Eigen Image Recognition of Pulmonary Nodules from Thoracic CT Images by Use of Subspace Method

Gentaro FUKANO; Yoshihiko NAKAMURA; Hotaka TAKIZAWA; Shinji MIZUNO; Shinji YAMAMOTO; Kunio DOI; Shigehiko KATSURAGAWA; Tohru MATSUMOTO; Yukio TATENO; Takeshi IINUMA

doi:10.1093/ietisy/e88-d.6.1273

Eigen Image Recognition of Pulmonary Nodules from Thoracic CT Images by Use of Subspace Method

Gentaro FUKANO, Yoshihiko NAKAMURA, Hotaka TAKIZAWA, Shinji MIZUNO, Shinji YAMAMOTO, Kunio DOI, Shigehiko KATSURAGAWA, Tohru MATSUMOTO, Yukio TATENO, Takeshi IINUMA

Full Text Views

0

Share
Cite this

Summary :

We have proposed a recognition method for pulmonary nodules based on experimentally selected feature values (such as contrast, circularity, etc.) of pathologic candidate regions detected by our Variable N-Quoit (VNQ) filter. In this paper, we propose a new recognition method for pulmonary nodules by use of not experimentally selected feature values, but each CT value itself in a region of interest (ROI) as a feature value. The proposed method has 2 phases: learning and recognition. In the learning phase, first, the pathologic candidate regions are classified into several clusters based on a principal component score. This score is calculated from a set of CT values in the ROI that are regarded as a feature vector, and then eigen vectors and eigen values are calculated for each cluster by application of principal component analysis to the cluster. The eigen vectors (we call them "eigen-images") corresponding to the S-th largest eigen values are utilized as base vectors for subspaces of the clusters in a feature space. In the recognition phase, correlations are measured between the feature vector derived from testing data and the subspace which is spanned by the eigen-images. If the correlation with the nodule subspace is large, the pathologic candidate region is determined to be a nodule, otherwise, it is determined to be a normal organ. In the experiment, first, we decide on the optimal number of subspace dimensions. Then, we demonstrated the robustness of our algorithm by using simulated nodule images.

Publication: IEICE TRANSACTIONS on Information Vol.E88-D No.6 pp.1273-1283

Publication Date: 2005/06/01

Publicized

Online ISSN

DOI: 10.1093/ietisy/e88-d.6.1273

Type of Manuscript: PAPER

Category: Biological Engineering

Cite this

Copy

Gentaro FUKANO, Yoshihiko NAKAMURA, Hotaka TAKIZAWA, Shinji MIZUNO, Shinji YAMAMOTO, Kunio DOI, Shigehiko KATSURAGAWA, Tohru MATSUMOTO, Yukio TATENO, Takeshi IINUMA, "Eigen Image Recognition of Pulmonary Nodules from Thoracic CT Images by Use of Subspace Method" in IEICE TRANSACTIONS on Information, vol. E88-D, no. 6, pp. 1273-1283, June 2005, doi: 10.1093/ietisy/e88-d.6.1273.
Abstract: We have proposed a recognition method for pulmonary nodules based on experimentally selected feature values (such as contrast, circularity, etc.) of pathologic candidate regions detected by our Variable N-Quoit (VNQ) filter. In this paper, we propose a new recognition method for pulmonary nodules by use of not experimentally selected feature values, but each CT value itself in a region of interest (ROI) as a feature value. The proposed method has 2 phases: learning and recognition. In the learning phase, first, the pathologic candidate regions are classified into several clusters based on a principal component score. This score is calculated from a set of CT values in the ROI that are regarded as a feature vector, and then eigen vectors and eigen values are calculated for each cluster by application of principal component analysis to the cluster. The eigen vectors (we call them "eigen-images") corresponding to the S-th largest eigen values are utilized as base vectors for subspaces of the clusters in a feature space. In the recognition phase, correlations are measured between the feature vector derived from testing data and the subspace which is spanned by the eigen-images. If the correlation with the nodule subspace is large, the pathologic candidate region is determined to be a nodule, otherwise, it is determined to be a normal organ. In the experiment, first, we decide on the optimal number of subspace dimensions. Then, we demonstrated the robustness of our algorithm by using simulated nodule images.
URL: https://globals.ieice.org/en_transactions/information/10.1093/ietisy/e88-d.6.1273/_p

Copy

@ARTICLE{e88-d_6_1273,
author={Gentaro FUKANO, Yoshihiko NAKAMURA, Hotaka TAKIZAWA, Shinji MIZUNO, Shinji YAMAMOTO, Kunio DOI, Shigehiko KATSURAGAWA, Tohru MATSUMOTO, Yukio TATENO, Takeshi IINUMA, },
journal={IEICE TRANSACTIONS on Information},
title={Eigen Image Recognition of Pulmonary Nodules from Thoracic CT Images by Use of Subspace Method},
year={2005},
volume={E88-D},
number={6},
pages={1273-1283},
abstract={We have proposed a recognition method for pulmonary nodules based on experimentally selected feature values (such as contrast, circularity, etc.) of pathologic candidate regions detected by our Variable N-Quoit (VNQ) filter. In this paper, we propose a new recognition method for pulmonary nodules by use of not experimentally selected feature values, but each CT value itself in a region of interest (ROI) as a feature value. The proposed method has 2 phases: learning and recognition. In the learning phase, first, the pathologic candidate regions are classified into several clusters based on a principal component score. This score is calculated from a set of CT values in the ROI that are regarded as a feature vector, and then eigen vectors and eigen values are calculated for each cluster by application of principal component analysis to the cluster. The eigen vectors (we call them "eigen-images") corresponding to the S-th largest eigen values are utilized as base vectors for subspaces of the clusters in a feature space. In the recognition phase, correlations are measured between the feature vector derived from testing data and the subspace which is spanned by the eigen-images. If the correlation with the nodule subspace is large, the pathologic candidate region is determined to be a nodule, otherwise, it is determined to be a normal organ. In the experiment, first, we decide on the optimal number of subspace dimensions. Then, we demonstrated the robustness of our algorithm by using simulated nodule images.},
keywords={},
doi={10.1093/ietisy/e88-d.6.1273},
ISSN={},
month={June},}

Copy

TY - JOUR
TI - Eigen Image Recognition of Pulmonary Nodules from Thoracic CT Images by Use of Subspace Method
T2 - IEICE TRANSACTIONS on Information
SP - 1273
EP - 1283
AU - Gentaro FUKANO
AU - Yoshihiko NAKAMURA
AU - Hotaka TAKIZAWA
AU - Shinji MIZUNO
AU - Shinji YAMAMOTO
AU - Kunio DOI
AU - Shigehiko KATSURAGAWA
AU - Tohru MATSUMOTO
AU - Yukio TATENO
AU - Takeshi IINUMA
PY - 2005
DO - 10.1093/ietisy/e88-d.6.1273
JO - IEICE TRANSACTIONS on Information
SN -
VL - E88-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2005
AB - We have proposed a recognition method for pulmonary nodules based on experimentally selected feature values (such as contrast, circularity, etc.) of pathologic candidate regions detected by our Variable N-Quoit (VNQ) filter. In this paper, we propose a new recognition method for pulmonary nodules by use of not experimentally selected feature values, but each CT value itself in a region of interest (ROI) as a feature value. The proposed method has 2 phases: learning and recognition. In the learning phase, first, the pathologic candidate regions are classified into several clusters based on a principal component score. This score is calculated from a set of CT values in the ROI that are regarded as a feature vector, and then eigen vectors and eigen values are calculated for each cluster by application of principal component analysis to the cluster. The eigen vectors (we call them "eigen-images") corresponding to the S-th largest eigen values are utilized as base vectors for subspaces of the clusters in a feature space. In the recognition phase, correlations are measured between the feature vector derived from testing data and the subspace which is spanned by the eigen-images. If the correlation with the nodule subspace is large, the pathologic candidate region is determined to be a nodule, otherwise, it is determined to be a normal organ. In the experiment, first, we decide on the optimal number of subspace dimensions. Then, we demonstrated the robustness of our algorithm by using simulated nodule images.
ER -