Collection and fuzzy estimation of truth labels in glial tumour segmentation studies

In this work, we propose a novel behavioural comparison strategy specifically oriented to accuracy assessment in MRI glial tumour segmentation studies. A salient aspect of the proposed strategy is the use of the fuzzy set framework in modelling visual inspection and interpretation processes. In particular, a reference estimation strategy based on fuzzy connectedness principles is designed to merge individual labels and produce a common segmentation. The estimation is based exclusively on highly reliable partial information provided by experts. Interaction is then drastically limited compared with a complete manual tracing, leaving the estimation of the complete segmentation to the fuzzy connectedness method. A set of experiments was conceived and conducted to evaluate the contribution of the solutions proposed in the process of truth label collection and reference data estimation. A comparison analysis was also developed to see whether our method could constitute a worthy alternative to well-known and state-of-the-art solutions.

[1]  S. Escalera,et al.  A fully-automatic caudate nucleus segmentation of brain MRI: Application in volumetric analysis of pediatric attention-deficit/hyperactivity disorder , 2011, Biomedical engineering online.

[2]  Simon K. Warfield,et al.  Estimation of Inferential Uncertainty in Assessing Expert Segmentation Performance from Staple , 2009, IPMI.

[3]  Hayit Greenspan,et al.  An Adaptive Mean-Shift Framework for MRI Brain Segmentation , 2009, IEEE Transactions on Medical Imaging.

[4]  Alan C. Evans,et al.  BrainWeb: Online Interface to a 3D MRI Simulated Brain Database , 1997 .

[5]  R P Velthuizen,et al.  MRI segmentation: methods and applications. , 1995, Magnetic resonance imaging.

[6]  William M. Wells,et al.  Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation , 2004, IEEE Transactions on Medical Imaging.

[7]  Ozy Sjahputera,et al.  Comparing soft clusters and partitions , 2011, 2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011).

[8]  Alan C. Evans,et al.  A fully automatic and robust brain MRI tissue classification method , 2003, Medical Image Anal..

[9]  Elisabetta Binaghi,et al.  Fuzzy reference data estimation in brain tumor segmentation studies , 2013 .

[10]  Martial Hebert,et al.  Toward Objective Evaluation of Image Segmentation Algorithms , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Shelly Lotenberg,et al.  Evaluation of uterine cervix segmentations using ground truth from multiple experts , 2009, Comput. Medical Imaging Graph..

[12]  R. Kikinis,et al.  An Automated Registration Algorithm for Measuring MRI Subcortical Brain Structures , 1997, NeuroImage.

[13]  Torsten Rohlfing,et al.  Expectation Maximization Strategies for Multi-atlas Multi-label Segmentation , 2003, IPMI.

[14]  Ricardo J. G. B. Campello,et al.  A fuzzy extension of the Rand index and other related indexes for clustering and classification assessment , 2007, Pattern Recognit. Lett..

[15]  D. Louis Collins,et al.  Design and construction of a realistic digital brain phantom , 1998, IEEE Transactions on Medical Imaging.

[16]  Carlos Ortiz-de-Solorzano,et al.  Combination Strategies in Multi-Atlas Image Segmentation: Application to Brain MR Data , 2009, IEEE Transactions on Medical Imaging.

[17]  K. K. Tan,et al.  Surface of the brain: three-dimensional MR images created with volume rendering. , 1989, Radiology.

[18]  Elisabetta Binaghi,et al.  A fuzzy set-based accuracy assessment of soft classification , 1999, Pattern Recognit. Lett..

[19]  Elisabetta Binaghi,et al.  Manual labeling strategy for ground truth estimation in MRI glial tumor segmentation , 2012, VIGTA '12.

[20]  Torsten Rohlfing,et al.  Shape-Based Averaging , 2007, IEEE Transactions on Image Processing.

[21]  Martha Elizabeth Shenton,et al.  On evaluating brain tissue classifiers without a ground truth , 2007, NeuroImage.

[22]  L. R. Dice.  Measures of the Amount of Ecologic Association Between Species , 1945 .

[23]  Patrick J. F. Groenen,et al.  Modern Multidimensional Scaling: Theory and Applications , 2003 .

[24]  Jayaram K. Udupa,et al.  Comparison of fuzzy connectedness and graph cut segmentation algorithms , 2011, Medical Imaging.

[25]  C. Meltzer,et al.  Brain tumor volume measurement: comparison of manual and semiautomated methods. , 1999, Radiology.

[26]  O. Commowick,et al.  Incorporating Priors on Expert Performance Parameters for Segmentation Validation and Label Fusion: A Maximum a Posteriori STAPLE , 2010, MICCAI.

[27]  Daniel Rueckert,et al.  Automatic anatomical brain MRI segmentation combining label propagation and decision fusion , 2006, NeuroImage.

[28]  Vladik Kreinovich,et al.  Fuzzy logic and its applications in medicine , 2001, Int. J. Medical Informatics.

[29]  Sébastien Ourselin,et al.  STEPS: Similarity and Truth Estimation for Propagated Segmentations and its application to hippocampal segmentation and brain parcelation , 2013, Medical Image Anal..

[30]  M. Stella Atkins,et al.  Fully automatic segmentation of the brain in MRI , 1998, IEEE Transactions on Medical Imaging.

[31]  Friedrich Steimann,et al.  Fuzzy set theory in medicine , 1997, Artif. Intell. Medicine.

[32]  Elisabetta Binaghi.  A fuzzy logic inference model for a rule-based system in medical diagnosis , 1990 .

[33]  Jerry L Prince,et al.  Current methods in medical image segmentation. , 2000, Annual review of biomedical engineering.

[34]  Bruno M. Carvalho,et al.  Algorithms for Fuzzy Segmentation , 1999, Pattern Analysis & Applications.

[35]  Abdul Rahman Ramli,et al.  Review of brain MRI image segmentation methods , 2010, Artificial Intelligence Review.

[36]  Stephen M Smith,et al.  Fast robust automated brain extraction , 2002, Human brain mapping.

[37]  Jayaram K. Udupa,et al.  Relative Fuzzy Connectedness and Object Definition: Theory, Algorithms, and Applications in Image Segmentation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[38]  Elisabetta Binaghi,et al.  Glial brain tumor detection by using symmetry analysis , 2012, Medical Imaging.

[39]  Roelof K. Brouwer.  Extending the rand, adjusted rand and jaccard indices to fuzzy partitions , 2008, Journal of Intelligent Information Systems.

[40]  Simon Duchesne,et al.  Label Fusion Strategy Selection , 2012, Int. J. Biomed. Imaging.

[41]  Simon K. Warfield,et al.  Estimating A Reference Standard Segmentation With Spatially Varying Performance Parameters: Local MAP STAPLE , 2012, IEEE Transactions on Medical Imaging.

[42]  Markus Voelter,et al.  State of the Art , 1997, Pediatric Research.

[43]  Jayaram K. Udupa,et al.  Scale-Based Fuzzy Connected Image Segmentation: Theory, Algorithms, and Validation , 2000, Comput. Vis. Image Underst..

[44]  Nelly Gordillo,et al.  State of the art survey on MRI brain tumor segmentation. , 2013, Magnetic resonance imaging.

[45]  G. W. Williams,et al.  Comparing the joint agreement of several raters with another rater. , 1976, Biometrics.

[46]  P. Jaccard.  THE DISTRIBUTION OF THE FLORA IN THE ALPINE ZONE.1 , 1912 .

[47]  Jayaram K. Udupa,et al.  Fuzzy-connected 3D image segmentation at interactive speeds , 2000, Graph. Model..

[48]  Yongmin Kim,et al.  A methodology for evaluation of boundary detection algorithms on medical images , 1997, IEEE Transactions on Medical Imaging.