DyABD is the first benchmark dataset for abdominal muscle segmentation in dynamic MRIs featuring exercise-induced anatomical changes and pre/post-surgery scans, where existing models achieve an average Dice score of 0.82.
hub Tool reference
The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification
Tool reference. 100% of classified Pith citations use this work as a method, library, or software dependency, not as a substantive claim.
37
Pith papers citing it
Method reference
100% of classified citations
abstract
The BraTS 2021 challenge celebrates its 10th anniversary and is jointly organized by the Radiological Society of North America (RSNA), the American Society of Neuroradiology (ASNR), and the Medical Image Computing and Computer Assisted Interventions (MICCAI) society. Since its inception, BraTS has been focusing on being a common benchmarking venue for brain glioma segmentation algorithms, with well-curated multi-institutional multi-parametric magnetic resonance imaging (mpMRI) data. Gliomas are the most common primary malignancies of the central nervous system, with varying degrees of aggressiveness and prognosis. The RSNA-ASNR-MICCAI BraTS 2021 challenge targets the evaluation of computational algorithms assessing the same tumor compartmentalization, as well as the underlying tumor's molecular characterization, in pre-operative baseline mpMRI data from 2,040 patients. Specifically, the two tasks that BraTS 2021 focuses on are: a) the segmentation of the histologically distinct brain tumor sub-regions, and b) the classification of the tumor's O[6]-methylguanine-DNA methyltransferase (MGMT) promoter methylation status. The performance evaluation of all participating algorithms in BraTS 2021 will be conducted through the Sage Bionetworks Synapse platform (Task 1) and Kaggle (Task 2), concluding in distributing to the top ranked participants monetary awards of $60,000 collectively.
hub tools
citation-role summary
dataset 5
method 1
citation-polarity summary
representative citing papers
NeuroQA is a large-scale 3D brain MRI visual question answering benchmark with verified image-grounded QA pairs, multi-domain coverage, and baseline evaluations showing current models lag behind text-only performance.
SEMIR replaces dense voxel computation with a learned topology-preserving graph minor that supports exact decoding and GNN-based inference for small-structure segmentation in large medical images.
AnomalyClaw turns single-step VLM anomaly judgments into a multi-round tool-grounded refutation process, delivering consistent macro-AUROC gains of 3.5-7.9 percentage points over direct inference across 12 cross-domain datasets.
Introduces the first large-scale 3D PET/CT dataset with fine-grained RoI annotations for Vietnamese and a graph-enhanced HiRRA framework that achieves SOTA report generation by modeling RoI dependencies.
Agentic LLMs autonomously execute complex neuro-radiological workflows like glioma segmentation and multi-timepoint response assessment by directing off-the-shelf tools, without any model training.
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.
LiFT factorizes 3D medical volume synthesis into per-slice 2D generation and inter-slice trajectory learning, using a tri-planar drifting loss for unconditional coherence and a z-context mixer for paired translation tasks.
A uniform benchmark across 77 experiments finds SRGAN superior to latent diffusion models for 3D medical image translation, with synthetic volumes indistinguishable from real ones in a 17-physician Turing test.
LARGO uses a low-rank hypernetwork with CP decomposition to unify 2^N-1 missing-modality models into one, ranking first in 47 of 52 configurations on BraTS and ISLES with small Dice gains over baselines.
DiGSeg repurposes diffusion U-Nets as generalist segmentation learners by conditioning on image-mask latents and multi-scale CLIP text features, achieving strong cross-domain performance.
VS-DDPM accelerates 3D diffusion models for medical modality translation, reaching SOTA Dice scores of 0.80-0.88 and SSIM 0.95 on missing MRI synthesis in BraTS2025 while remaining competitive on tumor removal and sCT tasks.
WFM achieves near-diffusion quality for all four BraTS MRI modalities with one 82M model in 1-2 steps by flowing from the mean of conditioning modalities in wavelet space, running 250-1000x faster.
MedFlowSeg is a conditional flow matching model for medical image segmentation that adds dual-branch spatial attention and frequency-aware attention to achieve more efficient inference than diffusion models while improving structural consistency.
Replacing the generic Stable Diffusion VAE with domain-specific MedVAE pretrained on 1.6M medical images improves diffusion-based SR PSNR by 2.91-3.29 dB on knee/brain MRI and chest X-ray, with gains in fine details and VAE quality predicting SR performance (R²=0.67).
LAKE identifies sparse anomaly-sensitive neurons in pre-trained VLMs using minimal normal samples to build compact normality representations and achieve SOTA anomaly detection with neuron-level interpretability.
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.
LLaBIT is a single instruction-finetuned LLM that performs report generation, VQA, segmentation, and translation on brain MRI images while outperforming task-specific models.
Patient identity and clinical features predict brain tumor segmentation accuracy more strongly than model choice, with localized spatial biases consistent across models and no formal fairness guarantees in any.
A single model trained on one normal sample per dataset from nine heterogeneous medical sources achieves state-of-the-art anomaly detection in one-shot universal, full-shot universal, one-shot specialized, and full-shot specialized settings.
UniMo is a unified DL framework for correcting rigid and deformable motion in medical images that generalizes across modalities after single-modality training.
A neural-network inpainting variant of BUQO that turns local artefact hypothesis testing into a primal-dual optimization problem for Fourier and Radon imaging operators.
SegGuidedNet achieves Dice scores of 0.905 on BraTS2021 and 0.897 on BraTS2023 with sub-region attention supervision that adds under 0.2% parameters and provides free spatial interpretability.
D3Seg improves brain tumor segmentation under missing MRI modalities via multi-hop graph fusion, latent diffusion imputation, and probability refinement, reporting 1-2% Dice gains on BraTS 2023.
citing papers explorer
-
DyABD: The Abdominal Muscle Segmentation in Dynamic MRI Benchmark
DyABD is the first benchmark dataset for abdominal muscle segmentation in dynamic MRIs featuring exercise-induced anatomical changes and pre/post-surgery scans, where existing models achieve an average Dice score of 0.82.
-
NeuroQA: A Large-Scale Image-Grounded Benchmark for 3D Brain MRI Understanding
NeuroQA is a large-scale 3D brain MRI visual question answering benchmark with verified image-grounded QA pairs, multi-domain coverage, and baseline evaluations showing current models lag behind text-only performance.
-
SEMIR: Semantic Minor-Induced Representation Learning on Graphs for Visual Segmentation
SEMIR replaces dense voxel computation with a learned topology-preserving graph minor that supports exact decoding and GNN-based inference for small-structure segmentation in large medical images.
-
AnomalyClaw: A Universal Visual Anomaly Detection Agent via Tool-Grounded Refutation
AnomalyClaw turns single-step VLM anomaly judgments into a multi-round tool-grounded refutation process, delivering consistent macro-AUROC gains of 3.5-7.9 percentage points over direct inference across 12 cross-domain datasets.
-
Region-Grounded Report Generation for 3D Medical Imaging: A Fine-Grained Dataset and Graph-Enhanced Framework
Introduces the first large-scale 3D PET/CT dataset with fine-grained RoI annotations for Vietnamese and a graph-enhanced HiRRA framework that achieves SOTA report generation by modeling RoI dependencies.
-
Agentic Large Language Models for Training-Free Neuro-Radiological Image Analysis
Agentic LLMs autonomously execute complex neuro-radiological workflows like glioma segmentation and multi-timepoint response assessment by directing off-the-shelf tools, without any model training.
-
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.
-
LiFT: Lifted Inter-slice Feature Trajectories for 3D Image Generation from 2D Generators
LiFT factorizes 3D medical volume synthesis into per-slice 2D generation and inter-slice trajectory learning, using a tri-planar drifting loss for unconditional coherence and a z-context mixer for paired translation tasks.
-
Cross Modality Image Translation In Medical Imaging Using Generative Frameworks
A uniform benchmark across 77 experiments finds SRGAN superior to latent diffusion models for 3D medical image translation, with synthetic volumes indistinguishable from real ones in a 17-physician Turing test.
-
LARGO: Low-Rank Hypernetwork for Handling Missing Modalities
LARGO uses a low-rank hypernetwork with CP decomposition to unify 2^N-1 missing-modality models into one, ranking first in 47 of 52 configurations on BraTS and ISLES with small Dice gains over baselines.
-
Diffusion Model as a Generalist Segmentation Learner
DiGSeg repurposes diffusion U-Nets as generalist segmentation learners by conditioning on image-mask latents and multi-scale CLIP text features, achieving strong cross-domain performance.
-
VS-DDPM: Efficient Low-Cost Diffusion Model for Medical Modality Translation
VS-DDPM accelerates 3D diffusion models for medical modality translation, reaching SOTA Dice scores of 0.80-0.88 and SSIM 0.95 on missing MRI synthesis in BraTS2025 while remaining competitive on tumor removal and sCT tasks.
-
WFM: 3D Wavelet Flow Matching for Ultrafast Multi-Modal MRI Synthesis
WFM achieves near-diffusion quality for all four BraTS MRI modalities with one 82M model in 1-2 steps by flowing from the mean of conditioning modalities in wavelet space, running 250-1000x faster.
-
MedFlowSeg: Flow Matching for Medical Image Segmentation with Frequency-Aware Attention
MedFlowSeg is a conditional flow matching model for medical image segmentation that adds dual-branch spatial attention and frequency-aware attention to achieve more efficient inference than diffusion models while improving structural consistency.
-
Domain-Specific Latent Representations Improve the Fidelity of Diffusion-Based Medical Image Super-Resolution
Replacing the generic Stable Diffusion VAE with domain-specific MedVAE pretrained on 1.6M medical images improves diffusion-based SR PSNR by 2.91-3.29 dB on knee/brain MRI and chest X-ray, with gains in fine details and VAE quality predicting SR performance (R²=0.67).
-
Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Models
LAKE identifies sparse anomaly-sensitive neurons in pre-trained VLMs using minimal normal samples to build compact normality representations and achieve SOTA anomaly detection with neuron-level interpretability.
-
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.
-
Visual Instruction-Finetuned Language Model for Versatile Brain MR Image Tasks
LLaBIT is a single instruction-finetuned LLM that performs report generation, VQA, segmentation, and translation on brain MRI images while outperforming task-specific models.
-
Fairboard: a quantitative framework for equity assessment of healthcare models
Patient identity and clinical features predict brain tumor segmentation accuracy more strongly than model choice, with localized spatial biases consistent across models and no formal fairness guarantees in any.
-
Semantic Iterative Reconstruction: One-Shot Universal Anomaly Detection
A single model trained on one normal sample per dataset from nine heterogeneous medical sources achieves state-of-the-art anomaly detection in one-shot universal, full-shot universal, one-shot specialized, and full-shot specialized settings.
-
A Unified Deep Learning Framework for Motion Correction in Medical Imaging
UniMo is a unified DL framework for correcting rigid and deformable motion in medical images that generalizes across modalities after single-modality training.
-
A Plug-and-Play Method with Inpainting Network for Bayesian Uncertainty Quantification in Imaging
A neural-network inpainting variant of BUQO that turns local artefact hypothesis testing into a primal-dual optimization problem for Fourier and Radon imaging operators.
-
SegGuidedNet: Sub-Region-Aware Attention Supervision for Interpretable Brain Tumor Segmentation
SegGuidedNet achieves Dice scores of 0.905 on BraTS2021 and 0.897 on BraTS2023 with sub-region attention supervision that adds under 0.2% parameters and provides free spatial interpretability.
-
D3Seg: Dependency-Aware Diffusion for Brain Tumor Segmentation with Missing Modalities
D3Seg improves brain tumor segmentation under missing MRI modalities via multi-hop graph fusion, latent diffusion imputation, and probability refinement, reporting 1-2% Dice gains on BraTS 2023.
-
MHMamba: Multi-Head Mamba for 3D Brain Tumor Segmentation
MHMamba combines a U-Net with multi-head Mamba, channel calibration, and adaptive skip fusion to improve 3D brain tumor segmentation accuracy and small-lesion sensitivity on BraTS datasets while retaining linear complexity.
-
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.
-
Vision Transformer-Conditioned UNet for Domain-Adaptive Semantic Segmentation
ViTC-UNet adapts frozen ViT representations to biomedical semantic segmentation by conditioning a UNet via learnable tokens and two-way attention decoding.
-
SynerMedGen: Synergizing Medical Multimodal Understanding with Generation via Task Alignment
SynerMedGen introduces generation-aligned understanding tasks and a two-stage training strategy that enables strong zero-shot medical image synthesis performance and outperforms specialized models when generation training is added.
-
RF-HiT: Rectified Flow Hierarchical Transformer for General Medical Image Segmentation
RF-HiT uses rectified flow and a multi-scale hierarchical transformer to reach 91.27% Dice on ACDC and 87.40% on BraTS 2021 with only 10.14 GFLOPs, 13.6M parameters, and three inference steps.
-
Improved Anomaly Detection in Medical Images via Mean Shift Density Enhancement
A new Mean Shift Density Enhancement procedure applied to self-supervised embeddings yields state-of-the-art anomaly detection AUC and average precision on seven medical imaging datasets.
-
Robust Glioblastoma Segmentation and Volumetry Without T2-FLAIR: External Validation of Targeted Dropout Training
Targeted T2-FLAIR dropout during training preserves glioblastoma segmentation performance with full MRI protocols and raises overall median DSC from 81.0% to 93.4% when T2-FLAIR is absent in external validation on 403 cases.
-
RASALoRE: Region Aware Spatial Attention with Location-based Random Embeddings for Weakly Supervised Anomaly Detection in Brain MRI Scans
A novel weakly supervised anomaly detection method for brain MRI that uses discriminative dual prompt tuning for pseudo masks and region-aware spatial attention with location-based random embeddings to achieve SOTA results with under 8 million parameters on BraTS and MSD datasets.
-
CoRE: Concept-Reasoning Expansion for Continual Brain Lesion Segmentation
CoRE aligns image tokens to a hierarchical concept library to simulate clinical reasoning for expert routing and demand-based growth in continual brain lesion segmentation, achieving SOTA on 12 tasks.
-
Improving Pre-trained Segmentation Models using Post-Processing
Adaptive post-processing refines outputs from pre-trained glioma segmentation models, improving challenge metrics by 14.9% in one task and 0.9% in another.
-
Adaptable Segmentation Pipeline for Diverse Brain Tumors with Radiomic-guided Subtyping and Lesion-Wise Model Ensemble
A radiomic-guided subtyping and lesion-wise ensemble pipeline delivers segmentation performance comparable to top entries on diverse BraTS 2025 brain tumor datasets.
-
Flemme: A Flexible and Modular Learning Platform for Medical Images
Flemme is a modular platform separating encoders (conv/transformer/SSM) from encoder-decoder architectures for medical images, with a hierarchical pyramid loss yielding reported average gains of 5.6% Dice and 5.57% PSNR.
- BrainDINO: A Brain MRI Foundation Model for Generalizable Clinical Representation Learning