REVIEW 16 cited by
Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation
read the original abstract
The Segment Anything Model (SAM) has recently gained popularity in the field of image segmentation due to its impressive capabilities in various segmentation tasks and its prompt-based interface. However, recent studies and individual experiments have shown that SAM underperforms in medical image segmentation, since the lack of the medical specific knowledge. This raises the question of how to enhance SAM's segmentation capability for medical images. In this paper, instead of fine-tuning the SAM model, we propose the Medical SAM Adapter (Med-SA), which incorporates domain-specific medical knowledge into the segmentation model using a light yet effective adaptation technique. In Med-SA, we propose Space-Depth Transpose (SD-Trans) to adapt 2D SAM to 3D medical images and Hyper-Prompting Adapter (HyP-Adpt) to achieve prompt-conditioned adaptation. We conduct comprehensive evaluation experiments on 17 medical image segmentation tasks across various image modalities. Med-SA outperforms several state-of-the-art (SOTA) medical image segmentation methods, while updating only 2\% of the parameters. Our code is released at https://github.com/KidsWithTokens/Medical-SAM-Adapter.
Forward citations
Cited by 16 Pith papers
-
PR-MaGIC: Prompt Refinement Via Mask Decoder Gradient Flow For In-Context Segmentation
PR-MaGIC refines prompts in in-context segmentation via test-time gradient flow from the mask decoder plus top-1 selection, yielding better masks across benchmarks without training.
-
Zero-Shot Learning in Industrial Scenarios: New Large-Scale Benchmark, Challenges and Baseline
Presents MMIO benchmark and RTVP method achieving state-of-the-art 42.2% AP in zero-shot industrial defect detection.
-
DeCoDrift: Stabilizing Decoder Coupling in Closed-Loop Foundation Segmentation
DeCoDrift stabilizes decoder coupling in closed-loop foundation segmentation by constraining prompt updates without retraining or ground truth.
-
SAMamba3D: adapting Segment Anything for generalizable 3D segmentation of multiphase pore-scale images
SAMamba3D adapts a frozen SAM encoder with Mamba volumetric context and cross-scale features to match or exceed 3D baselines on diverse sandstone and carbonate datasets while reducing case-specific retraining.
-
Learning to Synergize Semantic and Geometric Priors for Limited-Data Wheat Disease Segmentation
SGPer combines DINOv2 semantic priors converted to dense prompts with SAM geometric priors through disease-sensitive adapters and dynamic consistency filtering to deliver robust limited-data wheat disease segmentation.
-
SegSLR: Promptable Video Segmentation for Isolated Sign Language Recognition
SegSLR uses pose-guided SAM 2 video segmentations to focus RGB streams on the signer's body and hands, improving isolated sign language recognition on ChaLearn249 IsoGD.
-
COMMA: Coordinate-aware Modulated Mamba Network for 3D Dispersed Vessel Segmentation
Presents COMMA, a coordinate-aware Mamba network for 3D vessel segmentation that uses global and local branches, along with a new 570-case labeled dataset.
-
SAM 2: Segment Anything in Images and Videos
SAM 2 delivers more accurate video segmentation with 3x fewer user interactions and 6x faster image segmentation than the original SAM by training a streaming-memory transformer on the largest video segmentation datas...
-
Parameter-Efficient Fine-Tuning of Large Pretrained Models for Instance Segmentation Tasks
Empirical tests show adapters (2-3 per block) and LoRA on deformable attention achieve competitive instance segmentation with 1-6% parameters tuned versus 40-55% for full fine-tuning.
-
Anatomy-Anchored Self-Supervision: Distilling Vision Foundation Models for Invariant Ultrasound Representation
ANAUS introduces anatomy-anchored self-supervision with LP-SAM delineation and dual policies (inter-view anatomy alignment plus core-region prediction) to distill invariant ultrasound representations, claiming SOTA re...
-
Any2Any 3D Diffusion Models with Knowledge Transfer: A Radiotherapy Planning Study
DiffKT3D transfers priors from video diffusion models to 3D radiotherapy dose prediction via modality-specific embeddings and clinically guided RL, reducing voxel MAE from 2.07 to 1.93 and claiming SOTA over the GDP-H...
-
Deep Reprogramming Distillation for Medical Foundation Models
DRD introduces a reprogramming module and CKA-based distillation to enable efficient, robust adaptation of medical foundation models to downstream 2D/3D classification and segmentation tasks, outperforming prior PEFT ...
-
Align then Refine: Text-Guided 3D Prostate Lesion Segmentation
A text-guided multi-encoder U-Net with alignment loss, heatmap calibration, and confidence-gated cross-attention refiner sets new state-of-the-art 3D prostate lesion segmentation performance on the PI-CAI dataset.
-
Towards Any-Quality Image Segmentation via Generative and Adaptive Latent Space Enhancement
GleSAM++ improves SAM robustness on degraded images by using generative enhancement, feature alignment, and adaptive degradation prediction while adding few parameters.
-
Multimodal SAM-adapter for Semantic Segmentation
A side-tuning adapter injects RGB-plus-auxiliary-sensor fused features into SAM's encoder, reaching state-of-the-art semantic segmentation on DeLiVER, FMB, and MUSES.
-
Parameter-Efficient Adaptation of SAM 3 for Automated ITV Generation from 4DCT Images
LoRA-adapted SAM 3 with hard-negative mining and phase-coherent filtering achieves median Dice 0.968 on pulmonary structures from 4DCT using seven annotated volumes.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.