A semi-learning algorithm for noise rejection

An fNIRS study on ADHD children

Stephanie Sutoko, Tsukasa Funane, Takusige Katura, Hiroki Satou, Masashi Kiguchi, Atsushi Maki, Yukifumi Monden, Masako Nagashima, Takanori Yamagata, Ippeita Dan

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

Abstract

In pediatrics studies, the quality of functional near infrared spectroscopy (fNIRS) signals is often reduced by motion artifacts. These artifacts likely mislead brain functionality analysis, causing false discoveries. While noise correction methods and their performance have been investigated, these methods require several parameter assumptions that apparently result in noise overfitting. In contrast, the rejection of noisy signals serves as a preferable method because it maintains the originality of the signal waveform. Here, we describe a semi-learning algorithm to detect and eliminate noisy signals. The algorithm dynamically adjusts noise detection according to the predetermined noise criteria, which are spikes, unusual activation values (averaged amplitude signals within the brain activation period), and high activation variances (among trials). Criteria were sequentially organized in the algorithm and orderly assessed signals based on each criterion. By initially setting an acceptable rejection rate, particular criteria causing excessive data rejections are neglected, whereas others with tolerable rejections practically eliminate noises. fNIRS data measured during the attention response paradigm (oddball task) in children with attention deficit/hyperactivity disorder (ADHD) were utilized to evaluate and optimize the algorithm's performance. This algorithm successfully substituted the visual noise identification done in the previous studies and consistently found significantly lower activation of the right prefrontal and parietal cortices in ADHD patients than in typical developing children. Thus, we conclude that the semi-learning algorithm confers more objective and standardized judgment for noise rejection and presents a promising alternative to visual noise rejection.

Original languageEnglish
Title of host publicationOptical Tomography and Spectroscopy of Tissue XII
EditorsRobert R. Alfano, Eva Marie Sevick-Muraca, Bruce J. Tromberg, Arjun G. Yodh
PublisherSPIE
Volume10059
ISBN (Electronic)9781510605596
DOIs
Publication statusPublished - 2017 Jan 1
Externally publishedYes
EventOptical Tomography and Spectroscopy of Tissue XII - San Francisco, United States
Duration: 2017 Jan 302017 Feb 1

Other

OtherOptical Tomography and Spectroscopy of Tissue XII
CountryUnited States
CitySan Francisco
Period17/1/3017/2/1

Fingerprint

Near infrared spectroscopy
rejection
Learning algorithms
learning
Chemical activation
infrared spectroscopy
disorders
Brain
activation
Pediatrics
brain
artifacts
cortexes
spikes
waveforms

Keywords

  • ADHD
  • Controlled rejection
  • FNIRS
  • Motion artifact
  • Personalized evaluation
  • Semi-learning algorithm

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Sutoko, S., Funane, T., Katura, T., Satou, H., Kiguchi, M., Maki, A., ... Dan, I. (2017). A semi-learning algorithm for noise rejection: An fNIRS study on ADHD children. In R. R. Alfano, E. M. Sevick-Muraca, B. J. Tromberg, & A. G. Yodh (Eds.), Optical Tomography and Spectroscopy of Tissue XII (Vol. 10059). [1005914] SPIE. https://doi.org/10.1117/12.2249742

A semi-learning algorithm for noise rejection : An fNIRS study on ADHD children. / Sutoko, Stephanie; Funane, Tsukasa; Katura, Takusige; Satou, Hiroki; Kiguchi, Masashi; Maki, Atsushi; Monden, Yukifumi; Nagashima, Masako; Yamagata, Takanori; Dan, Ippeita.

Optical Tomography and Spectroscopy of Tissue XII. ed. / Robert R. Alfano; Eva Marie Sevick-Muraca; Bruce J. Tromberg; Arjun G. Yodh. Vol. 10059 SPIE, 2017. 1005914.

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

Sutoko, S, Funane, T, Katura, T, Satou, H, Kiguchi, M, Maki, A, Monden, Y, Nagashima, M, Yamagata, T & Dan, I 2017, A semi-learning algorithm for noise rejection: An fNIRS study on ADHD children. in RR Alfano, EM Sevick-Muraca, BJ Tromberg & AG Yodh (eds), Optical Tomography and Spectroscopy of Tissue XII. vol. 10059, 1005914, SPIE, Optical Tomography and Spectroscopy of Tissue XII, San Francisco, United States, 17/1/30. https://doi.org/10.1117/12.2249742
Sutoko S, Funane T, Katura T, Satou H, Kiguchi M, Maki A et al. A semi-learning algorithm for noise rejection: An fNIRS study on ADHD children. In Alfano RR, Sevick-Muraca EM, Tromberg BJ, Yodh AG, editors, Optical Tomography and Spectroscopy of Tissue XII. Vol. 10059. SPIE. 2017. 1005914 https://doi.org/10.1117/12.2249742
Sutoko, Stephanie ; Funane, Tsukasa ; Katura, Takusige ; Satou, Hiroki ; Kiguchi, Masashi ; Maki, Atsushi ; Monden, Yukifumi ; Nagashima, Masako ; Yamagata, Takanori ; Dan, Ippeita. / A semi-learning algorithm for noise rejection : An fNIRS study on ADHD children. Optical Tomography and Spectroscopy of Tissue XII. editor / Robert R. Alfano ; Eva Marie Sevick-Muraca ; Bruce J. Tromberg ; Arjun G. Yodh. Vol. 10059 SPIE, 2017.
@inproceedings{783fc123cd7042c5bdd49d6c24de3ff4,
title = "A semi-learning algorithm for noise rejection: An fNIRS study on ADHD children",
abstract = "In pediatrics studies, the quality of functional near infrared spectroscopy (fNIRS) signals is often reduced by motion artifacts. These artifacts likely mislead brain functionality analysis, causing false discoveries. While noise correction methods and their performance have been investigated, these methods require several parameter assumptions that apparently result in noise overfitting. In contrast, the rejection of noisy signals serves as a preferable method because it maintains the originality of the signal waveform. Here, we describe a semi-learning algorithm to detect and eliminate noisy signals. The algorithm dynamically adjusts noise detection according to the predetermined noise criteria, which are spikes, unusual activation values (averaged amplitude signals within the brain activation period), and high activation variances (among trials). Criteria were sequentially organized in the algorithm and orderly assessed signals based on each criterion. By initially setting an acceptable rejection rate, particular criteria causing excessive data rejections are neglected, whereas others with tolerable rejections practically eliminate noises. fNIRS data measured during the attention response paradigm (oddball task) in children with attention deficit/hyperactivity disorder (ADHD) were utilized to evaluate and optimize the algorithm's performance. This algorithm successfully substituted the visual noise identification done in the previous studies and consistently found significantly lower activation of the right prefrontal and parietal cortices in ADHD patients than in typical developing children. Thus, we conclude that the semi-learning algorithm confers more objective and standardized judgment for noise rejection and presents a promising alternative to visual noise rejection.",
keywords = "ADHD, Controlled rejection, FNIRS, Motion artifact, Personalized evaluation, Semi-learning algorithm",
author = "Stephanie Sutoko and Tsukasa Funane and Takusige Katura and Hiroki Satou and Masashi Kiguchi and Atsushi Maki and Yukifumi Monden and Masako Nagashima and Takanori Yamagata and Ippeita Dan",
year = "2017",
month = "1",
day = "1",
doi = "10.1117/12.2249742",
language = "English",
volume = "10059",
editor = "Alfano, {Robert R.} and Sevick-Muraca, {Eva Marie} and Tromberg, {Bruce J.} and Yodh, {Arjun G.}",
booktitle = "Optical Tomography and Spectroscopy of Tissue XII",
publisher = "SPIE",

}

TY - GEN

T1 - A semi-learning algorithm for noise rejection

T2 - An fNIRS study on ADHD children

AU - Sutoko, Stephanie

AU - Funane, Tsukasa

AU - Katura, Takusige

AU - Satou, Hiroki

AU - Kiguchi, Masashi

AU - Maki, Atsushi

AU - Monden, Yukifumi

AU - Nagashima, Masako

AU - Yamagata, Takanori

AU - Dan, Ippeita

PY - 2017/1/1

Y1 - 2017/1/1

N2 - In pediatrics studies, the quality of functional near infrared spectroscopy (fNIRS) signals is often reduced by motion artifacts. These artifacts likely mislead brain functionality analysis, causing false discoveries. While noise correction methods and their performance have been investigated, these methods require several parameter assumptions that apparently result in noise overfitting. In contrast, the rejection of noisy signals serves as a preferable method because it maintains the originality of the signal waveform. Here, we describe a semi-learning algorithm to detect and eliminate noisy signals. The algorithm dynamically adjusts noise detection according to the predetermined noise criteria, which are spikes, unusual activation values (averaged amplitude signals within the brain activation period), and high activation variances (among trials). Criteria were sequentially organized in the algorithm and orderly assessed signals based on each criterion. By initially setting an acceptable rejection rate, particular criteria causing excessive data rejections are neglected, whereas others with tolerable rejections practically eliminate noises. fNIRS data measured during the attention response paradigm (oddball task) in children with attention deficit/hyperactivity disorder (ADHD) were utilized to evaluate and optimize the algorithm's performance. This algorithm successfully substituted the visual noise identification done in the previous studies and consistently found significantly lower activation of the right prefrontal and parietal cortices in ADHD patients than in typical developing children. Thus, we conclude that the semi-learning algorithm confers more objective and standardized judgment for noise rejection and presents a promising alternative to visual noise rejection.

AB - In pediatrics studies, the quality of functional near infrared spectroscopy (fNIRS) signals is often reduced by motion artifacts. These artifacts likely mislead brain functionality analysis, causing false discoveries. While noise correction methods and their performance have been investigated, these methods require several parameter assumptions that apparently result in noise overfitting. In contrast, the rejection of noisy signals serves as a preferable method because it maintains the originality of the signal waveform. Here, we describe a semi-learning algorithm to detect and eliminate noisy signals. The algorithm dynamically adjusts noise detection according to the predetermined noise criteria, which are spikes, unusual activation values (averaged amplitude signals within the brain activation period), and high activation variances (among trials). Criteria were sequentially organized in the algorithm and orderly assessed signals based on each criterion. By initially setting an acceptable rejection rate, particular criteria causing excessive data rejections are neglected, whereas others with tolerable rejections practically eliminate noises. fNIRS data measured during the attention response paradigm (oddball task) in children with attention deficit/hyperactivity disorder (ADHD) were utilized to evaluate and optimize the algorithm's performance. This algorithm successfully substituted the visual noise identification done in the previous studies and consistently found significantly lower activation of the right prefrontal and parietal cortices in ADHD patients than in typical developing children. Thus, we conclude that the semi-learning algorithm confers more objective and standardized judgment for noise rejection and presents a promising alternative to visual noise rejection.

KW - ADHD

KW - Controlled rejection

KW - FNIRS

KW - Motion artifact

KW - Personalized evaluation

KW - Semi-learning algorithm

UR - http://www.scopus.com/inward/record.url?scp=85019225880&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019225880&partnerID=8YFLogxK

U2 - 10.1117/12.2249742

DO - 10.1117/12.2249742

M3 - Conference contribution

VL - 10059

BT - Optical Tomography and Spectroscopy of Tissue XII

A2 - Alfano, Robert R.

A2 - Sevick-Muraca, Eva Marie

A2 - Tromberg, Bruce J.

A2 - Yodh, Arjun G.

PB - SPIE

ER -