Tumor tissue detection using blood-oxygen-level-dependent functional MRI based on independent component analysis

Huiyuan Huang, Junfeng Lu, Jinsong Wu, Zhongxiang Ding, Shuda Chen, Lisha Duan, Jianling Cui, Fuyong Chen, Dezhi Kang, Le Qi, Wusi Qiu, Seong Whan Lee, Shi Jun Qiu, Dinggang Shen, Yu Feng Zang, Han Zhang

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Accurate delineation of gliomas from the surrounding normal brain areas helps maximize tumor resection and improves outcome. Blood-oxygen-level-dependent (BOLD) functional MRI (fMRI) has been routinely adopted for presurgical mapping of the surrounding functional areas. For completely utilizing such imaging data, here we show the feasibility of using presurgical fMRI for tumor delineation. In particular, we introduce a novel method dedicated to tumor detection based on independent component analysis (ICA) of resting-state fMRI (rs-fMRI) with automatic tumor component identification. Multi-center rs-fMRI data of 32 glioma patients from three centers, plus the additional proof-of-concept data of 28 patients from the fourth center with non-brain musculoskeletal tumors, are fed into individual ICA with different total number of components (TNCs). The best-fitted tumor-related components derived from the optimized TNCs setting are automatically determined based on a new template-matching algorithm. The success rates are 100%, 100% and 93.75% for glioma tissue detection for the three centers, respectively, and 85.19% for musculoskeletal tumor detection. We propose that the high success rate could come from the previously overlooked ability of BOLD rs-fMRI in characterizing the abnormal vascularization, vasomotion and perfusion caused by tumors. Our findings suggest an additional usage of the rs-fMRI for comprehensive presurgical assessment.

Original languageEnglish
Article number1223
JournalScientific Reports
Volume8
Issue number1
DOIs
Publication statusPublished - 2018 Dec 1

Fingerprint

Magnetic Resonance Imaging
Oxygen
Neoplasms
Glioma
Perfusion
Brain

ASJC Scopus subject areas

  • General

Cite this

Tumor tissue detection using blood-oxygen-level-dependent functional MRI based on independent component analysis. / Huang, Huiyuan; Lu, Junfeng; Wu, Jinsong; Ding, Zhongxiang; Chen, Shuda; Duan, Lisha; Cui, Jianling; Chen, Fuyong; Kang, Dezhi; Qi, Le; Qiu, Wusi; Lee, Seong Whan; Qiu, Shi Jun; Shen, Dinggang; Zang, Yu Feng; Zhang, Han.

In: Scientific Reports, Vol. 8, No. 1, 1223, 01.12.2018.

Research output: Contribution to journalArticle

Huang, H, Lu, J, Wu, J, Ding, Z, Chen, S, Duan, L, Cui, J, Chen, F, Kang, D, Qi, L, Qiu, W, Lee, SW, Qiu, SJ, Shen, D, Zang, YF & Zhang, H 2018, 'Tumor tissue detection using blood-oxygen-level-dependent functional MRI based on independent component analysis', Scientific Reports, vol. 8, no. 1, 1223. https://doi.org/10.1038/s41598-017-18453-0
Huang, Huiyuan ; Lu, Junfeng ; Wu, Jinsong ; Ding, Zhongxiang ; Chen, Shuda ; Duan, Lisha ; Cui, Jianling ; Chen, Fuyong ; Kang, Dezhi ; Qi, Le ; Qiu, Wusi ; Lee, Seong Whan ; Qiu, Shi Jun ; Shen, Dinggang ; Zang, Yu Feng ; Zhang, Han. / Tumor tissue detection using blood-oxygen-level-dependent functional MRI based on independent component analysis. In: Scientific Reports. 2018 ; Vol. 8, No. 1.
@article{019599409361422c979cefbc56c146a2,
title = "Tumor tissue detection using blood-oxygen-level-dependent functional MRI based on independent component analysis",
abstract = "Accurate delineation of gliomas from the surrounding normal brain areas helps maximize tumor resection and improves outcome. Blood-oxygen-level-dependent (BOLD) functional MRI (fMRI) has been routinely adopted for presurgical mapping of the surrounding functional areas. For completely utilizing such imaging data, here we show the feasibility of using presurgical fMRI for tumor delineation. In particular, we introduce a novel method dedicated to tumor detection based on independent component analysis (ICA) of resting-state fMRI (rs-fMRI) with automatic tumor component identification. Multi-center rs-fMRI data of 32 glioma patients from three centers, plus the additional proof-of-concept data of 28 patients from the fourth center with non-brain musculoskeletal tumors, are fed into individual ICA with different total number of components (TNCs). The best-fitted tumor-related components derived from the optimized TNCs setting are automatically determined based on a new template-matching algorithm. The success rates are 100{\%}, 100{\%} and 93.75{\%} for glioma tissue detection for the three centers, respectively, and 85.19{\%} for musculoskeletal tumor detection. We propose that the high success rate could come from the previously overlooked ability of BOLD rs-fMRI in characterizing the abnormal vascularization, vasomotion and perfusion caused by tumors. Our findings suggest an additional usage of the rs-fMRI for comprehensive presurgical assessment.",
author = "Huiyuan Huang and Junfeng Lu and Jinsong Wu and Zhongxiang Ding and Shuda Chen and Lisha Duan and Jianling Cui and Fuyong Chen and Dezhi Kang and Le Qi and Wusi Qiu and Lee, {Seong Whan} and Qiu, {Shi Jun} and Dinggang Shen and Zang, {Yu Feng} and Han Zhang",
year = "2018",
month = "12",
day = "1",
doi = "10.1038/s41598-017-18453-0",
language = "English",
volume = "8",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",
number = "1",

}

TY - JOUR

T1 - Tumor tissue detection using blood-oxygen-level-dependent functional MRI based on independent component analysis

AU - Huang, Huiyuan

AU - Lu, Junfeng

AU - Wu, Jinsong

AU - Ding, Zhongxiang

AU - Chen, Shuda

AU - Duan, Lisha

AU - Cui, Jianling

AU - Chen, Fuyong

AU - Kang, Dezhi

AU - Qi, Le

AU - Qiu, Wusi

AU - Lee, Seong Whan

AU - Qiu, Shi Jun

AU - Shen, Dinggang

AU - Zang, Yu Feng

AU - Zhang, Han

PY - 2018/12/1

Y1 - 2018/12/1

N2 - Accurate delineation of gliomas from the surrounding normal brain areas helps maximize tumor resection and improves outcome. Blood-oxygen-level-dependent (BOLD) functional MRI (fMRI) has been routinely adopted for presurgical mapping of the surrounding functional areas. For completely utilizing such imaging data, here we show the feasibility of using presurgical fMRI for tumor delineation. In particular, we introduce a novel method dedicated to tumor detection based on independent component analysis (ICA) of resting-state fMRI (rs-fMRI) with automatic tumor component identification. Multi-center rs-fMRI data of 32 glioma patients from three centers, plus the additional proof-of-concept data of 28 patients from the fourth center with non-brain musculoskeletal tumors, are fed into individual ICA with different total number of components (TNCs). The best-fitted tumor-related components derived from the optimized TNCs setting are automatically determined based on a new template-matching algorithm. The success rates are 100%, 100% and 93.75% for glioma tissue detection for the three centers, respectively, and 85.19% for musculoskeletal tumor detection. We propose that the high success rate could come from the previously overlooked ability of BOLD rs-fMRI in characterizing the abnormal vascularization, vasomotion and perfusion caused by tumors. Our findings suggest an additional usage of the rs-fMRI for comprehensive presurgical assessment.

AB - Accurate delineation of gliomas from the surrounding normal brain areas helps maximize tumor resection and improves outcome. Blood-oxygen-level-dependent (BOLD) functional MRI (fMRI) has been routinely adopted for presurgical mapping of the surrounding functional areas. For completely utilizing such imaging data, here we show the feasibility of using presurgical fMRI for tumor delineation. In particular, we introduce a novel method dedicated to tumor detection based on independent component analysis (ICA) of resting-state fMRI (rs-fMRI) with automatic tumor component identification. Multi-center rs-fMRI data of 32 glioma patients from three centers, plus the additional proof-of-concept data of 28 patients from the fourth center with non-brain musculoskeletal tumors, are fed into individual ICA with different total number of components (TNCs). The best-fitted tumor-related components derived from the optimized TNCs setting are automatically determined based on a new template-matching algorithm. The success rates are 100%, 100% and 93.75% for glioma tissue detection for the three centers, respectively, and 85.19% for musculoskeletal tumor detection. We propose that the high success rate could come from the previously overlooked ability of BOLD rs-fMRI in characterizing the abnormal vascularization, vasomotion and perfusion caused by tumors. Our findings suggest an additional usage of the rs-fMRI for comprehensive presurgical assessment.

UR - http://www.scopus.com/inward/record.url?scp=85040843168&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040843168&partnerID=8YFLogxK

U2 - 10.1038/s41598-017-18453-0

DO - 10.1038/s41598-017-18453-0

M3 - Article

C2 - 29352123

AN - SCOPUS:85040843168

VL - 8

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

IS - 1

M1 - 1223

ER -