Automated Segmentation of the Spinal Column in MRI Volumes Using Deep Learning

Renan Silva Carvalho; Leandro Henrique Furtado Pinto Silva; João Fernando Mari

doi:10.22456/2175-2745.150902

Authors

Renan Silva Carvalho Universidade Federal de Viçosa (UFV) https://orcid.org/0009-0005-5169-7156
Leandro Henrique Furtado Pinto Silva Universidade Federal de Viçosa (UFV) https://orcid.org/0000-0002-5765-5206
João Fernando Mari Universidade Federal de Viçosa (UFV) https://orcid.org/0000-0001-8271-3802

DOI:

https://doi.org/10.22456/2175-2745.150902

Keywords:

spinal segmentation, magnetic resonance imaging (MRI), deep learning, volumetric imaging

Abstract

Accurate segmentation of spinal structures in magnetic resonance imaging (MRI) is an important step for supporting the diagnosis of several diseases and related conditions. In this work, we present a systematic evaluation of three deep learning architectures, U-Net, Feature Pyramid Network (FPN), and SegFormer, combined with ResNet-50 and EfficientNet-B2 encoders for the semantic segmentation of the cervical spine (C1–C7) in MRI volumes from the VerSe 2020 dataset. The proposed pipeline includes dataset preparation, model training using Dice loss, Adam optimizer, and early stop strategy, and evaluation with standard metrics such as Intersection over Union (IoU), F1-Score, and accuracy. Results show that FPN with ResNet-50 achieved the best overall performance, reaching an IoU of 0.6696 and an F1-score of 0.8021, while EfficientNet-B2 provided more consistent results across different architectures. Data augmentation showed limited impact, with gains restricted to a few specific configurations. Qualitative analysis through 3D surface reconstruction further highlighted the limitations of 2D slice-based segmentation, particularly at the extremities of the vertebrae, suggesting the need for volumetric approaches. The contributions of this work include the development of a reproducible pipeline for spinal segmentation, a comparative evaluation of convolutional and Transformer-based models. Qualitative analysis suggests potential benefits in exploring 3D approaches in future work.

Downloads

Download data is not yet available.

References

[1] PEREIRA, J. F. M.; MARI, J. F.; SILVA, L. H. F. P. Exploiting data augmentation strategies to improve the classification of spinal disorders in x-ray images. Revista de Informática Teórica e Aplicada, v. 32, n. 1, p. 257–264, 2025.

[2] BHARADWAJ, U. U.; CHIN, C. T.; MAJUMDAR, S. Practical applications of artificial intelligence in spine imaging: a review. Radiologic Clinics, Elsevier, v. 62, n. 2, p. 355–370, 2024.

[3] BAUR, D. et al. Convolutional neural networks in spinal magnetic resonance imaging: a systematic review. World Neurosurgery, Elsevier, v. 166, p. 60–70, 2022.

[4] QU, B. et al. Current development and prospects of deep learning in spine image analysis: a literature review. Quantitative Imaging in Medicine and Surgery, v. 12, n. 6, p. 3454, 2022.

[5] HAN, Z. et al. Spine-gan: Semantic segmentation of multiple spinal structures. Medical image analysis, Elsevier, v. 50, p. 23–35, 2018.

[6] MÖLLER, H. et al. Spineps—automatic whole spine segmentation of t2-weighted mr images using a two-phase approach to multi-class semantic and instance segmentation. European Radiology, Springer, v. 35, n. 3, p. 1178–1189, 2025.

[7] SAEED, M. U. et al. 3d mfa: An automated 3d multi-feature attention based approach for spine segmentation using a multi-stage network pruning. Computers in Biology and Medicine, Elsevier, v. 185, p. 109526, 2025.

[8] LÖFFLER, M. T. et al. A vertebral segmentation dataset with fracture grading. Radiology: Artificial Intelligence, Radiological Society of North America, v. 2, n. 4, p. e190138, 2020.

[9] SEKUBOYINA, A. et al. Verse: a vertebrae labelling and segmentation benchmark for multi-detector ct images. Medical image analysis, Elsevier, v. 73, p. 102166, 2021.

[10] LIEBL, H. et al. A computed tomography vertebral segmentation dataset with anatomical variations and multi-vendor scanner data. Scientific Data, Nature Publishing Group UK London, v. 8, n. 1, p. 284, 2021.

[11] RONNEBERGER, O.; FISCHER, P.; BROX, T. U-Net: Convolutional networks for biomedical image segmentation. In: SPRINGER. International Conference on Medical Image Computing and Computer-Assisted Intervention. [S.l.], 2015. p. 234–241.

[12] LIN, T.-Y. et al. Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. [S.l.: s.n.], 2017. p. 2117–2125.

[13] XIE, E. et al. SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in Neural Information Processing Systems, v. 34, p. 12077–12090, 2021.

[14] HE, K. et al. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. [S.l.: s.n.], 2016. p. 770–778.

[15] TAN, M.; LE, Q. V. EfficientNet: Rethinking model scaling for convolutional neural networks. In: PMLR. International Conference on Machine Learning. [S.l.], 2019. p. 6105–6114.

[16] IAKUBOVSKII, P. Segmentation Models Pytorch. [S.l.]: GitHub, 2019. https://github.com/qubvel/segmentation_models.pytorch.

[17] LORENSEN, W. E.; CLINE, H. E. Marching cubes: A high resolution 3D surface construction algorithm. In: Seminal Graphics: Pioneering Efforts That Shaped the Field. [S.l.: s.n.], 1998. p. 347–353.

[18] CIGNONI, P. et al. MeshLab: an Open-Source Mesh Processing Tool. In: SCARANO, V.; CHIARA, R. D.; ERRA, U. (Ed.). Eurographics Italian Chapter Conference. [S.l.]: The Eurographics Association, 2008. ISBN 978-3-905673-68-5.