AXIAL: Attention-based eXplainability for Interpretable Alzheimer's Localized Diagnosis using 2D CNNs on 3D MRI brain scans

Name: AXIAL: Attention-based eXplainability for Interpretable Alzheimer's Localized Diagnosis using 2D CNNs on 3D MRI brain scans
Uploaded: 2026-10-02T10:37:29.332348+00:00
Duration: 1290 s
Description: This study introduces a method for classifying Alzheimer's disease from 3D MRI scans using 2D Convolutional Neural Networks (CNNs). It enhances model explainability by generating a voxel-level attention map, showing which brain regions the AI focuses on during diagnosis. This provides interpretable insights into AD detection.

This study introduces a method for classifying Alzheimer's disease from 3D MRI scans using 2D Convolutional Neural Networks (CNNs). It enhances model explainability by generating a voxel-level attention map, showing which brain regions the AI focuses on during diagnosis. This provides interpretable insights into AD detection.

Open the full episode