VitaminP uses paired H&E-mIF data to train a model that transfers molecular boundary information, enabling accurate whole-cell segmentation directly from routine H&E histology across 34 cancer types.
Version Number: 1
3 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
3
Pith papers citing it
1
external citations · external index
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 3years
2026 3roles
background 1polarities
unclear 1representative citing papers
An Atlas-foundation-model system for multi-cancer H&E tissue and cell profiling matches pathologist H&E accuracy against IHC-informed consensus and generalizes across 1,500+ cases.
CellDETR is a detection-guided framework extending Deformable DETR for cell representation learning from WSIs, with contrastive pretraining and cross-dataset transfer shown on PanNuke and Xenium data.
citing papers explorer
-
VitaminP: cross-modal learning enables whole-cell segmentation from routine histology
VitaminP uses paired H&E-mIF data to train a model that transfers molecular boundary information, enabling accurate whole-cell segmentation directly from routine H&E histology across 34 cancer types.
-
Atlas H&E-TME: Scalable AI-Based Tissue Profiling at Expert Pathologist-Level Accuracy
An Atlas-foundation-model system for multi-cancer H&E tissue and cell profiling matches pathologist H&E accuracy against IHC-informed consensus and generalizes across 1,500+ cases.
-
CellDETR: A Detection-Guided Framework for Scalable Cell Representation Learning from Histopathology Images
CellDETR is a detection-guided framework extending Deformable DETR for cell representation learning from WSIs, with contrastive pretraining and cross-dataset transfer shown on PanNuke and Xenium data.