Document Type


Date of Degree

Spring 2017

Degree Name

MS (Master of Science)

Degree In

Biomedical Engineering

First Advisor

Hans J. Johnson

First Committee Member

Edwin L Dove

Second Committee Member

Jatin Vaidya


Analysis of surface models reconstructed from human MR images gives re- searchers the ability to quantify the shape and size of the cerebral cortex. Increasing the reliability of automatic reconstructions would increase the precision and, therefore, power of studies utilizing cortical surface models. We looked at four different workflows for reconstructing cortical surfaces:


2) FreeSurfer + LOGISMOS-B;

3) BAW + FreeSurfer + Machine Learning + LOGISMOS-B;

4) Standard FreeSurfer(Dale et al. 1999).

Workflows 1-3 were developed in this project. Workflow 1 utilized both BRAINSAutoWorkup(BAW)(Kim et al. 2015) and a surface reconstruction tool called LOGISMOS-B(Oguz et al. 2014). Workflow 2 added LOGISMOS-B to a custom built FreeSurfer workflow that was highly optimized for parallel processing. Workflow 3 combined workflows 1 and 2 and added random forest classifiers for predicting the edges of the cerebral cortex. These predictions were then fed into LOGISMOS-B as the cost function for graph segmentation. To compare these work- flows, a dataset of 578 simulated cortical volume changes was created from 20 different sets of MR scans. The workflow utilizing machine learning (workflow 3) produced cortical volume changes with the least amount of error when compared to the known volume changes from the simulations. Machine learning can be effectively used to help reconstruct cortical surfaces that more precisely track changes in the cerebral cortex. This research could be used to increase the power of future projects studying correlations between cortical morphometrics and neurological health.

Public Abstract

For decades, evaluation of quantified metrics derived from human magnetic resonance imaging (MRI) studies have allowed researchers to advance the under- standing of the brain. Software innovation has allowed researchers to reconstruct three dimensional models of the surfaces that separate different types of tissue in the brain. Analysis of these models provides quantifiable features describing the shape and size of the brain. The reliability of these features is crucial for many research studies involving MRI scans of the brain.

The commonly used software for creating the three dimensional models rep- resenting the inner and outer edges of the cerebral cortex is FreeSurfer[4]. Although FreeSurfer is state-of-the-art, its reliability leaves much room for improvement. Furthermore, few, if any, alternatives to FreeSurfer exist.

Three methods for reconstructing the surfaces representing the edges of the cerebral cortex were created in this thesis. The methods were tested against FreeSurfer using a set of scans with simulated changes. The method that utilized machine learning to predict the locations of the edges of the cerebral cortex from the MRI scans proved to best detect the simulated changes.

Therefore, the machine learning method detailed in this work proved to be a promising alternative to FreeSurfer for reconstructing the surfaces of the cerebral cortex. Future research involving surface models of the cerebral cortex could be enhanced by using the machine learning method outlined in this thesis.


cortical reconstruction, machine learning, morphometrics, mri, random forest, surfaces


x, 62 pages


Includes bibliographical references (pages 56-62).


This thesis has been optimized for improved web viewing. If you require the original version, contact the University Archives at the University of Iowa:


Copyright © 2017 David G. Ellis