.png){kind=icon}
.png){kind=icon}
Return
A unified multi-task framework enables interpretable chest radiograph analysis
.png){kind=icon}
PRE
AI
L
Z
X
H
S
DOI：10.1016/j.medj.2026.101223.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A unified multi-task transformer for chest X-ray analysis was proposed • It links disease recognition, attributes, and evidence-based reporting • It achieves competitive performance across ten chest X-ray benchmarks • Radiologists rated 66% of AI reports comparable to or better than clinical reports
Journal
IF:
11.8
Papers:
771
Citations:
2.2K
Organization
Cited Papers