Statistical atlas construction via weighted functional boxplots

Yi Hong, Brad Davis, J. S. Marron, Roland Kwitt, Nikhil Singh, Julia S. Kimbell, Elizabeth Pitkin, Richard Superfine, Stephanie Davis, Carlton J. Zdanski, Marc Niethammer

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Atlas-building from population data is widely used in medical imaging. However, the emphasis of atlas-building approaches is typically to estimate a spatial alignment to compute a mean/median shape or image based on population data. In this work, we focus on the statistical characterization of the population data, once spatial alignment has been achieved. We introduce and propose the use of the weighted functional boxplot. This allows the generalization of concepts such as the median, percentiles, or outliers to spaces where the data objects are functions, shapes, or images, and allows spatio-temporal atlas-building based on kernel regression. In our experiments, we demonstrate the utility of the approach to construct statistical atlases for pediatric upper airways and corpora callosa revealing their growth patterns. We also define a score system based on the pediatric airway atlas to quantitatively measure the severity of subglottic stenosis (SGS) in the airway. This scoring allows the classification of pre- and post-surgery SGS subjects and radiographically normal controls. Experimental results show the utility of atlas information to assess the effect of airway surgery in children.

Original languageEnglish
Pages (from-to)684-698
Number of pages15
JournalMedical Image Analysis
Volume18
Issue number4
DOIs
StatePublished - 2014

Fingerprint

Atlases
Surgery
Pediatrics
Medical imaging
Pathologic Constriction
Population
Corpus Callosum
Diagnostic Imaging
Experiments
Growth

Keywords

  • Kernel regression
  • Pediatric upper airways
  • Statistical atlas-building
  • Weighted functional boxplots

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Radiology Nuclear Medicine and imaging
  • Health Informatics
  • Radiological and Ultrasound Technology
  • Medicine(all)

Cite this

Hong, Y., Davis, B., Marron, J. S., Kwitt, R., Singh, N., Kimbell, J. S., ... Niethammer, M. (2014). Statistical atlas construction via weighted functional boxplots. Medical Image Analysis, 18(4), 684-698. https://doi.org/10.1016/j.media.2014.03.001

Statistical atlas construction via weighted functional boxplots. / Hong, Yi; Davis, Brad; Marron, J. S.; Kwitt, Roland; Singh, Nikhil; Kimbell, Julia S.; Pitkin, Elizabeth; Superfine, Richard; Davis, Stephanie; Zdanski, Carlton J.; Niethammer, Marc.

In: Medical Image Analysis, Vol. 18, No. 4, 2014, p. 684-698.

Research output: Contribution to journalArticle

Hong, Y, Davis, B, Marron, JS, Kwitt, R, Singh, N, Kimbell, JS, Pitkin, E, Superfine, R, Davis, S, Zdanski, CJ & Niethammer, M 2014, 'Statistical atlas construction via weighted functional boxplots', Medical Image Analysis, vol. 18, no. 4, pp. 684-698. https://doi.org/10.1016/j.media.2014.03.001
Hong Y, Davis B, Marron JS, Kwitt R, Singh N, Kimbell JS et al. Statistical atlas construction via weighted functional boxplots. Medical Image Analysis. 2014;18(4):684-698. https://doi.org/10.1016/j.media.2014.03.001
Hong, Yi ; Davis, Brad ; Marron, J. S. ; Kwitt, Roland ; Singh, Nikhil ; Kimbell, Julia S. ; Pitkin, Elizabeth ; Superfine, Richard ; Davis, Stephanie ; Zdanski, Carlton J. ; Niethammer, Marc. / Statistical atlas construction via weighted functional boxplots. In: Medical Image Analysis. 2014 ; Vol. 18, No. 4. pp. 684-698.
@article{88421dd1aff34026a96b28c649ad3eb9,
title = "Statistical atlas construction via weighted functional boxplots",
abstract = "Atlas-building from population data is widely used in medical imaging. However, the emphasis of atlas-building approaches is typically to estimate a spatial alignment to compute a mean/median shape or image based on population data. In this work, we focus on the statistical characterization of the population data, once spatial alignment has been achieved. We introduce and propose the use of the weighted functional boxplot. This allows the generalization of concepts such as the median, percentiles, or outliers to spaces where the data objects are functions, shapes, or images, and allows spatio-temporal atlas-building based on kernel regression. In our experiments, we demonstrate the utility of the approach to construct statistical atlases for pediatric upper airways and corpora callosa revealing their growth patterns. We also define a score system based on the pediatric airway atlas to quantitatively measure the severity of subglottic stenosis (SGS) in the airway. This scoring allows the classification of pre- and post-surgery SGS subjects and radiographically normal controls. Experimental results show the utility of atlas information to assess the effect of airway surgery in children.",
keywords = "Kernel regression, Pediatric upper airways, Statistical atlas-building, Weighted functional boxplots",
author = "Yi Hong and Brad Davis and Marron, {J. S.} and Roland Kwitt and Nikhil Singh and Kimbell, {Julia S.} and Elizabeth Pitkin and Richard Superfine and Stephanie Davis and Zdanski, {Carlton J.} and Marc Niethammer",
year = "2014",
doi = "10.1016/j.media.2014.03.001",
language = "English",
volume = "18",
pages = "684--698",
journal = "Medical Image Analysis",
issn = "1361-8415",
publisher = "Elsevier",
number = "4",

}

TY - JOUR

T1 - Statistical atlas construction via weighted functional boxplots

AU - Hong, Yi

AU - Davis, Brad

AU - Marron, J. S.

AU - Kwitt, Roland

AU - Singh, Nikhil

AU - Kimbell, Julia S.

AU - Pitkin, Elizabeth

AU - Superfine, Richard

AU - Davis, Stephanie

AU - Zdanski, Carlton J.

AU - Niethammer, Marc

PY - 2014

Y1 - 2014

N2 - Atlas-building from population data is widely used in medical imaging. However, the emphasis of atlas-building approaches is typically to estimate a spatial alignment to compute a mean/median shape or image based on population data. In this work, we focus on the statistical characterization of the population data, once spatial alignment has been achieved. We introduce and propose the use of the weighted functional boxplot. This allows the generalization of concepts such as the median, percentiles, or outliers to spaces where the data objects are functions, shapes, or images, and allows spatio-temporal atlas-building based on kernel regression. In our experiments, we demonstrate the utility of the approach to construct statistical atlases for pediatric upper airways and corpora callosa revealing their growth patterns. We also define a score system based on the pediatric airway atlas to quantitatively measure the severity of subglottic stenosis (SGS) in the airway. This scoring allows the classification of pre- and post-surgery SGS subjects and radiographically normal controls. Experimental results show the utility of atlas information to assess the effect of airway surgery in children.

AB - Atlas-building from population data is widely used in medical imaging. However, the emphasis of atlas-building approaches is typically to estimate a spatial alignment to compute a mean/median shape or image based on population data. In this work, we focus on the statistical characterization of the population data, once spatial alignment has been achieved. We introduce and propose the use of the weighted functional boxplot. This allows the generalization of concepts such as the median, percentiles, or outliers to spaces where the data objects are functions, shapes, or images, and allows spatio-temporal atlas-building based on kernel regression. In our experiments, we demonstrate the utility of the approach to construct statistical atlases for pediatric upper airways and corpora callosa revealing their growth patterns. We also define a score system based on the pediatric airway atlas to quantitatively measure the severity of subglottic stenosis (SGS) in the airway. This scoring allows the classification of pre- and post-surgery SGS subjects and radiographically normal controls. Experimental results show the utility of atlas information to assess the effect of airway surgery in children.

KW - Kernel regression

KW - Pediatric upper airways

KW - Statistical atlas-building

KW - Weighted functional boxplots

UR - http://www.scopus.com/inward/record.url?scp=84907562761&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907562761&partnerID=8YFLogxK

U2 - 10.1016/j.media.2014.03.001

DO - 10.1016/j.media.2014.03.001

M3 - Article

VL - 18

SP - 684

EP - 698

JO - Medical Image Analysis

JF - Medical Image Analysis

SN - 1361-8415

IS - 4

ER -