Spatial Sequence Attention Network for Schizophrenia Classification from Structural Brain MR Images

TL;DR

This paper proposes a novel deep learning approach using Spatial Sequence Attention to improve schizophrenia classification from structural MRI, leveraging transfer learning with DenseNet to capture subtle brain morphological changes.

Contribution

It introduces the Spatial Sequence Attention mechanism for enhanced feature extraction in MRI-based schizophrenia diagnosis, outperforming existing attention models.

Findings

SSA outperforms Squeeze & Excitation Network in classification accuracy

Transfer learning with DenseNet effectively captures brain morphological features

Proposed method demonstrates improved diagnostic performance on clinical data

Abstract

Schizophrenia is a debilitating, chronic mental disorder that significantly impacts an individual's cognitive abilities, behavior, and social interactions. It is characterized by subtle morphological changes in the brain, particularly in the gray matter. These changes are often imperceptible through manual observation, demanding an automated approach to diagnosis. This study introduces a deep learning methodology for the classification of individuals with Schizophrenia. We achieve this by implementing a diversified attention mechanism known as Spatial Sequence Attention (SSA) which is designed to extract and emphasize significant feature representations from structural MRI (sMRI). Initially, we employ the transfer learning paradigm by leveraging pre-trained DenseNet to extract initial feature maps from the final convolutional block which contains morphological alterations associated with Schizophrenia. These features are further processed by the proposed SSA to capture and emphasize intricate spatial interactions and relationships across volumes within the brain. Our experimental studies conducted on a clinical dataset have revealed that the proposed attention mechanism outperforms the existing Squeeze & Excitation Network for Schizophrenia classification.