A novel approach for diabetic foot diagnosis: Deep learning-based detection of lower extremity arterial stenosis

Chongxin Wu; Changpeng Xu; Shuanji Ou; Xiaodong Wu; Jing Guo; Yong Qi; Shuting Cai

doi:10.1016/j.diabres.2023.111032

A novel approach for diabetic foot diagnosis: Deep learning-based detection of lower extremity arterial stenosis

Diabetes Res Clin Pract. 2024 Jan:207:111032. doi: 10.1016/j.diabres.2023.111032. Epub 2023 Dec 2.

Authors

Chongxin Wu¹, Changpeng Xu², Shuanji Ou², Xiaodong Wu², Jing Guo¹, Yong Qi³, Shuting Cai⁴

Affiliations

¹ School of Automation, Guangdong University of Technology, Guangzhou 510006, China.
² Department of Orthopaedics, Guangdong Second Provincial General Hospital, Guangzhou 510317, China.
³ Department of Orthopaedics, Guangdong Second Provincial General Hospital, Guangzhou 510317, China; Guangdong Traditional Medical and Sports Injury Rehabilitation Research Institute, Guangdong Second Provincial General Hospital, Guangzhou 510317, China. Electronic address: yongqi4040@163.com.
⁴ School of Integrated Circuits, Guangdong University of Technology, Guangzhou 510006, China. Electronic address: shutingcai@gdut.edu.cn.

PMID: 38049035
DOI: 10.1016/j.diabres.2023.111032

Abstract

Purpose of the study: Assessing the lower extremity arterial stenosis scores (LEASS) in patients with diabetic foot ulcer (DFU) is a challenging task that requires considerable time and efforts from physicians, and it may yield varying results. The presence of vascular wall calcification and other irrelevant tissue information surrounding the vessel can further compound the difficulties of this evaluation. Automatic detection of lower extremity arterial stenosis (LEAS) is expected to help doctors develop treatment plans for patients faster.

Methods: In this paper, we first reconstructed the 3D model of blood vessels by medical digital image processing and then utilized it as the training data for deep learning (DL) in conjunction with the non-calcified part of blood vessels in the original data. We proposed an improved model of vascular stenosis small target detection based on YOLOv5. We added Convolutional Block Attention Module (CBAM) in backbone, replaced Path Aggregation Network (PANET) with Bidirectional Feature Pyramid Network (BiFPN) and replaced C3 with GhostC3 in neck to improve the recognition of three types of stenosis targets (I: <50 %, II: 51 % - 99 %, III: completely occluded). Additionally, we utilized K-Means++ instead of K-Means for better algorithm convergence performance, and enhanced the Complete-IoU (CIoU) loss function to Alpha-Scylla-IoU (ASIoU) loss for faster reasoning and convergence. Lastly, we conducted comparisons between our approach and five other prominent models.

Result: Our method had the best average ability to detect three types of stenosis with 85.40% mean Average Precision (mAP) and 74.60 Frames Per Second (FPS) and explored the possibility of applying DL to the detection of LEAS in diabetic foot. The code is available at github.com/wuchongxin/yolov5_LEAS.git.

Keywords: Automatic detection; Deep learning; Diabetic foot disease; Lower extremity arterial stenosis.

MeSH terms

Algorithms
Constriction, Pathologic
Deep Learning*
Diabetes Mellitus*
Diabetic Foot* / diagnosis
Humans
Lower Extremity