Explainable Artificial Intelligence in Neuroimaging of Alzheimer’s Disease

Объяснимый искусственный интеллект в нейровизуализации болезни Альцгеймера
Siamak Pedrammehr, Ali Jafarizadeh, H M Dipu Kabir, Mahdieh Taiyeb Khosroshahi, Soroush Morsali, Sohrab Gharakhanlou, Alireza Motamedi, Saeid Hassanbaghlou, Hadi Vahedi
2025-03-04

Alzheimer’s diseaseGrad-CAMSHAPexplainable artificial intelligenceneuroimaging
Alzheimer's disease (AD) remains a significant global health challenge, affecting millions worldwide and imposing substantial burdens on healthcare systems. Advances in artificial intelligence (AI), particularly in deep learning and machine learning, have revolutionized neuroimaging-based AD diagnosis. However, the complexity and lack of interpretability of these models limit their clinical applicability. Explainable Artificial Intelligence (XAI) addresses this challenge by providing insights into model decision-making, enhancing transparency, and fostering trust in AI-driven diagnostics. This review explores the role of XAI in AD neuroimaging, highlighting key techniques such as SHAP, LIME, Grad-CAM, and Layer-wise Relevance Propagation (LRP). We examine their applications in identifying critical biomarkers, tracking disease progression, and distinguishing AD stages using various imaging modalities, including MRI and PET. Additionally, we discuss current challenges, including dataset limitations, regulatory concerns, and standardization issues, and propose future research directions to improve XAI's integration into clinical practice. By bridging the gap between AI and clinical interpretability, XAI holds the potential to refine AD diagnostics, personalize treatment strategies, and advance neuroimaging-based research.
1
Dataset limitations, regulatory concerns, and insufficient standardization currently hinder the integration of XAI into clinical practice.
2
Explainable artificial intelligence can improve the transparency and clinical trustworthiness of AI-based neuroimaging diagnostics for Alzheimer’s disease.
3
Improved XAI integration could refine Alzheimer’s diagnosis, enable more personalized treatment strategies, and advance neuroimaging research.
4
SHAP, LIME, Grad-CAM, and Layer-wise Relevance Propagation are highlighted as key techniques for interpreting neuroimaging models.
5
XAI methods support identification of Alzheimer’s biomarkers, monitoring disease progression, and distinguishing disease stages using MRI and PET.

neuroimaging-based artificial intelligence models for Alzheimer’s disease diagnosis, using MRI and PET data

the explainability, transparency, and clinical interpretability of AI-driven Alzheimer’s disease diagnostics, including biomarker identification, disease-progression tracking, and stage differentiation

Publication Details
Publication Date
2025-03-04
Journal
Publisher
ISSN
Cited by
78
Access Type
Author Information
Authors
Siamak Pedrammehr
Ali Jafarizadeh
H M Dipu Kabir
Mahdieh Taiyeb Khosroshahi
Soroush Morsali
Sohrab Gharakhanlou
Alireza Motamedi
Saeid Hassanbaghlou
Hadi Vahedi
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%