Automatic parcellation of cortical surfaces using random forests

Yu Meng, Gang Li, Yaozong Gao, Dinggang Shen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Automatic and accurate parcellation of cortical surfaces into anatomically and functionally meaningful regions is of fundamental importance in brain mapping. In this paper, we propose a new method leveraging random forests and graph cuts methods to parcellate cortical surfaces into a set of gyral-based regions, using multiple surface atlases with manual labels by experts. Specifically, our method first takes advantage of random forests and auto-context methods to learn the optimal utilization of cortical features for rough parcellation and then the graph cuts method to further refine the parcellation for improved accuracy and spatial consistency. Particularly, to capitalize on random forests, we propose a novel definition of Haar-like features on cortical surfaces based on spherical mapping. The proposed method has been validated on cortical surfaces from 39 adult brain MR images, each with 35 regions manually labeled by a neuroanatomist, achieving the average Dice ratio of 0.902, higher than the-state-of-art methods.

Original languageEnglish
Title of host publicationProceedings - International Symposium on Biomedical Imaging
PublisherIEEE Computer Society
Pages810-813
Number of pages4
Volume2015-July
ISBN (Print)9781479923748
DOIs
Publication statusPublished - 2015 Jul 21
Externally publishedYes
Event12th IEEE International Symposium on Biomedical Imaging, ISBI 2015 - Brooklyn, United States
Duration: 2015 Apr 162015 Apr 19

Other

Other12th IEEE International Symposium on Biomedical Imaging, ISBI 2015
CountryUnited States
CityBrooklyn
Period15/4/1615/4/19

Fingerprint

Brain mapping
Brain Mapping
Labels
Brain
Atlases
Forests

Keywords

  • context feature
  • Cortical surface parcellation
  • graph cuts
  • Haar-like features
  • random forests

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Meng, Y., Li, G., Gao, Y., & Shen, D. (2015). Automatic parcellation of cortical surfaces using random forests. In Proceedings - International Symposium on Biomedical Imaging (Vol. 2015-July, pp. 810-813). [7163995] IEEE Computer Society. https://doi.org/10.1109/ISBI.2015.7163995

Automatic parcellation of cortical surfaces using random forests. / Meng, Yu; Li, Gang; Gao, Yaozong; Shen, Dinggang.

Proceedings - International Symposium on Biomedical Imaging. Vol. 2015-July IEEE Computer Society, 2015. p. 810-813 7163995.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Meng, Y, Li, G, Gao, Y & Shen, D 2015, Automatic parcellation of cortical surfaces using random forests. in Proceedings - International Symposium on Biomedical Imaging. vol. 2015-July, 7163995, IEEE Computer Society, pp. 810-813, 12th IEEE International Symposium on Biomedical Imaging, ISBI 2015, Brooklyn, United States, 15/4/16. https://doi.org/10.1109/ISBI.2015.7163995
Meng Y, Li G, Gao Y, Shen D. Automatic parcellation of cortical surfaces using random forests. In Proceedings - International Symposium on Biomedical Imaging. Vol. 2015-July. IEEE Computer Society. 2015. p. 810-813. 7163995 https://doi.org/10.1109/ISBI.2015.7163995
Meng, Yu ; Li, Gang ; Gao, Yaozong ; Shen, Dinggang. / Automatic parcellation of cortical surfaces using random forests. Proceedings - International Symposium on Biomedical Imaging. Vol. 2015-July IEEE Computer Society, 2015. pp. 810-813
@inproceedings{263fbd16355b492bbf02f071b38c4c61,
title = "Automatic parcellation of cortical surfaces using random forests",
abstract = "Automatic and accurate parcellation of cortical surfaces into anatomically and functionally meaningful regions is of fundamental importance in brain mapping. In this paper, we propose a new method leveraging random forests and graph cuts methods to parcellate cortical surfaces into a set of gyral-based regions, using multiple surface atlases with manual labels by experts. Specifically, our method first takes advantage of random forests and auto-context methods to learn the optimal utilization of cortical features for rough parcellation and then the graph cuts method to further refine the parcellation for improved accuracy and spatial consistency. Particularly, to capitalize on random forests, we propose a novel definition of Haar-like features on cortical surfaces based on spherical mapping. The proposed method has been validated on cortical surfaces from 39 adult brain MR images, each with 35 regions manually labeled by a neuroanatomist, achieving the average Dice ratio of 0.902, higher than the-state-of-art methods.",
keywords = "context feature, Cortical surface parcellation, graph cuts, Haar-like features, random forests",
author = "Yu Meng and Gang Li and Yaozong Gao and Dinggang Shen",
year = "2015",
month = "7",
day = "21",
doi = "10.1109/ISBI.2015.7163995",
language = "English",
isbn = "9781479923748",
volume = "2015-July",
pages = "810--813",
booktitle = "Proceedings - International Symposium on Biomedical Imaging",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Automatic parcellation of cortical surfaces using random forests

AU - Meng, Yu

AU - Li, Gang

AU - Gao, Yaozong

AU - Shen, Dinggang

PY - 2015/7/21

Y1 - 2015/7/21

N2 - Automatic and accurate parcellation of cortical surfaces into anatomically and functionally meaningful regions is of fundamental importance in brain mapping. In this paper, we propose a new method leveraging random forests and graph cuts methods to parcellate cortical surfaces into a set of gyral-based regions, using multiple surface atlases with manual labels by experts. Specifically, our method first takes advantage of random forests and auto-context methods to learn the optimal utilization of cortical features for rough parcellation and then the graph cuts method to further refine the parcellation for improved accuracy and spatial consistency. Particularly, to capitalize on random forests, we propose a novel definition of Haar-like features on cortical surfaces based on spherical mapping. The proposed method has been validated on cortical surfaces from 39 adult brain MR images, each with 35 regions manually labeled by a neuroanatomist, achieving the average Dice ratio of 0.902, higher than the-state-of-art methods.

AB - Automatic and accurate parcellation of cortical surfaces into anatomically and functionally meaningful regions is of fundamental importance in brain mapping. In this paper, we propose a new method leveraging random forests and graph cuts methods to parcellate cortical surfaces into a set of gyral-based regions, using multiple surface atlases with manual labels by experts. Specifically, our method first takes advantage of random forests and auto-context methods to learn the optimal utilization of cortical features for rough parcellation and then the graph cuts method to further refine the parcellation for improved accuracy and spatial consistency. Particularly, to capitalize on random forests, we propose a novel definition of Haar-like features on cortical surfaces based on spherical mapping. The proposed method has been validated on cortical surfaces from 39 adult brain MR images, each with 35 regions manually labeled by a neuroanatomist, achieving the average Dice ratio of 0.902, higher than the-state-of-art methods.

KW - context feature

KW - Cortical surface parcellation

KW - graph cuts

KW - Haar-like features

KW - random forests

UR - http://www.scopus.com/inward/record.url?scp=84944323287&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84944323287&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2015.7163995

DO - 10.1109/ISBI.2015.7163995

M3 - Conference contribution

AN - SCOPUS:84944323287

SN - 9781479923748

VL - 2015-July

SP - 810

EP - 813

BT - Proceedings - International Symposium on Biomedical Imaging

PB - IEEE Computer Society

ER -