Brain Tumor Segmentation Based on Refined Fully Convolutional Neural Networks with A Hierarchical Dice Loss

TL;DR

This paper enhances brain tumor segmentation by refining fully convolutional neural networks with architectural adjustments and a novel hierarchical dice loss, leading to improved accuracy and robustness in segmentation tasks.

Contribution

It introduces a hierarchical dice loss function and network modifications that improve brain tumor segmentation performance over traditional FCNNs.

Findings

Improved segmentation accuracy measured by DSC and mIoU.

Network modifications enhance pixel-wise classification.

Hierarchical dice loss effectively handles class imbalance.

Abstract

As a basic task in computer vision, semantic segmentation can provide fundamental information for object detection and instance segmentation to help the artificial intelligence better understand real world. Since the proposal of fully convolutional neural network (FCNN), it has been widely used in semantic segmentation because of its high accuracy of pixel-wise classification as well as high precision of localization. In this paper, we apply several famous FCNN to brain tumor segmentation, making comparisons and adjusting network architectures to achieve better performance measured by metrics such as precision, recall, mean of intersection of union (mIoU) and dice score coefficient (DSC). The adjustments to the classic FCNN include adding more connections between convolutional layers, enlarging decoders after up sample layers and changing the way shallower layers' information is reused. Besides the structure modification, we also propose a new classifier with a hierarchical dice loss. Inspired by the containing relationship between classes, the loss function converts multiple classification to multiple binary classification in order to counteract the negative effect caused by imbalance data set. Massive experiments have been done on the training set and testing set in order to assess our refined fully convolutional neural networks and new types of loss function. Competitive figures prove they are more effective than their predecessors.