A two-stage pipeline using pretrained vision encoders with retrieval augmentation achieves 0.9423 held-out accuracy for leukemia versus normal detection, but ALL versus AML subtyping collapses under domain shift, showing within-domain performance comes largely from dataset artifacts.
Dinobloom: A foundation model for generalizable cell embeddings in hematology,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Retrieval-Augmented Vision Foundation Models for Robust Leukemia Cell Classification across Multiple Microscopy Datasets
A two-stage pipeline using pretrained vision encoders with retrieval augmentation achieves 0.9423 held-out accuracy for leukemia versus normal detection, but ALL versus AML subtyping collapses under domain shift, showing within-domain performance comes largely from dataset artifacts.