CytoSAE learns sparse, expert-validated morphological concepts from blood-cell images that generalize across datasets and can classify AML subtypes at patient level with F1 0.83.
NPJ digital medicine5(1), 156 (2022)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CytoSAE: Interpretable Cell Embeddings for Hematology
CytoSAE learns sparse, expert-validated morphological concepts from blood-cell images that generalize across datasets and can classify AML subtypes at patient level with F1 0.83.