Date Approved

6-25-2019

Embargo Period

7-30-2019

Document Type

Thesis

Degree Name

M.S. Electrical and Computer Engineering

Department

Electrical and Computer Engineering

College

Henry M. Rowan College of Engineering

First Advisor

Bouaynaya, Nidhal C.

Second Advisor

Fathallah-Shaykh, Hassan

Third Advisor

Rasool, Ghulam

Subject(s)

Magnetic resonance imaging; Neural networks (Computer science)

Disciplines

Biomedical Engineering and Bioengineering | Electrical and Computer Engineering

Abstract

Data plenitude is the power but also the bottleneck for data-driven approaches, including neural networks. In particular, Convolutional Neural Networks (CNNs) require an abundant database of training images to achieve a desired high accuracy. Current techniques employed for boosting small datasets are data augmentation and synthetic data generation, which suffer from computational complexity and imprecision compared to original datasets. In this thesis, we intercalate prior knowledge based on the temporal relation between the images in the third dimension. Specifically, we compute the gradient of subsequent images in the dataset to remove extraneous information and highlight subtle variations between the images. The approach is coined "Inverted Cone" because the volume of brain images below the level of the eyes is ordered to form an inverted cone geometry.

The application explored in this work is deboning, or brain extraction, in brain magnetic resonance imaging (MRI) scans. We considered a limited dataset of 23 patients with and without malignant glioblastoma provided by the University of Alabama at Birmingham School of Medicine. Automatic deboning was performed by employing an optimized CNN architecture with and without the Inverted Cone processing. The classic CNN achieved a validation accuracy of 77%, while the Inverted Cone CNN model achieved a validation accuracy of 86% in a dataset of 451 brain MRI slices.

Share

COinS