Sezgin Er

Routine clinical reports and historical scans can entirely replace manual voxel annotations, yielding dense tumor segmenters that outperform supervised public baselines at zero labeling cost.

Current AI models miss critical tumor detections in underrepresented demographics, revealing a hidden bias that could compromise patient outcomes.

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.