UNIGE document Doctoral Thesis
previous document  unige:89935  next document
add to browser collection
Title

Efficient extraction of musculoskeletal structures from multi-channel MR images

Author
Directors
Defense Thèse de doctorat : Univ. Genève, 2016 - Sc. 4994 - 2016/09/20
Abstract We propose the extraction of musculoskeletal structures (bones, muscles) from the lower limb, following three main objectives: development of an MRI protocol, processing and labelling of the image data, and the exploitation of multi-channel data during the segmentation of individual muscles. We propose an MR acquisition protocol that generates seamless, high-resolution images of thigh and calf. We present a method to identify air and muscle tissue in the image and massively parallel version of the approach. To identify the individual muscles, we align a muscle template which is modified with our deformable model framework under the influence of image forces to match the actual anatomy. This iterative process uses multi-channel image data to find relevant image features. We propose coupled multi-resolution deformable models that allow working on different resolutions in parallel. This work is aimed at helping the understanding of diseases by providing personalised anatomical models.
Keywords Biomedical Image ProcessingImage SegmentationDeformable ModelsMagnetic Resonance ImagingMulti-Channel Imaging
Identifiers
URN: urn:nbn:ch:unige-899357
Full text
Thesis (10.8 MB) - public document Free access
Structures
Research group MIRALab
Project FP7: MULTISCALEHUMAN
Citation
(ISO format)
BECKER, Matthias. Efficient extraction of musculoskeletal structures from multi-channel MR images. Université de Genève. Thèse, 2016. https://archive-ouverte.unige.ch/unige:89935

77 hits

37 downloads

Update

Deposited on : 2016-12-07

Export document
Format :
Citation style :