Please use this identifier to cite or link to this item:
http://hdl.handle.net/10609/147384
Title: | Detección temprana de cáncer de piel mediante clasificador de imágenes basado en Inteligencia Artificial |
Author: | Martín Tinaquero, David |
Tutor: | Solé-Ribalta, Albert |
Others: | Sanchez-Bocanegra, Carlos Luis Fernandez-Luque, Luis |
Abstract: | Finding skin cancer early often opens up more treatment options. Signs and symptoms do occur in some cases of early-stage disease, but this is not always the case. Currently, the most widespread methods to detect cancer in its early stages are self-examination and examination by a specialist doctor (dermatologist). The first method has the drawback that most citizens do not know how to distinguish a benign skin lesion from a cancerous one. The main drawback of the second alternative is the long waiting times to be seen by a dermatologist, since they are among the three most in-demand specialists, surpassed only by traumatologists and ophthalmologists. The objective of this work is to design and implement an early diagnosis tool that can be used in clinical practice as a support tool for the doctor, acting as a diagnostic assistant to optimize times, and also help people without dermatology knowledge by acting as an advisor for the detection of cancerous tumors during the self-examination of the skin. The work investigates the feasibility of using deep learning, specifically, convolutional and transformer neural networks, for the classification of skin lesions from images. |
Keywords: | skin cancer artificial intelligence deep learning |
Document type: | info:eu-repo/semantics/masterThesis |
Issue Date: | 15-Jan-2023 |
Publication license: | http://creativecommons.org/licenses/by-nc-nd/3.0/es/ |
Appears in Collections: | Bachelor thesis, research projects, etc. |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
TFM_David_Martin_Tinaquero.pptx | Presentación de la memoria | 3,06 MB | Microsoft Powerpoint XML | View/Open |
dmt88TFM0123memoria.pdf | Memoria del TFM | 3,74 MB | Adobe PDF | View/Open |
dmt88TFM0123presentacion.pdf | Presentación en PDF del TFM | 1,18 MB | Adobe PDF | View/Open |
Share:
This item is licensed under aCreative Commons License