AUTHOR=Wang Dongfang , Guo Lirui , Zhong Juan , Yu Huodan , Tang Yadi , Peng Li , Cai Qiuni , Qi Yangzhi , Zhang Dong , Lin Puxuan TITLE=A novel deep-learning based weighted feature fusion architecture for precise classification of pressure injury JOURNAL=Frontiers in Physiology VOLUME=Volume 15 - 2024 YEAR=2024 URL=https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2024.1304829 DOI=10.3389/fphys.2024.1304829 ISSN=1664-042X ABSTRACT=Precise classification has an important role in treatment of pressure injury (PI), while current machine-learning or deep-learning based methods of PI classification remain low accuracy. In this study, we developed a deep-learning based weighted feature fusion architecture for fine-grained classification, which combines a top-down and bottom-up pathway to fuse high-level semantic information and low-level detail representation. We validated it in our established database that consist of 1519 images from multi-center clinical cohorts. ResNeXt was set as the backbone network. We increased the accuracy of stage 3 PI from 60.3% to 76.2% by adding weighted feature pyramid network (wFPN). The accuracy for stage 1, 2, 4 PI were 0.870, 0.788, and 0.845 respectively. We found the overall accuracy, precision, recall, and F1-score of our network were 0.815, 0.808, 0.816, and 0.811 respectively. The area under the receiver operating characteristic curve was 0.940. Compared with current reported study, our network significantly increased the overall accuracy from 75% to 81.5% and showed great performance in predicting each stage. Upon further validation, our study will pave the path to the clinical application of our network in PI management.