Full text
| |
| Author(s): |
Oeslle Alexandre Soares de Lucena
Total Authors: 1
|
| Document type: | Master's Dissertation |
| Press: | Campinas, SP. |
| Institution: | Universidade Estadual de Campinas (UNICAMP). Faculdade de Engenharia Elétrica e de Computação |
| Defense date: | 2018-09-11 |
| Examining board members: |
Roberto de Alencar Lotufo;
Nina Sumiko Tomita Hirata;
José Mário De Martino
|
| Advisor: | Roberto de Alencar Lotufo; Leticia Rittner |
| Abstract | |
Convolutional neural networks (CNNs) are one branch of deep learning that have per- formed successfully in many brain magnetic resonance (MR) imaging analysis. CNNs are representation-learning methods with stacked layers comprised of a convolution op- eration followed by a non-linear activation and pooling layers. In these networks, each layer outputs a higher and more abstract representation from a given input, in which the weights of the convolutional layers are learned by an optimization problem. In this work, we tackled two problems using deep-learning-based approaches: skull-stripping (SS) and tractography. We firstly proposed a full CNN-based SS trained with what we refer to as silver standard masks. Segmenting brain tissue from non-brain tissue is a process known as brain extraction or skull-stripping. Silver standard masks are generated by forming the consensus from a set of eight, public, non-deep-learning-based SS methods using the algo- rithm Simultaneous Truth and Performance Level Estimation (STAPLE). Our approach reached state-of-the-art performance, generalized optimally, decreased inter-/intra-rater variability, and avoided CNN segmentation overfitting towards one specific manual anno- tation. Secondly, we investigated a CNN-based tractography solution for epilepsy surgery. The main goal of this analysis was to structure a baseline for a deep-learning-based- regression to predict white matter fiber orientations. Tractography is a visualization of the white matter fibers or tracts; its goal in presurgical planing is simply to identify the position of eloquent pathways, such as the motor, sensory, and language tracts to reduce the risk of damaging these critical structures. We performed analysis cross-validation us- ing only in a single patient per time, and also, training with data from 10 patients for training the CNN. Our results were not optimal, however, the tracts tended to be of a similar length and converged to the mean fiber tract locations. Additionally, to the best of our knowledge, our method is the first approach that investigates CNNs for tractography, and thus, our work is a baseline for this topic (AU) | |
| FAPESP's process: | 16/18332-8 - Deep learning for brain structures segmentation in MR imaging |
| Grantee: | Oeslle Alexandre Soares de Lucena |
| Support Opportunities: | Scholarships in Brazil - Master |