AI Paper Atlas

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

MaskSAM: Auto-prompt SAM with Mask Classification for Volumetric Medical Image Segmentation

Bin Xie, Hao Tang, Bin Duan, Dawen Cai, Yan Yan, Gady Agam

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Prompted SAM 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
use averaged mask-derived and learnable box prompts instead of masks only (ablation)MaskSAM · ACDCDice (DSC, %): 89.53 -> 91.45Improved
use averaged mask-derived and learnable box prompts instead of boxes only (ablation)MaskSAM · ACDCDice (DSC, %): 88.78 -> 91.45Improved
use averaged boxes instead of separate mask and box prompts (ablation)MaskSAM · ACDCDice (DSC, %): 90.08 -> 91.45Improved
add depth positional embedding (ablation)MaskSAM · ACDCDice (DSC, %): 91.45 -> 91.61Improved
add depth MLP after FC-Up of vanilla adapter (ablation)MaskSAM · ACDCDice (DSC, %): 91.61 -> 92.88Improved
add depth MLP before FC-Down of vanilla adapter (ablation)MaskSAM · ACDCDice (DSC, %): 91.61 -> 92.93Improved
use DMLPAdapter (depth MLP in middle of adapter) (ablation)MaskSAM · ACDCDice (DSC, %): 91.61 -> 93.10Improved
add DConvAdapter for image embeddings on top of DMLPAdapter (ablation)MaskSAM · ACDCDice (DSC, %): 93.10 -> 93.39Improved
fine-tune SAM with MaskSAM instead of SAMed (prompt-free)SAM · AMOS22 testDice (DSC, %): 0.772 -> 0.905Improved
use nnUNet-predicted box prompts with SAM instead of nnUNet itselfSAM · AMOS22 testDice (DSC, %): 0.878 -> 0.538Hurt
replace nnUNet with MaskSAMnnUNet · SynapseDice (DSC, %): 86.21 -> 87.23Improved
replace nnUNet with MaskSAMnnUNet · ACDCDice (DSC, %): 91.61 -> 93.39Improved

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