Add EmbeddingCollapseMetric: detect representational collapse in medi… (#8815)

…cal imaging embeddings

Closes #8808

Fixes # .

### Description

A few sentences describing the changes proposed in this pull request.

Adds EmbeddingCollapseMetric for detecting representational collapse in
embedding spaces — when class centroids converge, effective
dimensionality drops, or domains become indistinguishable, even while
AUROC/Dice look fine.

Computes five indicators (all [0, 1], higher = more collapsed):

centroid_similarity — L2-normalised class centroid cosine similarity
effective_rank_score — SVD effective rank (Roy & Vetterli, 2007)
per_class_rank_<cls> — per-class effective rank (asymmetric collapse)
domain_shift — linear CKA between domains (Kornblith et al., 2019)
separation — silhouette inter-class separation (sklearn optional)

Follows FIDMetric/MMDMetric pattern: inherits Metric,
tensor-in/tensor-out, torch-only core. Validated on pathology embeddings


### Types of changes
<!--- Put an `x` in all the boxes that apply, and remove the not
applicable items -->
- [x] Non-breaking change (fix or new feature that would not break
existing functionality).
- [ ] Breaking change (fix or new feature that would cause existing
functionality to change).
- [x] New tests added to cover the changes.
- [ ] Integration tests passed locally by running `./runtests.sh -f -u
--net --coverage`.
- [x] Quick tests passed locally by running `./runtests.sh --quick
--unittests --disttests`.
- [x] In-line docstrings updated.
- [ ] Documentation updated, tested `make html` command in the `docs/`
folder.

Signed-off-by: ekansh-arora0 <ekansh.arora0@gmail.com>
Co-authored-by: Eric Kerfoot <17726042+ericspod@users.noreply.github.com>

Author: ekansh-arora0

docs/source/metrics.rst

@@ -158,6 +158,13 @@ Metrics
 
 `Fréchet Inception Distance`
 ------------------------------
+`Embedding Collapse`
+------------------------------
+.. autofunction:: compute_embedding_collapse
+
+.. autoclass:: EmbeddingCollapseMetric
+    :members:
+
 .. autofunction:: compute_frechet_distance
 
 .. autoclass:: FIDMetric

monai/metrics/__init__.py

@@ -16,6 +16,7 @@
 from .calibration import CalibrationErrorMetric, CalibrationReduction, calibration_binning
 from .confusion_matrix import ConfusionMatrixMetric, compute_confusion_matrix_metric, get_confusion_matrix
 from .cumulative_average import CumulativeAverage
+from .embedding_collapse import EmbeddingCollapseMetric, compute_embedding_collapse
 from .f_beta_score import FBetaScore
 from .fid import FIDMetric, compute_frechet_distance
 from .froc import compute_fp_tp_probs, compute_fp_tp_probs_nd, compute_froc_curve_data, compute_froc_score