An L2-Normalized Spatial Attention Network For Accurate And Fast Classification Of Brain Tumors In 2D T1-Weighted CE-MRI Images

TL;DR

This paper introduces an L2-normalized spatial attention network that improves brain tumor classification accuracy in 2D MRI images while maintaining speed, outperforming existing lightweight models and benefiting from ensemble methods.

Contribution

The paper presents a novel L2-normalized spatial attention mechanism that enhances classification accuracy and acts as a regularizer against overfitting in brain tumor MRI classification.

Findings

Achieved a 1.79% accuracy improvement over state-of-the-art methods.

The proposed attention mechanism reduces overfitting during training.

Ensembling with VGG16 further improves accuracy at the cost of speed.

Abstract

We propose an accurate and fast classification network for classification of brain tumors in MRI images that outperforms all lightweight methods investigated in terms of accuracy. We test our model on a challenging 2D T1-weighted CE-MRI dataset containing three types of brain tumors: Meningioma, Glioma and Pituitary. We introduce an l2-normalized spatial attention mechanism that acts as a regularizer against overfitting during training. We compare our results against the state-of-the-art on this dataset and show that by integrating l2-normalized spatial attention into a baseline network we achieve a performance gain of 1.79 percentage points. Even better accuracy can be attained by combining our model in an ensemble with the pretrained VGG16 at the expense of execution speed. Our code is publicly available at https://github.com/juliadietlmeier/MRI_image_classification