A large annotated medical image dataset for the development and evaluation of segmentation algorithms

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.

References in corpus (1)

• Why rankings of biomedical image analysis competitions should be interpreted with care

Cited by in corpus (133)

• Automated Design of Deep Learning Methods for Biomedical Image Segmentation
• The Medical Segmentation Decathlon
• MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification
• CHAOS Challenge -- Combined (CT-MR) Healthy Abdominal Organ Segmentation
• Medical Image Segmentation Using Deep Learning: A Survey
• Segment Anything Model for Medical Image Analysis: an Experimental Study
• Segment Anything Model for Medical Images?
• Metrics reloaded: Recommendations for image analysis validation
• MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis
• Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation
• Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future
• UNETR: Transformers for 3D Medical Image Segmentation
• Transformers in Healthcare: A Survey
• 3D Self-Supervised Methods for Medical Imaging
• nnDetection: A Self-configuring Method for Medical Object Detection
• Recent Progress in Transformer-based Medical Image Analysis
• Reinventing 2D Convolutions for 3D Images
• Diminishing Uncertainty within the Training Pool: Active Learning for Medical Image Segmentation
• TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation
• Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging
• CLIP in Medical Imaging: A Survey
• Self-paced and self-consistent co-training for semi-supervised image segmentation
• One Network to Segment Them All: A General, Lightweight System for Accurate 3D Medical Image Segmentation
• Integrated Biophysical Modeling and Image Analysis: Application to Neuro-Oncology
• Interactive segmentation of medical images through fully convolutional neural networks
• Pancreas segmentation with probabilistic map guided bi-directional recurrent UNet
• HiDiff: Hybrid Diffusion Framework for Medical Image Segmentation
• QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation - Analysis of Ranking Scores and Benchmarking Results
• Compete to Win: Enhancing Pseudo Labels for Barely-supervised Medical Image Segmentation
• Prior-aware Neural Network for Partially-Supervised Multi-Organ Segmentation
• DeepReg: a deep learning toolkit for medical image registration
• Evaluating the Performance of StyleGAN2-ADA on Medical Images
• Learning joint segmentation of tissues and brain lesions from task-specific hetero-modal domain-shifted datasets
• Auto-FedAvg: Learnable Federated Averaging for Multi-Institutional Medical Image Segmentation
• Federated Multi-organ Segmentation with Inconsistent Labels
• CTSpine1K: A Large-Scale Dataset for Spinal Vertebrae Segmentation in Computed Tomography
• PGL: Prior-Guided Local Self-supervised Learning for 3D Medical Image Segmentation
• Learning Inductive Attention Guidance for Partially Supervised Pancreatic Ductal Adenocarcinoma Prediction
• Thickened 2D Networks for Efficient 3D Medical Image Segmentation
• DeepMRSeg: A convolutional deep neural network for anatomy and abnormality segmentation on MR images
• Deep Learning for Pancreas Segmentation: a Systematic Review
• Mediastinal lymph nodes segmentation using 3D convolutional neural network ensembles and anatomical priors guiding
• Boosting Semi-supervised Image Segmentation with Global and Local Mutual Information Regularization
• Incremental Learning for Multi-organ Segmentation with Partially Labeled Datasets
• M3d-CAM: A PyTorch library to generate 3D data attention maps for medical deep learning
• DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentation
• Efficient, high-performance pancreatic segmentation using multi-scale feature extraction
• C2FNAS: Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentation
• Theoretical analysis and experimental validation of volume bias of soft Dice optimized segmentation maps in the context of inherent uncertainty
• Domain Adaptive Relational Reasoning for 3D Multi-Organ Segmentation
• AbdomenCT-1K: Is Abdominal Organ Segmentation A Solved Problem?
• Saliency is a Possible Red Herring When Diagnosing Poor Generalization
• Efficient Context-Aware Network for Abdominal Multi-organ Segmentation
• Multi-organ segmentation: a progressive exploration of learning paradigms under scarce annotation
• Bootstrap Representation Learning for Segmentation on Medical Volumes and Sequences
• Deep Co-Training for Semi-Supervised Image Segmentation
• Exploring UMAP in hybrid models of entropy-based and representativeness sampling for active learning in biomedical segmentation
• 3D Brain and Heart Volume Generative Models: A Survey
• Treatment Learning Causal Transformer for Noisy Image Classification
• V-NAS: Neural Architecture Search for Volumetric Medical Image Segmentation
• Learning Euler's Elastica Model for Medical Image Segmentation
• Deep learning based registration using spatial gradients and noisy segmentation labels
• Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation
• AI-based Aortic Vessel Tree Segmentation for Cardiovascular Diseases Treatment: Status Quo
• Deep learning in magnetic resonance prostate segmentation: A review and a new perspective
• Improving Vessel Segmentation with Multi-Task Learning and Auxiliary Data Available Only During Model Training
• SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering
• A Systematic Collection of Medical Image Datasets for Deep Learning
• 3D U${}^2$-Net: A 3D Universal U-Net for Multi-Domain Medical Image Segmentation
• Increasing-Margin Adversarial (IMA) Training to Improve Adversarial Robustness of Neural Networks
• DoDNet: Learning to segment multi-organ and tumors from multiple partially labeled datasets
• w-Net: Dual Supervised Medical Image Segmentation Model with Multi-Dimensional Attention and Cascade Multi-Scale Convolution
• A Dual-Task Synergy-Driven Generalization Framework for Pancreatic Cancer Segmentation in CT Scans
• MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentation
• Deep Learning to Segment Pelvic Bones: Large-scale CT Datasets and Baseline Models
• Uncertainty-based graph convolutional networks for organ segmentation refinement
• Deep Distance Transform for Tubular Structure Segmentation in CT Scans
• Universal Lesion Detection by Learning from Multiple Heterogeneously Labeled Datasets
• Benefits of Linear Conditioning with Metadata for Image Segmentation
• MS-KD: Multi-Organ Segmentation with Multiple Binary-Labeled Datasets
• IntrA: 3D Intracranial Aneurysm Dataset for Deep Learning
• More than Encoder: Introducing Transformer Decoder to Upsample
• Marginal loss and exclusion loss for partially supervised multi-organ segmentation
• LAMP: Large Deep Nets with Automated Model Parallelism for Image Segmentation
• 3DQ: Compact Quantized Neural Networks for Volumetric Whole Brain Segmentation
• Exploiting Shared Knowledge from Non-COVID Lesions for Annotation-Efficient COVID-19 CT Lung Infection Segmentation
• Robust Pancreatic Ductal Adenocarcinoma Segmentation with Multi-Institutional Multi-Phase Partially-Annotated CT Scans
• Noisy Labels are Treasure: Mean-Teacher-Assisted Confident Learning for Hepatic Vessel Segmentation
• NeurReg: Neural Registration and Its Application to Image Segmentation
• Cross-Domain Medical Image Translation by Shared Latent Gaussian Mixture Model
• Self-supervised Tumor Segmentation through Layer Decomposition
• Test-Time Training for Deformable Multi-Scale Image Registration
• Perun: Secure Multi-Stakeholder Machine Learning Framework with GPU Support
• Multi-Objective Learning to Predict Pareto Fronts Using Hypervolume Maximization
• Hierarchical Self-Supervised Learning for Medical Image Segmentation Based on Multi-Domain Data Aggregation
• Spatial Context-Aware Self-Attention Model For Multi-Organ Segmentation
• Interactive Medical Image Segmentation with Self-Adaptive Confidence Calibration
• Uncertainty-aware Incremental Learning for Multi-organ Segmentation
• JSSR: A Joint Synthesis, Segmentation, and Registration System for 3D Multi-Modal Image Alignment of Large-scale Pathological CT Scans
• Bidirectional RNN-based Few Shot Learning for 3D Medical Image Segmentation
• Give me (un)certainty -- An exploration of parameters that affect segmentation uncertainty
• 3D-UCaps: 3D Capsules Unet for Volumetric Image Segmentation
• Eisen: a python package for solid deep learning
• Multi-organ Segmentation via Co-training Weight-averaged Models from Few-organ Datasets
• Automatic CT Segmentation from Bounding Box Annotations using Convolutional Neural Networks
• Training CNN Classifiers for Semantic Segmentation using Partially Annotated Images: with Application on Human Thigh and Calf MRI
• Federated Whole Prostate Segmentation in MRI with Personalized Neural Architectures
• Transferable Visual Words: Exploiting the Semantics of Anatomical Patterns for Self-supervised Learning
• Deep Structure Learning using Feature Extraction in Trained Projection Space
• SAR: Scale-Aware Restoration Learning for 3D Tumor Segmentation
• Probabilistic Semantic Segmentation Refinement by Monte Carlo Region Growing
• Survey of the Detection and Classification of Pulmonary Lesions via CT and X-Ray
• TCAM-Diff: Triplane-Aware Cross-Attention Medical Diffusion Model
• UXNet: Searching Multi-level Feature Aggregation for 3D Medical Image Segmentation
• Chameleon: A Semi-AutoML framework targeting quick and scalable development and deployment of production-ready ML systems for SMEs
• Universal Undersampled MRI Reconstruction
• Sli2Vol: Annotate a 3D Volume from a Single Slice with Self-Supervised Learning
• 3D medical image segmentation with labeled and unlabeled data using autoencoders at the example of liver segmentation in CT images
• MICS : Multi-steps, Inverse Consistency and Symmetric deep learning registration network
• Detecting Spurious Correlations with Sanity Tests for Artificial Intelligence Guided Radiology Systems
• Lesion Segmentation and RECIST Diameter Prediction via Click-driven Attention and Dual-path Connection
• Bayesian Generative Models for Knowledge Transfer in MRI Semantic Segmentation Problems
• PGD-UNet: A Position-Guided Deformable Network for Simultaneous Segmentation of Organs and Tumors
• 3D-OOCS: Learning Prostate Segmentation with Inductive Bias
• Exploiting Liver CT scans in Colorectal Carcinoma genomics mutation classification
• 3D Graph Anatomy Geometry-Integrated Network for Pancreatic Mass Segmentation, Diagnosis, and Quantitative Patient Management
• Robustness of different loss functions and their impact on networks learning capability
• DeepPrognosis: Preoperative Prediction of Pancreatic Cancer Survival and Surgical Margin via Contrast-Enhanced CT Imaging
• Label-Efficient Multi-Task Segmentation using Contrastive Learning
• Body Part Regression for CT Images
• Multi-task Federated Learning for Heterogeneous Pancreas Segmentation
• Anatomy-guided Multimodal Registration by Learning Segmentation without Ground Truth: Application to Intraprocedural CBCT/MR Liver Segmentation and Registration
• The Power of Proxy Data and Proxy Networks for Hyper-Parameter Optimization in Medical Image Segmentation