TotalSegmentator: Robust Segmentation of 104 Anatomic Structures in CT Images
2023/07/05 by Jakob Wasserthal, Hanns‐Christian Breit, Manfred T. Meyer +9 · 77 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 (https://doi.org/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
- MRISegmentator-Abdomen: A Fully Automated Multi-Organ and Structure Segmentation Tool for T1-weighted Abdominal MRI.
- 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 <scp>CT</scp> Images Using <scp>nnU</scp> ‐Net and <scp>3D</scp> 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
Related