A Deep Unsupervised Learning Approach Toward MTBI Identification Using Diffusion MRI

Shervin Minaee, Yao Wang, Anna Choromanska, Sohae Chung, Xiuyuan Wang, Els Fieremans, Steven Flanagan, Joseph Rath, Yvonne W. Lui

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

Abstract

Mild traumatic brain injury is a growing public health problem with an estimated incidence of over 1.7 million people annually in US. Diagnosis is based on clinical history and symptoms, and accurate, concrete measures of injury are lacking. This work aims to directly use diffusion MR images obtained within one month of trauma to detect injury, by incorporating deep learning techniques. To overcome the challenge due to limited training data, we describe each brain region using the bag of word representation, which specifies the distribution of representative patch patterns. We apply a convolutional auto-encoder to learn the patch-level features, from overlapping image patches extracted from the MR images, to learn features from diffusion MR images of brain using an unsupervised approach. Our experimental results show that the bag of word representation using patch level features learnt by the auto encoder provides similar performance as that using the raw patch patterns, both significantly outperform earlier work relying on the mean values of MR metrics in selected brain regions.

Original languageEnglish (US)
Title of host publication40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1267-1270
Number of pages4
Volume2018-July
ISBN (Electronic)9781538636466
DOIs
StatePublished - Oct 26 2018
Event40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018 - Honolulu, United States
Duration: Jul 18 2018Jul 21 2018

Other

Other40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018
CountryUnited States
CityHonolulu
Period7/18/187/21/18

Fingerprint

Diffusion Magnetic Resonance Imaging
Unsupervised learning
Magnetic resonance imaging
Brain
Learning
Wounds and Injuries
Brain Concussion
Public health
Medical problems
Public Health
Incidence

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Cite this

Minaee, S., Wang, Y., Choromanska, A., Chung, S., Wang, X., Fieremans, E., ... Lui, Y. W. (2018). A Deep Unsupervised Learning Approach Toward MTBI Identification Using Diffusion MRI. In 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018 (Vol. 2018-July, pp. 1267-1270). [8512556] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC.2018.8512556

A Deep Unsupervised Learning Approach Toward MTBI Identification Using Diffusion MRI. / Minaee, Shervin; Wang, Yao; Choromanska, Anna; Chung, Sohae; Wang, Xiuyuan; Fieremans, Els; Flanagan, Steven; Rath, Joseph; Lui, Yvonne W.

40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018. Vol. 2018-July Institute of Electrical and Electronics Engineers Inc., 2018. p. 1267-1270 8512556.

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

Minaee, S, Wang, Y, Choromanska, A, Chung, S, Wang, X, Fieremans, E, Flanagan, S, Rath, J & Lui, YW 2018, A Deep Unsupervised Learning Approach Toward MTBI Identification Using Diffusion MRI. in 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018. vol. 2018-July, 8512556, Institute of Electrical and Electronics Engineers Inc., pp. 1267-1270, 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018, Honolulu, United States, 7/18/18. https://doi.org/10.1109/EMBC.2018.8512556
Minaee S, Wang Y, Choromanska A, Chung S, Wang X, Fieremans E et al. A Deep Unsupervised Learning Approach Toward MTBI Identification Using Diffusion MRI. In 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018. Vol. 2018-July. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1267-1270. 8512556 https://doi.org/10.1109/EMBC.2018.8512556
Minaee, Shervin ; Wang, Yao ; Choromanska, Anna ; Chung, Sohae ; Wang, Xiuyuan ; Fieremans, Els ; Flanagan, Steven ; Rath, Joseph ; Lui, Yvonne W. / A Deep Unsupervised Learning Approach Toward MTBI Identification Using Diffusion MRI. 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018. Vol. 2018-July Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1267-1270
@inproceedings{84625669be634490acef4cdcb406203d,
title = "A Deep Unsupervised Learning Approach Toward MTBI Identification Using Diffusion MRI",
abstract = "Mild traumatic brain injury is a growing public health problem with an estimated incidence of over 1.7 million people annually in US. Diagnosis is based on clinical history and symptoms, and accurate, concrete measures of injury are lacking. This work aims to directly use diffusion MR images obtained within one month of trauma to detect injury, by incorporating deep learning techniques. To overcome the challenge due to limited training data, we describe each brain region using the bag of word representation, which specifies the distribution of representative patch patterns. We apply a convolutional auto-encoder to learn the patch-level features, from overlapping image patches extracted from the MR images, to learn features from diffusion MR images of brain using an unsupervised approach. Our experimental results show that the bag of word representation using patch level features learnt by the auto encoder provides similar performance as that using the raw patch patterns, both significantly outperform earlier work relying on the mean values of MR metrics in selected brain regions.",
author = "Shervin Minaee and Yao Wang and Anna Choromanska and Sohae Chung and Xiuyuan Wang and Els Fieremans and Steven Flanagan and Joseph Rath and Lui, {Yvonne W.}",
year = "2018",
month = "10",
day = "26",
doi = "10.1109/EMBC.2018.8512556",
language = "English (US)",
volume = "2018-July",
pages = "1267--1270",
booktitle = "40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - A Deep Unsupervised Learning Approach Toward MTBI Identification Using Diffusion MRI

AU - Minaee, Shervin

AU - Wang, Yao

AU - Choromanska, Anna

AU - Chung, Sohae

AU - Wang, Xiuyuan

AU - Fieremans, Els

AU - Flanagan, Steven

AU - Rath, Joseph

AU - Lui, Yvonne W.

PY - 2018/10/26

Y1 - 2018/10/26

N2 - Mild traumatic brain injury is a growing public health problem with an estimated incidence of over 1.7 million people annually in US. Diagnosis is based on clinical history and symptoms, and accurate, concrete measures of injury are lacking. This work aims to directly use diffusion MR images obtained within one month of trauma to detect injury, by incorporating deep learning techniques. To overcome the challenge due to limited training data, we describe each brain region using the bag of word representation, which specifies the distribution of representative patch patterns. We apply a convolutional auto-encoder to learn the patch-level features, from overlapping image patches extracted from the MR images, to learn features from diffusion MR images of brain using an unsupervised approach. Our experimental results show that the bag of word representation using patch level features learnt by the auto encoder provides similar performance as that using the raw patch patterns, both significantly outperform earlier work relying on the mean values of MR metrics in selected brain regions.

AB - Mild traumatic brain injury is a growing public health problem with an estimated incidence of over 1.7 million people annually in US. Diagnosis is based on clinical history and symptoms, and accurate, concrete measures of injury are lacking. This work aims to directly use diffusion MR images obtained within one month of trauma to detect injury, by incorporating deep learning techniques. To overcome the challenge due to limited training data, we describe each brain region using the bag of word representation, which specifies the distribution of representative patch patterns. We apply a convolutional auto-encoder to learn the patch-level features, from overlapping image patches extracted from the MR images, to learn features from diffusion MR images of brain using an unsupervised approach. Our experimental results show that the bag of word representation using patch level features learnt by the auto encoder provides similar performance as that using the raw patch patterns, both significantly outperform earlier work relying on the mean values of MR metrics in selected brain regions.

UR - http://www.scopus.com/inward/record.url?scp=85056643521&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056643521&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2018.8512556

DO - 10.1109/EMBC.2018.8512556

M3 - Conference contribution

VL - 2018-July

SP - 1267

EP - 1270

BT - 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -