ReXGroundingCT
PulseAugur coverage of ReXGroundingCT — every cluster mentioning ReXGroundingCT across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New system verifies LLM-generated chest CT reports by grounding findings to scans
Researchers have developed EviGround-CT, a novel system designed to verify findings in chest CT reports generated by large language models (LLMs). This system addresses the issue of LLM-generated reports sometimes descr…
-
New frameworks enhance medical VLM lesion interpretation using geometry and counterfactual reasoning · 3 sources tracked
Researchers have developed new frameworks for medical vision-language models (VLMs) to improve the interpretation of complex lesions with multiple phenotypes. The PureVision framework uses geometry-supervised learning t…
-
New AI method uses radiology reports to improve 3D CT scan abnormality segmentation
Researchers have developed Instance-Guided Report Anchoring (IGRA), a novel module designed to improve 3D abnormality segmentation in chest CT scans. IGRA leverages existing radiology reports to provide instance-specifi…
-
New CT scan segmentation method uses weak supervision from text reports
Researchers have developed a novel method for segmenting CT scans using weak supervision derived from textual reports. This approach combines voxel-level supervision with slice-level classification loss extracted from s…
-
New AI framework improves 3D medical image grounding · arXiv paper
Researchers have developed a novel two-stage framework for voxel-level grounding of free-text findings in 3D chest CT scans. This approach decouples the process into class-agnostic lesion segmentation followed by text-v…