Cross-link Space, model and dataset; state the model's actual role in the demo

README.md

@@ -15,7 +15,7 @@ tags:
 
 # MEDTRACE brain tumour segmentation (SegResNet)
 
-3D tumour compartment segmentation from four co-registered MRI sequences. Trained on BraTS 2023 GLI and used by the [MEDTRACE](https://huggingface.co/spaces/AIOmarRehan/medtrace) longitudinal workstation.
+3D tumour compartment segmentation from four co-registered MRI sequences. Trained on BraTS 2023 GLI and published as part of the [MEDTRACE](https://huggingface.co/spaces/AIOmarRehan/medtrace) longitudinal workstation, which deliberately **does not** measure with it. [Why](#a-note-on-how-medtrace-uses-this).
 
 > [!WARNING]
 > **Research prototype. Not a medical device.** Not for diagnosis, treatment planning, or any clinical decision. Not clinically validated. It has been measured against one annotation protocol on one dataset, which is agreement, not clinical accuracy.
@@ -85,7 +85,11 @@ MONAI 1.6.0, PyTorch 2.10.0+cu128.
 
 ## A note on how MEDTRACE uses this
 
-The hosted MEDTRACE demo does **not** run this model. Its measurements come from expert-corrected segmentations shipped with RHUH-GBM, because that dataset is post-operative and post-treatment, which is exactly the regime this model was not trained for. Publishing the model and measuring with it are separate decisions, and only one of them is justified by the numbers above.
+MEDTRACE does **not** measure with this model, hosted or local. The [hosted demo](https://huggingface.co/spaces/AIOmarRehan/medtrace) reads the expert-corrected segmentations that ship with [RHUH-GBM](https://huggingface.co/datasets/AIOmarRehan/medtrace-rhuh-gbm-derived); the local build reads DeepBraTumIA's masks on LUMIERE.
+
+The reason is measured rather than cautious. Run against DeepBraTumIA on 12 randomly chosen LUMIERE studies, this model reaches 0.923 median Dice on whole tumour but **0.486 on enhancing tumour, below 0.5 in 6 of the 12** — and enhancing tumour is the single compartment MEDTRACE reports change on. Split by how much enhancement is present, the weakness is specific rather than uniform: 0.861 median Dice where enhancement is bulky (>= 5 cm3, n=5) against 0.193 where it is small (< 5 cm3, n=7), overestimating volume roughly fourfold in the small group. Post-operative brains are outside this model's training distribution, and on small lesions a few tenths of a cm3 is what decides whether progression is reported.
+
+Publishing the model and measuring with it are separate decisions. Only the first is justified by the numbers above.
 
 ## Training data and required citations