A Multiscale Patch Based Convolutional Network for Brain Tumor Segmentation

TL;DR

This paper introduces a multiscale patch-based convolutional neural network that improves brain tumor segmentation accuracy in multi-modality 3D MR images, achieving high dice scores and low Hausdorff distances on the BRATS 2017 dataset.

Contribution

It proposes a novel multiscale deep supervision approach for CNN-based brain tumor segmentation, enhancing performance over existing methods.

Findings

Dice scores of 0.755, 0.900, 0.782 for tumor regions

Hausdorff distances of 3.63mm, 4.10mm, 6.81mm

Effective on BRATS 2017 challenge data

Abstract

This article presents a multiscale patch based convolutional neural network for the automatic segmentation of brain tumors in multi-modality 3D MR images. We use multiscale deep supervision and inputs to train a convolutional network. We evaluate the effectiveness of the proposed approach on the BRATS 2017 segmentation challenge where we obtained dice scores of 0.755, 0.900, 0.782 and 95% Hausdorff distance of 3.63mm, 4.10mm, and 6.81mm for enhanced tumor core, whole tumor and tumor core respectively.