SAM 3 outperforms SAM 2 under click prompting for zero-shot 3D medical segmentation across 16 datasets and 54 structures, with fewer failure modes in prompt-frame over-segmentation and prediction retention.
hub
A Large Annotated Medical Image Dataset for the Development and Evaluation of Segmentation Algorithms
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
abstract
Semantic segmentation of medical images aims to associate a pixel with a label in a medical image without human initialization. The success of semantic segmentation algorithms is contingent on the availability of high-quality imaging data with corresponding labels provided by experts. We sought to create a large collection of annotated medical image datasets of various clinically relevant anatomies available under open source license to facilitate the development of semantic segmentation algorithms. Such a resource would allow: 1) objective assessment of general-purpose segmentation methods through comprehensive benchmarking and 2) open and free access to medical image data for any researcher interested in the problem domain. Through a multi-institutional effort, we generated a large, curated dataset representative of several highly variable segmentation tasks that was used in a crowd-sourced challenge - the Medical Segmentation Decathlon held during the 2018 Medical Image Computing and Computer Aided Interventions Conference in Granada, Spain. Here, we describe these ten labeled image datasets so that these data may be effectively reused by the research community.
hub tools
representative citing papers
The authors release FOMO260K, a heterogeneous dataset of 260k+ 3D brain MRIs from 910 sources to support large-scale self-supervised learning in medical imaging.
U-Mamba is a hybrid CNN-SSM architecture that outperforms prior CNN and Transformer networks on biomedical image segmentation tasks by efficiently modeling long-range dependencies.
SAMRI fine-tunes only the mask decoder of SAM on 1.1 million MRI slices from 30 datasets to reach mean DSC 0.87 on 47 targets and strong zero-shot performance.
MedRCube is a new fine-grained evaluation framework that benchmarks 33 MLLMs on medical imaging, ranks Lingshu-32B highest, and finds a significant positive link between shortcut behaviors and diagnostic performance.
TaCo contrastively embeds semantic, generative, and transformation tasks from medical imaging into a joint space to reveal which tasks cluster, blend, or remain distinct.
GCNV-Net achieves state-of-the-art accuracy on multiple 3D medical segmentation benchmarks while cutting FLOPs by 56% and inference latency by 68% through dynamic nonvoid voxelization and geometric attention.
A self-supervised approach uses consistent spatial relationships of anatomical structures across patients to improve 3D multi-modal medical image representations, yielding modest gains on segmentation and classification tasks.
Introduces Implantable Adaptive Cells inserted into pre-trained U-Nets via Partially-Connected DARTS to achieve approximately 5 percentage point gains in segmentation accuracy on four medical MRI/CT datasets.
Vol-Mark embeds watermarks into 3D medical volumes using contrastive learning for feature extraction and cubic difference expansion for embedding, achieving ACC above 0.90 against most attacks with reversible low-distortion properties.
SGP-SAM transfers 3D SAM to lesion segmentation using a self-gated module for conditional multi-scale enhancement and a Zoom Loss, achieving 7.3% mDice gain over fine-tuning on MSD Liver Tumor data.
Hybrid U-Mamba architecture with Heat Conduction Operators achieves DSC of 0.8719 on Abdomen CT dataset by simulating frequency-domain thermal diffusion.
SAM (ViT-B) shows stable spleen segmentation in abdominal CT with mean Dice drop below 0.01 and no rise in failures under simulated domain shifts like noise, blur, and contrast changes.
citing papers explorer
-
Comparing SAM 2 and SAM 3 for Zero-Shot Segmentation of 3D Medical Data
SAM 3 outperforms SAM 2 under click prompting for zero-shot 3D medical segmentation across 16 datasets and 54 structures, with fewer failure modes in prompt-frame over-segmentation and prediction retention.
-
A large-scale heterogeneous 3D magnetic resonance brain imaging dataset for self-supervised learning
The authors release FOMO260K, a heterogeneous dataset of 260k+ 3D brain MRIs from 910 sources to support large-scale self-supervised learning in medical imaging.
-
U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation
U-Mamba is a hybrid CNN-SSM architecture that outperforms prior CNN and Transformer networks on biomedical image segmentation tasks by efficiently modeling long-range dependencies.
-
SAMRI: Segment Any MRI
SAMRI fine-tunes only the mask decoder of SAM on 1.1 million MRI slices from 30 datasets to reach mean DSC 0.87 on 47 targets and strong zero-shot performance.
-
MedRCube: A Multidimensional Framework for Fine-Grained and In-Depth Evaluation of MLLMs in Medical Imaging
MedRCube is a new fine-grained evaluation framework that benchmarks 33 MLLMs on medical imaging, ranks Lingshu-32B highest, and finds a significant positive link between shortcut behaviors and diagnostic performance.
-
Probing Intrinsic Medical Task Relationships: A Contrastive Learning Perspective
TaCo contrastively embeds semantic, generative, and transformation tasks from medical imaging into a joint space to reveal which tasks cluster, blend, or remain distinct.
-
Geometrical Cross-Attention and Nonvoid Voxelization for Efficient 3D Medical Image Segmentation
GCNV-Net achieves state-of-the-art accuracy on multiple 3D medical segmentation benchmarks while cutting FLOPs by 56% and inference latency by 68% through dynamic nonvoid voxelization and geometric attention.
-
Beyond Instance-Level Self-Supervision in 3D Multi-Modal Medical Imaging
A self-supervised approach uses consistent spatial relationships of anatomical structures across patients to improve 3D multi-modal medical image representations, yielding modest gains on segmentation and classification tasks.
-
Implantable Adaptive Cells: A Novel Enhancement for Pre-Trained U-Nets in Medical Image Segmentation
Introduces Implantable Adaptive Cells inserted into pre-trained U-Nets via Partially-Connected DARTS to achieve approximately 5 percentage point gains in segmentation accuracy on four medical MRI/CT datasets.
-
Vol-Mark: A Watermark for 3D Medical Volume Data Via Cubic Difference Expansion and Contrastive Learning
Vol-Mark embeds watermarks into 3D medical volumes using contrastive learning for feature extraction and cubic difference expansion for embedding, achieving ACC above 0.90 against most attacks with reversible low-distortion properties.
-
SGP-SAM: Self-Gated Prompting for Transferring 3D Segment Anything Models to Lesion Segmentation
SGP-SAM transfers 3D SAM to lesion segmentation using a self-gated module for conditional multi-scale enhancement and a Zoom Loss, achieving 7.3% mDice gain over fine-tuning on MSD Liver Tumor data.
-
Enhancing Medical Image Segmentation via Heat Conduction Equation
Hybrid U-Mamba architecture with Heat Conduction Operators achieves DSC of 0.8719 on Abdomen CT dataset by simulating frequency-domain thermal diffusion.
-
Robustness Evaluation of a Foundation Segmentation Model Under Simulated Domain Shifts in Abdominal CT: Implications for Health Digital Twin Deployment
SAM (ViT-B) shows stable spleen segmentation in abdominal CT with mean Dice drop below 0.01 and no rise in failures under simulated domain shifts like noise, blur, and contrast changes.