Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/127688
Title: Classificació del Melanoma mitjançant visualització artificial
Author: Casellas La Rosa, Pol
Tutor: Torre Gallart, Jordi de la
Abstract: It is called cancer in the set of diseases in which an uncontrolled process is observed in cell division in ANY part of the body. Today, cancer is one of the diseases with the highest mortality rate. More specifically, skin cancer is the most common type of cancer among the human population. Melanoma is the deadliest form, causing 75% of deaths from epithelial cancer. Despite the high mortality rate, as in other cancers, a rapid detection pot will lead to greater effectiveness of the treatment. Currently, the Assessment of Skin Diagnosis Diagnosis by Dermatologists has improved markedly thanks to dermatoscopy. However, it could significantly improve the accuracy of diagnostics using image classification algorithms. The image analysis tools that automate the diagnosis of melanoma have a great potential to improve the accuracy of the diagnosis of dermatologists and contribute to a rapid detection of melanoma by increasing, in this way, the probability of cure of the melanoma to millions of people. Throughout this project Patient Image Sets are used in order to determine the existence or not of melanoma using Image Classification algorithms.
Keywords: deep learning
image classification
melanoma
Document type: info:eu-repo/semantics/masterThesis
Issue Date: 3-Jan-2021
Publication license: http://creativecommons.org/licenses/by-nc-nd/3.0/es/  
Appears in Collections:Trabajos finales de carrera, trabajos de investigación, etc.

Files in This Item:
File Description SizeFormat 
pcasellaslTFM0121memòria.pdfMemòria del TFM2,18 MBAdobe PDFThumbnail
View/Open
Share:
Export:
View statistics

This item is licensed under aCreative Commons License Creative Commons