# Segmentation of Lung Nodules Using Improved 3D-UNet Neural Network

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

- (1)
- Methods based on the 2D convolutional neural network. Ding et al. [4] borrowed from the successful application of deep convolutional neural networks (DCNNs) in natural image recognition and proposed a lung nodule detection method based on DCNNs. In the faster R-CNN neural network, a deconvolution structure is introduced for candidate detection of axis slices. Aiming at the problem that the size of lung nodules is too small, and it is easy to lose features, a deconvolution is added after the VGG16 network to restore the size of the feature map so that the network can capture features more accurately. Deng Zhonghao et al. [5] aimed at solving the problem of low detection sensitivity of traditional algorithms and reducing the large number of false positives. The UNet network was improved to reduce the complexity of a deep neural network while maintaining its sensitivity. Although the two-dimensional detection and segmentation methods have made great progress compared with the traditional methods, a CT image is a three-dimensional image sequence, and the lung organs of the human body are not based on a two-dimensional plane, so making inferences about a three-dimensional object from single plane cuts is often not objective or specific enough. The artificial reduction of one dimension of information often results in low recall rates and high false positives. This undoubtedly brings a lot of unnecessary work to physicians. Therefore, because lung organs and lung nodules are three-dimensional objects, a three-dimensional convolutional neural network is required to further improve the detection and classification accuracy.
- (2)
- Methods based on the 3D convolutional neural network. Aiming at the characteristics of lung nodules in a three-dimensional space and its variability in shape, Zhu et al. [6] considered the three-dimensionality of lung CT data and the compactness of the dual-path network, and designed two deep three-dimensional DPNs for the nodules: Detection and classification. Specifically, a three-dimensional fast convolutional neural network area (R-CNN) is designed for nodule detection. This modified R-CNN uses a three-dimensional dual-path block and UNet encoding and decoding structure to effectively learn nodule characteristics. This method makes full use of a lung nodule’s spatial information and integrates feature maps with different abstract levels to repair the lost features, making the detection accuracy higher. Gong et al. [7] proposed an automatic computer-aided detection scheme for lung nodules based on deep convolutional neural networks (DCNNs). A three-dimensional dynamic neural network (SE-ResNet) based on a compressed excitation network and residual network was used to detect lung nodules and reduce false positives. Specifically, by fusing the 3D-SE-ResNet module to design a three-dimensional area suggestion network, with a UNet network structure to detect candidate lung nodules, the 3D-SE-ResNet module recalibrates the residual characteristic response of the channel to enhance the network. The model uses the 3D-SE-ResNet module to effectively learn the characteristics of nodules and improve nodule detection performance. Although this method detects lung nodules in three dimensions and can make full use of the spatiality and completeness of CT image sequences, it does not fully consider the adhesion of lung nodules and surrounding tissues, resulting in inaccurate segmentation.

## 2. Related Work

#### 2.1. UNet Segmentation Network

#### 2.2. 3D-UNet Segmentation Network

## 3. Method

#### 3.1. 3D-Res2Net

#### 3.2. Network Design

## 4. Experience and Results

#### 4.1. Dataset

#### 4.2. Data Preprocessing

#### 4.2.1. Data Format Conversion

#### 4.2.2. Lung Parenchymal Segmentation

#### 4.2.3. Voxel Value Normalization

#### 4.2.4. Data Enhancement

#### 4.3. Evaluation Standard

_{truepositive}represents the area where the lung nodule exists and is correctly segmented, N

_{falsepositive}represents the area where the lung nodule exists but is not correctly segmented, and N

_{falsenegative}represents the area where the lung nodule does not exist and is not segmented. When the invalid dice coefficient is close to 1, the loss function loss is infinitely close to 0. At this time, the model segmentation result matches the real result.

_{real}is the number of real nodules detected by the network, and N

_{nodule}is the number of real nodules in the sample. The formula is as follows:

_{no}is the network detected. The number of non-nodules, N

_{sample}is the total number of training samples, and the formula is as follows:

#### 4.4. Experimental Results

#### Model Comparison

## 5. Discussion

## 6. Conclusions

## Author Contributions

## Funding

## Conflicts of Interest

## References

- Siegel, R.L.; Miller, K.D.; Jemal, A. Cancer statistics, 2019. CA Cancer J. Clin.
**2019**, 69, 7–34. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Carvalho, A.O.; Sampaio, W.B.; Silva, A.C.; de Paiva, A.C.; Nunes, R.A.; Gattass, M. Automatic detection of solitary lung nodules using quality threshold clustering, genetic algorithm and diversity index. Artif. Intell. Med.
**2014**, 60, 165–177. [Google Scholar] [CrossRef] [PubMed] - Messay, T.; Hardie, R.C.; Rogers, S.K. A new computationally efficient CAD system for pulmonary nodule detection in CT imagery. Med Image Anal.
**2010**, 14, 390–406. [Google Scholar] [CrossRef] [PubMed] - Ding, J.; Li, A.; Hu, Z. Accurate pulmonary nodule detection in computed tomography images using deep convolutional neural networks. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2017), Quebec City, QC, Canda, 10–14 September 2017; pp. 559–567. [Google Scholar]
- Deng, Z.; Chen, X. Pulmonary nodule detection algorithm based on deep convolutional neural network. J. Comput. Appl.
**2019**, 39, 2019–2115. [Google Scholar] - Zhu, W.; Liu, C.; Fan, W.; Xie, X. Deeplung: Deep 3D dual path nets for automated pulmonary nodule detection and classification. In Proceedings of the 18th IEEE Winter Conference on Applications of Computer Vision, Lake Tahoe, Stateline, NV, USA; 2017; pp. 673–681. [Google Scholar]
- Gong, L.; Jiang, S.; Yang, Z.Y.; Zhang, G.; Wang, L. Automated pulmonary nodule detection in CT images using 3D deep squeeze-and-excitation networks. Int. J. Comput. Assist. Radiol. Surg.
**2019**, 14, 1969–1979. [Google Scholar] [CrossRef] - Ronneberger, O.; Fischer, P.; Brox, T. U-Net: Convolutional Networks for Biomedical Image Segmentation. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, 5–9 October 2015; 9351, pp. 234–241. Available online: https://arxiv.org/abs/1505.04597v1 (accessed on 11 September 2020).
- Çiçek, Ö.; Abdulkadir, A.; Lienkamp, S.S.; Brox, T.; Ronneberger, O. 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation. In Proceedings of the International Conference on Medical Image Computing and Computer Assisted Intervention, Athens, Greece, 17–21 October 2016; pp. 424–432. [Google Scholar] [CrossRef] [Green Version]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Deep Residual Learning for Image Recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; IEEE: New York, NY, USA, 2016; pp. 770–778. Available online: http://arXiv.org/pdf/1512.03385 (accessed on 15 September 2020).
- Gao, S.; Cheng, M.M.; Zhao, K.; Zhang, X.Y.; Yang, M.H.; Torr, P.H. Res2Net: A New Multi-scale Backbone Architecture. In IEEE Transactions on Pattern Analysis and Machine Intelligence; IEEE: New York, NY, USA, 2019. [Google Scholar] [CrossRef] [Green Version]
- Armato, S.G.; Mclennan, G.; Bidautl, L.; McNitt-Gray, M.F.; Meyer, C.R.; Reeves, A.P.; Zhao, B.; Aberle, D.R.; Henschke, C.I.; Hoffman, E.A.; et al. The lung image database consortium (LIDC) and image database resource initiative (IDRI): A completed reference database of lung nodules on CT scans. Med. Phys.
**2011**, 38, 915–931. [Google Scholar] [CrossRef] [PubMed] - Mansoor, A.; Bagci, U.; Xu, Z.; Foster, B.; Olivier, K.N.; Elinoff, J.M.; Suffredini, A.F.; Jayaram, K.U.; Mollura, D.J. A generic approach to pathological lung segmentation. IEEE Trans. Med. Imaging
**2014**, 33, 2293–2310. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Huang, S.W.; Lin, C.T.; Chen, S.P.; Wu, Y.-Y.; Hsu, P.-H.; Lai, S.-H. AugGAN: Cross Domain Adaptation with GAN-based Data Augmentation. In ECCV 2018: European Conference on Computer Vision; Springer: Cham, UK, 2018; pp. 731–744. [Google Scholar] [CrossRef]
- Dice, L.R.; Dice, L.R. Measures of the Amount of Ecologic Association Between Species. Ecology
**1944**, 26, 297–302. [Google Scholar] [CrossRef] - Hou, T.X.; Zhao, J.J.; Qiang, Y. Pulmonary nodules segmentation based on CRF 3D-UNet structure. Comput. Eng. Des.
**2020**, 41, 1663–1669. [Google Scholar] - Murphy, K.; Ginneken, B.V.; Schilham, A.M.R.; de Hoop, B.J.; Gietema, H.A.; Prokop, M. A large-scale evaluation of automatic pulmonary nodule detection in chest CT using local image features and k-nearest-neighbour classification. Med. Image Anal.
**2009**, 13, 757–770. [Google Scholar] [CrossRef] [PubMed] - Tan, M.; Deklerck, R.; Jansen, B.; Bister, M.; Corneli, J. A novel computer-aided lung nodule detection system for CT images. Med. Phys.
**2011**, 38, 5630–5645. [Google Scholar] [CrossRef] [PubMed] - Setio, A.A.A.; Ciompi, F.; Litjens, G.; Gerke, P.; Jacobs, C.; van Riel, S.J.; Winkler, M.M.; Naqibullah, M.; Sánchez, C.I.; van Ginneken, B. Pulmonary nodule detection in CT images: False positive reduction using multi-view convolutional networks. IEEE Trans. Med. Imaging
**2016**, 35, 1160–1169. [Google Scholar] [CrossRef] [PubMed] - Lung Nodule Analysis 2016. Available online: https://luna16.grand-challenge.org (accessed on 18 January 2016).
- Dou, Q.; Chen, H.; Jin, Y. Automated pulmonary nodule detection via 3D convnets with online sample filtering and hybrid-loss residual learning. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2017), Quebec City, QC, Canada, 10–14 September 2017; pp. 630–638. [Google Scholar]

**Figure 6.**The detection results of lung nodules. (

**a**) Results of lung nodule detection. (

**b**) The overall effect of lung nodule segmentation.

**Figure 10.**3D-Res2UNet contrast network dice coefficient. (

**a**) Describe the dice coefficient of 3D-Res2UNet

^{1,2}, (

**b**) describe the dice coefficient of 3D-Res2UNet

^{1,3}, (

**c**) describe the dice coefficient of 3D-Res2UNet

^{2,4}, (

**d**) describe the dice coefficient of 3D-Res2UNet

^{3,4}.

Seriesuid | CoordX | CoordY | CoordZ | Diameter (mm) |
---|---|---|---|---|

LKDS-00539 | −70.7218023 | −87.5886319 | 36.5 | 9.4028638 |

LKDS-00540 | −50.2048319 | −90.0324701 | 50.5 | 7.9106295 |

Name of Organization | HU Values |
---|---|

Air | −1000 |

Lung | −500 |

Fat | −100~−50 |

Water | 0 |

Aorta | 35~50 |

Kidney | 40~60 |

Bones | 150~3000 |

Network Name | Dice (%) |
---|---|

UNet | 81.32 |

3D-UNet | 89.12 |

3D-UNet+fully CRF [16] | 93.25 |

3D-Res2UNet (Ours) | 95.30 |

Algorithm | Recall (%) | Number of False Positive Lung Nodules/CT |
---|---|---|

ISICAD [17] | 85.7 | 329.3 |

ETROCAD [18] | 92.2 | 333.0 |

DIAG_CONVENT [19] | 93.3 | 269.0 |

LUNA16_V1 [20] | 94.4 | 622.0 |

Dou [21] | 97.1 | 219.1 |

LUNA16_V2 [20] | 98.3 | 850.2 |

3D-Res2UNet (Ours) | 99.1 | 276.3 |

Name | Dice | Recall | Number of False Positive Lung Nodules/CT |
---|---|---|---|

3D-Res2UNet ^{1,2} | 92.4 | 97.2 | 320.7 |

3D-Res2UNet ^{1,3} | 92.7 | 96.6 | 351.5 |

3D-Res2UNet ^{2,4} | 93.50 | 98.5 | 300.1 |

3D-Res2UNet ^{3,4} | 94.52 | 98.8 | 330.4 |

3D-Res2UNet ^{2,3} | 95.30 | 99.1 | 276.3 |

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**

Xiao, Z.; Liu, B.; Geng, L.; Zhang, F.; Liu, Y.
Segmentation of Lung Nodules Using Improved 3D-UNet Neural Network. *Symmetry* **2020**, *12*, 1787.
https://doi.org/10.3390/sym12111787

**AMA Style**

Xiao Z, Liu B, Geng L, Zhang F, Liu Y.
Segmentation of Lung Nodules Using Improved 3D-UNet Neural Network. *Symmetry*. 2020; 12(11):1787.
https://doi.org/10.3390/sym12111787

**Chicago/Turabian Style**

Xiao, Zhitao, Bowen Liu, Lei Geng, Fang Zhang, and Yanbei Liu.
2020. "Segmentation of Lung Nodules Using Improved 3D-UNet Neural Network" *Symmetry* 12, no. 11: 1787.
https://doi.org/10.3390/sym12111787