Automatic Segmentation of Diffuse White Matter Abnormality on T2-weighted Brain MR Images Using Deep Learning in Very Preterm Infants

Hailong Li, Ming Chen, Jinghua Wang, Venkata Sita Priyanka Illapani, Nehal A Parikh, Lili He, Hailong Li, Ming Chen, Jinghua Wang, Venkata Sita Priyanka Illapani, Nehal A Parikh, Lili He

Abstract

About 50%-80% of very preterm infants (VPIs) (≤ 32 weeks gestational age) exhibit diffuse white matter abnormality (DWMA) on their MR images at term-equivalent age. It remains unknown if DWMA is associated with developmental impairments, and further study is warranted. To aid in the assessment of DWMA, a deep learning model for DWMA quantification on T2-weighted MR images was developed. This secondary analysis of prospective data was performed with an internal cohort of 98 VPIs (data collected from December 2014 to April 2016) and an external cohort of 28 VPIs (data collected from January 2012 to August 2014) who had already undergone MRI at term-equivalent age. Ground truth DWMA regions were manually annotated by two human experts with the guidance of a prior published semiautomated algorithm. In a twofold cross-validation experiment using the internal cohort of 98 infants, the three-dimensional (3D) ResU-Net model accurately segmented DWMA with a Dice similarity coefficient of 0.907 ± 0.041 (standard deviation) and balanced accuracy of 96.0% ± 2.1, outperforming multiple peer deep learning models. The 3D ResU-Net model that was trained with the whole internal cohort (n = 98) was further tested on an independent external test cohort (n = 28) and achieved a Dice similarity coefficient of 0.877 ± 0.059 and balanced accuracy of 92.3% ± 3.9. The externally validated 3D ResU-Net deep learning model for accurately segmenting DWMA may facilitate the clinical diagnosis of DWMA in VPIs. Supplemental material is available for this article. Keywords: Brain/Brain Stem, Convolutional Neural Network (CNN), MR-Imaging, Pediatrics, Segmentation, Supervised learning © RSNA, 2021.

Conflict of interest statement

Disclosures of Conflicts of Interest: H.L. Activities related to the present article: institution and work supported by the National Institutes of Health (NIH) grants R01-EB029944, R21-HD094085, R01-NS094200, and R01-NS096037. Activities not related to the present article: disclosed no relevant relationships. Other relationships: disclosed no relevant relationships. M.C. disclosed no relevant relationships. J.W. disclosed no relevant relationships. V.S.P.I. disclosed no relevant relationships. N.A.P. Activities related to the present article: institution received grant from NIH. Activities not related to the present article: disclosed no relevant relationships. Other relationships: disclosed no relevant relationships. L.H. Activities related to the present article: institution received grant from NIH (R01-EB029944, R21-HD094085, R01-NS094200, and R01-NS096037). Activities not related to the present article: disclosed no relevant relationships. Other relationships: disclosed no relevant relationships.

2021 by the Radiological Society of North America, Inc.

Figures

Figure 1:
Figure 1:
Study overview. A, Ground truth diffuse white matter abnormality (DWMA) maps annotation. The T2-weighted brain MR images were annotated for DWMA segmentation by human raters. B, DWMA segmentation using three-dimensional (3D) ResU-Net. Image patches of cerebral tissues (white matter and gray matter) and ground truth DWMA maps were used to train the model in a supervised manner.
Figure 2:
Figure 2:
Visualization of diffuse white matter abnormality (DWMA) segmentation (highlighted in yellow) in five very preterm infants. Left column: T2-weighted images; middle column: corresponding images with ground truth DWMA maps; right column: corresponding images with DWMA maps segmented using three-dimensional (3D) ResU-Net.

References

    1. Maalouf EF, Duggan PJ, Rutherford MA, et al. . Magnetic resonance imaging of the brain in a cohort of extremely preterm infants. J Pediatr 1999;135(3):351–357.
    1. Inder TE, Anderson NJ, Spencer C, Wells S, Volpe JJ. White matter injury in the premature infant: a comparison between serial cranial sonographic and MR findings at term. AJNR Am J Neuroradiol 2003;24(5):805–809.
    1. Krishnan ML, Dyet LE, Boardman JP, et al. . Relationship between white matter apparent diffusion coefficients in preterm infants at term-equivalent age and developmental outcome at 2 years. Pediatrics 2007;120(3):e604–e609.
    1. de Bruïne FT, van den Berg-Huysmans AA, Leijser LM, et al. . Clinical implications of MR imaging findings in the white matter in very preterm infants: a 2-year follow-up study. Radiology 2011;261(3):899–906.
    1. Jeon TY, Kim JH, Yoo SY, et al. . Neurodevelopmental outcomes in preterm infants: comparison of infants with and without diffuse excessive high signal intensity on MR images at near-term-equivalent age. Radiology 2012;263(2):518–526.
    1. Hagmann CF, De Vita E, Bainbridge A, et al. . T2 at MR imaging is an objective quantitative measure of cerebral white matter signal intensity abnormality in preterm infants at term-equivalent age. Radiology 2009;252(1):209–217.
    1. Skiöld B, Horsch S, Hallberg B, et al. . White matter changes in extremely preterm infants, a population-based diffusion tensor imaging study. Acta Paediatr 2010;99(6):842–849.
    1. Parikh NA, He L, Bonfante-Mejia E, et al. . Automatically quantified diffuse excessive high signal intensity on MRI predicts cognitive development in preterm infants. Pediatr Neurol 2013;49(6):424–430.
    1. Dyet LE, Kennea N, Counsell SJ, et al. . Natural history of brain lesions in extremely preterm infants studied with serial magnetic resonance imaging from birth and neurodevelopmental assessment. Pediatrics 2006;118(2):536–548.
    1. Iwata S, Nakamura T, Hizume E, et al. . Qualitative brain MRI at term and cognitive outcomes at 9 years after very preterm birth. Pediatrics 2012;129(5):e1138–e1147.
    1. Hart AR, Whitby EH, Clark SJ, Paley MN, Smith MF. Diffusion-weighted imaging of cerebral white matter and the cerebellum following preterm birth. Dev Med Child Neurol 2010;52(7):652–659.
    1. Cainelli E, Arrigoni F, Vedovelli L. White matter injury and neurodevelopmental disabilities: A cross-disease (dis)connection. Prog Neurobiol 2020;193101845.
    1. Rath CP, Desai S, Rao SC, Patole S. Diffuse excessive high signal intensity on term equivalent MRI does not predict disability: a systematic review and meta-analysis. Arch Dis Child Fetal Neonatal Ed 2021;106(1):9–16.
    1. Hart AR, Smith MF, Rigby AS, Wallis LI, Whitby EH. Appearances of diffuse excessive high signal intensity (DEHSI) on MR imaging following preterm birth. Pediatr Radiol 2010;40(8):1390–1396.
    1. Keunen K, Kersbergen KJ, Groenendaal F, Isgum I, de Vries LS, Benders MJ. Brain tissue volumes in preterm infants: prematurity, perinatal risk factors and neurodevelopmental outcome: a systematic review. J Matern Fetal Neonatal Med 2012;25(Suppl 1):89–100.
    1. Mathur AM, Neil JJ, Inder TE. Understanding brain injury and neurodevelopmental disabilities in the preterm infant: the evolving role of advanced magnetic resonance imaging. Semin Perinatol 2010;34(1):57–66.
    1. He L, Parikh NA. Atlas-guided quantification of white matter signal abnormalities on term-equivalent age MRI in very preterm infants: findings predict language and cognitive development at two years of age. PLoS One 2013;8(12):e85475.
    1. Li H, Parikh NA, Wang J, et al. . Objective and Automated Detection of Diffuse White Matter Abnormality in Preterm Infants Using Deep Convolutional Neural Networks. Front Neurosci 2019;13610.
    1. Bhalerao M, Thakur S. Brain Tumor Segmentation Based on 3D Residual U-Net. In: Crimi A, Bakas S, eds. Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. BrainLes 2019. Lecture Notes in Computer Science, vol 11993. Cham, Switzerland: Springer, 2020; 218–2251.
    1. He L, Parikh NA. Aberrant Executive and Frontoparietal Functional Connectivity in Very Preterm Infants With Diffuse White Matter Abnormalities. Pediatr Neurol 2015;53(4):330–337.
    1. Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv:1412.6980 [preprint] . Posted December 22, 2014. Accessed June 11, 2018.
    1. Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Navab N, Hornegger J, Wells W, Frangi A, eds. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. MICCAI 2015. Lecture Notes in Computer Science, vol 9351. Cham, Switzerland: Springer, 2015; 234–241.
    1. Pednekar GV, Udupa JK, McLaughlin DJ, et al. . Image Quality and Segmentation. In: Fei B, Webster RJ III, eds. Proceedings of SPIE: medical imaging 2018—image-guided procedures, robotic interventions, and modeling. Vol 10576. Bellingham, Wash: International Society for Optics and Photonics, 2018; 105762N.

Source: PubMed

Patrocinadores y Colaboradores

Condiciones médicas

Intervenciones de drogas

3
Suscribir