Online demos
Four deep-learning models from our papers and theses, running on the lab’s NVIDIA RTX A6000 GPU. Each page explains how the model works, what it takes and what it returns. Jobs wait in one GPU queue; each page shows your place in it and the expected time.
Treatment Response (pCR)
Predict whether breast cancer will respond completely to neoadjuvant chemotherapy, from MRI before and early in treatment.
Input: Pre-treatment breast DCE-MRI volume (NIfTI, .nii or .nii.gz) …
Output: Probability of pCR (≥ 0.5 → predicted pCR)
Identity Recognition
Decide whether two mammography exams belong to the same woman.
Input: Exam A: 2–4 mammogram DICOM files (at least CC and MLO of one side) …
Output: Probability that both exams are of the same person (> 0.5 → same)
Physiological Age
Estimate the physiological age of the breast from screening mammograms and compare it with the actual age.
Input: 1–4 mammogram DICOM files (L/R, CC/MLO) …
Output: Predicted physiological age (the model's range is 25–47 years)
Risk Assessment: manipulated-image detection
Check whether a mammogram has been altered by a generative model that removed a lesion.
Input: One mammogram: DICOM, or PNG/TIFF (16-bit preferred)
Output: p-value and verdict (manipulated if p < 0.05)