Download PDF
Am J Perinatol 2019; 36(11): 1157-1170
DOI: 10.1055/s-0038-1675375
Original Article
Thieme Medical Publishers 333 Seventh Avenue, New York, NY 10001, USA.

An Accurate Automated Local Similarity Factor-Based Neural Tree Approach toward Tissue Segmentation of Newborn Brain MRI

Tushar H. Jaware
1   R C Patel Institute of Technology, Shirpur, Maharashtra, India
,
K. B. Khanchandani
2   Shri Sant Gajanan Maharaj College of Engineering, Shegaon, Maharashtra, India
,
Anita Zurani
2   Shri Sant Gajanan Maharaj College of Engineering, Shegaon, Maharashtra, India
› Author Affiliations
Further Information

Publication History

16 October 2017

14 September 2018

Publication Date:
15 December 2018 (online)

    Permissions and Reprints

Abstract

Background Segmentation of brain MR images of neonates is a primary step for assessment of brain evolvement. Advanced segmentation techniques used for adult brain MRI are not companionable for neonates, due to extensive dissimilarities in tissue properties and head structure. Existing segmentation methods for neonates utilizes brain atlases or requires manual elucidation, which results into improper and atlas dependent segmentation.

Objective The primary objective of this work is to develop fully automatic, atlas free, and robust system to segment and classify brain tissues of newborn infants from magnetic resonance images.

Study Design In this study, we propose a fully automatic, atlas-free pipeline based Neural Tree approach for segmentation of newborn brain MRI which utilizes resourceful local resemblance factor such as concerning, connectivity, structure, and relative tissue location. Physical collaboration and uses of an atlas are not required in proposed method and at the same time skirting atlas-associated bias which results in improved segmentation. Proposed technique segments and classify brain tissues both at global and tissue level.

Results We examined our results through visual assessment by neonatologists and quantitative comparisons that show first-rate concurrence with proficient manual segmentations. The implementation results of the proposed technique provided a good overall accuracy of 91.82% for the segmentation of brain tissues as compared with other methods.

Conclusion The pipelined-based neural tree approach along with local similarity factor segments and classify brain tissues. The proposed automated system have higher dice similarity coefficient as well as computational speed.

Keywords

neonate brain MRI - local similarity factor - image segmentation - pipeline-based neural tree - intensity homogeneity correction - affine registration - noise reduction
 

  • References

  • 1 Devi CN, Chandrasekharan A, Sundararaman VK, Alex ZC. Neonatal brain MRI segmentation: a review. Comput Biol Med 2015; 64: 163-178
    CrossrefPubMedGoogle Scholar
  • 2 Ahirwar A. Study of techniques used for medical image segmentation and computation of statistical test for region classification of brain MRI. Int J Inform Tech Comp Sci 2013; 5 (05) 44-53
    PubMedGoogle Scholar
  • 3 Yang KLD. Image processing and image mining using decision trees. J Inf Sci Eng 2009; 25 (04) 989-1003
    PubMedGoogle Scholar
  • 4 Dubois J, Dehaene-Lambertz G, Kulikova S, Poupon C, Hüppi PS, Hertz-Pannier L. The early development of brain white matter: a review of imaging studies in fetuses, newborns and infants. Neuroscience 2014; 276: 48-71
    CrossrefPubMedGoogle Scholar
  • 5 Daliri M, Moghaddam AH. Skull segmentation in 3D neonatal MRI using hybrid Hopfield neural network. EMBS, IEEE; 2010: 4060-4063
    Google Scholar
  • 6 Kobashi S, Hashioka A. A priori knowledge based deformable surface model for newborn brain MR image segmentation. Kakenhi, IEEE; 2013: 1-5
    Google Scholar
  • 7 Prastawa M, Gilmore JH, Lin W, Gerig G. Automatic segmentation of MR images of the developing newborn brain. Med Image Anal 2005; 9 (05) 457-466
    CrossrefPubMedGoogle Scholar
  • 8 Schore AN. Early organization of the nonlinear right brain and development of a predisposition to psychiatric disorders. Dev Psychopathol 1997; 9 (04) 595-631
    CrossrefPubMedGoogle Scholar
  • 9 Hüppi PS, Maier SE, Peled S. , et al. Microstructural development of human newborn cerebral white matter assessed in vivo by diffusion tensor magnetic resonance imaging. Pediatr Res 1998; 44 (04) 584-590
    CrossrefPubMedGoogle Scholar
  • 10 Weisenfeld NI, Warfield SK. Automatic segmentation of newborn brain MRI. Neuroimage 2009; 47 (02) 564-572
    CrossrefPubMedGoogle Scholar
  • 11 Kobashi S, Jayaram UK. Fuzzy object model based fuzzy connectedness image segmentation of newborn brain MR images. In Systems, Man, and Cybernetics (SMC). International Conference on IEEE; 2012 :1422–1427
    PubMedGoogle Scholar
  • 12 Kazemi K, Ghadimi S. Neonatal probabilistic models of brain, CSF and skull using T1-MRI data: preliminary results. EMBS Conference, IEEE; 2008 :3892–3895
    PubMedGoogle Scholar
  • 13 Hashioka A, Kuramoto K. Fuzzy object shape model for newborn brain MR image segmentation. SCIS-ISIS, IEEE; 2012: 1253-1258
    Google Scholar
  • 14 Despotovic I, Deburchgraeve W. Development of a realistic head model for EEG, event-detection and source localization in newborn infants. IEEE EMBS, IEEE; 2009: 2296-2299
    Google Scholar
  • 15 Pagnozzi AM, Gal Y, Boyd RN. , et al. The need for improved brain lesion segmentation techniques for children with cerebral palsy: a review. Int J Dev Neurosci 2015; 47 (Pt B): 229-246
    CrossrefPubMedGoogle Scholar
  • 16 Kim SH, Fonov VS, Dietrich C. , et al; IBIS network. Adaptive prior probability and spatial temporal intensity change estimation for segmentation of the one-year-old human brain. J Neurosci Methods 2013; 212 (01) 43-55
    CrossrefPubMedGoogle Scholar
  • 17 Thakurand P, Dhiman ES. An efficient image segmentation technique by integrating FELICM with negative selection algorithm. International Journal of Signal Processing, Image Processing and Pattern Recognition 2015; 8 (10) 63-70
    PubMedGoogle Scholar
  • 18 Verma V, Bhaiya LP. MRI brain images classification using soft computing techniques. IJCTA 2012; 3 (03) 1179-1182
    PubMedGoogle Scholar
  • 19 Anbeek P, Išgum I, van Kooij BJ. , et al. Automatic segmentation of eight tissue classes in neonatal brain MRI. PLoS One 2013; 8 (12) e81895
    CrossrefPubMedGoogle Scholar
  • 20 Chiţă SM. , et al. Automatic segmentation of the preterm neonatal brain with MRI using supervised classification. Image Processing. Int Soc Optics Photonics 2013; 8669: 86693
    PubMedGoogle Scholar
  • 21 Warfield SK, Kaus M, Jolesz FA, Kikinis R. Adaptive, template moderated, spatially varying statistical classification. Med Image Anal 2000; 4 (01) 43-55
    CrossrefPubMedGoogle Scholar
  • 22 Moeskops P, Benders MJ, Chiţ SM. , et al. Automatic segmentation of MR brain images of preterm infants using supervised classification. Neuroimage 2015; 118: 628-641
    CrossrefPubMedGoogle Scholar
  • 23 Beare RJ, Chen J, Kelly CE. , et al. Neonatal brain tissue classification with morphological adaptation and unified segmentation. Front Neuroinform 2016; 10 (12) 12
    PubMedGoogle Scholar
  • 24 Anblagan D, Pataky R, Evans MJ. , et al. Association between preterm brain injury and exposure to chorioamnionitis during fetal life. Sci Rep 2016; 6: 37932
    CrossrefPubMedGoogle Scholar
  • 25 Kim H, Lepage C, Maheshwary R. , et al. NEOCIVET: towards accurate morphometry of neonatal gyrification and clinical applications in preterm newborns. Neuroimage 2016; 138: 28-42
    CrossrefPubMedGoogle Scholar
  • 26 Hajiaboli MR. An anisotropic fourth-order diffusion filter for image noise removal. Int J Comput Vis 2011; 92 (02) 177-191
    CrossrefPubMedGoogle Scholar
  • 27 Heimowitz A, Keller Y. Image segmentation via probabilistic graph matching. IEEE Trans Image Process 2016; 25 (10) 4743-4752
    CrossrefPubMedGoogle Scholar
  • 28 Mendrik AM, Vincken KL, Kuijf HJ. , et al. MR BrainS Challenge: online evaluation framework for brain image segmentation in 3T MRI scans. Comp Intell Neurosci 2015; 813696
    PubMedGoogle Scholar
  • 29 Li G, Wang L, Shi F. , et al. Cortical thickness and surface area in neonates at high risk for schizophrenia. Brain Struct Funct 2016; 221 (01) 447-461
    CrossrefPubMedGoogle Scholar
  • 30 Wang L, Gao Y, Shi F. , et al. LINKS: learning-based multi-source IntegratioN frameworK for Segmentation of infant brain images. Neuroimage 2015; 108: 160-172
    CrossrefPubMedGoogle Scholar
  • 31 Zhang W, Li R, Deng H. Deep convolutional neural networks for multi-modality isointense infant brain image segmentation. Neuroimage 2015; 108: 214-224
    CrossrefPubMedGoogle Scholar