Proceedings of the Korean Institute of Information and Commucation Sciences Conference (한국정보통신학회:학술대회논문집)
- 2019.05a
- /
- Pages.432-435
- /
- 2019
Automatic Volumetric Brain Tumor Segmentation using Convolutional Neural Networks
- Yavorskyi, Vladyslav (Korea University) ;
- Sull, Sanghoon (Korea University)
- Published : 2019.05.23
Abstract
Convolutional Neural Networks (CNNs) have recently been gaining popularity in the medical image analysis field because of their image segmentation capabilities. In this paper, we present a CNN that performs automated brain tumor segmentations of sparsely annotated 3D Magnetic Resonance Imaging (MRI) scans. Our CNN is based on 3D U-net architecture, and it includes separate Dilated and Depth-wise Convolutions. It is fully-trained on the BraTS 2018 data set, and it produces more accurate results even when compared to the winners of the BraTS 2017 competition despite having a significantly smaller amount of parameters.