TotalSegmentator: Robust Segmentation of 104 Anatomic Structures in CT Images
2023/07/05 by Jakob Wasserthal, Hanns‐Christian Breit, Manfred T. Meyer +9 · 172 citations
Engineering · Medicine · #Advanced X-ray and CT Imaging #Medical Imaging and Analysis #Radiomics and Machine Learning in Medical Imaging
paper · doi:10.1148/ryai.230024
openalex publication_date 2023/07/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/30
Abstract
Purpose To present a deep learning segmentation model that can automatically and robustly segment all major anatomic structures on body CT images. Materials and Methods In this retrospective study, 1204 CT examinations (from 2012, 2016, and 2020) were used to segment 104 anatomic structures (27 organs, 59 bones, 10 muscles, and eight vessels) relevant for use cases such as organ volumetry, disease characterization, and surgical or radiation therapy planning. The CT images were randomly sampled from routine clinical studies and thus represent a real-world dataset (different ages, abnormalities, scanners, body parts, sequences, and sites). The authors trained an nnU-Net segmentation algorithm on this dataset and calculated Dice similarity coefficients to evaluate the model’s performance. The trained algorithm was applied to a second dataset of 4004 whole-body CT examinations to investigate age-dependent volume and attenuation changes. Results The proposed model showed a high Dice score (0.943) on the test set, which included a wide range of clinical data with major abnormalities. The model significantly outperformed another publicly available segmentation model on a separate dataset (Dice score, 0.932 vs 0.871; P < .001). The aging study demonstrated significant correlations between age and volume and mean attenuation for a variety of organ groups (eg, age and aortic volume [rs = 0.64; P < .001]; age and mean attenuation of the autochthonous dorsal musculature [rs = −0.74; P < .001]). Conclusion The developed model enables robust and accurate segmentation of 104 anatomic structures. The annotated dataset (10.5281/zenodo.6802613) and toolkit (https://www.github.com/wasserth/TotalSegmentator) are publicly available. Keywords: CT, Segmentation, Neural Networks Supplemental material is available for this article. © RSNA, 2023 See also commentary by Sebro and Mongan in this issue.
Citations
Cited by
- Impact on Cost and Expert Time of Data-Efficient Deep Learning for Medical Image Segmentation
- Automated Delineation of Couinaud Segments at CT for Future Liver Remnant Volumetry
- Unlocking Robust Segmentation: Decoding Domain Randomization for Radiologists
- Better Data and Smarter AI: Automated Quality Control for Chest Radiographs
- Post-Training Network Compression for 3D Medical Image Segmentation: Reducing Computational Efforts via Tucker Decomposition
- The Emergence of Generalist AI in Medical Image Segmentation
- Full-scale indexing and semantic annotation of CT imaging: boosting FAIRness
- Bone Appetit: Skellytour Sets the Table for Robust Skeletal Segmentation
- Turning Routine CT into Reference Values for Quantitative Radiology
- The RSNA Abdominal Traumatic Injury CT (RATIC) Dataset
- Statistical shape model for anatomical landmarks prediction in humerus and mixed reality visualization
- Random Convolutions for Domain Generalization of Deep Learning–based Medical Image Segmentation Models
- Progressive Growing of Patch Size: Curriculum Learning for Accelerated and Improved Medical Image Segmentation
- In vivo evidence of blood flow slippage: failure of the no-slip boundary condition assumption
- Evaluating Skellytour for Automated Skeleton Segmentation from Whole-Body CT Images
- Comprehensive language-image pre-training for 3D medical image understanding
- Scaling Artificial Intelligence for Multi-Tumor Early Detection with More Reports, Fewer Masks
- Artificial intelligence for simplified patient-centered dosimetry in radiopharmaceutical therapies
- Are Video Models Emerging as Zero-Shot Learners and Reasoners in Medical Imaging?
- Automated Deep Learning–based Segmentation of the Dentate Nucleus Using Quantitative Susceptibility Mapping MRI
- Agentic Systems in Radiology: Design, Applications, Evaluation, and Challenges
- WAW-TACE: A Hepatocellular Carcinoma Multiphase CT Dataset with Segmentations, Radiomics Features, and Clinical Data
- Efficient Universal Models for Medical Image Segmentation via Weakly Supervised In-Context Learning
- nnSAM2: nnUNet-Enhanced One-Prompt SAM2 for Few-shot Multi-Modality Segmentation and Composition Analysis of Lumbar Paraspinal Muscles
- Flow Matching for Conditional MRI-CT and CBCT-CT Image Synthesis
- Beyond one-hot encoding? Journey into compact encoding for large multi-class segmentation
- K-Prism: A Knowledge-Guided and Prompt Integrated Universal Medical Image Segmentation Model
- Opportunistic assessment of steatotic liver disease in lung cancer screening eligible individuals
- Deep Learning-Based Cross-Anatomy CT Synthesis Using Adapted nnResU-Net with Anatomical Feature Prioritized Loss
- RAU: Reference-based Anatomical Understanding with Vision Language Models
- OpenDose3D: A Free, Open-Source Clinical Dosimetry Software for Patient-Specific Dosimetry
- Contour-informed inter-patient deformable registration of Head-and-Neck patients
- AuricularWorld: Hierarchical Action-Guided World Modeling for Fine-Grained Auricular Structure Segmentation from CT Scans
- Artificial intelligence-based biomarkers for treatment decisions in oncology
- Real‐time, high‐precision detection of aortic dissection key components for emergency triage using an enhanced deep learning model
- Accurate iodine quantification and residual error reduction with principal component analysis multimaterial decomposition using spectral CT
- Domain and Task-Focused Example Selection for Data-Efficient Contrastive Medical Image Segmentation
- AI as teacher: effectiveness of an AI-based training module to improve trainee pediatric fracture detection
- The Missing Piece: A Case for Pre-Training in 3D Medical Object Detection
- Ideal Registration? Segmentation is All You Need
- Transplant-Ready? Evaluating AI Lung Segmentation Models in Candidates with Severe Lung Disease
- ROOM: A Physics-Based Continuum Robot Simulator for Photorealistic Medical Datasets Generation
- DyGLNet: Hybrid Global-Local Feature Fusion with Dynamic Upsampling for Medical Image Segmentation
- Medverse: A Universal Model for Full-Resolution 3D Medical Image Segmentation, Transformation and Enhancement
- Generating Synthetic Contrast-Enhanced Chest CT Images from Non-Contrast Scans Using Slice-Consistent Brownian Bridge Diffusion Network
- Organ Segmentation in CT Images Using nnU ‐Net and 3D Model Generation With Marching Cubes
- CardioComposer: Leveraging Differentiable Geometry for Compositional Control of Anatomical Diffusion Models
- Curia: A Multi-Modal Foundation Model for Radiology
- TopoSculpt: Betti-Steered Topological Sculpting of 3D Fine-grained Tubular Shapes
- MedVista3D: Vision-Language Modeling for Reducing Diagnostic Errors in 3D CT Disease Detection, Understanding and Reporting
- Advancing Positron Emission Tomography Image Quantification: Artificial Intelligence-Driven Methods, Clinical Challenges, and Emerging Opportunities in Long-Axial Field-of-View Positron Emission Tomography/Computed Tomography Imaging
- autoPET IV challenge: Incorporating organ supervision and human guidance for lesion segmentation in PET/CT
- MedDINOv3: How to adapt vision foundation models for medical image segmentation?
- 4D Virtual Imaging Platform for Dynamic Joint Assessment via Uni-Plane X-ray and 2D-3D Registration
- Unified Supervision For Vision-Language Modeling in 3D Computed Tomography
- Multimodal Conditional MeshGAN for Personalized Aneurysm Growth Prediction
- The clinical value of quantitative cardiovascular molecular imaging: a step towards precision medicine
- Lifespan Pancreas Morphology for Control vs Type 2 Diabetes using AI on Largescale Clinical Imaging
- State of Abdominal CT Datasets: A Critical Review of Bias, Clinical Relevance, and Real-world Applicability
- Data-Driven Abdominal Phenotypes of Type 2 Diabetes in Lean, Overweight, and Obese Cohorts
- MInDI-3D: Iterative Deep Learning in 3D for Sparse-view Cone Beam Computed Tomography
- Anatomy-Aware Low-Dose CT Denoising via Pretrained Vision Models and Semantic-Guided Contrastive Learning
- Geometric Aging of the Thoracic Aorta: Insights From 2 Large Cohorts
- ContourDiff: Unpaired Medical Image Translation with Structural Consistency
- FIVA: Federated Inverse Variance Averaging for Universal CT Segmentation with Uncertainty Estimation
- CT-GRAPH: Hierarchical Graph Attention Network for Anatomy-Guided CT Report Generation
- FedGIN: Federated Learning with Dynamic Global Intensity Non-linear Augmentation for Organ Segmentation using Multi-modal Images
- Generative Artificial Intelligence in Medical Imaging: Foundations, Progress, and Clinical Translation
- TotalRegistrator: Towards a Lightweight Foundation Model for CT Image Registration
- GRASPing Anatomy to Improve Pathology Segmentation
- SSFMamba: Symmetry-driven Spatial-Frequency Feature Fusion for 3D Medical Image Segmentation
- Toward Using Machine Learning as a Shape Quality Metric for Liver Point Cloud Generation
- Boosting Vision Semantic Density with Anatomy Normality Modeling for Medical Vision-language Pre-training
- Your other Left! Vision-Language Models Fail to Identify Relative Positions in Medical Images
- Rethink Domain Generalization in Heterogeneous Sequence MRI Segmentation
- ReXGroundingCT: A 3D Chest CT Dataset for Segmentation of Findings from Free-Text Reports
- A Study of Anatomical Priors for Deep Learning-Based Segmentation of Pheochromocytoma in Abdominal CT
- HA-U <mml:mrow/> 3 Net: A modality-agnostic framework for 3D medical image segmentation using nested V-Net structure and hybrid attention
- Benchmarking of Deep Learning Methods for Generic MRI Multi-Organ Abdominal Segmentation
- Evaluation of rapamycin as a neuroprotective treatment in Alzheimer’s disease: a six-month single-arm open-label clinical pilot trial
- Automated Muscle and Fat Segmentation in Computed Tomography for Comprehensive Body Composition Analysis
- Content-based 3D Image Retrieval and a ColBERT-inspired Re-ranking for Tumor Flagging and Staging
- Semantic Segmentation for Preoperative Planning in Transcatheter Aortic Valve Replacement
- AortaDiff: Volume-Guided Conditional Diffusion Models for Multi-Branch Aortic Surface Generation
- MRISegmentator-Abdomen: A Fully Automated Multi-Organ and Structure Segmentation Tool for T1-weighted Abdominal MRI
- 3D Wavelet Latent Diffusion Model for Whole-Body MR-to-CT Modality Translation
- A Survey on Medical Image Compression: From Traditional to Learning-Based
- RadiomicsRetrieval: A Customizable Framework for Medical Image Retrieval Using Radiomics Features
- Raptor: Scalable Train-Free Embeddings for 3D Medical Volumes Leveraging Pretrained 2D Foundation Models
- Dataset and Benchmark for Enhancing Critical Retained Foreign Object Detection
- RAPS-3D: Efficient interactive segmentation for 3D radiological imaging
- PSAT: Pediatric Segmentation Approaches via Adult Augmentations and Transfer Learning
- AnatomyCarve: A VR occlusion management technique for medical images based on segment-aware clipping
- Mamba Goes HoME: Hierarchical Soft Mixture-of-Experts for 3D Medical Image Segmentation
- Learning Segmentation from Radiology Reports
- SPIDER: Structure-Preferential Implicit Deep Network for Biplanar X-ray Reconstruction
- PanTS: The Pancreatic Tumor Segmentation Dataset
- MedGround-R1: Advancing Medical Image Grounding via Spatial-Semantic Rewarded Group Relative Policy Optimization
- Is Visual in-Context Learning for Compositional Medical Tasks within Reach?
- Automated anatomy-based post-processing reduces false positives and improved interpretability of deep learning intracranial aneurysm detection
- SonoGym: High Performance Simulation for Challenging Surgical Tasks with Robotic Ultrasound
- Towards 3D Semantic Image Synthesis for Medical Imaging
- UltraTwin: Towards Cardiac Anatomical Twin Generation from Multi-view 2D Ultrasound
- Region-Aware Multimodal Large Language Model via SlowFast Tokenization and Pseudo-Mask Guidance for 3D CT Report Generation
- Prompt Mechanisms in Medical Imaging: A Comprehensive Survey
- Cardiovascular disease classification using radiomics and geometric features from cardiac CT
- HyperSORT: Self-Organising Robust Training with hyper-networks
- Exploring the Design Space of 3D MLLMs for CT Report Generation
- NeRF-based CBCT Reconstruction needs Normalization and Initialization
- Snap-and-tune: combining deep learning and test-time optimization for high-fidelity cardiovascular volumetric meshing
- Brain Imaging Foundation Models, Are We There Yet? A Systematic Review of Foundation Models for Brain Imaging and Biomedical Research
- Unleashing Diffusion and State Space Models for Medical Image Segmentation
- 3D Skin Segmentation Methods in Medical Imaging: A Comparison
- Enhancing Privacy: The Utility of Stand-Alone Synthetic CT and MRI for Tumor and Bone Segmentation
- Framework of a multiscale data-driven DT of the musculoskeletal system
- Deep Learning for Lymph Node Metastasis Detection in Pancreatic Ductal Adenocarcinoma
- Generalist Models in Medical Image Segmentation: A Survey and Performance Comparison with Task-Specific Approaches
- Modality-AGnostic Image Cascade (MAGIC) for Multi-Modality Cardiac Substructure Segmentation
- TissUnet: Improved Extracranial Tissue and Cranium Segmentation for Children through Adulthood
- Text2CT: Towards 3D CT Volume Generation from Free-text Descriptions Using Diffusion Model
- Conformal coronary calcification volume estimation with conditional coverage via histogram clustering
- Advancements in Artificial Intelligence Applications for Cardiovascular Disease Research
- Rethinking Whole-Body CT Image Interpretation: An Abnormality-Centric Approach
- Implicit Deformable Medical Image Registration with Learnable Kernels
- A Large Convolutional Neural Network for Clinical Target and Multi-organ Segmentation in Gynecologic Brachytherapy with Multi-stage Learning
- TumorGen: Boundary-Aware Tumor-Mask Synthesis with Rectified Flow Matching
- ImmunoDiff: A Diffusion Model for Immunotherapy Response Prediction in Lung Cancer
- Advancing Generalizable Tumor Segmentation with Anomaly-Aware Open-Vocabulary Attention Maps and Frozen Foundation Diffusion Models
- Surf2CT: Cascaded 3D Flow Matching Models for Torso 3D CT Synthesis from Skin Surface
- Cascaded 3D Diffusion Models for Whole-body 3D 18-F FDG PET/CT synthesis from Demographics
- Multipath cycleGAN for harmonization of paired and unpaired low-dose lung computed tomography reconstruction kernels
- Good Enough: Is it Worth Improving your Label Quality?
- Multiscale Parallel Simulation of Malignant Pleural Mesothelioma via Adaptive Domain Partitioning -- an Efficiency Analysis Study
- Pixels to Prognosis: Harmonized Multi-Region CT-Radiomics and Foundation-Model Signatures Across Multicentre NSCLC Data
- Render-FM: A Foundation Model for Real-time Photorealistic Volumetric Rendering
- Beyond BMI: Deep Learning Segmentation-Driven CT Reveals Body Composition Changes after Metabolic and Bariatric Surgery
- TAGS: 3D Tumor-Adaptive Guidance for SAM
- Patient-Specific Autoregressive Models for Organ Motion Prediction in Radiotherapy
- Location-Aware Fine-Grained Representation Learning for Medical Vision Foundation Models
- Generalizable cardiac substructures segmentation from contrast and non-contrast CTs using pretrained transformers
- Semantically Calibrated Evidence Composition for CT Vision-Language Learning
- Using Foundation Models as Pseudo-Label Generators for Pre-Clinical 4D Cardiac CT Segmentation
- MedSAM2-Anatomy: Training-Free Inference-Time Optimization for Musculoskeletal Segmentation
- Calibration and Uncertainty for multiRater Volume Assessment in multiorgan Segmentation (CURVAS) challenge results
- Robust Kidney Abnormality Segmentation: A Validation Study of an AI-Based Framework
- MAIS: Memory-Attention for Interactive Segmentation
- BodyGPS: Anatomical Positioning System
- Multi-Modal Explainable Medical AI Assistant for Trustworthy Human-AI Collaboration
- Automated Thoracolumbar Stump Rib Detection and Analysis in a Large CT Cohort
- Regression is all you need for medical image translation
- Accelerating Volumetric Medical Image Annotation via Short-Long Memory SAM 2
- A Unified 2D Framework for DeepLesion Detection, Segmentation and Short Report Generation
- Automated segmentation of pediatric neuroblastoma on multi-modal MRI: Results of the SPPIN challenge at MICCAI 2023
- Self-Auditing Parameter-Efficient Fine-Tuning for Few-Shot 3D Medical Image Segmentation
- Unpaired Image-to-Image Translation via a Self-Supervised Semantic Bridge
- A simple and effective approach for body part recognition on CT scans based on projection estimation
- μMatch: Foundation Models for Semi-supervised Learning and Domain Adaptation in EM
- Boosting 3D Liver Shape Datasets with Diffusion Models and Implicit Neural Representations
- Automatic Patient-Specific Microwave Ablation Planning Accelerated by a Physics-Guided Deep Learning Model
- LocAnyMed: Vision-Language Grounding for Multimodal Medical Images
- Anatomy-constrained modelling of image-derived input functions in dynamic PET using multi-organ segmentation
- Towards prediction of morphological heart age from computed tomography angiography
- Performance Estimation for Supervised Medical Image Segmentation Models on Unlabeled Data Using UniverSeg
- ALTER: Modeling Longitudinal Changes via Regional Differencing for 3D CT Report Generation
- Bi-PT: Bidirectional Cross-Attention Point Transformers for Four-Chamber Heart Reconstruction from Sparse Cardiac MRI Data
- Clinically Interpretable Survival Risk Stratification in Head and Neck Cancer Using Bayesian Networks and Markov Blankets
- seg2med: a bridge from artificial anatomy to multimodal medical images
- SynthFM: Training Modality-agnostic Foundation Models for Medical Image Segmentation without Real Medical Data
- Benchmarking Multi-Organ Segmentation Tools for Multi-Parametric T1-weighted Abdominal MRI
- Synthetic CT Generation from Time-of-Flight Non-Attenutaion-Corrected PET for Whole-Body PET Attenuation Correction
- Large Scale Supervised Pretraining For Traumatic Brain Injury Segmentation
- Longitudinal Assessment of Lung Lesion Burden in CT
- Leveraging Anatomical Priors for Automated Pancreas Segmentation on Abdominal CT
- Biomechanical Constraints Assimilation in Deep-Learning Image Registration: Application to sliding and locally rigid deformations
Related