Robustness of Brain Tumor Segmentation

TL;DR

This study evaluates the generalization of brain tumor segmentation methods, revealing that current deep learning models perform well on benchmarks but poorly in real-world clinical settings, with U-net showing the best robustness.

Contribution

The paper compares multiple segmentation methods and proposes simple modifications, highlighting the limited generalization of deep neural networks in clinical brain tumor segmentation.

Findings

U-net exhibits the best generalization among tested methods

Extensions to models can be ineffective or harmful in realistic scenarios

Current models are optimized for benchmark data, not clinical application

Abstract

Purpose: The segmentation of brain tumors is one of the most active areas of medical image analysis. While current methods perform superhuman on benchmark data sets, their applicability in daily clinical practice has not been evaluated. In our work we investigate the generalization behavior of deep neural networks in this scenario. Approach: We evaluate the performance of three state-of-the-art methods, a basic U-net architecture and a cascadic Mumford-Shah approach. We also propose two simple modifications (which do not change the topology) to improve generalization performance. Results: In our experiments we show that a well-trained U-network shows the best generalization behavior and is sufficient to solve this segmentation problem. We illustrate why extensions of this model in a realistic scenario can be not only pointless but even harmful. Conclusions: We conclude from our experiments that the generalization performance of deep neural networks is severely limited in medical image analysis especially in the area of brain tumor segmentation. In our opinion, current topologies are optimized for the actual benchmark data set, but are not directly applicable in daily clinical practice.