Please use this identifier to cite or link to this item: http://hdl.handle.net/2445/143897
Title: Unsupervised representation learning for medical imaging
Author: Garcia Sanchez, Albert
Director/Tutor: Seguí Mesquida, Santi
Keywords: Aprenentatge automàtic
Càpsula endoscòpica
Programari
Treballs de fi de grau
Imatges mèdiques
Xarxes neuronals (Informàtica)
Aparell digestiu
Machine learning
Capsule endoscopy
Computer software
Imaging systems in medicine
Neural networks (Computer science)
Bachelor's thesis
Digestive organs
Issue Date: 27-Jun-2019
Abstract: [en] The aim of this project is to achieve good image representations through the use of Deep Learning technologies which are part of a broader family of Artificial Intelligence methods named Machine Learning. These image representations are vectors of representative float numbers called embeddings that, for the project, are focused on the entire digestive aparatus for medical purposes. Triplet loss is used altogether with a state of the art Convolutional Neural Network, ResNet, in order to achieve this goal. A series of tests are done in order to compare different training approaches of the ResNet model, seeking for the best image representations in the domain of the digestive aparatus. It is shown that ImageNet transfer learning underperforms with respect to not applying transfer learning for really specialized domains. To conclude, it is found that unsupervised representation learning through the use of Triplet loss enables transfer learning for specialized image domains such as the digestive aparatus.
Note: Treballs Finals de Grau d'Enginyeria Informàtica, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2019, Director: Santi Seguí Mesquida
URI: http://hdl.handle.net/2445/143897
Appears in Collections:Treballs Finals de Grau (TFG) - Enginyeria Informàtica
Programari - Treballs de l'alumnat

Files in This Item:
File Description SizeFormat 
codi.zipCodi font66.35 MBzipView/Open
memoria.pdfMemòria7.54 MBAdobe PDFView/Open


This item is licensed under a Creative Commons License Creative Commons