A new 490-scan PE dataset and benchmark of nine 2D/3D CNN and ViT models shows 3D U-Net with ResNet blocks as top performer with consistent error patterns across architectures and releases open weights.
Label up: Learning pulmonary embolism segmentation from image level annotation through model explainability.arXiv preprint arXiv:2412.07384, 2024
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
-
Rethinking Pulmonary Embolism Segmentation: A Study of Current Approaches and Challenges with an Open Weight Model
A new 490-scan PE dataset and benchmark of nine 2D/3D CNN and ViT models shows 3D U-Net with ResNet blocks as top performer with consistent error patterns across architectures and releases open weights.