RadGPT: Constructing 3D Image-Text Tumor Datasets

PRAS Bassi, MC Yavuz, K Wang, X Chen, W Li… - arxiv preprint arxiv …, 2025 - arxiv.org
With over 85 million CT scans performed annually in the United States, creating tumor-
related reports is a challenging and time-consuming task for radiologists. To address this …

Text-driven tumor synthesis

X Li, Y Shuai, C Liu, Q Chen, Q Wu, P Guo… - arxiv preprint arxiv …, 2024 - arxiv.org
Tumor synthesis can generate examples that AI often misses or over-detects, improving AI
performance by training on these challenging cases. However, existing synthesis methods …

Efficient MedSAMs: Segment Anything in Medical Images on Laptop

J Ma, F Li, S Kim, R Asakereh, BH Le… - arxiv preprint arxiv …, 2024 - arxiv.org
Promptable segmentation foundation models have emerged as a transformative approach to
addressing the diverse needs in medical images, but most existing models require …