Multiple k-Nearest Neighbor Classifier and Its Application to Tissue Characterization of Coronary Plaque

Eiji UCHINO; Ryosuke KUBOTA; Takanori KOGA; Hideaki MISAWA; Noriaki SUETAKE

doi:10.1587/transinf.2015EDP7351

Multiple k-Nearest Neighbor Classifier and Its Application to Tissue Characterization of Coronary Plaque

Eiji UCHINO, Ryosuke KUBOTA, Takanori KOGA, Hideaki MISAWA, Noriaki SUETAKE

Full Text Views

0

Cite this

Summary :

In this paper we propose a novel classification method for the multiple k-nearest neighbor (MkNN) classifier and show its practical application to medical image processing. The proposed method performs fine classification when a pair of the spatial coordinate of the observation data in the observation space and its corresponding feature vector in the feature space is provided. The proposed MkNN classifier uses the continuity of the distribution of features of the same class not only in the feature space but also in the observation space. In order to validate the performance of the present method, it is applied to the tissue characterization problem of coronary plaque. The quantitative and qualitative validity of the proposed MkNN classifier have been confirmed by actual experiments.

Publication: IEICE TRANSACTIONS on Information Vol.E99-D No.7 pp.1920-1927

Publication Date: 2016/07/01

Publicized: 2016/04/15

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2015EDP7351

Type of Manuscript: PAPER

Category: Biological Engineering

Authors

Eiji UCHINO
  Yamaguchi University,Fuzzy Logic Systems Institute (FLSI)
Ryosuke KUBOTA
  Ube College
Takanori KOGA
  Tokuyama College
Hideaki MISAWA
  Ube College
Noriaki SUETAKE
  Yamaguchi University

Keyword

acute coronary syndromes (ACS), coronary plaque tissue characterization, intravascular ultrasound (IVUS) method, multiple k-nearest neighbor (MkNN) classifier

Cite this

Copy

Eiji UCHINO, Ryosuke KUBOTA, Takanori KOGA, Hideaki MISAWA, Noriaki SUETAKE, "Multiple k-Nearest Neighbor Classifier and Its Application to Tissue Characterization of Coronary Plaque" in IEICE TRANSACTIONS on Information, vol. E99-D, no. 7, pp. 1920-1927, July 2016, doi: 10.1587/transinf.2015EDP7351.
Abstract: In this paper we propose a novel classification method for the multiple k-nearest neighbor (MkNN) classifier and show its practical application to medical image processing. The proposed method performs fine classification when a pair of the spatial coordinate of the observation data in the observation space and its corresponding feature vector in the feature space is provided. The proposed MkNN classifier uses the continuity of the distribution of features of the same class not only in the feature space but also in the observation space. In order to validate the performance of the present method, it is applied to the tissue characterization problem of coronary plaque. The quantitative and qualitative validity of the proposed MkNN classifier have been confirmed by actual experiments.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2015EDP7351/_p

Copy

@ARTICLE{e99-d_7_1920,
author={Eiji UCHINO, Ryosuke KUBOTA, Takanori KOGA, Hideaki MISAWA, Noriaki SUETAKE, },
journal={IEICE TRANSACTIONS on Information},
title={Multiple k-Nearest Neighbor Classifier and Its Application to Tissue Characterization of Coronary Plaque},
year={2016},
volume={E99-D},
number={7},
pages={1920-1927},
abstract={In this paper we propose a novel classification method for the multiple k-nearest neighbor (MkNN) classifier and show its practical application to medical image processing. The proposed method performs fine classification when a pair of the spatial coordinate of the observation data in the observation space and its corresponding feature vector in the feature space is provided. The proposed MkNN classifier uses the continuity of the distribution of features of the same class not only in the feature space but also in the observation space. In order to validate the performance of the present method, it is applied to the tissue characterization problem of coronary plaque. The quantitative and qualitative validity of the proposed MkNN classifier have been confirmed by actual experiments.},
keywords={},
doi={10.1587/transinf.2015EDP7351},
ISSN={1745-1361},
month={July},}

Copy

TY - JOUR
TI - Multiple k-Nearest Neighbor Classifier and Its Application to Tissue Characterization of Coronary Plaque
T2 - IEICE TRANSACTIONS on Information
SP - 1920
EP - 1927
AU - Eiji UCHINO
AU - Ryosuke KUBOTA
AU - Takanori KOGA
AU - Hideaki MISAWA
AU - Noriaki SUETAKE
PY - 2016
DO - 10.1587/transinf.2015EDP7351
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2016
AB - In this paper we propose a novel classification method for the multiple k-nearest neighbor (MkNN) classifier and show its practical application to medical image processing. The proposed method performs fine classification when a pair of the spatial coordinate of the observation data in the observation space and its corresponding feature vector in the feature space is provided. The proposed MkNN classifier uses the continuity of the distribution of features of the same class not only in the feature space but also in the observation space. In order to validate the performance of the present method, it is applied to the tissue characterization problem of coronary plaque. The quantitative and qualitative validity of the proposed MkNN classifier have been confirmed by actual experiments.
ER -