BreastGPT, trained on a new workflow-aligned breast imaging instruction corpus, outperforms prior MLLMs with 75.66% closed-ended and 89.92% open-ended scores on a held-out benchmark spanning screening, diagnosis, and treatment planning.
Unique 2D / 3D images
1 Pith paper cite this work, alongside 16 external citations. Polarity classification is still indexing.
1
Pith paper citing it
16
external citations · OpenAlex
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
BreastGPT: A Multimodal Large Language Model for the Full Spectrum of Breast Cancer Clinical Routine
BreastGPT, trained on a new workflow-aligned breast imaging instruction corpus, outperforms prior MLLMs with 75.66% closed-ended and 89.92% open-ended scores on a held-out benchmark spanning screening, diagnosis, and treatment planning.