MRI-based Alzheimer's disease classification using Vision Transformer and time-series transformer: A step-by-step guide

Alp S., Akan S., Akan T., Bhuiyan M. A. N.

Software Impacts, cilt.25, 2025 (Scopus) identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 25
  • Basım Tarihi: 2025
  • Doi Numarası: 10.1016/j.simpa.2025.100771
  • Dergi Adı: Software Impacts
  • Derginin Tarandığı İndeksler: Scopus
  • Anahtar Kelimeler: Alzheimer's disease, MRI, Sequence classification, Transfer learning, Vision transformer
  • İstanbul Üniversitesi Adresli: Hayır

Özet

This study introduces a reproducible pipeline for classifying Alzheimer's Disease from structural brain MRI utilizing a joint transformer architecture that integrates Vision Transformer and Time-Series Transformer models. The proposed framework uses pre-trained ViT for feature extraction from 2D slices of MRI volumes, followed by sequential modeling with a transformer-based classifier to capture inter-slice dependencies. The method is evaluated on the ADNI dataset, involving both binary (AD vs. NC) and multiclass (AD, MCI, NC) classification tasks across axial, sagittal, and coronal planes.