Innovative AI Tool Identifies Nine Types of Dementia Using a Single Brain Scan

Researchers at Mayo Clinic have introduced an advanced artificial intelligence (AI) system capable of differentiating nine distinct types of dementia, including Alzheimer's disease, through analysis of just one standard brain scan. This breakthrough technology marks a significant step forward in the early and accurate diagnosis of dementia, a condition that currently poses substantial diagnostic challenges.

The AI tool, known as StateViewer, demonstrated a remarkable ability to correctly identify the dementia subtype in 88% of cases examined during testing. It also significantly expedited the interpretation process, making assessments nearly twice as fast and up to three times more accurate compared to conventional methods. The system was trained and validated using over 3,600 brain scans from individuals with varied cognitive conditions, emphasizing its robustness and potential clinical utility.

This innovation addresses a critical need in dementia care: early detection and precise classification, which are vital for timely intervention and tailored treatment plans. Accurate diagnosis is especially challenging when multiple neurodegenerative conditions coexist. By simplifying and speeding up the diagnostic process, StateViewer could be particularly beneficial for clinics with limited access to neurology specialists.

The technology evaluates FDG-PET scans, which map brain glucose usage—a marker of neural activity. It then compares these patterns to an extensive database to identify characteristic signatures of different dementia types. Visualized through color-coded brain maps, the system highlights regions affected by various dementias, providing clinicians with clear, intuitive insights to aid diagnosis.

Led by Dr. David Jones, neurologist and director of the Mayo Clinic Neurology AI Program, the development of StateViewer was a collaborative effort that combines deep learning with practical clinical needs. Dr. Jones emphasizes the importance of harnessing machine learning to improve patient outcomes by enabling earlier and more precise diagnosis.

Mayo Clinic plans to expand the use of this AI tool and evaluate its effectiveness across diverse clinical settings. As dementia diagnoses become more accurate and accessible, the potential for personalized treatment and improved quality of life for patients increases. This technology represents a promising leap toward transforming neurodegenerative disease management.

For further details, see the study: Leland Barnard et al, "An FDG-PET–Based Machine Learning Framework to Support Neurologic Decision-Making in Alzheimer Disease and Related Disorders," published in Neurology, June 2025.