SPAN is a hierarchical attention framework that constructs multi-scale pyramid representations from single-scale patch inputs for WSI classification and segmentation while preserving spatial relationships.
Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
Global color moments and RGB/HSV histograms alone support binary benign-malignant classification at up to 89% accuracy with classical ML classifiers, substantially above random baselines.
citing papers explorer
-
Learning Spatial-Preserving Hierarchical Representations for Digital Pathology
SPAN is a hierarchical attention framework that constructs multi-scale pyramid representations from single-scale patch inputs for WSI classification and segmentation while preserving spatial relationships.
-
Beyond Morphology: Quantifying the Diagnostic Power of Color Features in Cancer Classification
Global color moments and RGB/HSV histograms alone support binary benign-malignant classification at up to 89% accuracy with classical ML classifiers, substantially above random baselines.