A conditional latent diffusion model jointly generates histology images, distance maps, and cell-type masks, and adding its outputs to real training data improves cell segmentation and classification by about 2-3% on two public datasets.
Medical Image Analysis58, 101563 (2019)
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
-
HistoSmith: Single-Stage Histology Image-Label Generation via Conditional Latent Diffusion for Enhanced Cell Segmentation and Classification
A conditional latent diffusion model jointly generates histology images, distance maps, and cell-type masks, and adding its outputs to real training data improves cell segmentation and classification by about 2-3% on two public datasets.