Show simple item record

dc.contributorBenítez Iglesias, Raúl
dc.contributorMalagarriga Guasch, Daniel
dc.contributor.authorJorba Soler, Christian
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Física
dc.date.accessioned2021-07-15T09:55:28Z
dc.date.available2021-07-15T09:55:28Z
dc.date.issued2020-09
dc.identifier.urihttp://hdl.handle.net/2117/349401
dc.description.abstractArtificial 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.
dc.language.isoeng
dc.publisherUniversitat Politècnica de Catalunya
dc.rightsS'autoritza la difusió de l'obra mitjançant la llicència Creative Commons o similar 'Reconeixement-NoComercial- SenseObraDerivada'
dc.subjectÀrees temàtiques de la UPC::Física
dc.subject.lcshMachine learning
dc.subject.lcshArtificial intelligence
dc.subject.lcshNeural networks (Computer science)
dc.subject.othermachine learning
dc.subject.otherartificial intelligence
dc.subject.otherinterpretability
dc.subject.otherdeep learning
dc.subject.otherconvolutional neural network
dc.subject.othertransfer learning
dc.subject.otherLIME
dc.subject.otherocclusion
dc.subject.otherclass activation mapping
dc.subject.othersaliency maps
dc.subject.otheractivation maximization
dc.titleVisual interpretability of deep learning algorithms in medical applications
dc.title.alternativeVisual interpretability of deep learning algorithms in medical applications
dc.typeMaster thesis
dc.subject.lemacAprenentatge automàtic
dc.subject.lemacIntel·ligència artificial
dc.subject.lemacXarxes neuronals (Informàtica)
dc.identifier.slugETSETB-230.154492
dc.rights.accessOpen Access
dc.date.updated2021-06-29T09:15:41Z
dc.audience.educationlevelMàster
dc.audience.mediatorEscola Tècnica Superior d'Enginyeria de Telecomunicació de Barcelona
dc.audience.degreeMÀSTER UNIVERSITARI EN FÍSICA PER A L'ENGINYERIA (Pla 2018)


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record