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.
This is likely due to the increased complexity of the REACTIV AS data closely adjacent glomeruli sharing bor- ders, making segmentation more difficult
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.