Machine Learning in the Prevention, Diagnosis and Management of Diabetic Foot Ulcers: A Systematic Review

Tulloch, Jack; Zamani, Reza; Akrami, Mohammad

doi:10.1109/access.2020.3035327

Cited by 51 publications

(29 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, CNN has taken some medical imaging classification tasks to different level from traditional diagnosis to automated diagnosis with tremendous performance. Examples of these tasks are diabetic foot ulcer (DFU) (as normal and abnormal (DFU) classes) [87,[243][244][245][246], sickle cells anemia (SCA) (as normal, abnormal (SCA), and other blood components) [86,247], breast cancer by classify hematoxylin-eosin-stained breast biopsy images into four classes: invasive carcinoma, in-situ carcinoma, benign tumor and normal tissue [42,88,[248][249][250][251][252], and multi-class skin cancer classification [253][254][255].…”

Section: Classificationmentioning

confidence: 99%

Review of deep learning: concepts, CNN architectures, challenges, applications, future directions

et al. 2021

View full text Add to dashboard Cite

In the last few years, the deep learning (DL) computing paradigm has been deemed the Gold Standard in the machine learning (ML) community. Moreover, it has gradually become the most widely used computational approach in the field of ML, thus achieving outstanding results on several complex cognitive tasks, matching or even beating those provided by human performance. One of the benefits of DL is the ability to learn massive amounts of data. The DL field has grown fast in the last few years and it has been extensively used to successfully address a wide range of traditional applications. More importantly, DL has outperformed well-known ML techniques in many domains, e.g., cybersecurity, natural language processing, bioinformatics, robotics and control, and medical information processing, among many others. Despite it has been contributed several works reviewing the State-of-the-Art on DL, all of them only tackled one aspect of the DL, which leads to an overall lack of knowledge about it. Therefore, in this contribution, we propose using a more holistic approach in order to provide a more suitable starting point from which to develop a full understanding of DL. Specifically, this review attempts to provide a more comprehensive survey of the most important aspects of DL and including those enhancements recently added to the field. In particular, this paper outlines the importance of DL, presents the types of DL techniques and networks. It then presents convolutional neural networks (CNNs) which the most utilized DL network type and describes the development of CNNs architectures together with their main features, e.g., starting with the AlexNet network and closing with the High-Resolution network (HR.Net). Finally, we further present the challenges and suggested solutions to help researchers understand the existing research gaps. It is followed by a list of the major DL applications. Computational tools including FPGA, GPU, and CPU are summarized along with a description of their influence on DL. The paper ends with the evolution matrix, benchmark datasets, and summary and conclusion.

show abstract

Section: Classificationmentioning

confidence: 99%

Review of deep learning: concepts, CNN architectures, challenges, applications, future directions

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The cost of DFU treatment is usually high, and mortality rates increase if the condition is not treated at an early stage. The critical parameters for predicting the DFU's amputation risk or healing potential are detecting and diagnosing the infection or areas of ischemia (Tulloch, Zamani & Akrami, 2020). Chronic diabetes in the human body causes poor blood circulation that in turn causes ischemia (Everett & Mathioudakis, 2018).…”

Section: Diabetic Foot Ulcermentioning

confidence: 99%

Deepening into the suitability of using pre-trained models of ImageNet against a lightweight convolutional neural network in medical imaging: an experimental study

Alzubaidi

Duan

Al-Dujaili

et al. 2021

PeerJ Computer Science

View full text Add to dashboard Cite

Transfer learning (TL) has been widely utilized to address the lack of training data for deep learning models. Specifically, one of the most popular uses of TL has been for the pre-trained models of the ImageNet dataset. Nevertheless, although these pre-trained models have shown an effective performance in several domains of application, those models may not offer significant benefits in all instances when dealing with medical imaging scenarios. Such models were designed to classify a thousand classes of natural images. There are fundamental differences between these models and those dealing with medical imaging tasks regarding learned features. Most medical imaging applications range from two to ten different classes, where we suspect that it would not be necessary to employ deeper learning models. This paper investigates such a hypothesis and develops an experimental study to examine the corresponding conclusions about this issue. The lightweight convolutional neural network (CNN) model and the pre-trained models have been evaluated using three different medical imaging datasets. We have trained the lightweight CNN model and the pre-trained models with two scenarios which are with a small number of images once and a large number of images once again. Surprisingly, it has been found that the lightweight model trained from scratch achieved a more competitive performance when compared to the pre-trained model. More importantly, the lightweight CNN model can be successfully trained and tested using basic computational tools and provide high-quality results, specifically when using medical imaging datasets.

show abstract

“…Preventive care by regular monitoring and correct assessment limits the incidence of disabling conditions and the lower-limb amputations associated with acute cases [4][5][6]. Therefore, improved medical care, by monitoring the patient's condition over time, is required to identify higher risk patients and prevent the significant impact caused by economic burden [7]. This demands fast, simple, autonomous, repeatable and precise screening protocols, avoiding error-prone and labor-intensive processes as well as the requirement of special training [6,7].…”

Section: Introductionmentioning

confidence: 99%

“…However, the optimal cut-off is a subject of controversy. In patients affected by diabetic foot infection, a plantar foot asymmetry of 1.35 • C suffices to seek urgent treatment [16], whereas a threshold of 2.2 • C is usually considered for an inflammatory process and the impending development of a foot ulcer [7,17,18]. In fact, it has been suggested that thermal asymmetry monitoring has no additional value for assessing the severity of diabetic foot infections [15].…”

Section: Introductionmentioning

confidence: 99%

Morphological Foot Model for Temperature Pattern Analysis Proposed for Diabetic Foot Disorders

et al. 2021

View full text Add to dashboard Cite

Infrared thermography is a non-invasive and accessible tool that maps the surface temperature of a body. This technology is particularly useful for diabetic foot disorders, since it facilitates the identification of higher risk patients by frequent monitoring and therefore limits the incidence of disabling conditions. The aim of this work is to provide a methodology to explore the entire plantar aspects of both feet, based on infrared thermography, for the assessment of diabetic foot anomalies. A non-invasive methodology was established to identify areas of higher risk and track their progress via longitudinal monitoring. A standard morphological model was extracted from a group of healthy subjects, nine females and 13 males, by spatial image registration. This healthy foot model can be taken as a template for the assessment of temperature asymmetry, even in cases in which partial amputations or deformations are present. A pixel-wise comparison of the temperature patterns was carried out by Wilcoxon´s matched-pairs test using the corresponding template. For all the subjects, the left foot was compared to the contralateral foot, the right one, providing a map of statistically significant areas of variation, within the template, among the healthy subjects at different time points. In the female case, the main areas of variability were the boundaries of the feet, whereas for the male, in addition to this, substantial changes that exhibited a clear pattern were observed. A fast and simple monitoring tool is provided to be used for personalized medical diagnosis in patients affected by diabetic foot disorders.

show abstract

Machine Learning in the Prevention, Diagnosis and Management of Diabetic Foot Ulcers: A Systematic Review

Cited by 51 publications

References 54 publications

Review of deep learning: concepts, CNN architectures, challenges, applications, future directions

Review of deep learning: concepts, CNN architectures, challenges, applications, future directions

Deepening into the suitability of using pre-trained models of ImageNet against a lightweight convolutional neural network in medical imaging: an experimental study

Morphological Foot Model for Temperature Pattern Analysis Proposed for Diabetic Foot Disorders

Contact Info

Product

Resources

About