Automatic segmentation of brain structures in magnetic resonance images using deep learning techniques

This PhD thesis focuses on the development of deep learning based methods for accurate segmentation of the sub-cortical brain structures from MRI. First, we have proposed a 2.5D CNN architecture that combines convolutional and 2/2 spatial features. Second, we proposed a supervised domain adaptation...

Descripción completa

Detalles Bibliográficos
Autor: Kushibar, Kaisar
Tipo de recurso: tesis doctoral
Estado:Versión publicada
Fecha de publicación:2020
País:España
Institución:CBUC, CESCA
Repositorio:TDR. Tesis Doctorales en Red
OAI Identifier:oai:www.tdx.cat:10803/670766
Acceso en línea:http://hdl.handle.net/10803/670766
Access Level:acceso abierto
Palabra clave:Brain structures
Estructures cerebrals
Estructuras cerebrales
MRI
Magnetic resonance imaging
Imatgeria per ressonància magnètica
Imágenes por resonancia magnética
Deep learning
Aprenentatge profund
Aprendizaje profundo
Subcortical structures
Estructures subcorticals
Estructuras subcorticales
CNN
Convolutional neural network
Xarxa neuronal convolucional
Red neuronal convolucional
004
616.8
Descripción
Sumario:This PhD thesis focuses on the development of deep learning based methods for accurate segmentation of the sub-cortical brain structures from MRI. First, we have proposed a 2.5D CNN architecture that combines convolutional and 2/2 spatial features. Second, we proposed a supervised domain adaptation technique to improve the robustness and consistency of deep learning model. Third, an unsupervised domain adaptation method was proposed to eliminate the requirement of manual intervention to train a deep learning model that is robust to differences in the MRI images from multi-centre and multi-scanner datasets. The experimental results for all the proposals demonstrated the effectiveness of our approaches in accurately segmenting the sub-cortical brain structures and has shown state-of-the-art performance on well-known publicly available datasets