Development of Diabetic Foot Ulcer Datasets: An Overview

This paper provides conceptual foundation and procedures used in the development of diabetic foot ulcer datasets over the past decade, with a timeline to demonstrate progress. We conduct a survey on data capturing methods for foot photographs, an overview of research in developing private and public datasets, the related computer vision tasks (detection, segmentation and classification), the diabetic foot ulcer challenges and the future direction of the development of the datasets. We report the distribution of dataset users by country and year. Our aim is to share the technical challenges that we encountered together with good practices in dataset development, and provide motivation for other researchers to participate in data sharing in this domain.

[1]  Chuan Wang,et al.  Recognition of Ischaemia and Infection in Diabetic Foot Ulcers: Dataset and Techniques , 2019, Comput. Biol. Medicine.

[2]  Ross Brown,et al.  MyFootCare: a mobile self-tracking tool to promote self-care amongst people with diabetic foot ulcers , 2017, OZCHI.

[3]  J. Contreras-Ruiz,et al.  Telemedicine in Wound Care: A Review , 2013, Advances in skin & wound care.

[4]  David G. Armstrong,et al.  Diabetic Foot Ulcer Grand Challenge 2021: Evaluation and Summary , 2021, DFUC@MICCAI.

[5]  Moi Hoon Yap,et al.  Manual Whisker Annotator (MWA): A Modular Open-Source Tool , 2016 .

[7]  W. Mack,et al.  Initial Clinical Experience with a Simple, Home System for Early Detection and Monitoring of Diabetic Foot Ulcers: The Foot Selfie , 2021, Journal of diabetes science and technology.

[8]  C. Attinger,et al.  Cost of treating diabetic foot ulcers in five different countries , 2012, Diabetes/metabolism research and reviews.

[9]  J. Lindberg Predicting Clinical Outcomes in a Diabetic Foot Ulcer Population Using Fluorescence Imaging. , 2021, Advances in skin & wound care.

[10]  Xiaoxuan Liu,et al.  Characteristics of publicly available skin cancer image datasets: a systematic review. , 2021, The Lancet. Digital health.

[11]  Moi Hoon Yap,et al.  Diabetic foot ulcer classification using mapped binary patterns and convolutional neural networks , 2021, Comput. Biol. Medicine.

[12]  Moi Hoon Yap,et al.  Diabetic Foot Ulcers Grand Challenge 2022 , 2021 .

[13]  Bengisu Tulu,et al.  Smartphone-Based Wound Assessment System for Patients With Diabetes , 2015, IEEE Transactions on Biomedical Engineering.

[14]  Moi Hoon Yap,et al.  Analysis of the ISIC image datasets: Usage, benchmarks and recommendations , 2021, Medical Image Anal..

[15]  Moi Hoon Yap,et al.  Diabetic Foot Ulcers Grand Challenge 2020 , 2020 .

[16]  J. Teh,et al.  MRI of the diabetic foot: differentiation of infection from neuropathic change. , 2007, The British journal of radiology.

[17]  Moi Hoon Yap,et al.  Analysis Towards Classification of Infection and Ischaemia of Diabetic Foot Ulcers , 2021, 2021 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI).

[18]  Neil D. Reeves,et al.  Fully convolutional networks for diabetic foot ulcer segmentation , 2017, 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[19]  Moi Hoon Yap,et al.  Diabetic Foot Ulcers Grand Challenge 2021 , 2020 .

[20]  B. Tulu,et al.  An Automatic Assessment System of Diabetic Foot Ulcers Based on Wound Area Determination, Color Segmentation, and Healing Score Evaluation , 2016, Journal of diabetes science and technology.

[21]  M. Huijberts,et al.  Delivery of care to diabetic patients with foot ulcers in daily practice: results of the Eurodiale Study, a prospective cohort study , 2008, Diabetic medicine : a journal of the British Diabetic Association.

[22]  J. Shaw,et al.  Diabetes: a 21st century challenge. , 2014, The lancet. Diabetes & endocrinology.

[23]  R. Forsythe,et al.  Assessment of foot perfusion in patients with a diabetic foot ulcer , 2016, Diabetes/metabolism research and reviews.

[24]  F. Vinicor The Public Health Burden of Diabetes and the Reality of Limits , 1998, Diabetes Care.

[25]  P. Tschandl,et al.  Checklist for Evaluation of Image-Based Artificial Intelligence Reports in Dermatology: CLEAR Derm Consensus Guidelines From the International Skin Imaging Collaboration Artificial Intelligence Working Group. , 2021, JAMA dermatology.

[26]  Zeyun Yu,et al.  Fully automatic wound segmentation with deep convolutional neural networks , 2020, Scientific Reports.

[27]  Neil D. Reeves,et al.  DFUNet: Convolutional Neural Networks for Diabetic Foot Ulcer Classification , 2017, IEEE Transactions on Emerging Topics in Computational Intelligence.

[28]  Moi Hoon Yap,et al.  Computer Vision Algorithms in the Detection of Diabetic Foot Ulceration , 2016, Journal of diabetes science and technology.

[29]  G. V. von Schulthess,et al.  Unsuspected osteomyelitis is frequent in persistent diabetic foot ulcer and better diagnosed by MRI than by 18F‐FDG PET or 99mTc‐MOAB , 2007, Journal of internal medicine.

[30]  Abhishek Dutta,et al.  The VGG Image Annotator (VIA) , 2019, ArXiv.

[31]  Moi Hoon Yap,et al.  A Cloud-Based Deep Learning Framework for Remote Detection of Diabetic Foot Ulcers , 2021, IEEE Pervasive Computing.

[32]  Zeyun Yu,et al.  Foot Ulcer Segmentation Challenge 2021 , 2021 .

[33]  David G Armstrong,et al.  Validation of a Diabetic Wound Classification System: The contribution of depth, infection, and ischemia to risk of amputation , 1998, Diabetes Care.

[34]  Manu Goyal,et al.  Region of Interest Detection in Dermoscopic Images for Natural Data-augmentation , 2018, ArXiv.

[35]  Sicco A Bus,et al.  Diabetic Foot Ulcers and Their Recurrence. , 2017, The New England journal of medicine.

[36]  David Wertheim,et al.  Infrared imaging in diabetic foot ulceration , 1998, Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol.20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No.98CH36286).

[37]  Philip Foden,et al.  Innovative intelligent insole system reduces diabetic foot ulcer recurrence at plantar sites: a prospective, randomised, proof-of-concept study. , 2019, The Lancet. Digital health.

[38]  Manu Goyal,et al.  Robust Methods for Real-Time Diabetic Foot Ulcer Detection and Localization on Mobile Devices , 2019, IEEE Journal of Biomedical and Health Informatics.

[39]  J. V. van Netten,et al.  Infrared Thermal Imaging for Automated Detection of Diabetic Foot Complications , 2013, Journal of diabetes science and technology.

[40]  Moi Hoon Yap,et al.  The DFUC 2020 Dataset: Analysis Towards Diabetic Foot Ulcer Detection. , 2021, TouchREVIEWS in endocrinology.

[41]  Bengisu Tulu,et al.  Area Determination of Diabetic Foot Ulcer Images Using a Cascaded Two-Stage SVM-Based Classification , 2017, IEEE Transactions on Biomedical Engineering.

[42]  Saeed Hassanpour,et al.  Deep Learning in Diabetic Foot Ulcers Detection: A Comprehensive Evaluation , 2020, Comput. Biol. Medicine.

[43]  Moi Hoon Yap,et al.  A New Mobile Application for Standardizing Diabetic Foot Images , 2018, Journal of diabetes science and technology.