How to use

  1. Decide which model to use:
    Low magnification (5×) = overall disease pattern
    High magnification (40×) = individual aggregates
  2. Take snapshots:
    Extract square snapshots from the region of interest at the correct magnification.
  3. Prepare your images:
    Save snapshots into a single folder.
    Ensure images match the selected model:
    • Low magnification – representative field of the region
    • High magnification – one aggregate per image
  4. Upload images:
    Select the folder to upload. Multiple images will be processed automatically.
  5. Interpret outputs:
    The model returns class probabilities (%) for each image.
    Higher values indicate stronger morphological similarity to a trained class.
  6. Export results:
    Download predictions as an Excel file for further analysis.
*Models were trained on AT8-stained tau pathology images, but may generalise to other tau immunostains.
*Predictions are probabilistic outputs from a supervised convolutional neural network and should be interpreted alongside full neuropathological assessment, not used as a standalone diagnostic tool.
Abbreviations

Pick's – Pick’s disease
RA – Ramified astrocyte
PSP – Progressive supranuclear palsy
TA – Tufted astrocyte
CBD – Corticobasal degeneration
AP – Astrocytic plaque
GGT – Globular glial tauopathy
GGA – Globular glial astrocyte
CTE – Chronic traumatic encephalopathy
TSA – Thorn-shaped astrocyte
PART – Primary age-related tauopathy
GFA – Granular fuzzy astrocyte
Low AD – Low Alzheimer's disease
Ageing NP – Ageing neuritic plaque
AD – Alzheimer's disease
AD NP – Alzheimer's disease neuritic plaque
NFT – Neurofibrillary tangle

Tau-Net

Each section below corresponds to a magnification model.
Upload a folder of images into the one you wish to test.

Low magnification
Disease classifier (5×, 900 px²)

Low magnification examples

High magnification
Aggregate classifier (40×, single aggregate)

High magnification examples