Ir al contenido (pulsa Retorno)

Universitat Politècnica de Catalunya

    • Català
    • Castellano
    • English
    • LoginRegisterLog in (no UPC users)
  • mailContact Us
  • world English 
    • Català
    • Castellano
    • English
  • userLogin   
      LoginRegisterLog in (no UPC users)

UPCommons. Global access to UPC knowledge

Banner header
66.625 UPC academic works
You are here:
View Item 
  •   DSpace Home
  • Treballs acadèmics
  • Màsters oficials
  • Màster universitari en Física per a l'Enginyeria (Pla 2018)
  • View Item
  •   DSpace Home
  • Treballs acadèmics
  • Màsters oficials
  • Màster universitari en Física per a l'Enginyeria (Pla 2018)
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Visual interpretability of deep learning algorithms in medical applications

Thumbnail
View/Open
MASTER_THESIS_christian.pdf (5,237Mb)
  View Usage Statistics
  LA Referencia / Recolecta stats
Cita com:
hdl:2117/349401

Show full item record
Jorba Soler, Christian
Tutor / directorBenítez Iglesias, RaúlMés informacióMés informacióMés informació; Malagarriga Guasch, DanielMés informació
Document typeMaster thesis
Date2020-09
Rights accessOpen Access
All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder
Abstract
Artificial intelligence is having a very big boost in recent times, and after the success of deep learning algorithms in many applications, they are also providing successful results for medical imaging, especially because of the good performance of convolutional neural networks. However, the black box behaviour of these networks makes it very difficult to assign them tasks that an expert human normally does. This project aims to interpret in human terms what a convolutional neural network trained to classify fetal different ultrasound planes is based on. We use transfer learning to build a network with good performance in the classification task and apply interpretability techniques on it. These methods include Activation Maximization, Saliency Maps, Occlusion Sensitivity Maps, Class Activation Mapping and LIME. The trained network is able to classify fetal ultrasound images with an accuracy of 91.7%, and we provide a robust interpretation of its performance that allows us to understand the most important characteristics of each class for the model.
SubjectsMachine learning, Artificial intelligence, Neural networks (Computer science), Aprenentatge automàtic, Intel·ligència artificial, Xarxes neuronals (Informàtica)
DegreeMÀSTER UNIVERSITARI EN FÍSICA PER A L'ENGINYERIA (Pla 2018)
URIhttp://hdl.handle.net/2117/349401
Collections
  • Màsters oficials - Màster universitari en Física per a l'Enginyeria (Pla 2018) [24]
  View Usage Statistics

Show full item record

FilesDescriptionSizeFormatView
MASTER_THESIS_christian.pdf5,237MbPDFView/Open

Browse

This CollectionBy Issue DateAuthorsOther contributionsTitlesSubjectsThis repositoryCommunities & CollectionsBy Issue DateAuthorsOther contributionsTitlesSubjects

© UPC Obrir en finestra nova . Servei de Biblioteques, Publicacions i Arxius

info.biblioteques@upc.edu

  • About This Repository
  • Contact Us
  • Send Feedback
  • Privacy Settings
  • Inici de la pàgina