A U-Net architecture with specialized boundary attention decoder, built on pathology foundation models, reports higher Dice and IoU scores than prior methods for glomeruli segmentation.
Metrics reloaded: recommendations for image analysis validation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-bio.TO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A deep learning framework for glomeruli segmentation with boundary attention
A U-Net architecture with specialized boundary attention decoder, built on pathology foundation models, reports higher Dice and IoU scores than prior methods for glomeruli segmentation.