Squeeze Excitation Embedded Attention UNet for Brain Tumor Segmentation

TL;DR

This paper introduces SEEA-UNet, a novel brain tumor segmentation architecture combining Attention UNet and Squeeze Excitation Network to enhance feature extraction at spatial and channel levels, outperforming existing models with fewer training epochs.

Contribution

The paper presents a new architecture, SEEA-UNet, integrating attention mechanisms and squeeze excitation for improved brain tumor segmentation.

Findings

SEEA-UNet outperforms existing architectures in fewer epochs.

Binary focal loss and Jaccard Coefficient effectively monitor performance.

The model achieves better predictions with enhanced feature extraction.

Abstract

Deep Learning based techniques have gained significance over the past few years in the field of medicine. They are used in various applications such as classifying medical images, segmentation and identification. The existing architectures such as UNet, Attention UNet and Attention Residual UNet are already currently existing methods for the same application of brain tumor segmentation, but none of them address the issue of how to extract the features in channel level. In this paper, we propose a new architecture called Squeeze Excitation Embedded Attention UNet (SEEA-UNet), this architecture has both Attention UNet and Squeeze Excitation Network for better results and predictions, this is used mainly because to get information at both Spatial and channel levels. The proposed model was compared with the existing architectures based on the comparison it was found out that for lesser number of epochs trained, the proposed model performed better. Binary focal loss and Jaccard Coefficient were used to monitor the model's performance.