TotalSpineSeg is a tool for automatic instance segmentation of all vertebrae, intervertebral discs (IVDs), spinal cord, and spinal canal in MRI images. It is robust to various MRI contrasts, acquisition orientations, and resolutions. The model used in TotalSpineSeg is based on nnU-Net as the backbone for training and inference [1,2]. TotalSpineSeg uses a hybrid approach that integrates nnU-Net with an iterative algorithm for instance segmentation and labeling of vertebrae, IVDs, spinal cord, and spinal canal. The process involves two main steps: Step 1: An nnU-Net model (Dataset101) was trained to identify nine classes in total. This includes four main classes: spinal cord, spinal canal, IVDs, and vertebrae. Additionally, it identifies four specific IVDs: C2-C3, C7-T1, T12-L1, and L5-S, which represent key anatomical landmarks along the spine, as well as the C1 vertebra to determine whether the MRI images include C1. The output segmentation was processed using an iterative algorithm to extract individual IVDs, from which the odd IVDs segmentation was extracted. Step 2: A second nnU-Net model (Dataset102) was trained to identify ten classes in total. This includes five main classes: spinal cord, spinal canal, IVDs, odd vertebrae, and even vertebrae. Additionally, it identifies four specific IVDs: C2-C3, C7-T1, T12-L1, and L5-S, which represent key anatomical landmarks along the spine, as well as the sacrum. This model uses two input channels: the MRI image and the odd IVDs extracted from the first step. The output segmentation was processed using an algorithm that assigns individual labels to each vertebra and IVD in the final segmentation. The model was trained on these 3 main datasets: Private whole-spine dataset SPIDER project dataset [3] Spine Generic Project, including single and multi subject datasets [4,5] Manual labels from the SPIDER dataset were utilized for training. For other datasets, spinal cord segmentation was obtained using multiple models [6–8], followed by manual correction using 3D Slicer and subsequent registration to the PAM50 template to obtain the vertebrae, IVDs, and spinal canal segmentations using the Spinal Cord Toolbox (SCT) [9,10]. An initial segmentation model was trained with these labels, applied to the datasets, and the resulting outputs were further refined through manual correction in 3D Slicer. Additional public datasets were used during this project to generate sacrum segmentations: GoldAtlas [11] SynthRAD2023 [12] MRSpineSeg [13] When not available, sacrum segmentations were generated using the TotalSegmentator model [14]. References Isensee F, Jaeger PF, Kohl SAA, Petersen J, Maier-Hein KH. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods. 2021;18: 203–211. doi:10.1038/s41592-020-01008-z Isensee F, Wald T, Ulrich C, Baumgartner M, Roy S, Maier-Hein K, et al. NnU-Net revisited: A call for rigorous validation in 3D medical image segmentation. arXiv [cs.CV]. 2024. doi:10.48550/ARXIV.2404.09556 van der Graaf JW, van Hooff ML, Buckens CFM, Rutten M, van Susante JLC, Kroeze RJ, et al. SPIDER - Lumbar spine segmentation in MR images: a dataset and a public benchmark. Zenodo; 2023. doi:10.5281/ZENODO.10159290 Cohen-Adad J. Spine generic public database (single subject). Zenodo; 2020. doi:10.5281/ZENODO.4299148 Cohen-Adad J, Alonso-Ortiz E, Abramovic M, Arneitz C, Atcheson N, Barlow L, et al. Spine generic public database (multi-subject). Zenodo; 2020. doi:10.5281/ZENODO.4299140 Gros C, De Leener B, Badji A, Maranzano J, Eden D, Dupont SM, et al. Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks. Neuroimage. 2019;184: 901–915. doi:10.1016/j.neuroimage.2018.09.081 Bédard S, Karthik EN, Tsagkas C, Pravatà E, Granziera C, Smith A, et al. Towards contrast-agnostic soft segmentation of the spinal cord. arXiv [eess.IV]. 2023. doi:10.48550/ARXIV.2310.15402 Karthik EN, Valošek J, Farner L, Pfyffer D, Schading-Sassenhausen S, Lebret A, et al. SCIsegV2: A universal tool for segmentation of intramedullary lesions in spinal cord injury. arXiv [cs.CV]. 2024. doi:10.48550/ARXIV.2407.17265 De Leener B, Fonov VS, Collins DL, Callot V, Stikov N, Cohen-Adad J. PAM50: Unbiased multimodal template of the brainstem and spinal cord aligned with the ICBM152 space. Neuroimage. 2018;165: 170–179. doi:10.1016/j.neuroimage.2017.10.041 De Leener B, Lévy S, Dupont SM, Fonov VS, Stikov N, Louis Collins D, et al. SCT: Spinal Cord Toolbox, an open-source software for processing spinal cord MRI data. Neuroimage. 2017;145: 24–43. doi:10.1016/j.neuroimage.2016.10.009 Nyholm T, Svensson S, Andersson S, Jonsson J, Sohlin M, Gustavsson C, et al. Gold atlas - male pelvis - gentle radiotherapy. Zenodo; 2017. doi:10.5281/ZENODO.601461 Thummerer A, Huijben E, Terpstra M, Gurney-Champion O, Afonso M, Pai S, et al. SynthRAD2023 Challenge design. Zenodo; 2023. doi:10.5281/ZENODO.7746020 Pang S, Pang C, Zhao L, Chen Y, Su Z, Zhou Y, et al. SpineParseNet: Spine parsing for volumetric MR image by a two-stage segmentation framework with semantic image representation. IEEE Trans Med Imaging. 2021;40: 262–273. doi:10.1109/TMI.2020.3025087 Wasserthal J, Breit H-C, Meyer MT, Pradella M, Hinck D, Sauter AW, et al. TotalSegmentator: Robust Segmentation of 104 Anatomic Structures in CT Images. Radiol Artif Intell. 2023;5: e230024. doi:10.1148/ryai.230024 Acknowledgments Funded by the Canada Research Chair in Quantitative Magnetic Resonance Imaging [CRC-2020-00179], the Canadian Institute of Health Research [PJT-190258], the Canada Foundation for Innovation [32454, 34824], the Fonds de Recherche du Québec - Santé [322736, 324636], the Natural Sciences and Engineering Research Council of Canada [RGPIN-2019-07244], the Canada First Research Excellence Fund (IVADO and TransMedTech), the Courtois NeuroMod project, the Quebec BioImaging Network [5886, 35450], INSPIRED (Spinal Research, UK; Wings for Life, Austria; Craig H. Neilsen Foundation, USA), Mila - Tech Transfer Funding Program.