Abstract—Ensemble method has been shown a great success
for 2D image segmentation, while 3D brain segmentation has
received less attention using 2D pre-trained model. In this work,
we present various 2D ensemble methods to utilize the 2D
pre-trained models for the brain MRI segmentation task using
given small medical 3D data. We perform a series of experiments
by comparing several 2D single pre-trained models to build and
analyze the various 2D ensemble methods. We evaluate the
ensemble methods against 3D single scratch model in terms of
accuracy, time, and crop size. In addition, we investigate the
relationship between different compositions of train data and
performance for semantic segmentation using MRBrainS18
train dataset. Experimental results demonstrate a significant
improvement of the proposed ensemble method in comparison
with existing methods using 3D CNN models for brain MRI
segmentation.
Index Terms—2D ensemble, pre-trained models, 3D small
medical data, various composed train data, brain segmentation.
Sang-il Ahn, Toan Duc Bui, Hyekoung Hwang, and Jitae Shin are with
the Department of Electrical and Computer Engineering, Sungkyunkwan
University, Suwon, Republic of Korea (e-mail: il2s@skku.edu,
toanhoi@skku.edu, ristar1234@skku.edu, jtshin@skku.edu).
[PDF]
Cite:Sang-il Ahn, Toan Duc Bui, Hyekyoung Hwang, and Jitae Shin, "Performance of Ensemble Methods with 2D Pre-trained Deep Learning Networks for 3D MRI Brain Segmentation," International Journal of Information and Electronics Engineering vol. 9, no. 2, pp. 50-53, 2019.
