Multi-Threshold Attention U-Net (MTAU) based Model for Multimodal Brain Tumor Segmentation in MRI scans

TL;DR

This paper introduces a multi-threshold attention U-Net model for segmenting different tumor regions in MRI scans, achieving competitive accuracy in identifying glioma components for improved diagnosis.

Contribution

The study presents a novel multi-path attention U-Net architecture with separate models for tumor regions, enhancing segmentation accuracy in brain MRI analysis.

Findings

Achieved mean Dice Coefficients of 0.59, 0.72, and 0.61 for training.

Achieved mean Dice Coefficients of 0.57, 0.73, and 0.61 for validation.

Achieved mean Dice Coefficients of 0.59, 0.72, and 0.57 for testing.

Abstract

Gliomas are one of the most frequent brain tumors and are classified into high grade and low grade gliomas. The segmentation of various regions such as tumor core, enhancing tumor etc. plays an important role in determining severity and prognosis. Here, we have developed a multi-threshold model based on attention U-Net for identification of various regions of the tumor in magnetic resonance imaging (MRI). We propose a multi-path segmentation and built three separate models for the different regions of interest. The proposed model achieved mean Dice Coefficient of 0.59, 0.72, and 0.61 for enhancing tumor, whole tumor and tumor core respectively on the training dataset. The same model gave mean Dice Coefficient of 0.57, 0.73, and 0.61 on the validation dataset and 0.59, 0.72, and 0.57 on the test dataset.