End-to-End Boundary Aware Networks for Medical Image Segmentation

TL;DR

This paper introduces boundary aware CNNs for medical image segmentation that incorporate boundary information through specialized network components and loss functions, improving accuracy in brain tumor segmentation.

Contribution

The proposed boundary aware CNNs integrate boundary information via an edge branch and edge-aware loss, trained end-to-end, enhancing segmentation accuracy in medical images.

Findings

Improved segmentation accuracy on BraTS 2018 dataset.

Effective incorporation of boundary information in CNNs.

Potential for broader application in medical image segmentation.

Abstract

Fully convolutional neural networks (CNNs) have proven to be effective at representing and classifying textural information, thus transforming image intensity into output class masks that achieve semantic image segmentation. In medical image analysis, however, expert manual segmentation often relies on the boundaries of anatomical structures of interest. We propose boundary aware CNNs for medical image segmentation. Our networks are designed to account for organ boundary information, both by providing a special network edge branch and edge-aware loss terms, and they are trainable end-to-end. We validate their effectiveness on the task of brain tumor segmentation using the BraTS 2018 dataset. Our experiments reveal that our approach yields more accurate segmentation results, which makes it promising for more extensive application to medical image segmentation.