# Lung Lobe Segmentation Based on Lung Fissure Surface Classification Using a Point Cloud Region Growing Approach

^{1}

^{2}

^{3}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Lung Lobe Segmentation Algorithm

#### 2.1. Lung Segmentation

#### 2.2. Pulmonary Fissure Classification

#### 2.2.1. Pulmonary Fissure Segmentation

#### 2.2.2. Lung Fissure Surface Classification Using a Point Cloud Region Growing Approach

Algorithm 1 Regional growth clustering | |

Input: | lung fissure point cloud $X$, surface normal vector $N$, surface curvature $c$, neighborhood search function $\mathsf{\Omega}$, curvature threshold ${c}_{th}$, angle threshold ${\theta}_{th}$ |

Output: | regional clustering set $R$ |

1: | initialization: $R\leftarrow \varnothing ,$ available point cloud set: $\left\{A\right\}\leftarrow X$; |

2: | while$A\ne NULL$do |

3: | current growth region $\left\{{R}_{c}\right\}\leftarrow \varnothing $; |

4: | current seed point set $\left\{{S}_{c}\right\}\leftarrow \varnothing $; |

5: | ${P}_{min}$= minimum curvature point in $A$; |

6: | $\left\{{S}_{c}\right\}\leftarrow \left\{{S}_{c}\right\}{\displaystyle \cup}{P}_{min},\hspace{1em}\left\{{R}_{c}\right\}\leftarrow \left\{{R}_{c}\right\}{\displaystyle \cup}{P}_{min},\left\{A\right\}\leftarrow \left\{A\right\}\backslash {P}_{min}$; |

7: | for $i=1$ to size({${S}_{c}$}) do |

8: | neighborhood point cloud of current seed $\left\{{B}_{c}\right\}\leftarrow \mathsf{\Omega}\left({S}_{c}\left\{i\right\}\right)$; |

9: | for $j=0$ to size({${B}_{c}$}) do |

10: | current neighborhood point ${P}_{j}\leftarrow {B}_{c}\left\{j\right\}$; |

11: | if {$A$} contain ${P}_{j}$ and $co{s}^{-1}\left(\left|\left(N\left\{{S}_{c}\left\{i\right\}\right\},N\left\{{P}_{j}\right\}\right)\right|\right){\theta}_{th}$ then |

12: | $\left\{{R}_{c}\right\}\leftarrow \left\{{R}_{c}\right\}{\displaystyle \cup}{P}_{j}$; |

13: | $\left\{A\right\}\leftarrow \left\{A\right\}\backslash {P}_{j}$; |

14: | if $c\left\{{P}_{j}\right\}<{c}_{th}$ then |

15: | $\left\{{S}_{c}\right\}\leftarrow \left\{{S}_{c}\right\}{\displaystyle \cup}{P}_{j}$; |

16: |
end if |

17: | end if |

18: | end for |

19: | end for |

20: | add the current growth region to the cluster set $\left\{R\right\}\leftarrow \left\{R\right\}{\displaystyle \cup}\left\{{R}_{c}\right\}$; |

21: | end while |

#### 2.3. Lung Fissure Surface Fitting and Lung Lobe Segmentation

## 3. Experimental Results

#### 3.1. Visual Evaluation

#### 3.2. Quantitative Evaluation

## 4. Discussion

## Author Contributions

## Funding

## Acknowledgments

## Conflicts of Interest

## References

- Han, M.K.; Agusti, A.; Calverley, P.M.; Celli, B.R.; Criner, G.; Curtis, J.L.; Fabbri, L.M.; Goldin, J.G.; Jones, P.W.; MacNee, W.; et al. Chronic obstructive pulmonary disease phenotypes: The future of COPD. Am. J. Respir. Crit. Care Med.
**2010**, 182, 598–604. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Doel, T.; Gavaghan, D.J.; Grau, V. Review of automatic pulmonary lobe segmentation methods from CT. Comput. Med. Imaging Graph.
**2015**, 40, 13–29. [Google Scholar] [CrossRef] [PubMed] - George, K.; Harrison, A.P.; Jin, D.; Xu, Z.; Mollura, D.J. Pathological pulmonary lobe segmentation from CT images using progressive holistically nested neural networks and random walker. In Proceedings of the Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Quebec, QC, Canada, 14 September 2017; Springer: Berlin/Heidelberg, Germany, 2017; pp. 195–203. [Google Scholar]
- Imran, A.A.Z.; Hatamizadeh, A.; Ananth, S.P.; Ding, X.; Terzopoulos, D.; Tajbakhsh, N. Automatic segmentation of pulmonary lobes using a progressive dense V-Network. arXiv
**2019**, arXiv:1902.06362. [Google Scholar] - Ferreira, F.T.; Sousa, P.; Galdran, A.; Sousa, M.R.; Campilho, A. End-to-end supervised lung lobe segmentation. In Proceedings of the International Joint Conference on Neural Networks (IJCNN), Rio De Janeiro, Brazil, 8–13 July 2018; IEEE: Piscataway, NJ, USA, 2018; pp. 1–8. [Google Scholar]
- Ukil, S.; Reinhardt, J.M. Smoothing lung segmentation surfaces in three-dimensional x-ray ct images using anatomic guidance1. Acad. Radiol.
**2005**, 12, 1502–1511. [Google Scholar] [CrossRef] [PubMed] - Sun, X.; Zhang, H.; Duan, H. 3D computerized segmentation of lung volume with computed tomography. Acad. Radiol.
**2006**, 13, 670–677. [Google Scholar] [CrossRef] [PubMed] - Pu, J.; Roos, J.; Chin, A.Y.; Napel, S.; Rubin, G.D.; Paik, D.S. Adaptive border marching algorithm: Automatic lung segmentation on chest CT images. Comput. Med. Imaging Graph.
**2008**, 32, 452–462. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Saita, S.; Kubo, M.; Kawata, Y.; Niki, N.; Ohmatsu, H.; Moriyama, N. An algorithm for the extraction of pulmonary fissures from low-dose multislice CT image. Syst. Comput. Jpn.
**2006**, 37, 63–76. [Google Scholar] [CrossRef] - Pu, J.; Leader, J.K.; Zheng, B.; Knollmann, F.; Fuhrman, C.; Sciurba, F.C.; Gur, D. A computational geometry approach to automated pulmonary fissure segmentation in CT examinations. IEEE Trans. Med. Imaging
**2009**, 28, 710. [Google Scholar] [PubMed] [Green Version] - Ukil, S.; Reinhardt, J.M. Anatomy-guided lung lobe segmentation in X-ray CT images. IEEE Trans. Med. Imaging
**2008**, 28, 202–214. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Doel, T.; Matin, T.N.; Gleeson, F.V.; Gavaghan, D.J.; Grau, V. Pulmonary lobe segmentation from CT images using fissureness, airways, vessels and multilevel B-splines. In Proceedings of the Biomedical Imaging (ISBI), 2012 9th IEEE International Symposium on, Barcelona, Spain, 2–4 May 2012; IEEE: Piscataway, NJ, USA, 2012; pp. 1491–1494. [Google Scholar]
- Zhao, H.; Stoel, B.C.; Staring, M.; Bakker, M.E.; Stolk, J.; Zhou, P.; Xiao, C. A framework for pulmonary fissure segmentation in 3D CT images using a directional derivative of plate filter. Signal Process.
**2020**, 173, 107602. [Google Scholar] [CrossRef] - VanRikxoort, E.M.; deHoop, B.; Viergever, M.A.; Prokop, M.; Van Ginneken, B.B. Automatic lung segmentation from thoracic computed tomography scans using a hybrid approach with error detection. Med. Phys.
**2009**, 36, 2934–2947. [Google Scholar] [CrossRef] [PubMed] - Wold, S.; Esbensen, K.; Geladi, P. Principal component analysis. Chemom. Intell. Lab. Syst.
**1987**, 2, 37–52. [Google Scholar] [CrossRef] - Region Growing Approach. Available online: http://pointclouds.org/documentation/tutorials (accessed on 14 October 2020).
- Lee, S.; Wolberg, G.; Shin, S.Y. Scattered data interpolation with multilevel B-splines. IEEE Trans. Vis. Comput. Graph.
**1997**, 3, 228–244. [Google Scholar] [CrossRef] [Green Version] - Competition Website. Available online: https://lola11.grand-challenge.org (accessed on 14 October 2020).
- MeVisLab. Available online: http://www.mevislab.de (accessed on 14 October 2020).
- Gerard, S.E.; Reinhardt, J.M. Pulmonary lobe segmentation using a sequence of convolutional neural networks for marginal learning. In Proceedings of the Biomedical Imaging (ISBI), 2019 16th IEEE International Symposium on Biomedical Imaging, Venezia, Italy, 24–27 April 2019; IEEE: Piscataway, NJ, USA, 2019; pp. 1207–1211. [Google Scholar]

**Figure 3.**Results of pulmonary fissure classification: (

**a**) original pulmonary fissure point cloud, and (

**b**) clustered pulmonary fissure point cloud.

**Figure 4.**Results of lung fissure surface fitting: (

**a**) original right lung oblique fissure, (

**b**) fitted right lung oblique fissure, (

**c**) original right lung horizontal fissure, and (

**d**) fitted right lung horizontal fissure.

**Figure 5.**Results of lung lobe segmentation: (

**a**) original right lung, (

**b**) segmentation using oblique fissure, (

**c**) segmentation using horizontal fissure, and (

**d**) segmentation result.

**Figure 7.**Comparison between present method (second line) and Doel’s method (first line) when the pulmonary fissure is visible.

**Figure 8.**Comparison between our method (the second row) and Doel’s method (the first row) for moderate and low score segmentation results.

**Figure 9.**Quantitative evaluation results of lung lobe segmentation in the LOLA11 dataset: (

**a**) results of case 01−case 30, and (

**b**) results of case 31−case 55. The lll, lul, rll, rml and rul are left lower lobe, left upper lobe, right lower lobe, right middle lobe and right upper lobe, respectively.

Mean | SD | Min | Q1 | Median | Q3 | Max | |
---|---|---|---|---|---|---|---|

Left lower lobe | 0.89 | 0.23 | 0.0 | 0.95 | 0.97 | 0.98 | 0.99 |

Left upper lobe | 0.93 | 0.18 | 0.02 | 0.96 | 0.99 | 0.99 | 1 |

Right upper lobe | 0.84 | 0.27 | 0.0 | 0.8 | 0.96 | 0.99 | 1 |

Right middle lobe | 0.65 | 0.4 | 0.0 | 0.06 | 0.82 | 0.96 | 1 |

Right lower lobe | 0.88 | 0.24 | 0.0 | 0.93 | 0.97 | 0.98 | 0.99 |

Total score | 0.84 |

LobeNet_V2 | V-Net | The Proposed Method | |
---|---|---|---|

Left lower lobe | 0.91 | 0.88 | 0.89 |

Left upper lobe | 0.95 | 0.92 | 0.93 |

Right lower lobe | 0.96 | 0.92 | 0.88 |

Right middle lobe | 0.87 | 0.76 | 0.65 |

Right upper lobe | 0.94 | 0.91 | 0.84 |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Chen, X.; Zhao, H.; Zhou, P.
Lung Lobe Segmentation Based on Lung Fissure Surface Classification Using a Point Cloud Region Growing Approach. *Algorithms* **2020**, *13*, 263.
https://doi.org/10.3390/a13100263

**AMA Style**

Chen X, Zhao H, Zhou P.
Lung Lobe Segmentation Based on Lung Fissure Surface Classification Using a Point Cloud Region Growing Approach. *Algorithms*. 2020; 13(10):263.
https://doi.org/10.3390/a13100263

**Chicago/Turabian Style**

Chen, Xin, Hong Zhao, and Ping Zhou.
2020. "Lung Lobe Segmentation Based on Lung Fissure Surface Classification Using a Point Cloud Region Growing Approach" *Algorithms* 13, no. 10: 263.
https://doi.org/10.3390/a13100263