Stro-VIGRU: Defining the Vision Recurrent-Based Baseline Model for Brain Stroke Classification

TL;DR

This paper proposes a Vision Transformer and Bi-GRU based transfer learning framework for early brain stroke detection from CT scans, achieving high accuracy and addressing class imbalance with data augmentation.

Contribution

It introduces a novel combination of ViT and Bi-GRU for stroke classification, with selective fine-tuning and data augmentation for improved performance.

Findings

Achieved 94.06% accuracy in stroke classification

Effectively handled class imbalance with data augmentation

Demonstrated the potential of transformer-based models for medical diagnosis

Abstract

Stroke majorly causes death and disability worldwide, and early recognition is one of the key elements of successful treatment of the same. It is common to diagnose strokes using CT scanning, which is fast and readily available, however, manual analysis may take time and may result in mistakes. In this work, a pre-trained Vision Transformer-based transfer learning framework is proposed for the early identification of brain stroke. A few of the encoder blocks of the ViT model are frozen, and the rest are allowed to be fine-tuned in order to learn brain stroke-specific features. The features that have been extracted are given as input to a single-layer Bi-GRU to perform classification. Class imbalance is handled by data augmentation. The model has achieved 94.06% accuracy in classifying brain stroke from the Stroke Dataset.