DeepN4: Learning N4ITK Bias Field Correction for T1-weighted Images.
3D U-Net
Bias field correction
Inhomogeneity
N4ITK
T1-weighted images
Journal
Neuroinformatics
ISSN: 1559-0089
Titre abrégé: Neuroinformatics
Pays: United States
ID NLM: 101142069
Informations de publication
Date de publication:
25 Mar 2024
25 Mar 2024
Historique:
accepted:
19
12
2023
medline:
25
3
2024
pubmed:
25
3
2024
entrez:
25
3
2024
Statut:
aheadofprint
Résumé
T1-weighted (T1w) MRI has low frequency intensity artifacts due to magnetic field inhomogeneities. Removal of these biases in T1w MRI images is a critical preprocessing step to ensure spatially consistent image interpretation. N4ITK bias field correction, the current state-of-the-art, is implemented in such a way that makes it difficult to port between different pipelines and workflows, thus making it hard to reimplement and reproduce results across local, cloud, and edge platforms. Moreover, N4ITK is opaque to optimization before and after its application, meaning that methodological development must work around the inhomogeneity correction step. Given the importance of bias fields correction in structural preprocessing and flexible implementation, we pursue a deep learning approximation / reinterpretation of the N4ITK bias fields correction to create a method which is portable, flexible, and fully differentiable. In this paper, we trained a deep learning network "DeepN4" on eight independent cohorts from 72 different scanners and age ranges with N4ITK-corrected T1w MRI and bias field for supervision in log space. We found that we can closely approximate N4ITK bias fields correction with naïve networks. We evaluate the peak signal to noise ratio (PSNR) in test dataset against the N4ITK corrected images. The median PSNR of corrected images between N4ITK and DeepN4 was 47.96 dB. In addition, we assess the DeepN4 model on eight additional external datasets and show the generalizability of the approach. This study establishes that incompatible N4ITK preprocessing steps can be closely approximated by naïve deep neural networks, facilitating more flexibility. All code and models are released at https://github.com/MASILab/DeepN4 .
Identifiants
pubmed: 38526701
doi: 10.1007/s12021-024-09655-9
pii: 10.1007/s12021-024-09655-9
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Informations de copyright
© 2024. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
Références
Agrawal, A., Amos, B., Barratt, S., Boyd, S., Diamond, S., & Kolter, J. Z. (2019). Differentiable convex optimization layers. Advances in neural information processing systems (Vol. 32).
Ashburner, J., & Friston, K. J. (2005). Unified segmentation. NeuroImage, 26(3), 839–851.
pubmed: 15955494
doi: 10.1016/j.neuroimage.2005.02.018
Avants, B. B., Tustison, N., & Song, G. (2009). Advanced normalization tools (ANTS). Insight J, 2(365), 1–35.
Axel, L., Costantini, J., & Listerud, J. (1987). Intensity correction in surface-coil MR imaging. AJR American Journal of Roentgenology, 148(2), 418–420.
pubmed: 3492123
doi: 10.2214/ajr.148.2.418
Bakas, S., Akbari, H., Sotiras, A., et al. (2017). Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features. Scientific Data, 4(1), 1–13.
doi: 10.1038/sdata.2017.117
Beekly, D. L., Ramos, E. M., Lee, W. W., et al. (2007). The National Alzheimer’s Coordinating Center (NACC) database: The uniform data set. Alzheimer Disease & Associated Disorders, 21(3), 249–258.
doi: 10.1097/WAD.0b013e318142774e
Beekly, D. L., Ramos, E. M., van Belle, G., et al. (2004). The national Alzheimer’s coordinating center (NACC) database: An Alzheimer disease database. Alzheimer Disease & Associated Disorders, 18(4), 270–277.
Besser, L. M., Kukull, W. A., Teylan, M. A., et al. (2018). The revised National Alzheimer’s Coordinating Center’s Neuropathology Form—available data and new analyses. Journal of Neuropathology & Experimental Neurology, 77(8), 717–726.
doi: 10.1093/jnen/nly049
Brinkmann, B. H., Manduca, A., & Robb, R. A. (1998). Optimized homomorphic unsharp masking for MR grayscale inhomogeneity correction. IEEE Transactions on Medical Imaging, 17(2), 161–171.
pubmed: 9688149
doi: 10.1109/42.700729
Chen, C., Qin, C., Qiu, H., Ouyang, C., Wang, S., Chen, L., & Rueckert, D. (2020). Realistic adversarial data augmentation for MR image segmentation. Medical Image Computing and Computer Assisted Intervention–MICCAI 2020: 23rd International Conference, Lima, Peru, October 4–8, 2020, Proceedings, Part I 23 (pp. 667–677). Springer International Publishing.
Chuang, K.-H., Wu, P.-H., Li, Z., Fan, K.-H., & Weng, J.-C. (2022). Deep learning network for integrated coil inhomogeneity correction and brain extraction of mixed MRI data. Scientific Reports, 12(1), 8578.
pubmed: 35595829
pmcid: 9123199
doi: 10.1038/s41598-022-12587-6
Damadian, R. (1971). Tumor detection by nuclear magnetic resonance. Science, 171(3976), 1151–1153.
pubmed: 5544870
doi: 10.1126/science.171.3976.1151
Esteban, O., Markiewicz, C. J., Blair, R. W., et al. (2019). fMRIPrep: A robust preprocessing pipeline for functional MRI. Nature Methods, 16(1), 111–116.
pubmed: 30532080
doi: 10.1038/s41592-018-0235-4
Fischl, B. (2012). FreeSurfer. Neuroimage, 62(2), 774–781.
pubmed: 22248573
doi: 10.1016/j.neuroimage.2012.01.021
Froeling, M., Tax, C. M., Vos, S. B., Luijten, P. R., & Leemans, A. (2017). “MASSIVE” brain dataset: Multiple acquisitions for standardization of structural imaging validation and evaluation. Magnetic Resonance in Medicine, 77(5), 1797–1809.
pubmed: 27173617
doi: 10.1002/mrm.26259
Gaillochet, M., Tezcan, K. C., & Konukoglu, E. (2020). Joint reconstruction and bias field correction for undersampled MR imaging. International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 44–52). Cham: Springer International Publishing.
Gispert, J. D., Reig, S., Pascau, J., Vaquero, J. J., García-Barreno, P., & Desco, M. (2004). Method for bias field correction of brain T1-weighted magnetic resonance images minimizing segmentation error. Human Brain Mapping, 22(2), 133–144.
pubmed: 15108301
pmcid: 6871800
doi: 10.1002/hbm.20013
Goldfryd, T., Gordon, S., & Raviv, T. R. (2021). Deep semi-supervised bias field correction of Mr images (pp. 1836–1840). IEEE.
Gorgolewski, K., Burns, C. D., Madison, C., et al. (2011). Nipype: A flexible, lightweight and extensible neuroimaging data processing framework in python. Frontiers in Neuroinformatics, 5, 13.
pubmed: 21897815
pmcid: 3159964
doi: 10.3389/fninf.2011.00013
Harms, M. P., Somerville, L. H., Ances, B. M., et al. (2018). Extending the Human Connectome Project across ages: Imaging protocols for the Lifespan Development and Aging projects. NeuroImage, 183, 972–984.
pubmed: 30261308
doi: 10.1016/j.neuroimage.2018.09.060
Huo, Y., Xu, Z., Xiong, Y., et al. (2019). 3D whole brain segmentation using spatially localized atlas network tiles. NeuroImage, 194, 105–119.
pubmed: 30910724
doi: 10.1016/j.neuroimage.2019.03.041
IXI Dataset - Information eXtraction from images. (2020). Biomedical Image Analysis Group, Imperial College London. https://brain-development.org/ixi-dataset/
Jack, C. R., Jr., Bernstein, M. A., Fox, N. C., et al. (2008). The Alzheimer’s disease neuroimaging initiative (ADNI): MRI methods. Journal of Magnetic Resonance Imaging: An Official Journal of the International Society for Magnetic Resonance in Medicine, 27(4), 685–691.
doi: 10.1002/jmri.21049
Jefferson, A. L., Gifford, K. A., Acosta, L. M. Y., et al. (2016). The Vanderbilt Memory & Aging Project: Study design and baseline cohort overview. Journal of Alzheimer’s Disease, 52(2), 539–559.
pubmed: 26967211
doi: 10.3233/JAD-150914
Johnson, K. A. (2016). Basic proton MR imaging: tissue signal characteristics. Harvard Medical School. Archived from the original on, 03-05.
Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint. arXiv:14126980
LaMontagne, P. J., Benzinger, T. L., Morris, J. C., et al. (2019). OASIS-3: longitudinal neuroimaging, clinical, and cognitive dataset for normal aging and Alzheimer disease. MedRxiv, 2019.12. 13.19014902.
Landman, B. A., Huang, A. J., Gifford, A., et al. (2011). Multi-parametric neuroimaging reproducibility: A 3-T resource study. NeuroImage, 54(4), 2854–2866.
pubmed: 21094686
doi: 10.1016/j.neuroimage.2010.11.047
Mascalchi, M., Marzi, C., Giannelli, M., et al. (2018). Histogram analysis of DTI-derived indices reveals pontocerebellar degeneration and its progression in SCA2. PLoS ONE, 13(7), e0200258.
pubmed: 30001379
pmcid: 6042729
doi: 10.1371/journal.pone.0200258
Mihara, H., Iriguchi, N., & Ueno, S. (1998). A method of RF inhomogeneity correction in MR imaging. Magnetic Resonance Materials in Physics, Biology and Medicine, 7(2), 115–120.
doi: 10.1007/BF02592235
Miller, N., Liu, Y., Krivochenitser, R., & Rokers, B. (2019). Linking neural and clinical measures of glaucoma with diffusion magnetic resonance imaging (dMRI). PLoS ONE, 14(5), e0217011.
pubmed: 31150402
pmcid: 6544345
doi: 10.1371/journal.pone.0217011
Narayana, P., Brey, W., Kulkarni, M., & Sievenpiper, C. (1988). Compensation for surface coil sensitivity variation in magnetic resonance imaging. Magnetic Resonance Imaging, 6(3), 271–274.
pubmed: 3398733
doi: 10.1016/0730-725X(88)90401-8
Payares-Garcia, D., Mateu, J., & Schick, W. (2023). NeuroNorm: An R package to standardize multiple structural MRI. Neurocomputing, 550, 126493.
doi: 10.1016/j.neucom.2023.126493
Pineda, L., Fan, T., Monge, M., et al. (2022). Theseus: A library for differentiable nonlinear optimization. Advances in Neural Information Processing Systems, 35, 3801–3818.
Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18 (pp. 234–241). Springer International Publishing.
Sacktor, N., Soldan, A., Grega, M., Farrington, L., Cai, Q., Wang, M. C., & Albert, M. (2017). The BIOCARD index: a summary measure to predict onset of mild cognitive impairment (P1. 095). AAN Enterprises.
doi: 10.1097/WAD.0000000000000194
Schiffmann, R., & van der Knaap, M. S. (2009). Invited article: An MRI-based approach to the diagnosis of white matter disorders. Neurology, 72(8), 750–759.
pubmed: 19237705
pmcid: 2677542
doi: 10.1212/01.wnl.0000343049.00540.c8
Schilling, K. G., Blaber, J., Hansen, C., et al. (2020). Distortion correction of diffusion weighted MRI without reverse phase-encoding scans or field-maps. PLoS ONE, 15(7), e0236418.
pubmed: 32735601
pmcid: 7394453
doi: 10.1371/journal.pone.0236418
Shock, N. W. (1984). Normal human aging: The Baltimore longitudinal study of aging (No. 84). US Department of Health and Human Services, Public Health Service, National Institutes of Health, National Institute on Aging, Gerontology Research Center.
Simkó, A., Löfstedt, T., Garpebring, A., Nyholm, T., & Jonsson, J. (2022). MRI bias field correction with an implicitly trained CNN. International Conference on Medical Imaging with Deep Learning (pp. 1125–1138). PMLR.
Simmons, A., Tofts, P. S., Barker, G. J., & Arridge, S. R. (1994). Sources of intensity nonuniformity in spin echo images at 1.5 T. Magnetic Resonance in Medicine, 32(1), 121–128.
pubmed: 8084227
doi: 10.1002/mrm.1910320117
Sled, J. G., Zijdenbos, A. P., & Evans, A. C. (1998). A nonparametric method for automatic correction of intensity nonuniformity in MRI data. IEEE Transactions on Medical Imaging, 17(1), 87–97.
pubmed: 9617910
doi: 10.1109/42.668698
Song, S., Zheng, Y., & He, Y. (2017). A review of methods for bias correction in medical images. Biomedical Engineering Review, 1(1).
Sridhara, S. N., Akrami, H., Krishnamurthy, V., & Joshi, A. A. (2021). Bias field correction in 3D-MRIs using convolutional autoencoders. Medical Imaging 2021: Image Processing (Vol. 11596, pp. 671–676). SPIE.
Tournier, J. D., Calamante, F., & Connelly, A. (2012). MRtrix: Diffusion tractography in crossing fiber regions. International Journal of Imaging Systems and Technology, 22(1), 53–66.
doi: 10.1002/ima.22005
Tustison, N. J., Avants, B. B., Cook, P. A., et al. (2010). N4ITK: Improved N3 bias correction. IEEE Transactions on Medical Imaging, 29(6), 1310–1320.
pubmed: 20378467
pmcid: 3071855
doi: 10.1109/TMI.2010.2046908
Tustison, N. J., Cook, P. A., Holbrook, A. J., et al. (2021). The ANTsX ecosystem for quantitative biological and medical imaging. Scientific Reports, 11(1), 9068.
pubmed: 33907199
pmcid: 8079440
doi: 10.1038/s41598-021-87564-6
Van Essen, D. C., Smith, S. M., Barch, D. M., et al. (2013). The WU-Minn human connectome project: An overview. NeuroImage, 80, 62–79.
pubmed: 23684880
doi: 10.1016/j.neuroimage.2013.05.041
Vovk, U., Pernus, F., & Likar, B. (2007). A review of methods for correction of intensity inhomogeneity in MRI. IEEE Transactions on Medical Imaging, 26(3), 405–421.
pubmed: 17354645
doi: 10.1109/TMI.2006.891486
Wan, F., Smedby, Ö., & Wang, C. (2019). Simultaneous MR knee image segmentation and bias field correction using deep learning and partial convolution. Medical Imaging 2019: Image Processing (Vol. 10949, pp. 61–67). SPIE.
Weintraub, S., Besser, L., Dodge, H. H., et al. (2018). Version 3 of the Alzheimer Disease Centers’ neuropsychological test battery in the Uniform Data Set (UDS). Alzheimer Disease and Associated Disorders, 32(1), 10.
pubmed: 29240561
pmcid: 5821520
doi: 10.1097/WAD.0000000000000223
Weintraub, S., Salmon, D., Mercaldo, N., et al. (2009). The Alzheimer’s disease centers’ uniform data set (UDS): The neuropsychological test battery. Alzheimer Disease and Associated Disorders, 23(2), 91.
pubmed: 19474567
pmcid: 2743984
doi: 10.1097/WAD.0b013e318191c7dd
Xu, Y., Wang, Y., Hu, S., & Du, Y. (2022). Deep convolutional neural networks for bias field correction of brain magnetic resonance images. The Journal of Supercomputing, 78(16), 17943–17968.
doi: 10.1007/s11227-022-04575-4
Yaniv, Z., Lowekamp, B. C., Johnson, H. J., & Beare, R. (2018). SimpleITK image-analysis notebooks: A collaborative environment for education and reproducible research. Journal of Digital Imaging, 31(3), 290–303.
pubmed: 29181613
doi: 10.1007/s10278-017-0037-8