Context Aware 3D CNNs for Brain Tumor Segmentation

Abstract : In this work we propose a novel deep learning based pipeline for the task of brain tumor segmentation. Our pipeline consists of three primary components: (i) a preprocessing stage that exploits histogram standardization to mitigate inaccuracies in measured brain modalities, (ii) a first prediction stage that uses the V-Net deep learning architecture to output dense, per voxel class probabilities, and (iii) a prediction refinement stage that uses a Conditional Random Field (CRF) with a bilateral filtering objective for better context awareness. Additionally, we compare the V-Net architecture with a custom 3D Residual Network architecture, trained on a multi-view strategy, and our ablation experiments indicate that V-Net outperforms the 3D ResNet-18 with all bells and whistles, while fully connected CRFs as post processing, boost the performance of both networks. We report competitive results on the BraTS 2018 validation and test set.
Liste complète des métadonnées

https://hal.inria.fr/hal-01959610
Contributor : Maria Vakalopoulou <>
Submitted on : Tuesday, December 18, 2018 - 7:04:49 PM
Last modification on : Wednesday, April 3, 2019 - 2:10:04 PM
Document(s) archivé(s) le : Wednesday, March 20, 2019 - 10:08:25 AM

File

chandra_etal.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01959610, version 1

Citation

Siddhartha Chandra, Maria Vakalopoulou, Lucas Fidon, Enzo Battistella, Théo Estienne, et al.. Context Aware 3D CNNs for Brain Tumor Segmentation. MICCAI Brainlesion Workshop, Sep 2018, Granada, Spain. ⟨hal-01959610⟩

Share

Metrics

Record views

98

Files downloads

138