AI-Enhanced Imaging for Diabetic Foot Ulcer Risk Assessment and Diagnosis: A Retrospective Cohort Study
Authors' conclusion
The comparative analysis demonstrated that the proposed method significantly improved both segmentation and classification of DFUs, thereby supporting enhanced clinical management of the condition.
Study context
- Population
- Patients with diabetic foot ulcer (DFU) in India
- Participants
- 510 patients1,339 ulcer images
- Outcome
- DFU segmentation and Wagner-grade severity classification performance
Methodological detailsArtificial intelligence (AI) model development and evaluation, Images augmented to 6579 for AI-model generalizability, AI-powered mobile app developed for real-time and remote DFU severity assessment
- AI model development and evaluation
- Images augmented to 6579 for AI-model generalizability
- AI-powered mobile app developed for real-time and remote DFU severity assessment
Main finding
As reported in the abstract
- Segmentation Dice similarity coefficient
- 0.99
- Classification accuracy
- 95.58%
- Classification sensitivity
- 95.58%
- Classification specificity
- 99.16%
- Classification F1 score
- 95.53%
- False-positive rate
- 0.84%
- False-negative rate
- 4.83%
Observational data: associations, not effects.
Original publication
AI-Enhanced Imaging for Diabetic Foot Ulcer Risk Assessment and Diagnosis: A Retrospective Cohort Study. J Diabetes Sci Technol. Published 15 January 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →