Share Email Print
cover

Proceedings Paper

Classification of lung area using multidetector-row CT images
Author(s): Tsutomu Mukaibo; Yoshiki Kawata; Noboru Niki; Hironobu Ohmatsu; Ryutaro Kakinuma; Kenji Eguchi; Masahiro Kaneko; Noriyuki Moriyama
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Recently, we can get high quality images in the short time for the progress of X-ray CT scanner. And the three dimensional (3-D) analysis of pulmonary organs using multidetector-row CT (MDCT) images, is expected. This paper presents a method for classifying lung area into each lobe using pulmonary MDCT images of the whole lung area. It is possible to recognize the position of nodule by classifying lung area into these lobes. The structure of lungs differs on the right one and left one. The right lung is divided into three domains by major fissure and minor fissure. And, the left lung is divided into two domains by major fissure. Watching MDCT images carefully, we find that the surroundings of fissures have few blood vessels. Therefore, lung area is classified by extraction of the domain that the distance from pulmonary blood vessels is large and connective search of these extracted domains. These extraction and search are realized by 3-D weighted Hough transform.

Paper Details

Date Published: 9 May 2002
PDF: 9 pages
Proc. SPIE 4684, Medical Imaging 2002: Image Processing, (9 May 2002); doi: 10.1117/12.467089
Show Author Affiliations
Tsutomu Mukaibo, Univ. of Tokushima (Japan)
Yoshiki Kawata, Univ. of Tokushima (Japan)
Noboru Niki, Univ. of Tokushima (Japan)
Hironobu Ohmatsu, National Cancer Ctr. Hospital East (Japan)
Ryutaro Kakinuma, National Cancer Ctr. Hospital East (Japan)
Kenji Eguchi, National Shikoku Cancer Ctr. Hospital (Japan)
Masahiro Kaneko, National Cancer Ctr. Hospital (Japan)
Noriyuki Moriyama, National Cancer Ctr. Hospital East (Japan)


Published in SPIE Proceedings Vol. 4684:
Medical Imaging 2002: Image Processing
Milan Sonka; J. Michael Fitzpatrick, Editor(s)

© SPIE. Terms of Use
Back to Top