Segmentation of brain MRI structures with deep machine learning
Several studies on brain Magnetic Resonance Images (MRI) show relations between neuroanatomical abnormalities of brain structures and neurological disorders, such as Attention De fficit Hyperactivity Disorder (ADHD) and Alzheimer. These abnormalities seem to be correlated with the size and shape of...
| Autor: | |
|---|---|
| Formato: | tesis de maestría |
| Fecha de publicación: | 2012 |
| País: | España |
| Recursos: | Universitat Politècnica de Catalunya (UPC) |
| Repositorio: | UPCommons. Portal del coneixement obert de la UPC |
| Idioma: | inglés |
| OAI Identifier: | oai:upcommons.upc.edu:2099.1/15836 |
| Acesso em linha: | https://hdl.handle.net/2099.1/15836 |
| Access Level: | acceso abierto |
| Palavra-chave: | Machine learning Neural networks (Computer science) Brain--Magnetic resonance imaging Aprenentatge automàtic Xarxes neuronals (Informàtica) Cervell--Imatges per ressonància magnètica Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic Àrees temàtiques de la UPC::Ciències de la salut::Medicina::Neurologia |
| Resumo: | Several studies on brain Magnetic Resonance Images (MRI) show relations between neuroanatomical abnormalities of brain structures and neurological disorders, such as Attention De fficit Hyperactivity Disorder (ADHD) and Alzheimer. These abnormalities seem to be correlated with the size and shape of these structures, and there is an active fi eld of research trying to find accurate methods for automatic MRI segmentation. In this project, we study the automatic segmentation of structures from the Basal Ganglia and we propose a new methodology based on Stacked Sparse Autoencoders (SSAE). SSAE is a strategy that belongs to the family of Deep Machine Learning and consists on a supervised learning method based on an unsupervisely pretrained Feed-forward Neural Network. Moreover, we present two approaches based on 2D and 3D features of the images. We compare the results obtained on the di fferent regions of interest with those achieved by other machine learning techniques such as Neural Networks and Support Vector Machines. We observed that in most cases SSAE improves those other methods. We demonstrate that the 3D features do not report better results than the 2D ones as could be thought. Furthermore, we show that SSAE provides state-of-the-art Dice Coe fficient results (left, right): Caudate (90.6+-3 1.4, 90.31 +-1.7), Putamen (91.03 +-1.4, 90.82+- 1.4), Pallidus (85.11+-1.8, 83.47 +-2.2), Accumbens (74.26+- 4.4, 74.46 +-4.6). |
|---|