On the Evaluation of Automated MRI Brain Segmentations: Technical and Conceptual Tools

  • Elisabetta Binaghi
  • Valentina Pedoia
  • Desiree Lattanzi
  • Emanuele Monti
  • Sergio Balbi
  • Renzo Minotto
Part of the Lecture Notes in Computational Vision and Biomechanics book series (LNCVB, volume 19)


The present work deals with segmentation of Glial Tumors in MRI images focusing on critical aspects in manual labeling and reference estimation for segmentation validation purposes. A reproducibility analysis was conducted confirming the presence of different sources of uncertainty involved in the process of manual segmentation and responsible of high intra-operator and inter-operator variability. Technical and conceptual solutions aimed to reduce operator variability and support in the reference estimation process are integrated in GliMAn (Glial Tumor Manual Annotator), an application allowing to view and manipulate MRI volumes and implementing a label fusion strategy based on fuzzy connectedness. A set of experiments was conceived and conducted to evaluate the contribution of the solutions proposed in the process of manual segmentation and reference data estimation.


Vote Rule Manual Segmentation Glial Tumor Operator Variability Tumor Segmentation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Clarke L, Velthuizen R, Camacho M, Heine J, Vaidyanathan M, Hall L, Thatcher R, Silbiger M (1995) MRI segmentation: methods and applications. Magn Reson Imaging 13(3):34–3CrossRefGoogle Scholar
  2. 2.
    Bouix S, Martin-Fernandez M, Ungar L, Koo MNMS, McCarley RW, Shenton ME (2007) On evaluating brain tissue classifiers without a ground truth. Neuroimage, 36:1207–1224CrossRefGoogle Scholar
  3. 3.
    Balafar MA Ramli AR, Saripan MI, Mashohor S Review of brain MRI image segmentation methods. Artif Intell Rev 33(3):261–274 (2010)CrossRefGoogle Scholar
  4. 4.
    Warfield SK, Zou KH, Wells WM (2004) Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation. IEEE Transactions Medical Imaging 23(7):903–921. Scholar
  5. 5.
    Rohlfing T, Maurer CR Jr (2007) Shape-based averaging. IEEE Trans Image Process 61:153–161Google Scholar
  6. 6.
    Robitaille N, Duchesne S (2012) Label fusion strategy selection. Int J Biomed Imaging 2012:431095. doi:10.1155/2012/431095Google Scholar
  7. 7.
    Pedoia V, De Benedictis A, Renis G, Monti E, Balbi S, Binaghi E (2012) Proceedings of the 1st International Workshop on Visual Interfaces for Ground Truth Collection in Computer Vision Applications. (ACM, New York, NY, USA, 2012), VIGTA ’12, pp 8:1–8:4. doi:10.1145/2304496.2304504.
  8. 8.
    Udupa J, Samarasekera S (1996) Fuzzy connectedness and object definition: theory, algorithms, and applications in image segmentation. Gr Models Image Process 58(3):246–261CrossRefGoogle Scholar
  9. 9.
    Duffau H (2009) Surgery of low-grade gliomas: towards a ‘functional neurooncology’. Curr Opin Oncol 21:543–549CrossRefGoogle Scholar
  10. 10.
    Duffau H (2005) Lessons from brain mapping in surgery for low-grade glioma: insights into associations between tumour and brain plasticity. Lancet Neurol 4(8):476–486Google Scholar
  11. 11.
    Pallud J, Varlet P, Devaux B, Geha S, Badoual M, Deroulers C (2010) Diffuse low-grade oligodendrogliomas extend beyond MRI-defined abnormalities. Neurology 74(21):172–4CrossRefGoogle Scholar
  12. 12.
    Kelly PJ, Daumas-Duport C, Kispert DB, Kall BA, Scheithauer BW, Illig JJ (1987) Imaging-based stereotaxic serial biopsies in untreated intracranial glial neoplasms. Journal of Neurosurgery 66(6):865–875CrossRefGoogle Scholar
  13. 13.
    Jaccard P (1912) New Phytologist 11(2):3–7Google Scholar
  14. 14.
    Binaghi E, Pedoia V, Lattanzi D, Balbi S, Monti E, Minotto R (2013) Proceedings Vision And Medical Image Processing, VipIMAGE.Google Scholar
  15. 15.
    Wallis J, Miller T, Lerner C, Kleerup E (1989) Three-dimensional display in nuclear medicine. IEEE Trans Med Imagin 8(4):297–230. doi:10.1109/42.41482CrossRefGoogle Scholar
  16. 16.
    Heckemann RA, Hajnal JV, Aljabar P, Rueckert D, Hammers A (2006) Automatic anatomical brain MRI segmentation combining label propagation and decision fusion. Neuroimage 33(1):115–126. doi:10.1016/j.neuroimage.2006.05.061. CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Elisabetta Binaghi
    • 1
  • Valentina Pedoia
    • 2
  • Desiree Lattanzi
    • 3
  • Emanuele Monti
    • 3
  • Sergio Balbi
    • 3
  • Renzo Minotto
    • 4
  1. 1.Dipartimento di Scienze Teoriche e Applicate—Sezione InformaticaUniversità degli Studi dell’InsubriaVareseItaly
  2. 2.Musculoskeletal Quantitative Imaging Research Group Department of Radiology and Biomedical Imaging University of CaliforniaSan FranciscoUSA
  3. 3.Dipartimento di Biotecnologie e Scienze della VitaUniversità degli Studi dell’Insubria VareseVareseItaly
  4. 4.Unità Operativa di Neuroradiologia Ospedale di Circolo e Fondazione MacchiVareseItaly

Personalised recommendations