ABRA shows radiology agents excel at tool execution (89%+) but struggle with outcomes (0-25%), with oracle perception raising outcomes to 69-100%, identifying perception as the primary bottleneck.
and Grimm, Lars J
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
dataset 1polarities
use dataset 1representative citing papers
Releases a new public multi-center European breast MRI dataset of 741 cases with heterogeneous protocols and provides baseline transformer model benchmarks.
A stepwise clinically-guided multimodal attention model for pCR prediction from breast MRI improves sensitivity and cross-institutional generalization over non-guided baselines.
citing papers explorer
-
ABRA: Agent Benchmark for Radiology Applications
ABRA shows radiology agents excel at tool execution (89%+) but struggle with outcomes (0-25%), with oracle perception raising outcomes to 69-100%, identifying perception as the primary bottleneck.
-
A European Multi-Center Breast Cancer MRI Dataset
Releases a new public multi-center European breast MRI dataset of 741 cases with heterogeneous protocols and provides baseline transformer model benchmarks.
-
Multimodal Stepwise Clinically-Guided Attention Learning for Pathological Complete Response Prediction in Breast Cancer
A stepwise clinically-guided multimodal attention model for pCR prediction from breast MRI improves sensitivity and cross-institutional generalization over non-guided baselines.