Convolutional neural networks for automated segmentation of the lumbar paraspinal muscles in people with low back pain | Scientific Reports – Nature.com | Region & Cash

  • Hey: D. et al. The global burden of back pain: estimates from the Global Burden of Disease 2010 study. ann. Rheumatism. Dis. 73968-974 (2014).

    Article Google Scholar

  • O’Sullivan, P., Caneiro, JP, O’Keeffe, M. & O’Sullivan, K. Unraveling the complexity of back pain. J.Orthop. sports phys. thermal 46932-937 (2016).

    Article Google Scholar

  • Goubert, D., Oosterwijck, JV, Meeus, M. & Danneels, L. Structural changes in the lumbar muscles in nonspecific low back pain: A systematic review. pain physical 19E985-E1000 (2016).

    Google Scholar

  • Crawford, R.J et al. Geography of lumbar paravertebral muscle fat infiltration. Spine (Phila Pa 1976) 441294-1302 (2019).

    Article Google Scholar

  • Kjaer, P., Bendix, T., Sorensen, JS, Korsholm, L. & Leboeuf-Yde, C. Are MRI-defined fatty infiltrations in the multifidus muscles associated with back pain? BMC Med. 52 (2007).

    Article Google Scholar

  • Teichtahl, AJ et al. Fatty infiltration of the paraspinal muscles is associated with low back pain, disability, and structural abnormalities in community adults. Spine J fifteen1593-1601 (2015).

    Article Google Scholar

  • Berry, DB et al. Methodological considerations for region-of-interest definition for paraspinal muscles in axial MRIs of the lumbar spine. BMC musculoskeletal. Disarray. 19135 (2018).

    Article Google Scholar

  • Crawford, RJ, Cornwall, J, Abbott, R & Elliott, JM. BMC musculoskeletal. Disarray. 1825 (2017).

    Article Google Scholar

  • Hu, Z.-J. et al. An assessment of the intra- and inter-reliability of lumbar paraspinal muscle parameters using CT scan and magnetic resonance imaging. Spine (Phila Pa 1976) 1976(36), E868-E874 (2011).

    Article Google Scholar

  • big, c et al. Automated segmentation of the spinal cord and intramedullary multiple sclerosis lesions using convolutional neural networks. neuroimage 184901-915 (2018).

    Article Google Scholar

  • Dam, E.B., Lillholm, M., Marques, J. & Nielsen, M. Automated segmentation of high- and low-field knee MRIs using knee image quantification with data from the Osteoarthritis Initiative. J.Med. imaging 2024001 (2015).

    Article Google Scholar

  • Crawford, RJ, Fortin, M., Weber, KA, Smith, A. & Elliott, JM Are magnetic resonance imaging technologies critical to our understanding of spinal diseases?. J.Orthop. sports phys. thermal 49320-329 (2019).

    Article Google Scholar

  • Shen, H et al. A deep learning-based, fully automated program for segmentation and quantification of key spinal components in axial magnetic resonance imaging of the lumbar spine. physics thermal https://doi.org/10.1093/ptj/pzab041 (2021).

    Article PubMedGoogle Scholar

  • Weber, KA et al. Deep learning convolutional neural networks to automatically quantify muscle fat infiltration after whiplash. Science. representative 97973 (2019).

    ADS article Google Scholar

  • Ronneberger O, Fischer P & Brox T U-Net: Convolutional networks for biomedical image segmentation. Lecture. Notes computer. Science. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics) 9351234-241 (2015).

  • Milletari, F., Navab, N. & Ahmadi, S.-A. V-Net: Fully convolutional neural networks for volumetric medical image segmentation. spinal cord 45304-309 (2016).

    Google Scholar

  • Cornwall, J., Stringer, MD & Duxson, M. Functional morphology of the thoracolumbar transverse spinal muscles. Spine (Phila Pa 1976) 36E1053-E1061 (2011).

    Article Google Scholar

  • Tustison, NJ et al. N4ITK: Improved N3 bias correction. IEEE Trans. Medical Imaging 291310-1320 (2010).

    Article Google Scholar

  • Desai AD, Gold GE, Hargreaves BA & Chaudhari AS Technical considerations on semantic segmentation in MRI using convolutional neural networks. (2019). https://doi.org/10.48550/arXiv.1902.01977.

  • Oktai, O et al. Attention U-Net: Learn where to look for the pancreas. (2018). https://doi.org/10.48550/arxiv.1804.03999.

  • Issee, F. et al. Automatic assessment of heart disease in cine-MRI using time-series segmentation and domain-specific features. https://doi.org/10.1007/978-3-319-75541-0 (2017).

  • Liu, S et al. Hybrid Anisotropic 3D Network: Transferring convolution features from 2D images to 3D anisotropic volumes. Lecture. Notes computer. Science. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics) 11071 LNCS851-858 (2017).

  • Zettler, N. & Mastmeyer, A. Comparison of 2D vs. 3D U-mesh organ segmentation in 3D abdominal CT images. 41-50 (2021). https://doi.org/10.48550/arxiv.2107.04062.

  • Milletari, F., Navab, N. & Ahmadi, S.-A. V-Net: Fully convolutional neural networks for volumetric medical image segmentation. Proc. – 2016 4th Int. Conf. 3D Vision, 3DV 2016 565-571 (2016).

  • Ioffe, S. & Szegedy, C. Batch normalization: accelerating deep network training by reducing internal covariate shifting. 32nd Int. conf mach To learn. ICML 2015 1448-456 (2015).

  • Wu, Y. & He, K. Group normalization. international J. Computer. Vis. 128742-755 (2018).

    Article Google Scholar

  • Ulyanov, D., Vedaldi, A. & Lempitsky, V. Instance Normalization: The Missing Ingredient for Rapid Stylization. (2016), https://doi.org/10.48550/arxiv.1607.08022.

  • Hesamian, MH, Jia, W., He, X. & Kennedy, P. Deep learning techniques for medical image segmentation: achievements and challenges. J. Digit. imaging 32582-596 (2019).

    Article Google Scholar

  • Mikevicius, P. et al. Mixed precision training. 6. Int. conf learning. Represent. ICLR 2018 – Conf. Track Proc. (2017), https://doi.org/10.48550/arxiv.1710.03740.

  • Ni, R., Meyer, CH, Blemker, SS, Hart, JM & Feng, X. Automated segmentation of all lower extremity muscles from high-resolution magnetic resonance imaging using a cascaded three-dimensional deep convolutional neuron network. J.Med. Imaging (Bellingham, Washington) 61 (2019).

    Article Google Scholar

  • Shahid, B et al. The lumbar multifidus muscle degenerates in individuals with chronic degenerative pathology of the lumbar spine. J.Orthop. resolution 352700-2706 (2017).

    CAS article Google Scholar

  • Fortin, M., Omidyeganeh, M., Battié, MC, Ahmad, O. & Rivaz, H. Evaluation of an automated thresholding algorithm for quantifying paraspinal muscle composition from MRI images. Biomed. Closely. On-line 1661 (2017).

    Article Google Scholar

  • Hancock, MJ et al. Risk factors for recurrence of low back pain. Spine J fifteen2360-2368 (2015).

    Article Google Scholar

  • Scheinost, D et al. Ten simple rules for predictive modeling of individual differences in neuroimaging. neuroimage 19335 (2019).

    Article Google Scholar

  • Consortium, M. MONAI: Medical Open Network for AI. (2022) 10.5281/ZENODO.6114127.

  • Çiçek, Ö., Abdulkadir, A., Lienkamp, ​​​​SS, Brox, T. & Ronneberger, O. 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation. Lecture. Notes computer. Science. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics) 9901 LNCS424-432 (2016).

  • Kerfoot, E. et al. Quantification of the left ventricle with residual U-Net. Lecture. Notes computer. Science. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics) 11395 LNCS371-380 (2019).

  • He, K., Zhang, X., Ren, S. & Sun, J. Diving deep into rectifiers: exceeding human-level performance in ImageNet classification. in the 2015 IEEE International Conference on Computer Vision (ICCV) volume 2015 Inter 1026-1034 (IEEE, 2015).

  • Falk, T et al. U-Net: Deep Learning for Cell Counting, Recognition and Morphometry. nat. methods 1667-70 (2019).

    CAS article Google Scholar

  • He K, Zhang X, Ren S & Sun J. Deep residual learning for image recognition. in the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Volumes 2016-December 770–778 (IEEE, 2016).

  • Loshchilov, I. & Hutter, F. Regularization of decoupled weight loss. 7. Int. conf learning. Represent. ICLR 2019 (2017), https://doi.org/10.48550/arxiv.1711.05101.

  • Perone, CS, Calabrese, E. & Cohen-Adad, J. Segmentation of spinal cord gray matter using deep dilated convolutions. Science. representative 8th5966 (2018).

    ADS article Google Scholar

  • Leave a Comment