Simultaneous brain tumor segmentation and molecular profiling using deep learning and T2w magnetic resonance images

Chandan Ganesh Bangalore Yogananda; Bhavya R. Shah; Fang F. Yu; Sahil S. Nalawade; James Holcomb; Divya Reddy; Benjamin C. Wagner; Marco C. Pinho; Bruce Mickey; Toral R. Patel; Baowei Fei; Ananth J. Madhuranthakam; Joseph A. Maldjian

doi:10.1016/B978-0-323-91171-9.00005-3

Simultaneous brain tumor segmentation and molecular profiling using deep learning and T2w magnetic resonance images

Chandan Ganesh Bangalore Yogananda, Bhavya R. Shah, Fang F. Yu, Sahil S. Nalawade, James Holcomb, Divya Reddy, Benjamin C. Wagner, Marco C. Pinho, Bruce Mickey, Toral R. Patel, Baowei Fei, Ananth J. Madhuranthakam, Joseph A. Maldjian

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

Abstract

Gliomas demonstrate diverse imaging features, variable response to therapy, and differences in prognosis. This is largely a function of genetic heterogeneity. Several key mutations serve as therapeutic and prognostic markers such as isocitrate dehydrogenase (IDH) mutation status, O6-methyl guanine-DNA methyltransferase (MGMT) promoter status, and 1p/19q co-deletion status. Currently, the gold standard for molecular marker determination requires tissue from either an invasive brain biopsy or surgical resection. Here we describe our work in developing highly accurate simultaneous deep learning segmentation and classification approaches for noninvasive profiling of molecular markers using T2-weighted magnetic resonance images only.

Original language	English (US)
Title of host publication	Brain Tumor MRI Image Segmentation Using Deep Learning Techniques
Publisher	Elsevier
Pages	57-79
Number of pages	23
ISBN (Electronic)	9780323911719
ISBN (Print)	9780323983952
DOIs	https://doi.org/10.1016/B978-0-323-91171-9.00005-3
State	Published - Jan 1 2021

Keywords

1p/19q
Convolutional Neural Networks (CNN)
Deep learning
Dense-U-net
Glioma
Isocitrate dehydrogenase
Magnetic resonance imaging
Methyl guanine-DNA methyltransferase

ASJC Scopus subject areas

General Biochemistry, Genetics and Molecular Biology

Access to Document

10.1016/B978-0-323-91171-9.00005-3

Cite this

Yogananda, C. G. B., Shah, B. R., Yu, F. F., Nalawade, S. S., Holcomb, J., Reddy, D., Wagner, B. C., Pinho, M. C., Mickey, B., Patel, T. R., Fei, B., Madhuranthakam, A. J., & Maldjian, J. A. (2021). Simultaneous brain tumor segmentation and molecular profiling using deep learning and T2w magnetic resonance images. In Brain Tumor MRI Image Segmentation Using Deep Learning Techniques (pp. 57-79). Elsevier. https://doi.org/10.1016/B978-0-323-91171-9.00005-3

Yogananda, CGB , Shah, BR , Yu, FF, Nalawade, SS, Holcomb, J, Reddy, D, Wagner, BC, Pinho, MC , Mickey, B , Patel, TR , Fei, B , Madhuranthakam, AJ & Maldjian, JA 2021, Simultaneous brain tumor segmentation and molecular profiling using deep learning and T2w magnetic resonance images. in Brain Tumor MRI Image Segmentation Using Deep Learning Techniques. Elsevier, pp. 57-79. https://doi.org/10.1016/B978-0-323-91171-9.00005-3

@inbook{23d0120225a54c40b94e4df0f5858c8d,

title = "Simultaneous brain tumor segmentation and molecular profiling using deep learning and T2w magnetic resonance images",

abstract = "Gliomas demonstrate diverse imaging features, variable response to therapy, and differences in prognosis. This is largely a function of genetic heterogeneity. Several key mutations serve as therapeutic and prognostic markers such as isocitrate dehydrogenase (IDH) mutation status, O6-methyl guanine-DNA methyltransferase (MGMT) promoter status, and 1p/19q co-deletion status. Currently, the gold standard for molecular marker determination requires tissue from either an invasive brain biopsy or surgical resection. Here we describe our work in developing highly accurate simultaneous deep learning segmentation and classification approaches for noninvasive profiling of molecular markers using T2-weighted magnetic resonance images only.",

keywords = "1p/19q, Convolutional Neural Networks (CNN), Deep learning, Dense-U-net, Glioma, Isocitrate dehydrogenase, Magnetic resonance imaging, Methyl guanine-DNA methyltransferase",

author = "Yogananda, {Chandan Ganesh Bangalore} and Shah, {Bhavya R.} and Yu, {Fang F.} and Nalawade, {Sahil S.} and James Holcomb and Divya Reddy and Wagner, {Benjamin C.} and Pinho, {Marco C.} and Bruce Mickey and Patel, {Toral R.} and Baowei Fei and Madhuranthakam, {Ananth J.} and Maldjian, {Joseph A.}",

year = "2021",

month = jan,

day = "1",

doi = "10.1016/B978-0-323-91171-9.00005-3",

language = "English (US)",

isbn = "9780323983952",

pages = "57--79",

booktitle = "Brain Tumor MRI Image Segmentation Using Deep Learning Techniques",

publisher = "Elsevier",

}

TY - CHAP

T1 - Simultaneous brain tumor segmentation and molecular profiling using deep learning and T2w magnetic resonance images

AU - Yogananda, Chandan Ganesh Bangalore

AU - Shah, Bhavya R.

AU - Yu, Fang F.

AU - Nalawade, Sahil S.

AU - Holcomb, James

AU - Reddy, Divya

AU - Wagner, Benjamin C.

AU - Pinho, Marco C.

AU - Mickey, Bruce

AU - Patel, Toral R.

AU - Fei, Baowei

AU - Madhuranthakam, Ananth J.

AU - Maldjian, Joseph A.

PY - 2021/1/1

Y1 - 2021/1/1

N2 - Gliomas demonstrate diverse imaging features, variable response to therapy, and differences in prognosis. This is largely a function of genetic heterogeneity. Several key mutations serve as therapeutic and prognostic markers such as isocitrate dehydrogenase (IDH) mutation status, O6-methyl guanine-DNA methyltransferase (MGMT) promoter status, and 1p/19q co-deletion status. Currently, the gold standard for molecular marker determination requires tissue from either an invasive brain biopsy or surgical resection. Here we describe our work in developing highly accurate simultaneous deep learning segmentation and classification approaches for noninvasive profiling of molecular markers using T2-weighted magnetic resonance images only.

AB - Gliomas demonstrate diverse imaging features, variable response to therapy, and differences in prognosis. This is largely a function of genetic heterogeneity. Several key mutations serve as therapeutic and prognostic markers such as isocitrate dehydrogenase (IDH) mutation status, O6-methyl guanine-DNA methyltransferase (MGMT) promoter status, and 1p/19q co-deletion status. Currently, the gold standard for molecular marker determination requires tissue from either an invasive brain biopsy or surgical resection. Here we describe our work in developing highly accurate simultaneous deep learning segmentation and classification approaches for noninvasive profiling of molecular markers using T2-weighted magnetic resonance images only.

KW - 1p/19q

KW - Convolutional Neural Networks (CNN)

KW - Deep learning

KW - Dense-U-net

KW - Glioma

KW - Isocitrate dehydrogenase

KW - Magnetic resonance imaging

KW - Methyl guanine-DNA methyltransferase

UR - http://www.scopus.com/inward/record.url?scp=85130651431&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85130651431&partnerID=8YFLogxK

U2 - 10.1016/B978-0-323-91171-9.00005-3

DO - 10.1016/B978-0-323-91171-9.00005-3

M3 - Chapter

AN - SCOPUS:85130651431

SN - 9780323983952

SP - 57

EP - 79

BT - Brain Tumor MRI Image Segmentation Using Deep Learning Techniques

PB - Elsevier

ER -

Simultaneous brain tumor segmentation and molecular profiling using deep learning and T2w magnetic resonance images

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this