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
Sponsor
National Science Foundation
Advisor
Bouaynaya, Nidhal C.
Committee Member 1
Fathallah-Shaykh, Hassan
Committee Member 2
Rasool, Ghulam
Keywords
artificial intelligence, deep learning, human brain, object recognition, object classification
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.
Recommended Citation
Palumbo, Oliver John, "Inverted cone convolutional neural network for deboning MRIs" (2019). Theses and Dissertations. 2682.
https://rdw.rowan.edu/etd/2682
Included in
Biomedical Engineering and Bioengineering Commons, Electrical and Computer Engineering Commons