Convolutional 3D to 2D Patch Conversion for Pixel-wise Glioma Segmentation in MRI Scans

TL;DR

This paper introduces a novel 3D to 2D patch conversion framework using CNNs for pixel-wise glioma segmentation in MRI scans, effectively leveraging multimodal data for improved accuracy.

Contribution

The study proposes a new convolutional architecture that combines 3D patch extraction with 2D CNNs, enabling efficient and accurate pixel-wise brain tumor segmentation.

Findings

Effective segmentation of brain tumors in multimodal MRI.

Jointly exploits local and global features for improved accuracy.

Implicitly weights modalities for optimal contribution.

Abstract

Structural magnetic resonance imaging (MRI) has been widely utilized for analysis and diagnosis of brain diseases. Automatic segmentation of brain tumors is a challenging task for computer-aided diagnosis due to low-tissue contrast in the tumor subregions. To overcome this, we devise a novel pixel-wise segmentation framework through a convolutional 3D to 2D MR patch conversion model to predict class labels of the central pixel in the input sliding patches. Precisely, we first extract 3D patches from each modality to calibrate slices through the squeeze and excitation (SE) block. Then, the output of the SE block is fed directly into subsequent bottleneck layers to reduce the number of channels. Finally, the calibrated 2D slices are concatenated to obtain multimodal features through a 2D convolutional neural network (CNN) for prediction of the central pixel. In our architecture, both local inter-slice and global intra-slice features are jointly exploited to predict class label of the central voxel in a given patch through the 2D CNN classifier. We implicitly apply all modalities through trainable parameters to assign weights to the contributions of each sequence for segmentation. Experimental results on the segmentation of brain tumors in multimodal MRI scans (BraTS'19) demonstrate that our proposed method can efficiently segment the tumor regions.