Assessing accuracy of automated segmentation methods for brain lateral ventricles in MRI data

Main Article Content

Mahadev Bhalla Haaris Mahmood


The incidence of Alzheimer’s disease (AD) has steadily increased over the last few decades. AD leads to a decreased quality of life for those affected, hence, there is an urgent need to identify a reference point that can assist in early identification of the presence of AD. An objective and sensitive measure that may assist in the detection of AD is the lateral ventricle volume. In high-resolution magnetic resonance (MR) images, a relationship between lateral ventricle enlargement and AD progression can be examined. Volumetric data analyses for the ventricles require that they be segmented by neuro-anatomy experts using manual tracing. Since manual segmentation methods are impractical due to time requirements and rater variability, automated methods are frequently used to reliably and accurately segment brain regions. Thus, our goal was to compare the performance of two automated segmentation methods, FreeSurfer (FS) and FreeSurfer combined with Large Deformation Diffeomorphic Metric Mapping label propagation (FS+LDDMM), for the task of lateral ventricle segmentation. The Dice Similarity Coefficient (DSC) was used to evaluate the segmentation accuracy obtained by these two automated methods. When compared to the manual segmentation labels, the FS+LDDMM method had a greater mean DSC than the FreeSurfer method. Moreover, the manual vs. FS+LDDMM DSC values ranged from 99-100, while manual vs. FreeSurfer ranged from 73-92. Both of these results illustrate that FS+LDDMM is an automated method that has a high degree of accuracy and can be used in place of manual segmentation, while FreeSurfer should only be used as a preliminary automatic segmentation method.

Article Details

Author Biographies

Mahadev Bhalla, Queen's University, Kingston, Ontario, Canada.

Supervised by: Dr. Mirza Faisal Beg, Simon Fraser University

Haaris Mahmood, Queen's University, Kingston, Ontario, Canada.

Supervised by: Dr. Mirza Faisal Beg, Simon Fraser University.