Significant Dimension Reduction of 3D Brain MRI using 3D Convolutional Autoencoders

Hayato Arai, Yusuke Chayama, Hitoshi Iyatomi, Kenichi Oishi

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

Abstract

Content-based image retrieval (CBIR) is a technology designed to retrieve images from a database based on visual features. While the CBIR is highly desired, it has not been applied to clinical neuroradiology, because clinically relevant neuroradiological features are swamped by a huge number of noisy and unrelated voxel information. Thus, effective dimension reduction is the key to successful CBIR. We propose a novel dimensional compression method based on 3D convolutional autoencoders (3D-CAE), which was applied to the ADNI2 3D brain MRI dataset. Our method succeeded in compressing 5 million voxel information to only 150 dimensions, while preserving clinically relevant neuroradiological features. The RMSE per voxel was as low as 8.4%, suggesting a promise of our method toward the application to the CBIR.

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.
Pages5162-5165
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

Image retrieval
Magnetic resonance imaging
Brain
Databases
Technology

ASJC Scopus subject areas

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

Cite this

Arai, H., Chayama, Y., Iyatomi, H., & Oishi, K. (2018). Significant Dimension Reduction of 3D Brain MRI using 3D Convolutional Autoencoders. In 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018 (Vol. 2018-July, pp. 5162-5165). [8513469] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC.2018.8513469

Significant Dimension Reduction of 3D Brain MRI using 3D Convolutional Autoencoders. / Arai, Hayato; Chayama, Yusuke; Iyatomi, Hitoshi; Oishi, Kenichi.

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. 5162-5165 8513469.

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

Arai, H, Chayama, Y, Iyatomi, H & Oishi, K 2018, Significant Dimension Reduction of 3D Brain MRI using 3D Convolutional Autoencoders. in 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018. vol. 2018-July, 8513469, Institute of Electrical and Electronics Engineers Inc., pp. 5162-5165, 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.2018.8513469
Arai H, Chayama Y, Iyatomi H, Oishi K. Significant Dimension Reduction of 3D Brain MRI using 3D Convolutional Autoencoders. 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. 5162-5165. 8513469 https://doi.org/10.1109/EMBC.2018.8513469
Arai, Hayato ; Chayama, Yusuke ; Iyatomi, Hitoshi ; Oishi, Kenichi. / Significant Dimension Reduction of 3D Brain MRI using 3D Convolutional Autoencoders. 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. 5162-5165
@inproceedings{0542538cd66844dca8b6dd87659d025d,
title = "Significant Dimension Reduction of 3D Brain MRI using 3D Convolutional Autoencoders",
abstract = "Content-based image retrieval (CBIR) is a technology designed to retrieve images from a database based on visual features. While the CBIR is highly desired, it has not been applied to clinical neuroradiology, because clinically relevant neuroradiological features are swamped by a huge number of noisy and unrelated voxel information. Thus, effective dimension reduction is the key to successful CBIR. We propose a novel dimensional compression method based on 3D convolutional autoencoders (3D-CAE), which was applied to the ADNI2 3D brain MRI dataset. Our method succeeded in compressing 5 million voxel information to only 150 dimensions, while preserving clinically relevant neuroradiological features. The RMSE per voxel was as low as 8.4{\%}, suggesting a promise of our method toward the application to the CBIR.",
author = "Hayato Arai and Yusuke Chayama and Hitoshi Iyatomi and Kenichi Oishi",
year = "2018",
month = "10",
day = "26",
doi = "10.1109/EMBC.2018.8513469",
language = "English (US)",
volume = "2018-July",
pages = "5162--5165",
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 - Significant Dimension Reduction of 3D Brain MRI using 3D Convolutional Autoencoders

AU - Arai, Hayato

AU - Chayama, Yusuke

AU - Iyatomi, Hitoshi

AU - Oishi, Kenichi

PY - 2018/10/26

Y1 - 2018/10/26

N2 - Content-based image retrieval (CBIR) is a technology designed to retrieve images from a database based on visual features. While the CBIR is highly desired, it has not been applied to clinical neuroradiology, because clinically relevant neuroradiological features are swamped by a huge number of noisy and unrelated voxel information. Thus, effective dimension reduction is the key to successful CBIR. We propose a novel dimensional compression method based on 3D convolutional autoencoders (3D-CAE), which was applied to the ADNI2 3D brain MRI dataset. Our method succeeded in compressing 5 million voxel information to only 150 dimensions, while preserving clinically relevant neuroradiological features. The RMSE per voxel was as low as 8.4%, suggesting a promise of our method toward the application to the CBIR.

AB - Content-based image retrieval (CBIR) is a technology designed to retrieve images from a database based on visual features. While the CBIR is highly desired, it has not been applied to clinical neuroradiology, because clinically relevant neuroradiological features are swamped by a huge number of noisy and unrelated voxel information. Thus, effective dimension reduction is the key to successful CBIR. We propose a novel dimensional compression method based on 3D convolutional autoencoders (3D-CAE), which was applied to the ADNI2 3D brain MRI dataset. Our method succeeded in compressing 5 million voxel information to only 150 dimensions, while preserving clinically relevant neuroradiological features. The RMSE per voxel was as low as 8.4%, suggesting a promise of our method toward the application to the CBIR.

UR - http://www.scopus.com/inward/record.url?scp=85056582612&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056582612&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2018.8513469

DO - 10.1109/EMBC.2018.8513469

M3 - Conference contribution

C2 - 30441502

AN - SCOPUS:85056582612

VL - 2018-July

SP - 5162

EP - 5165

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 -