Resumen de Automatic segmentation of brain structures in magnetic resonance images using deep learning techniques
The sub-cortical brain structures are located beneath the cerebral cortex and include the thalamus, caudate, putamen, pallidum, hippocampus, amygdala, and accumbens structures. These bilateral structures -- symmetrically located within the left and right hemispheres -- are involved in systematic activities such as emotion, pleasure, memory and hormone production. Their deviations in volume are associated with different neurological diseases such as Alzheimer's disorder, bipolar disorder or multiple sclerosis, among others. Manual segmentation of these structures is a time-consuming task and suffers from rater inter- and intra-variability. Therefore, developing automated methods for accurately segmenting the sub-cortical brain structures is important and it is an active research area.
This PhD thesis focuses on the development of deep learning based methods for accurate segmentation of the sub-cortical brain structures from Magnetic Resonance Images (MRI). This goal has been carried out in several stages. In the first stage, we have proposed a 2.5D -- i.e. three 2D orthogonal planes of a 3D volume -- Convolutional Neural Network (CNN) architecture that combines convolutional and spatial features. Additionally, we proposed a selective sample selection technique from structure boundaries. Second, we proposed a supervised domain adaptation technique with minimal user interaction to improve the robustness and consistency of deep learning model. Third, an unsupervised domain adaptation method has been 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-centrer and multi-scanner datasets. The experimental results for all the proposals demonstrated the effectiveness of our approaches in accurately segmenting all the sub-cortical brain structures and has shown state-of-the-art performance on well-known publicly available datasets.
All these completed stages paved the way for achieving an accurate and robust automated deep learning based method for segmenting all the sub-cortical brain structures. Moreover, this PhD thesis has been part of research frameworks within the projects of the ViCOROB group and different collaborating hospital centres. Furthermore, the methods developed during this PhD thesis were compiled into a toolbox and made publicly available for the research community.
