Multi-Planar Spatial-ConvNet for Segmentation of Brain Tumors

Submitted: December 03, 2018 Last updated: December 03, 2018
  • File:
    student-ambassador-subhashis-poster.pdf
  • Size:
    2.02 MB
Download

Detailed Description

Subhashis Banerjee

This presentation introduces a new deep learning method for the automatic delineation and segmentation of brain tumors from multisequence magnetic resonance imaging (MRI). It includes a radiomic model to predict the overall survival based on the features extracted from the segmented volume of interest (VOI). Also included is an encoder-decoder-type convolutional neural network (ConvNet) model for pixel-wise segmentation of the tumor along three anatomical planes (axial, sagittal, and coronal) at the slice level.

Product and Performance Information

1

Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex.