A Cloud-Based Deep Learning Framework for Remote Detection of Diabetic Foot Ulcers

Bill Cassidy,David Gillespie,Samantha Haycocks,Naseer Ahmad,Joseph M Pappachan,Moi Hoon Yap,Neil D Reeves

doi:10.1109/mprv.2021.3135686

Abstract

This research proposes a mobile and cloud-based framework for the automatic detection of diabetic foot ulcers and conducts an investigation of its performance. The system uses a cross-platform mobile framework which enables the deployment of mobile apps to multiple platforms using a single TypeScript code base. A deep convolutional neural network was deployed to a cloud-based platform where the mobile app could send photographs of patient's feet for inference to detect the presence of diabetic foot ulcers. The functionality and usability of the system were tested in two clinical settings: Salford Royal NHS Foundation Trust and Lancashire Teaching Hospitals NHS Foundation Trust. The benefits of the system, such as the potential use of the app by patients to identify and monitor their condition are discussed.

Highlights

A deep convolutional neural network was deployed to a cloud-based platform where the mobile app could send photographs of patient’s feet for inference to detect the presence of diabetic foot ulcers
We developed a cross-platform mobile app and a cloud-based deep learning framework for the automatic detection of Diabetic foot ulcers (DFU)
The dataset obtained over the six-month evaluation period will be used to retrain the existing model to improve its ability to detect DFU at various stages of development

Summary

Introduction

Lancashire Teaching Hospitals NHS Foundation Trust, PR2 9HT, U.K., Manchester Metropolitan University, Manchester, M1 5GD, U.K. and University of Manchester, Manchester, M13 9PL, U.K. Naseer Ahmad, Manchester University NHS Foundation Trust, Manchester, M13 9WL, U.K. Samantha Haycocks, Salford Royal NHS Foundation Trust, Salford, M6 8HD, U.K. David Gillespie and Moi Hoon Yap , Manchester Metropolitan University, Manchester, M1 5GD, U.K. This research proposes a mobile and cloud-based framework for the automatic detection of diabetic foot ulcers and conducts an investigation of its performance. Diabetes mellitus is a chronic metabolic disorder, and a growing world-wide epidemic.[1] Diabetic foot ulcers (DFU) are wounds developed on the feet that represent serious complications resulting from diabetes, and are prone to high recurrence and infection.[2] There are numerous potential contributing factors to the development of DFU, with diagnosis, monitoring, and treatment programs requiring multidisciplinary medical expertise. More than half of DFUs become infected, with approximately 20% of moderate or severe DFU infections leading to lower extremity amputation.[5]

Objectives

Results

Conclusion