Single-label imaging-modality classification for medical images. One shared ConvNet backbone, two softmax heads (family, modality), shipped as a static-INT8 ONNX graph. Predicts what kind of image this is, not what is in it. Anatomy is a different model. Softmax, temperature and thresholds live outside the graph so calibration and policy stay configuration. modality-taxonomy.json travels with the weights - a 20-element logits vector is 20 meaningless numbers without it. Tier is a statement about evidence, not difficulty. modeltrained means the corpus had at least two independent sources and enough patients to make the number falsifiable. experimental means it did not. nottrained classes are…