AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

SegAnyPET: Universal Promptable Segmentation from Positron Emission Tomography Images

Yichi Zhang, Le Xue, Wenbo Zhang, Lanlan Li, Yuchen Liu, Chen Jiang, Yuan Cheng, Yuan Qi

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 14 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add cross prompting consistency regularization on LQ images (ablation)SegAnyPET · PETS-5k seen organs, 1 pointDSC (%): 87.61 -> 89.28Improved
add cross prompting consistency regularization on LQ images (ablation)SegAnyPET · PETS-5k unseen organs, 1 pointDSC (%): 62.74 -> 67.52Improved
add uncertainty-guided self-rectification on top of consistency (full CPCL) (ablation)SegAnyPET · PETS-5k seen organs, 1 pointDSC (%): 89.28 -> 90.49Improved
add uncertainty-guided self-rectification on top of consistency (full CPCL) (ablation)SegAnyPET · PETS-5k unseen organs, 1 pointDSC (%): 67.52 -> 73.96Improved
add uncertainty-guided self-rectification on top of consistency (full CPCL) (ablation)SegAnyPET · PETS-5k unseen organs, 5 pointsDSC (%): 70.97 -> 77.87Improved
increase prompt points from 1 to 5SegAnyPET · PETS-5k seen organsDSC (%): 90.49 -> 91.05Improved
increase prompt points from 1 to 5SAM-Med3D-turbo · PETS-5k seen organsDSC (%): 72.09 -> 78.35Improved
use 3D volumetric model instead of slice-by-slice 2D SAMSegAnyPET vs SAM · PETS-5k seen organs, 1 pointDSC (%): 13.15 -> 90.49Improved
train on PET with PETS-5k instead of using CT-based SAM-Med3D-turboSegAnyPET · organ segmentation, 1 pointDSC (%): 66.59 -> 90.49Improved
use SegAnyPET promptable model instead of automatic nnUNetSegAnyPET · PETS-5k seen organsDSC (%): 89.83 -> 90.49Improved
apply 3D SegAnyPET to scattered tumor lesionsSegAnyPET vs SAM · AutoPET tumor, 5 pointsDSC (%): 40.91 -> 24.93Hurt
evaluate SegAnyPET on unseen AutoPET-Organ lung and aorta organsSegAnyPET vs SAM-Med3D · AutoPET-Organ Lung-UL, 1 pointDSC (%): 51.69 -> 10.80Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy