Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

T. Schaffer, A. Brawanski, S. Wein, A. M. Tomé, E. W. Lang

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.

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

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.
Paper Structure (20 sections, 6 figures, 4 tables)

This paper contains 20 sections, 6 figures, 4 tables.

Table of Contents

  1. Introduction
  2. State-of-the-Art
  3. Datasets
  4. Methods
  5. Image preprocessing
  6. Reference segmentation model
  7. 3D U-Net with general filter blocks
  8. Filter block structures
  9. An upscaling PAU-Net
  10. Extraction of NET compartments from BraTS 2018 data
  11. Results
  12. Training of the upscaling PAU-Net model
  13. NET volume distributions
  14. Analysis of variance for intensity masks
  15. Training of a unified 4-Label BraTS 2018/2021 Dataset
  16. ...and 5 more sections

Figures (6)

  • Figure 1: Different types of residual filter blocks. Each type can be used in the above U-Net architecture
  • Figure 2: Two variants of the new up-scaling PAU-Net.
  • Figure 3: Records from the BraTS 2018 dataset BraTS2018 named CBICA-ANI-1, CBICA-AXO-1, CBICA-AQQ-1, TCIA03-419 (top to bottom). Left: Flair (CBICA-ANI-1, CBICA-AXO-1) or T1C (CBICA-AQQ-1, TCIA03-419) slice. Center: original BraTS 2018 segmentation mask (ED yellow, NCR+NET red, ET blue). Right: NCR (red) and NET (green) separated and filtered.
  • Figure 4: Sample record from BraTS 2021 dataset BraTS2021. Top row from left to right: T1, T2, T1C, Flair; Bottom row left: BraTS 2021 tumor segmentation data, right: tumor segmentation data extended with NET region (yellow)
  • Figure 5: Results for training the PAU-Net on BraTS 2018 subset with extracted NET segments. Training was performed with 100 epochs, 1044ms/step, learning rate $10^{-4}$ with 5% decay per epoch, training data size 68, batch size 1, GPU Tesla T4. Left: final DSCs, Right: Learning curves
  • ...and 1 more figures