Research impact: Smart technology and ulcer detection
The development of FootSnap AI, an app that can identify diabetic foot ulcers, aims to reduce amputation rates and deliver significant time and cost-savings for health services.
Research summary
Research summary
Diabetic foot problems are a global financial and health burden.
In Greater Manchester, where 7,000 wounds (ulcers) are dressed on average twice a week, foot ulcers resulting from diabetes are one of the major causes of limb amputation - an operation to remove part of the foot or leg.
In partnership with Manchester University NHS Foundation Trust and Oracle Cloud Platform, our research is focusing on a solution to reduce the number and severity of diabetic foot ulcerations.
Using Oracle’s high-performance computing, we have developed artificial intelligence (AI) algorithms that use computer vision technology to identify a foot ulcer at various stages of its development.
The FootSnap AI application can automatically identify diabetic foot ulcers and associated pathologies using deep learning.
Statistics
FootSnap AI
Automated ulcer detection
FootSnap AI uses a mobile app to send photos of a patient’s feet to cloud-based AI technology.
The AI then determines whether there is an ulcer on the foot or not. In less than 20 seconds, patients can get feedback on their condition and relevant self-care information.
The app, which will work on any type of smartphone or tablet, will link patients to a specialist in case of a suspected foot ulcer.
The roll-out of this technology aims to reduce:
- the number of lower limb amputations
- the burden and cost of ulceration on the UK NHS
How FootSnap AI works
Dr Naseer Ahmad, Consultant Vascular Surgeon at Manchester University NHS Foundation Trust, and Dr Moi Hoon Yap, Reader in Computer Vision at Manchester Met, explain the app.Quote
Understanding the treatment of ulceration and whether these wounds are getting better or worse is essentially pattern recognition. The real breakthrough will come if we can identify these wounds much earlier and initiate much more timely treatment. This is where artificial intelligence is potentially a game-changer.
Research outputs
Research outputs
Academic papers
-
Goyal, M, Reeves, ND, Rajbhandari, S, Ahmad, N, Wang C and Yap, MH (2020) Recognition of ischaemia and infection in diabetic foot ulcers: Dataset and techniques. Computers in biology and medicine 2020 Feb 1;117:103616
-
Goyal, M, Reeves, ND, Rajbhandari, S and Yap, MH (2019) Robust Methods for Real-Time Diabetic Foot Ulcer Detection and Localization on Mobile Devices. IEEE J Biomed Health Inform. 2019;23(4):1730-1741
- Abbott, CA, Chatwin, KE, Foden, P, Hasan, AN, Sange, C, Rajbhandari, SM, Reddy, PN, Vileiktye, L, Bowling, FL, Boulton, AJM and Reeves, ND (2019) Innovative intelligent insole system reduces diabetic foot ulcer recurrence at plantar sites: a prospective, randomised, proof-of-concept study The Lancet Digital Health, 1(6), e308-e318
- Chatwin, KE, Abbott, CA, Reddy, PN, Bowling, FL, Boulton, AJM and Reeves, ND. A Foreign Body Through the Shoe of a Person With Diabetic Peripheral Neuropathy Alters Contralateral Biomechanics: Captured Through Innovative Plantar Pressure Technology. Int J Low Extrem Wounds. 2018;17(2):125-129
- Yap, MH, Chatwin, KE and Ng CC (2018) A New Mobile Application for Standardizing Diabetic Foot Images. J Diabetes Sci Technol. 2018;12(1):169-173
- Yap, MH, Ng, CC, Chatwin, K, Abbott, CA, Bowling, FL, Boulton, AJ and Reeves, ND (2015) Computer Vision Algorithms in the Detection of Diabetic Foot Ulceration: A New Paradigm for Diabetic Foot Care? Journal of diabetes science and technology, 10(2), 612–613
Research team
Research team
Partnerships
In partnership with
Manchester NHS Foundation Trust
Oracle Cloud Platform
Contact us
Contact us
For general enquiries about the Movement Impairment research theme, you can contact its lead Dr Chris Morse.
