Towards Home-Based Diabetic Foot Ulcer Monitoring: A Systematic Review

Abstract

It is considered that 1 in 10 adults worldwide have diabetes. Diabetic foot ulcers are some of the most common complications of diabetes, and they are associated with a high risk of lower-limb amputation and, as a result, reduced life expectancy. Timely detection and periodic ulcer monitoring can considerably decrease amputation rates. Recent research has demonstrated that computer vision can be used to identify foot ulcers and perform non-contact telemetry by using ulcer and tissue area segmentation. However, the applications are limited to controlled lighting conditions, and expert knowledge is required for dataset annotation. This paper reviews the latest publications on the use of artificial intelligence for ulcer area detection and segmentation. The PRISMA methodology was used to search for and select articles, and the selected articles were reviewed to collect quantitative and qualitative data. Qualitative data were used to describe the methodologies used in individual studies, while quantitative data were used for generalization in terms of dataset preparation and feature extraction. Publicly available datasets were accounted for, and methods for preprocessing, augmentation, and feature extraction were evaluated. It was concluded that public datasets can be used to form a bigger, more diverse datasets, and the prospects of wider image preprocessing and the adoption of augmentation require further research.

Analysis of Training Data Augmentation for Diabetic Foot Ulcer Semantic Segmentation

“…This section introduces the most common augmentation methods [8]; only the classical methods [7] are considered. Classical methods can be grouped into two bulk categories: geometric and photometric.…”

“…Blending ratio: al pha ∈ [0.0; 30] All the augmentation techniques listed in the above table were implemented using the imgaug library [31]. Parameter ranges, as provided in the above table, were derived from the metadata of a systematic review [8] and were considered as a good starting point that was proven in previous research. In past research, the actual parameter values (except for flip augmentation) or rules for their selection have rarely been defined; therefore, we decided to use boundary and middle (original samples) values.…”

“…In a recent systematic review on monitoring diabetic foot ulcers using deep learning [8], it was found that some researchers use augmentation excessively and not enough test data…”

Protocol for metadata and image collection at diabetic foot ulcer clinics: enabling research in wound analytics and deep learning

“…Research and development of such methods for DFU diagnosis and treatment have been limited for two reasons [ 21 – 25 ]: 1. absence of large holistic DFU datasets, and 2. incomparability of available datasets due to a wide variety of data collection methods. For example, whilst regular red–green–blue (RGB) images [ 26 ] are important in classifying DFUs, other factors such as temperature, moisture, odour, pain, wound onset, age, sex, and gender are essential in evaluating the wound condition [ 27 , 28 ].…”

A feasibility study on the efficacy of a patient-owned wound surveillance system for diabetic foot ulcer care (ePOWS study)

“… 10 Besides these commercially available solutions, a number of de-novo machine learning algorithms to recognize, assess, or predict the healing of DFUs have also been described in the literature by academic groups. 11 – 14 Patients empowered with these semi-autonomous solutions may, in theory, be able to conduct their technology-guided wound surveillance.…”