Brain Tumor Segmentation with Special Emphasis on the Non-Enhancing Brain Tumor Compartment

TL;DR

This paper introduces a U-Net based deep learning method for brain tumor segmentation on MRI, with a focus on accurately delineating the non-enhancing tumor compartment, which is crucial for prognosis and treatment planning.

Contribution

The study emphasizes the importance of the non-enhancing tumor compartment and develops a segmentation approach that specifically targets this region, addressing a gap in recent challenges.

Findings

Effective segmentation of non-enhancing tumor regions achieved

Improved correlation between segmented tumor and patient prognosis

Demonstrated the clinical relevance of non-enhancing tumor delineation

Abstract

A U-Net based deep learning architecture is designed to segment brain tumors as they appear on various MRI modalities. Special emphasis is lent to the non-enhancing tumor compartment. The latter has not been considered anymore in recent brain tumor segmentation challenges like the MICCAI challenges. However, it is considered to be indicative of the survival time of the patient as well as of areas of further tumor growth. Hence it deems essential to have means to automatically delineate its extension within the tumor.