隐空间实验室 LatentLab

← All demos · Treatment Response (pCR) · Identity Recognition · Risk Assessment: manipulated-image detection

Physiological Age

Estimate the physiological age of the breast from screening mammograms and compare it with the actual age.

How it works

INPUT 1–4 mammograms L-CC R-CC L-MLO R-MLO DICOM optional: actual age Normalise min–max to 0–255 resize to 224 × 224 ResNet-50 (GPU) 23 classes: 25, 26, … 47 years Combine most likely age per view, then the mean OUTPUT Physiological age 41.5years vs actual age: difference in years

Each mammogram is normalised, resized to 224 × 224 and classified by a ResNet-50 into one-year age classes from 25 to 47. The predicted ages of all uploaded views are averaged. If an actual age is entered (or present in the DICOM header), the difference is shown.

Input

  • 1–4 mammogram DICOM files (L/R, CC/MLO)
  • Optional: actual age in years

Output

  • Predicted physiological age (the model's range is 25–47 years)
  • Per-view prediction with the class probabilities

Lab model trained on normal mammograms (validation MAE 3.15 years). Typical run time: A few seconds.

Your data is not saved. Uploaded files are written only to a temporary folder on the lab GPU computer and deleted the moment the computation ends (or fails, or you cancel). Results are held in memory for 15 minutes so this page can show them, then discarded. Nothing is copied to our storage or logs.
Remove patient identity information before uploading. Strip names, IDs, birth dates, addresses, hospital and physician names from the files (for DICOM, use your PACS or a de-identification tool). This page checks DICOM headers in your browser before upload and warns you if such fields are still filled in. Research demo only — not for diagnosis or treatment decisions. Upload limit: 400 MB.

Run it

Click or drop 1–4 DICOM files (CC/MLO, left/right)
    Used only to show the difference. If empty, the age in the DICOM header (if any) is used.