A slice-by-slice vision-language model with a Z-former and Vicuna-7B generates radiology reports that outperform 3D-patch baselines on chest CT and rectal MRI.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Read Like a Radiologist: Efficient Vision-Language Model for 3D Medical Imaging Interpretation
A slice-by-slice vision-language model with a Z-former and Vicuna-7B generates radiology reports that outperform 3D-patch baselines on chest CT and rectal MRI.