Literature DB >> 22003715

Learning likelihoods for labeling (L3): a general multi-classifier segmentation algorithm.

Neil I Weisenfeld1, Simon K Warfield.   

Abstract

PURPOSE: To develop an MRI segmentation method for brain tissues, regions, and substructures that yields improved classification accuracy. Current brain segmentation strategies include two complementary strategies. Multi-spectral classification techniques generate excellent segmentations for tissues with clear intensity contrast, but fail to identify structures defined largely by location, such as lobar parcellations and certain subcortical structures. Conversely, multi-template label fusion methods are excellent for structures defined largely by location, but perform poorly when segmenting structures that cannot be accurately identified through a consensus of registered templates.
METHODS: We propose here a novel multi-classifier fusion algorithm with the advantages of both types of segmentation strategy. We illustrate and validate this algorithm using a group of 14 expertly hand-labeled images.
RESULTS: Our method generated segmentations of cortical and subcortical structures that were more similar to hand-drawn segmentations than majority vote label fusion or a recently published intensity/label fusion method.
CONCLUSIONS: We have presented a novel, general segmentation algorithm with the advantages of both statistical classifiers and label fusion techniques.

Entities:  

Mesh:

Year:  2011        PMID: 22003715      PMCID: PMC3694428          DOI: 10.1007/978-3-642-23626-6_40

Source DB:  PubMed          Journal:  Med Image Comput Comput Assist Interv


  10 in total

1.  Automated model-based tissue classification of MR images of the brain.

Authors:  K Van Leemput; F Maes; D Vandermeulen; P Suetens
Journal:  IEEE Trans Med Imaging       Date:  1999-10       Impact factor: 10.048

2.  Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation.

Authors:  Simon K Warfield; Kelly H Zou; William M Wells
Journal:  IEEE Trans Med Imaging       Date:  2004-07       Impact factor: 10.048

3.  Performance-based classifier combination in atlas-based image segmentation using expectation-maximization parameter estimation.

Authors:  Torsten Rohlfing; Daniel B Russakoff; Calvin R Maurer
Journal:  IEEE Trans Med Imaging       Date:  2004-08       Impact factor: 10.048

4.  Incorporating priors on expert performance parameters for segmentation validation and label fusion: a maximum a posteriori STAPLE.

Authors:  Olivier Commowick; Simon K Warfield
Journal:  Med Image Comput Comput Assist Interv       Date:  2010

5.  Adaptive segmentation of MRI data.

Authors:  W M Wells; W L Grimson; R Kikinis; F A Jolesz
Journal:  IEEE Trans Med Imaging       Date:  1996       Impact factor: 10.048

6.  Multi-atlas based segmentation of brain images: atlas selection and its effect on accuracy.

Authors:  P Aljabar; R A Heckemann; A Hammers; J V Hajnal; D Rueckert
Journal:  Neuroimage       Date:  2009-02-23       Impact factor: 6.556

7.  Multispectral analysis of magnetic resonance images.

Authors:  M W Vannier; R L Butterfield; D Jordan; W A Murphy; R G Levitt; M Gado
Journal:  Radiology       Date:  1985-01       Impact factor: 11.105

8.  A generative model for image segmentation based on label fusion.

Authors:  Mert R Sabuncu; B T Thomas Yeo; Koen Van Leemput; Bruce Fischl; Polina Golland
Journal:  IEEE Trans Med Imaging       Date:  2010-06-17       Impact factor: 10.048

9.  Automatic segmentation of newborn brain MRI.

Authors:  Neil I Weisenfeld; Simon K Warfield
Journal:  Neuroimage       Date:  2009-05-03       Impact factor: 6.556

10.  Fast and robust multi-atlas segmentation of brain magnetic resonance images.

Authors:  Jyrki Mp Lötjönen; Robin Wolz; Juha R Koikkalainen; Lennart Thurfjell; Gunhild Waldemar; Hilkka Soininen; Daniel Rueckert
Journal:  Neuroimage       Date:  2009-10-24       Impact factor: 6.556

  10 in total
  16 in total

1.  Out-of-atlas likelihood estimation using multi-atlas segmentation.

Authors:  Andrew J Asman; Lola B Chambless; Reid C Thompson; Bennett A Landman
Journal:  Med Phys       Date:  2013-04       Impact factor: 4.071

2.  Automatic labeling of MR brain images by hierarchical learning of atlas forests.

Authors:  Lichi Zhang; Qian Wang; Yaozong Gao; Guorong Wu; Dinggang Shen
Journal:  Med Phys       Date:  2016-03       Impact factor: 4.071

3.  OUT-OF-ATLAS LABELING: A MULTI-ATLAS APPROACH TO CANCER SEGMENTATION.

Authors:  Andrew J Asman; Bennett A Landman
Journal:  Proc IEEE Int Symp Biomed Imaging       Date:  2012-12-31

4.  Simultaneous Segmentation and Statistical Label Fusion.

Authors:  Andrew J Asman; Bennett A Landmana
Journal:  Proc SPIE Int Soc Opt Eng       Date:  2012-02-23

5.  Formulating spatially varying performance in the statistical fusion framework.

Authors:  Andrew J Asman; Bennett A Landman
Journal:  IEEE Trans Med Imaging       Date:  2012-03-15       Impact factor: 10.048

6.  iSTAPLE: Improved Label Fusion for Segmentation by Combining STAPLE with Image Intensity.

Authors:  Xiaofeng Liu; Albert Montillo; Ek T Tan; John F Schenck
Journal:  Proc SPIE Int Soc Opt Eng       Date:  2013-03-13

7.  Multi-atlas multi-shape segmentation of fetal brain MRI for volumetric and morphometric analysis of ventriculomegaly.

Authors:  Ali Gholipour; Alireza Akhondi-Asl; Judy A Estroff; Simon K Warfield
Journal:  Neuroimage       Date:  2012-02-10       Impact factor: 6.556

8.  A magnetic resonance imaging study of cerebellar volume in tuberous sclerosis complex.

Authors:  Neil I Weisenfeld; Jurriaan M Peters; Peter T Tsai; Sanjay P Prabhu; Kira A Dies; Mustafa Sahin; Simon K Warfield
Journal:  Pediatr Neurol       Date:  2013-02       Impact factor: 3.372

9.  Non-local STAPLE: an intensity-driven multi-atlas rater model.

Authors:  Andrew J Asman; Bennett A Landman
Journal:  Med Image Comput Comput Assist Interv       Date:  2012

10.  Hierarchical performance estimation in the statistical label fusion framework.

Authors:  Andrew J Asman; Bennett A Landman
Journal:  Med Image Anal       Date:  2014-07-04       Impact factor: 8.545

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.