.png){kind=icon}
.png){kind=icon}
Return
Automated identification of incidentalomas requiring follow-up: A multi-anatomy evaluation of LLM-based and supervised approaches
.png){kind=icon}
PRE
AI
N
F
Z
K
E
J
Ö
M
M
DOI：10.1016/j.jbi.2026.105048.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
To evaluate large language models (LLMs) against supervised baselines for fine-grained, lesion-level detection of incidentalomas requiring follow-up, addressing the limitations of current document-level classification systems.
Keywords:
incidentalomas
fine-grained detection
lesion-level analysis
large language models
supervised baselines
Journal
IF:
4.5
Papers:
3.5K
Citations:
1.9W
Organization
Cited Papers