Brain extraction network trained with "silver standard" data and fine-tuned with manual annotation for improved segmentation

  • Roberto Souza University of Calgary
  • Oeslle Lucena King's College University
  • Mariana Bento University of Calgary
  • Julia Garrafa University of Campinas
  • Leticia Rittner University of Campinas
  • Simone Appenzeller University of Campinas
  • Roberto Lotufo University of Campinas
  • Richard Frayne University of Calgary

Resumo


Training convolutional neural networks (CNNs) formedical image segmentation often requires large and representativesets of images and their corresponding annotations.Obtaining annotated images usually requires manual intervention,which is expensive and time consuming, as it typicallyrequires a specialist. An alternative approach is to leverageexisting automatic segmentation tools and combine them to createconsensus-based “silver-standards†annotations. A drawback tothis approach is that silver-standards are usually smooth andthis smoothness is transmitted to the output segmentation ofthe network. Our proposal is to use a two-staged approach.First, silver-standard datasets are used to generate a large setof annotated images in order to train the brain extractionnetwork from scratch. Second, fine-tuning is performed usingmuch smaller amounts of manually annotated data so that thenetwork can learn the finer details that are not preserved inthe silver-standard data. As an example, our two-staged brainextraction approach has been shown to outperform seven state-of-the-art techniques across three different public datasets. Ourresults also suggest that CNNs can potentially capture inter-raterannotation variability between experts who annotate the sameset of images following the same guidelines, and also adapt todifferent annotation guidelines.

Palavras-chave: segmentation, MRI, brain

Referências

O. Ronneberger P. Fischer T. Brox "U-net: Convolutional networks for biomedical image segmentation" International Conference on Medical Image Computing and Computer-assisted Intervention pp. 234-2015.

B. B. Avants N. J. Tustison G. Song P. A. Cook A. Klein J. C. Gee "A reproducible evaluation of ANTs similarity metric performance in brain image registration" NeuroImage vol. 54 no. 3 pp. 2033-2044 2011.

R. Beare J. Chen C. Adamson T. Silk D. Thompson J. Yang V. Anderson M. Seal A. Wood "Brain extraction using the watershed transform from markers" Frontiers in Neuroinformatics vol. 7 no. 32 December 2013.

S. F. Eskildsen P. Coupé V. Fonov J. V. Manjón K. K. Leung N. Guizard S. N. Wassef L. R. Østergaard D. L. Collins "BEaST: Brain extraction based on non-local segmentation technique" NeuroImage vol. 59 no. 3 pp. 2362-22012.

J. E. Iglesias C. Y. Liu P. M. Thompson Z. Tu "Robust brain extraction across datasets and comparison with publicly available methods" IEEE Transactions on Medical Imaging vol. 30 no. 9 pp. 1617-1Sept 2011.

E. S. Lutkenhoff M. Rosenberg J. Chiang K. Zhang J. D. Pickard A. M. Owen M. M. Monti "Optimized brain extraction for pathological brains (OPTIBET)" PLoS ONE vol. 9 no. 12 pp. 1-13 2014.

F. Ségonne A. M. Dale B. E. Busa B. M. Glessner B. D. Salat B. H. K. Hahn B. F. A "A hybrid approach to the skull stripping problem in MRI" NeuroImage vol. 22 2004.

D. W. Shattuck S. R. Sandor-Leahy K. A. Schaper D. A. Rottenberg R. M. Leahy "Magnetic resonance image tissue classification using a partial volume model" NeuroImage vol. 13 no. 5 pp. 856-876 may 2001.

R. Souza O. Lucena J. Garrafa D. Gobbi M. Saluzzi S. Appenzeller L. Rittner R. Frayne R. Lotufo "An open multi-vendor multi-field-strength brain mr dataset and analysis of publicly available skull stripping methods agreement" NeuroImage vol. pp. 482-2018.

O. Lucena R. Souza L. Rittner R. Frayne R. Lotufo "Silver standard masks for data augmentation applied to deep-learning-based skull-stripping" International Symposium on Biomedical Imaging 2018.

J. Kleesiek G. Urban A. Hubert D. Schwarz K. Maier-Hein M. Bendszus A. Biller "Deep MRI brain extraction: A 3D convolutional neural network for skull stripping" NeuroImage vol. pp. 460-2016.

S. S. M. Salehi D. Erdogmus A. Gholipour "Auto-context convolutional neural network (auto-net) for brain extraction in magnetic resonance imaging" IEEE Transactions on Medical Imaging vol. 36 no. 11 pp. 2319-22017.

G. Zhao F. Liu J. A. Oler M. E. Meyerand N. H. Kalin R. M. Birn "Bayesian convolutional neural network based mri brain extraction on nonhuman primates" NeuroImage vol. pp. 32-44 2018.

O. Lucena R. Souza L. Rittner R. Frayne R. Lotufo "Convo-lutional neural networks for skull-stripping in brain mr imaging using silver standard masks" Artificial Intelligence in Medicine vol. 98 pp. 48-58 2019.

D. W. Shattuck M. Mirza V. Adisetiyo C. Hojatkashani G. Salamon K. L. Narr R. A. Poldrack R. M. Bilder A. W. Toga "Construction of a 3D probabilistic atlas of human cortical structures" NeuroImage vol. 39 no. 3 pp. 1064-1080 2008.

S. M. Smith "Fast robust automated brain extraction" Human Brain Mapping vol. 17 no. 3 pp. 143-Nov. 2002.

D. S. Marcus T. H. Wang J. Parker J. G. Csernansky J. C. Morris R. L. Buckner "Open access series of imaging studies (OASIS): Cross-sectional MRI data in young middle aged nondemented and demented older adults" J. Cognitive Neuroscience vol. 19 no. 9 pp. 1498-1Sep. 2007.

S. K. Warfield K. H. Zou W. M. Wells "Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation" IEEE Transactions on Medical Imaging vol. 23 no. 7 pp. 903-921 July 2004.

H. K. Hahn H. Peitgen "The skull stripping problem in MRI solved by a single 3D watershed transform" Proceedings of the Third International Conference on Medical Image Computing and Computer-Assisted Intervention ser. MICCAI '00 pp. 134-2000.

P. A. Yushkevich J. Piven H. Cody Hazlett R. Gimpel Smith S. Ho J. C. Gee G. Gerig "User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability" NeuroImage vol. 31 no. 3 pp. 1116-12006.

L. Vincent "Morphological area openings and closings for grey-scale images" Shape in Picture. Springer pp. 197-1994.

R. Souza L. Rittner R. Machado R. Lotufo "iamxt: Max-tree toolbox for image processing and analysis" SoftwareX vol. 6 pp. 81-84 2017.

T. Sørensen "A method of establishing groups of equal amplitude in plant sociology based on similarity of species and its application to analyses of the vegetation on danish commons" Biol. Skr. vol. 5 pp. 1-34 1948.

D. P. Kingma J. Ba Adam: A method for stochastic optimization 2014.

F. Wilcoxon "Individual comparisons by ranking methods" Biometrics Bulletin vol. 1 no. 6 pp. 80-83 1945.

R. Souza O. Lucena M. Bento J. Garrafa S. Appenzeller L. Rittner R. Lotufo R. Frayne "Reliability of using single specialist annotation for designing and evaluating automatic segmentation methods: a skull stripping case study" International Symposium on Biomedical Imaging 2018.

A. M. Dale B. Fischl M. I. Sereno "Cortical surface-based analysis. I. Segmentation and surface reconstruction" NeuroImage pp. 179-1999.

M. Jenkinson C. F. Beckmann T. E. Behrens M. W. Woolrich S. M. Smith "FSL" NeuroImage vol. 62 no. 2 pp. 782-2012.

B. Thyreau K. Sato H. Fukuda Y. Taki "Segmentation of the hippocampus by transferring algorithmic knowledge for large cohort processing" Medical Image Analysis vol. 43 pp. 214-2018.
Publicado
28/10/2019
Como Citar

Selecione um Formato
SOUZA, Roberto; LUCENA, Oeslle; BENTO, Mariana; GARRAFA, Julia; RITTNER, Leticia; APPENZELLER, Simone; LOTUFO, Roberto; FRAYNE, Richard. Brain extraction network trained with "silver standard" data and fine-tuned with manual annotation for improved segmentation. In: CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 32. , 2019, Rio de Janeiro. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2019 . DOI: https://doi.org/10.5753/sibgrapi.2019.9796.