TotalSegmentator: Robust Segmentation of 104 Anatomic Structures in CT Images.

By Jakob Wasserthal, H. Breit, Manfred T. Meyer, M. Pradella, Daniel Hinck, A. Sauter, T. Heye, Daniel T Boll, Joshy Cyriac, Shan Yang and 2 more. Radiology: Artificial Intelligence, 2022

1,723 citations recorded by the source corpus.

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, 2023See also commentary by Sebro and Mongan in this issue.

Subfields: Biomedical Engineering, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/586f5754f6825d445afa5026c0fede55a65290a1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

1. Jun Ma
2. Bo Wang
3. Klaus Hermann Maier-Hein
4. Fabian Isensee

In Radiology, Nuclear Medicine and Imaging

1. Fabian Isensee
2. Klaus Hermann Maier-Hein

Citations in the corpus

• nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation (2024, methodology): “Since STU-Net was presented as a model for transfer learning, we fine-tuned a STU-Net L network, that was pre-trained on the totalsegmentator dataset [35] for 4000 epochs, on the other datasets, analogous to the corresponding publication [20].”
• U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation (2024, background): “One immediate direction is to leverage large-scale datasets for train U-Mamba, aiming to create readily deployable segmentation tools or provide pre-trained model weights for fine-tuning on data-limited tasks, as exemplified by similar initiatives like TotalSegmentator [47] and STU-Net [21].”