A synthetic data pipeline that inserts anatomy-guided shapes and cut-paste objects into chest X-rays trains foreign-object segmentation models to match fully supervised performance with 93 percent fewer manual masks.
Performance on Synthetic Data In Fig
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
-
Foreign object segmentation in chest x-rays through anatomy-guided shape insertion
A synthetic data pipeline that inserts anatomy-guided shapes and cut-paste objects into chest X-rays trains foreign-object segmentation models to match fully supervised performance with 93 percent fewer manual masks.