Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/91366
Title: Classificació automatitzada d'imatges histològiques mitjançant una xarxa neuronal convolucional. Una aplicació per al tractament del càncer colorrectal
Author: Borràs Ros, Jan
Tutor: Alférez, Santiago  
Others: Prados Carrasco, Ferran  
Abstract: In the present study the main target is to train a Convolutional Neural Network with the capacity to classify 8 different colorrectal cancer tissue types from cancer histology. After that we tested the performance of the algorithm to classify the regions of real biopsy images obtained from colorrectal cancer patients. To build the Convolutional Network we have used Python with PyTorch library, developed and mantained by Facebook Inc. Altogether with PyTorch we have used Fastai library which allows to use a set of functions to test good practices with the aim to improve final accuracy. This good practices methods have been developed by other researchers in the application of other Convolutional Neural Network models.
Keywords: convolutional neural network
PyTorch
colorectal cancer
Document type: info:eu-repo/semantics/masterThesis
Issue Date: Jan-2019
Publication license: http://www.gnu.org/copyleft/fdl.html
Appears in Collections:Trabajos finales de carrera, trabajos de investigación, etc.

Files in This Item:
File Description SizeFormat 
jborrasrosTFM0119memoria.pdfMemòria del TFM7,81 MBAdobe PDFThumbnail
View/Open
Share:
Export:
View statistics

Items in repository are protected by copyright, with all rights reserved, unless otherwise indicated.