Segmentation of multi-structures in cardiac MRI using deep learning

Gutierrez Castilla, Nicolas

Segmentation of multi-structures in cardiac MRI using deep learning

dc.contributor.advisor	Montoya Zegarra, Javier Alexander
dc.contributor.author	Gutierrez Castilla, Nicolas
dc.date.accessioned	2021-09-23T03:22:18Z
dc.date.available	2021-09-23T03:22:18Z
dc.date.issued	2020
dc.description.abstract	The heart is one of the most important organs in our body and many critical diseases are associated with its malfunctioning. To assess the risk for heart diseases, Magnetic Resonance Imaging (MRI) has become the golden standard imaging technique, as it provides to the clinicians stacks of images for analyzing the heart structures, such as the ventricles, and thus to make a diagnosis of the patient’s health. However, the examination of these stacks, often based on the delineation of the heart structures, is a tedious and an error prone task due to inter- and intra-variability in the manual delineations. For this reason, the investigation of fully automated methods to support heart segmentation is paramount. Most of the successful methods proposed to solve this problem are based on deep-learning solutions. Especially, encoder-decoder architectures, such as the U-Net (Ronneberger et al., 2015), have demonstrated to be very effective and robust architectures for medical image segmentation. In this work, we propose to use long-range skip connections on the decoder-part of the architecture to incorporate multi-context information onto the predicted segmentation masks and to improve the generalization of the models (see Figure 1). This new module is named Dense-Decoder module and can be easily added to state-of-the-art encoder-decoder architectures, such as the U-Net, with almost no extra additional parameters allowing the model’s size to remain constant. To evaluate the benefits of our module, we performed experiments on two challenging cardiac segmentation datasets, namely the ACDC (Bernard et al., 2018) and the LVSC (Radau et al., 2009) heart segmentation challenges. Experiments performed on both datasets demonstrate that our method leads to an improvement on both the total Average Dice score and the Ejection Fraction Correlation, when combined with state-of-the-art encoder-decoder architectures.	es_PE
dc.description.uri	Tesis	es_PE
dc.format	application/pdf	es_PE
dc.identifier.other	1073412
dc.identifier.uri	https://hdl.handle.net/20.500.12590/16852
dc.language.iso	eng	es_PE
dc.publisher	Universidad Católica San Pablo	es_PE
dc.publisher.country	PE	es_PE
dc.rights	info:eu-repo/semantics/openAccess	es_PE
dc.rights.uri	https://creativecommons.org/licenses/by/4.0/	es_PE
dc.source	Universidad Católica San Pablo	es_PE
dc.source	Repositorio Institucional - UCSP	es_PE
dc.subject	Deep Learning	es_PE
dc.subject	Cardiac Magnetic Resonance Imaging	es_PE
dc.subject	Image Segmentation	es_PE
dc.subject	Medical Imaging	es_PE
dc.subject.ocde	http://purl.org/pe-repo/ocde/ford#1.02.01	es_PE
dc.title	Segmentation of multi-structures in cardiac MRI using deep learning	es_PE
dc.type	info:eu-repo/semantics/masterThesis
dc.type	info:eu-repo/semantics/masterThesis
dc.type.version	info:eu-repo/semantics/publishedVersion	es_PE
renati.advisor.dni	41312254
renati.advisor.orcid	https://orcid.org/0000-0002-3652-1954	es_PE
renati.author.dni	73637385
renati.discipline	611017	es_PE
renati.juror	Joao Paulo Papa	es_PE
renati.juror	Alexander Xavier Falcao	es_PE
renati.juror	José Eduardo Ochoa Luna	es_PE
renati.level	https://purl.org/pe-repo/renati/level#maestro
renati.type	https://purl.org/pe-repo/renati/type#tesis
thesis.degree.discipline	Ciencia de la Computación	es_PE
thesis.degree.grantor	Universidad Católica San Pablo. Departamento de Ciencia de la Computación	es_PE
thesis.degree.level	Maestría	es_PE
thesis.degree.name	Maestro en Ciencia de la Computación	es_PE
thesis.degree.program	Programa Profesional de Ciencia de la Computación	es_PE