A segmentation method for lung nodule image sequences based on superpixels and density-based spatial clustering of applications with noise

Wei Zhang, Xiaolong Zhang, Juanjuan Zhao, Yan Qiang, Qi Tian, Xiaoxian Tang

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

The fast and accurate segmentation of lung nodule image sequences is the basis of subsequent processing and diagnostic analyses. However, previous research investigating nodule segmentation algorithms cannot entirely segment cavitary nodules, and the segmentation of juxta-vascular nodules is inaccurate and inefficient. To solve these problems, we propose a new method for the segmentation of lung nodule image sequences based on superpixels and density-based spatial clustering of applications with noise (DBSCAN). First, our method uses three-dimensional computed tomography image features of the average intensity projection combined with multi-scale dot enhancement for preprocessing. Hexagonal clustering and morphological optimized sequential linear iterative clustering (HMSLIC) for sequence image oversegmentation is then proposed to obtain superpixel blocks. The adaptive weight coefficient is then constructed to calculate the distance required between superpixels to achieve precise lung nodules positioning and to obtain the subsequent clustering starting block. Moreover, by fitting the distance and detecting the change in slope, an accurate clustering threshold is obtained. Thereafter, a fast DBSCAN superpixel sequence clustering algorithm, which is optimized by the strategy of only clustering the lung nodules and adaptive threshold, is then used to obtain lung nodule mask sequences. Finally, the lung nodule image sequences are obtained. The experimental results show that our method rapidly, completely and accurately segments various types of lung nodule image sequences.

Original languageEnglish (US)
Article numbere0184290
JournalPloS one
Volume12
Issue number9
DOIs
StatePublished - Sep 1 2017

Fingerprint

Cluster Analysis
Noise
lungs
Lung
Clustering algorithms
Tomography
Masks
Processing
methodology
computed tomography
blood vessels
Blood Vessels
Weights and Measures
Research

All Science Journal Classification (ASJC) codes

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

@article{c7539d635abe44f7970020250cc6ad65,
title = "A segmentation method for lung nodule image sequences based on superpixels and density-based spatial clustering of applications with noise",
abstract = "The fast and accurate segmentation of lung nodule image sequences is the basis of subsequent processing and diagnostic analyses. However, previous research investigating nodule segmentation algorithms cannot entirely segment cavitary nodules, and the segmentation of juxta-vascular nodules is inaccurate and inefficient. To solve these problems, we propose a new method for the segmentation of lung nodule image sequences based on superpixels and density-based spatial clustering of applications with noise (DBSCAN). First, our method uses three-dimensional computed tomography image features of the average intensity projection combined with multi-scale dot enhancement for preprocessing. Hexagonal clustering and morphological optimized sequential linear iterative clustering (HMSLIC) for sequence image oversegmentation is then proposed to obtain superpixel blocks. The adaptive weight coefficient is then constructed to calculate the distance required between superpixels to achieve precise lung nodules positioning and to obtain the subsequent clustering starting block. Moreover, by fitting the distance and detecting the change in slope, an accurate clustering threshold is obtained. Thereafter, a fast DBSCAN superpixel sequence clustering algorithm, which is optimized by the strategy of only clustering the lung nodules and adaptive threshold, is then used to obtain lung nodule mask sequences. Finally, the lung nodule image sequences are obtained. The experimental results show that our method rapidly, completely and accurately segments various types of lung nodule image sequences.",
author = "Wei Zhang and Xiaolong Zhang and Juanjuan Zhao and Yan Qiang and Qi Tian and Xiaoxian Tang",
year = "2017",
month = "9",
day = "1",
doi = "10.1371/journal.pone.0184290",
language = "English (US)",
volume = "12",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "9",

}

A segmentation method for lung nodule image sequences based on superpixels and density-based spatial clustering of applications with noise. / Zhang, Wei; Zhang, Xiaolong; Zhao, Juanjuan; Qiang, Yan; Tian, Qi; Tang, Xiaoxian.

In: PloS one, Vol. 12, No. 9, e0184290, 01.09.2017.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A segmentation method for lung nodule image sequences based on superpixels and density-based spatial clustering of applications with noise

AU - Zhang, Wei

AU - Zhang, Xiaolong

AU - Zhao, Juanjuan

AU - Qiang, Yan

AU - Tian, Qi

AU - Tang, Xiaoxian

PY - 2017/9/1

Y1 - 2017/9/1

N2 - The fast and accurate segmentation of lung nodule image sequences is the basis of subsequent processing and diagnostic analyses. However, previous research investigating nodule segmentation algorithms cannot entirely segment cavitary nodules, and the segmentation of juxta-vascular nodules is inaccurate and inefficient. To solve these problems, we propose a new method for the segmentation of lung nodule image sequences based on superpixels and density-based spatial clustering of applications with noise (DBSCAN). First, our method uses three-dimensional computed tomography image features of the average intensity projection combined with multi-scale dot enhancement for preprocessing. Hexagonal clustering and morphological optimized sequential linear iterative clustering (HMSLIC) for sequence image oversegmentation is then proposed to obtain superpixel blocks. The adaptive weight coefficient is then constructed to calculate the distance required between superpixels to achieve precise lung nodules positioning and to obtain the subsequent clustering starting block. Moreover, by fitting the distance and detecting the change in slope, an accurate clustering threshold is obtained. Thereafter, a fast DBSCAN superpixel sequence clustering algorithm, which is optimized by the strategy of only clustering the lung nodules and adaptive threshold, is then used to obtain lung nodule mask sequences. Finally, the lung nodule image sequences are obtained. The experimental results show that our method rapidly, completely and accurately segments various types of lung nodule image sequences.

AB - The fast and accurate segmentation of lung nodule image sequences is the basis of subsequent processing and diagnostic analyses. However, previous research investigating nodule segmentation algorithms cannot entirely segment cavitary nodules, and the segmentation of juxta-vascular nodules is inaccurate and inefficient. To solve these problems, we propose a new method for the segmentation of lung nodule image sequences based on superpixels and density-based spatial clustering of applications with noise (DBSCAN). First, our method uses three-dimensional computed tomography image features of the average intensity projection combined with multi-scale dot enhancement for preprocessing. Hexagonal clustering and morphological optimized sequential linear iterative clustering (HMSLIC) for sequence image oversegmentation is then proposed to obtain superpixel blocks. The adaptive weight coefficient is then constructed to calculate the distance required between superpixels to achieve precise lung nodules positioning and to obtain the subsequent clustering starting block. Moreover, by fitting the distance and detecting the change in slope, an accurate clustering threshold is obtained. Thereafter, a fast DBSCAN superpixel sequence clustering algorithm, which is optimized by the strategy of only clustering the lung nodules and adaptive threshold, is then used to obtain lung nodule mask sequences. Finally, the lung nodule image sequences are obtained. The experimental results show that our method rapidly, completely and accurately segments various types of lung nodule image sequences.

UR - http://www.scopus.com/inward/record.url?scp=85029806193&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029806193&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0184290

DO - 10.1371/journal.pone.0184290

M3 - Article

C2 - 28880916

AN - SCOPUS:85029806193

VL - 12

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 9

M1 - e0184290

ER -