Volumetric multimodality neural network for brain tumor segmentation

Laura Silvana Castillo; Laura Alexandra Daza; Luis Carlos Rivera; Pablo Arbeláez

doi:10.1117/12.2285942

Translator Disclaimer

17 November 2017 Volumetric multimodality neural network for brain tumor segmentation

Laura Silvana Castillo, Laura Alexandra Daza, Luis Carlos Rivera, Pablo Arbeláez

Author Affiliations +

Proceedings Volume 10572, 13th International Conference on Medical Information Processing and Analysis; 105720E (2017) https://doi.org/10.1117/12.2285942
Event: 13th International Symposium on Medical Information Processing and Analysis, 2017, San Andres Island, Colombia

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%.

Citation Download Citation

Laura Silvana Castillo, Laura Alexandra Daza, Luis Carlos Rivera, and Pablo Arbeláez "Volumetric multimodality neural network for brain tumor segmentation", Proc. SPIE 10572, 13th International Conference on Medical Information Processing and Analysis, 105720E (17 November 2017); https://doi.org/10.1117/12.2285942

ACCESS THE FULL ARTICLE