A decoupled watershed-plus-EfficientNet pipeline recovers 75.95% of cells without annotations and reaches 98.36% stage classification accuracy with instance-level explainability on the NIH BBBC041 dataset.
Delgado-Ortet, A
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MalariAI: A Label-Resilient Decoupled Framework for Universal Cell Segmentation and Explainable Stage Classification in Dense Malaria Blood Smears
A decoupled watershed-plus-EfficientNet pipeline recovers 75.95% of cells without annotations and reaches 98.36% stage classification accuracy with instance-level explainability on the NIH BBBC041 dataset.