Segmentation of nodular medulloblastoma using random walker and hierarchical normalized cuts

Lev Tchikindas; Rachel Sparks; Jennifer Baccon; David Ellison; Alexander R. Judkins; Anant Madabhushi

doi:10.1109/NEBC.2011.5778640

Segmentation of nodular medulloblastoma using random walker and hierarchical normalized cuts

Lev Tchikindas, Rachel Sparks, Jennifer Baccon, David Ellison, Alexander R. Judkins, Anant Madabhushi

Department of Pathology and Laboratory Medicine

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Scopus citations

Abstract

Medulloblastoma (MB) is the most common brain tumor in children. Recent studies have demonstrated a relationship between specific signaling pathway abnormalities, a tendency to more favorable outcomes, and a histopathological feature: nodular growth patterns. In this work we present a new segmentation scheme which requires minimal user interaction to segment nodules on MB histopathological sections. Our segmentation scheme consists of two steps: (1) color reduction using Hierarchical Normalized Cuts (HNCut), (2) Random Walker (RW) segmentation within the reduced HNCut color space. Across a cohort of 18 nodular MB images, our integrated HNCut and RW scheme yielded nodule segmentations with a Dice coefficient of 83:55 ± 12:4% and Predictive Positive Value (PPV) of 93:71 ± 9:0%.

Original language	English (US)
Title of host publication	2011 IEEE 37th Annual Northeast Bioengineering Conference, NEBEC 2011
DOIs	https://doi.org/10.1109/NEBC.2011.5778640
State	Published - 2011
Event	37th Annual Northeast Bioengineering Conference, NEBEC 2011 - Troy, NY, United States Duration: Apr 1 2011 → Apr 3 2011

Publication series

Name	2011 IEEE 37th Annual Northeast Bioengineering Conference, NEBEC 2011

Other

Other	37th Annual Northeast Bioengineering Conference, NEBEC 2011
Country/Territory	United States
City	Troy, NY
Period	4/1/11 → 4/3/11

All Science Journal Classification (ASJC) codes

Bioengineering

Access to Document

10.1109/NEBC.2011.5778640

Cite this

Tchikindas, L., Sparks, R., Baccon, J., Ellison, D., Judkins, A. R., & Madabhushi, A. (2011). Segmentation of nodular medulloblastoma using random walker and hierarchical normalized cuts. In 2011 IEEE 37th Annual Northeast Bioengineering Conference, NEBEC 2011 Article 5778640 (2011 IEEE 37th Annual Northeast Bioengineering Conference, NEBEC 2011). https://doi.org/10.1109/NEBC.2011.5778640

@inproceedings{e793aa6d27184407bd9131424b551c79,

title = "Segmentation of nodular medulloblastoma using random walker and hierarchical normalized cuts",

abstract = "Medulloblastoma (MB) is the most common brain tumor in children. Recent studies have demonstrated a relationship between specific signaling pathway abnormalities, a tendency to more favorable outcomes, and a histopathological feature: nodular growth patterns. In this work we present a new segmentation scheme which requires minimal user interaction to segment nodules on MB histopathological sections. Our segmentation scheme consists of two steps: (1) color reduction using Hierarchical Normalized Cuts (HNCut), (2) Random Walker (RW) segmentation within the reduced HNCut color space. Across a cohort of 18 nodular MB images, our integrated HNCut and RW scheme yielded nodule segmentations with a Dice coefficient of 83:55 ± 12:4% and Predictive Positive Value (PPV) of 93:71 ± 9:0%.",

author = "Lev Tchikindas and Rachel Sparks and Jennifer Baccon and David Ellison and Judkins, {Alexander R.} and Anant Madabhushi",

year = "2011",

doi = "10.1109/NEBC.2011.5778640",

language = "English (US)",

isbn = "9781612848273",

series = "2011 IEEE 37th Annual Northeast Bioengineering Conference, NEBEC 2011",

booktitle = "2011 IEEE 37th Annual Northeast Bioengineering Conference, NEBEC 2011",

}

Tchikindas, L, Sparks, R, Baccon, J, Ellison, D, Judkins, AR & Madabhushi, A 2011, Segmentation of nodular medulloblastoma using random walker and hierarchical normalized cuts. in 2011 IEEE 37th Annual Northeast Bioengineering Conference, NEBEC 2011., 5778640, 2011 IEEE 37th Annual Northeast Bioengineering Conference, NEBEC 2011, 37th Annual Northeast Bioengineering Conference, NEBEC 2011, Troy, NY, United States, 4/1/11. https://doi.org/10.1109/NEBC.2011.5778640

Segmentation of nodular medulloblastoma using random walker and hierarchical normalized cuts. / Tchikindas, Lev; Sparks, Rachel; Baccon, Jennifer et al.
2011 IEEE 37th Annual Northeast Bioengineering Conference, NEBEC 2011. 2011. 5778640 (2011 IEEE 37th Annual Northeast Bioengineering Conference, NEBEC 2011).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Segmentation of nodular medulloblastoma using random walker and hierarchical normalized cuts

AU - Tchikindas, Lev

AU - Sparks, Rachel

AU - Baccon, Jennifer

AU - Ellison, David

AU - Judkins, Alexander R.

AU - Madabhushi, Anant

PY - 2011

Y1 - 2011

N2 - Medulloblastoma (MB) is the most common brain tumor in children. Recent studies have demonstrated a relationship between specific signaling pathway abnormalities, a tendency to more favorable outcomes, and a histopathological feature: nodular growth patterns. In this work we present a new segmentation scheme which requires minimal user interaction to segment nodules on MB histopathological sections. Our segmentation scheme consists of two steps: (1) color reduction using Hierarchical Normalized Cuts (HNCut), (2) Random Walker (RW) segmentation within the reduced HNCut color space. Across a cohort of 18 nodular MB images, our integrated HNCut and RW scheme yielded nodule segmentations with a Dice coefficient of 83:55 ± 12:4% and Predictive Positive Value (PPV) of 93:71 ± 9:0%.

AB - Medulloblastoma (MB) is the most common brain tumor in children. Recent studies have demonstrated a relationship between specific signaling pathway abnormalities, a tendency to more favorable outcomes, and a histopathological feature: nodular growth patterns. In this work we present a new segmentation scheme which requires minimal user interaction to segment nodules on MB histopathological sections. Our segmentation scheme consists of two steps: (1) color reduction using Hierarchical Normalized Cuts (HNCut), (2) Random Walker (RW) segmentation within the reduced HNCut color space. Across a cohort of 18 nodular MB images, our integrated HNCut and RW scheme yielded nodule segmentations with a Dice coefficient of 83:55 ± 12:4% and Predictive Positive Value (PPV) of 93:71 ± 9:0%.

UR - http://www.scopus.com/inward/record.url?scp=79958730160&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79958730160&partnerID=8YFLogxK

U2 - 10.1109/NEBC.2011.5778640

DO - 10.1109/NEBC.2011.5778640

M3 - Conference contribution

AN - SCOPUS:79958730160

SN - 9781612848273

T3 - 2011 IEEE 37th Annual Northeast Bioengineering Conference, NEBEC 2011

BT - 2011 IEEE 37th Annual Northeast Bioengineering Conference, NEBEC 2011

T2 - 37th Annual Northeast Bioengineering Conference, NEBEC 2011

Y2 - 1 April 2011 through 3 April 2011

ER -

Segmentation of nodular medulloblastoma using random walker and hierarchical normalized cuts

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this