3-D Convolutional Neural Networks for Glioblastoma Segmentation

TL;DR

This paper introduces a novel 3-D CNN framework with DoG filters for accurate glioblastoma segmentation from MRI data, demonstrating high median Dice scores on the BRATS dataset.

Contribution

It presents a new 3-D CNN architecture with DoG filters for tumor segmentation, improving on state-of-the-art methods with a unique decoupling approach.

Findings

Achieved median Dice score of 89% in glioblastoma segmentation

Demonstrated effective learning from medium-sized MRI datasets

Outperformed existing segmentation methods on BRATS dataset

Abstract

Convolutional Neural Networks (CNN) have emerged as powerful tools for learning discriminative image features. In this paper, we propose a framework of 3-D fully CNN models for Glioblastoma segmentation from multi-modality MRI data. By generalizing CNN models to true 3-D convolutions in learning 3-D tumor MRI data, the proposed approach utilizes a unique network architecture to decouple image pixels. Specifically, we design a convolutional layer with pre-defined Difference- of-Gaussian (DoG) filters to perform true 3-D convolution incorporating local neighborhood information at each pixel. We then use three trained convolutional layers that act to decouple voxels from the initial 3-D convolution. The proposed framework allows identification of high-level tumor structures on MRI. We evaluate segmentation performance on the BRATS segmentation dataset with 274 tumor samples. Extensive experimental results demonstrate encouraging performance of the proposed approach comparing to the state-of-the-art methods. Our data-driven approach achieves a median Dice score accuracy of 89% in whole tumor glioblastoma segmentation, revealing a generalized low-bias possibility to learn from medium-size MRI datasets.