Share Email Print

Proceedings Paper

Volumetric multimodality neural network for brain tumor segmentation
Author(s): Laura Silvana Castillo; Laura Alexandra Daza; Luis Carlos Rivera; Pablo Arbeláez
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Brain lesion segmentation is one of the hardest tasks to be solved in computer vision with an emphasis on the medical field. We present a convolutional neural network that produces a semantic segmentation of brain tumors, capable of processing volumetric data along with information from multiple MRI modalities at the same time. This results in the ability to learn from small training datasets and highly imbalanced data. Our method is based on DeepMedic, the state of the art in brain lesion segmentation. We develop a new architecture with more convolutional layers, organized in three parallel pathways with different input resolution, and additional fully connected layers. We tested our method over the 2015 BraTS Challenge dataset, reaching an average dice coefficient of 84%, while the standard DeepMedic implementation reached 74%.

Paper Details

Date Published: 17 November 2017
PDF: 8 pages
Proc. SPIE 10572, 13th International Conference on Medical Information Processing and Analysis, 105720E (17 November 2017); doi: 10.1117/12.2285942
Show Author Affiliations
Laura Silvana Castillo, Univ. de los Andes (Colombia)
Laura Alexandra Daza, Univ. de los Andes (Colombia)
Luis Carlos Rivera, Univ. de los Andes (Colombia)
Pablo Arbeláez, Univ. de los Andes (Colombia)

Published in SPIE Proceedings Vol. 10572:
13th International Conference on Medical Information Processing and Analysis
Eduardo Romero; Natasha Lepore; Jorge Brieva; Juan David García, Editor(s)

© SPIE. Terms of Use
Back to Top