Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

Myocardial Segmentation in MR images using fully Convolutional Neural Networks

Nilsson, Mattias LU (2018) In Master Thesis in Mathematical Sciences FMAM05 20172
Mathematics (Faculty of Engineering)
Abstract
A convolutional neural network for automatic myocardial segmentation of MR images is described and implemented, based on the readily available architecture SegNet. A general network trained on both end-systolic and end-diastolic images is determined to be superior to the networks trained on the separate data. The evaluation of myocardial segmentation is discussed, as well as the importance of manual, visual inspection.
Popular Abstract (Swedish)
Detta arbete har undersökt hur ett neuralt nätverk bör tränas för att utlinjera hjärtmuskeln i MR-bilder. Med en begränsad mängd data såg vi hur man bör behandla sin data för att producera en välfungerande modell.
Please use this url to cite or link to this publication:
author
Nilsson, Mattias LU
supervisor
organization
alternative title
Utlinjering av hjärtmuskeln i MR-bilder med maskininlärning
course
FMAM05 20172
year
type
H2 - Master's Degree (Two Years)
subject
keywords
machine learning, artificial neural networks, convolutional neural networks, medical image analysis, image analysys, MRI, cardiac MRI, cardiac image analysis
publication/series
Master Thesis in Mathematical Sciences
report number
LUTFMA-3340-2018
ISSN
1404-6342
other publication id
2018:E6
language
English
id
8960038
date added to LUP
2018-12-28 14:36:09
date last changed
2019-07-12 09:56:10
@misc{8960038,
  abstract     = {{A convolutional neural network for automatic myocardial segmentation of MR images is described and implemented, based on the readily available architecture SegNet. A general network trained on both end-systolic and end-diastolic images is determined to be superior to the networks trained on the separate data. The evaluation of myocardial segmentation is discussed, as well as the importance of manual, visual inspection.}},
  author       = {{Nilsson, Mattias}},
  issn         = {{1404-6342}},
  language     = {{eng}},
  note         = {{Student Paper}},
  series       = {{Master Thesis in Mathematical Sciences}},
  title        = {{Myocardial Segmentation in MR images using fully Convolutional Neural Networks}},
  year         = {{2018}},
}