logo SBA

ETD

Archivio digitale delle tesi discusse presso l’Università di Pisa

Tesi etd-06282021-105622


Tipo di tesi
Tesi di laurea magistrale
Autore
LORENZINI, NICOLA
URN
etd-06282021-105622
Titolo
Design and development of a dynamic thermography system to support skin lesions assessment
Dipartimento
INGEGNERIA DELL'INFORMAZIONE
Corso di studi
INGEGNERIA BIOMEDICA
Relatori
relatore Prof. Ciuti, Gastone
Parole chiave
  • thermal imaging camera
  • melanoma
  • skin lesion
  • skin cancer
Data inizio appello
16/07/2021
Consultabilità
Non consultabile
Data di rilascio
16/07/2091
Riassunto
Skin cancer is a particularly common disease. In fact, in 2020, according to the World Health Organisation skin cancer was accounted for about 8 percent of all cancers. Skin cancers, and in particular cutaneous melanoma, are easily treatable if diagnosed in the early stages. Mortality, however, increases dramatically in the more advanced stages of the disease. The aim of this study is to develop a dynamic thermography system to support the diagnosis of skin melanoma. Dynamic thermography is a non-destructive analysis technique that evaluates the thermal behaviour of a body following a thermal stimulus. The developed system includes all the necessary components and accessories to perform the thermographic procedure without additional external components. It consists of two main devices:
one, based on the use of a thermal imaging camera combined with a single board computer, is dedicated to the acquisition and processing of the acquired data.
one, based on a thermoelectric cooler, is responsible for producing the thermal stimulus.
The whole system is battery-operated, and it has been designed to be robust, easy to use and low cost.
The system was tested on some malignant lesions (including suspected melanomas and suspected basal cell carcinomas) and benign moles. Preliminary results appear to confirm the system's ability to discriminate some skin lesions from healthy tissue. However, the system has a number of limitations, in particular related to motion artefacts. The thermal image processing algorithms are not robust enough to provide accurate results under all operating conditions. Despite its many limitations, the proposed method is intended as an auxiliary tool to support current diagnostic techniques.

File