Research Article
Segmenting Brain Tissues from Chinese Visible Human Dataset by Deep-Learned Features with Stacked Autoencoder
Table 2
Mean and standard deviation of Dice ratio (in ) for measuring the performance of the three tissue types with five different architectures trained by using different patch sizes of , , , , and , respectively. The experiments were conducted in a leave-one-out manner and eight test results were collected for each tissue.
|