Development of a Stand-Alone Independent Graphical User Interface for Neurological Disease Prediction with Automated Extraction and Segmentation of Gray and White Matter in Brain MRI Images
Table 2
Performance and accuracy comparison of the authors’ proposed automatic brain MRI segmentation algorithm [83] with previous algorithms [88] using Dice coefficients as similarity measure estimated between manual expert tracings and automatic algorithm-based segmentation.
Methods
Procedure
Average of Dice coefficients (gray matter)
Average of Dice coefficients (white matter)
Average of Dice coefficients (total cortical matter)
K-means
Statistical distance-based k-means clustering with preprocessing using median filters
0.70
0.71
0.71
Intensity-based fuzzy c-means
Pixel intensity and membership-based fuzzy c-means clustering with preprocessing using median filters
0.71
0.79
0.75
Adaptive fuzzy c-means with preprocessing and postprocessing (proposed method in this work)
Pixel intensity and membership-based fuzzy c-means clustering with preprocessing using elliptical Hough transform and postprocessing using connected region analysis
