Ruijin Hospital, Shanghai University

Language: English

Topic: Burn Injury Management and Outcomes

Subfield: Epidemiology

Field: Medicine

Domain: Health Sciences

SDG: Good health and well-being

Open Access status: diamond

Funders: National Natural Science Foundation of China, Science and Technology Innovation Plan Of Shanghai Science and Technology Commission