Search papers, labs, and topics across Lattice.
University of Zurich
5
0
5
Automated segmentation of all blood vessels in CT images could revolutionize cardiovascular diagnostics by enabling systemic health assessments rather than isolated analyses.
RadAgent doesn't just give you the answer; it shows its work, offering clinicians a transparent, step-by-step reasoning trace for AI-generated CT reports.
Representing complex 3D biomedical graphs as learned tokens unlocks generative modeling and efficient analysis of anatomical structures.
Ditch fixed-size 3D blocks: SigVLP uses rotary embeddings to let vision-language models handle CT volumes with variable slice counts, unlocking better pre-training.
VariViT lets you train vision transformers on variable-sized images without resizing, boosting accuracy on medical imaging tasks by better preserving irregularly shaped structures.
