polito.it
Politecnico di Torino (logo)

Neuromorphic methods for the analysis, detection and classification of chronic wounds

Sara Becchi

Neuromorphic methods for the analysis, detection and classification of chronic wounds.

Rel. Jacopo Secco, Filippo Begarani, Elisabetta Spinazzola. Politecnico di Torino, Corso di laurea magistrale in Ingegneria Biomedica, 2024

[img]
Preview
PDF (Tesi_di_laurea) - Tesi
Licenza: Creative Commons Attribution Non-commercial No Derivatives.

Download (11MB) | Preview
Abstract:

Vulnology is a field focused on treating wounds, an often underestimated health issue. When a chronic ulcer worsens without monitoring it can become chronic in 30 % of cases sometimes leading to non healing wounds and, in severe instances, even death. Hence consistent follow up care is essential to prevent complications. It's crucial to establish protocols in this area and incorporate telemedicine tools to aid healthcare providers. With the advancements in deep learning technology for image analysis neuromorphic systems are now being integrated into devices to assist clinicians during examinations. These systems can automatically analyze wound images using deep learning algorithms reducing the need for contact and lowering the risk of exacerbating the wound condition. It is crucial to assess the capability of these algorithms to identify and classify wounds, and simultaneously determine which medical images are best suited for extracting useful features. After examining the field and considering the methods used, it was decided to evaluate the capabilities of the algorithm through the use of thermal images.This method represents a new approach within the framework of automated assessments to wound management. By accomplishing this task we can offer vulnologists an AI powered tool that streamlines their work process, enhances examination quality and follow up care and fosters efficient healing outcomes for patients.

Relators: Jacopo Secco, Filippo Begarani, Elisabetta Spinazzola
Academic year: 2023/24
Publication type: Electronic
Number of Pages: 73
Subjects:
Corso di laurea: Corso di laurea magistrale in Ingegneria Biomedica
Classe di laurea: New organization > Master science > LM-21 - BIOMEDICAL ENGINEERING
Aziende collaboratrici: Omnidermal Biomedics srl
URI: http://webthesis.biblio.polito.it/id/eprint/32093
Modify record (reserved for operators) Modify record (reserved for operators)