Please use this identifier to cite or link to this item:
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 Baquero, Edwin Santiago
Keywords: convolutional neural network
colorectal cancer
Issue Date: Jan-2019
Publisher: Universitat Oberta de Catalunya (UOC)
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.
Language: Catalan
Appears in Collections:Bachelor thesis, research projects, etc.

Files in This Item:
File Description SizeFormat 
jborrasrosTFM0119memoria.pdfMemòria del TFM7.81 MBAdobe PDFView/Open

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