Advancing Brain Tumor Segmentation via Attention-based 3D U-Net Architecture and Digital Image Processing

TL;DR

Addresses brain tumor segmentation from multi‑modal MRI, where irregular tumor shapes and boundary ambiguity hinder accurate delineation. Proposes a two‑part approach that combines an attention‑augmented 3D U‑Net with a digital image processing‑based tumor detector to balance training data and prioritize informative regions. On BraTS2020, the method achieves Dice = 0.975, specificity = 0.988, and sensitivity = 0.995, with an overall accuracy around 0.992, showcasing improved boundary delineation over related work. The approach holds promise for more reliable, clinically actionable segmentation in diagnostic workflows.

Abstract

In the realm of medical diagnostics, rapid advancements in Artificial Intelligence (AI) have significantly yielded remarkable improvements in brain tumor segmentation. Encoder-Decoder architectures, such as U-Net, have played a transformative role by effectively extracting meaningful representations in 3D brain tumor segmentation from Magnetic resonance imaging (MRI) scans. However, standard U-Net models encounter challenges in accurately delineating tumor regions, especially when dealing with irregular shapes and ambiguous boundaries. Additionally, training robust segmentation models on high-resolution MRI data, such as the BraTS datasets, necessitates high computational resources and often faces challenges associated with class imbalance. This study proposes the integration of the attention mechanism into the 3D U-Net model, enabling the model to capture intricate details and prioritize informative regions during the segmentation process. Additionally, a tumor detection algorithm based on digital image processing techniques is utilized to address the issue of imbalanced training data and mitigate bias. This study aims to enhance the performance of brain tumor segmentation, ultimately improving the reliability of diagnosis. The proposed model is thoroughly evaluated and assessed on the BraTS 2020 dataset using various performance metrics to accomplish this goal. The obtained results indicate that the model outperformed related studies, exhibiting dice of 0.975, specificity of 0.988, and sensitivity of 0.995, indicating the efficacy of the proposed model in improving brain tumor segmentation, offering valuable insights for reliable diagnosis in clinical settings.

Figures (6)

• Figure 1: The pipeline of the proposed approach for 3D BraTS
• Figure 2: Tumor detection results
• Figure 3: The architecture of 3D U-Net model with attention gate
• Figure 4: Performance metrics vs. epochs for the first round
• Figure 5: Performance metrics vs. epochs for the second round