Research Article
Steps Towards Intelligent Diabetic Foot Ulcer Follow-Up Based on Deep Learning
@INPROCEEDINGS{10.1007/978-3-031-38204-8_7, author={Ant\^{o}nio Chaves and Regina Sousa and Ant\^{o}nio Abelha and Hugo Peixoto}, title={Steps Towards Intelligent Diabetic Foot Ulcer Follow-Up Based on Deep Learning}, proceedings={AI-assisted Solutions for COVID-19 and Biomedical Applications in Smart Cities. Third EAI International Conference, AISCOVID-19 2022, Braga, Portugal, November 16-18, 2022, Proceedings}, proceedings_a={AISCOVID-19}, year={2023}, month={7}, keywords={Diabetes Computer Aided Diagnosis Deep Learning Ulcer Classification Application Development}, doi={10.1007/978-3-031-38204-8_7} }- António Chaves
Regina Sousa
António Abelha
Hugo Peixoto
Year: 2023
Steps Towards Intelligent Diabetic Foot Ulcer Follow-Up Based on Deep Learning
AISCOVID-19
Springer
DOI: 10.1007/978-3-031-38204-8_7
Abstract
Diabetes is a chronic disease that affects the effective production of insulin in an individual. This incapacity leads to great damage to the cardiovascular system as well as the nervous system. Unfortunately this is a very present disease in today’s population. Indeed, global diabetes prevalence is estimated to be between 9,5% and 10,5%. Diabetic patients have a need for constant monitoring and evaluation by the healthcare professional whenever diabetic foot wounds show symptoms of infection and ulceration. The high number of patients with this diagnosis makes follow-up a problem for health professionals as well as for the patient. Lack of communication and access to health care are major contributing factors to lower extremity amputations, high mortality and morbidity interventions. In order to solve this gap, the present work presents an architecture for the development of a collaborative and decision support tool, between not only health professionals but also patients, capable of rapidly and automatically identifying, assessing and treating ulcer and symptoms of the pathology. This automation will be implemented through classification models with Deep Learning.
