A novel approach for diabetic foot diagnosis: Deep learning-based detection of lower extremity arterial stenosis
Study context
- Population
- Patients with diabetic foot ulcer (DFU); detection of three types of lower extremity arterial stenosis (LEAS) (I: <50 %, II: 51 % - 99 %, III: completely occluded)
- Comparison
- Improved YOLOv5-based model vs five other prominent models
- Outcome
- Average ability to detect three types of stenosis
Methodological detailsdeep learning, improved YOLOv5 model, comparison with five other models
- Deep learning
- Improved YOLOv5 model
- Comparison with five other models
Performance
As reported in the abstract
Our method had the best average ability to detect three types of stenosis: Mean Average Precision (mAP)
85.40%
Our method: Frames Per Second (FPS)
74.60
Original publication
A novel approach for diabetic foot diagnosis: Deep learning-based detection of lower extremity arterial stenosis. Diabetes Res Clin Pract. Published 2 December 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →