Aifu Han*,***, Yongze Zhang**,****, Qiong Liu*****, Qiujie Dong*,***, Fengying Zhao**,****, Ximei Shen**,****, Yanting Liu*, Sunjie Yan**,****,#, Shengzong Zhou*,#
*Fujian Institute of Research on the Structure of Matter Chinese Academy of Sciences, Fuzhou 350002, China - **Department of Endocrinology, the First Affiliated Hospital of Fujian Medical University, Fuzhou 350005, China - ***North University of China, Taiyuan 030051, China - ****Diabetes Research Institute of Fujian Province, Fuzhou 350005, China- *****Department of Control and Systems Engineering, Nanjing University, Nanjing, 210093, China
Objective: To developed auto screening diabetic foot Wagner grade systems as a means of assisted diagnosis and assessment to alleviate part of the workload for podiatrists.
Methods: we propose to use the Faster-RCNN algorithm based on the ResNet-50 backbone network to achieve automatic detection and localization of the Wagner grades of diabetic foot. To build a robust deep learning model, we collected 2,688 images of the diabetic foot as datasets for model training. We combines the Kmeans++ algorithm to improve the generation method of anchor boxes and obtains the Wagner grades automatic screening model for the diabetic foot with good robust performance.
Results: By improving the generation method of anchor boxes, refinements on Faster-RCNN models reach a mean average precision (mAP) of 91.36% in the diabetic foot datasets.
Conclusion: This work has the potential to lead to nursing methods shift in the clinical treatment of diabetic feet in the future, to provide a better self-management solution for patients with diabetic feet.
Diabetic foot, Faster-RCNN, deep learning, Wagner grades.
10.19193/0393-6384_2020_1_104