# A Clinical Decision-Support System Based on Three-Stage Integrated Image Analysis for Diagnosing Lung Disease

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Related Works

#### 2.1. Singular Value Decomposition (SVD)

#### 2.2. Discrete Wavelet Packet Transform (DWPT)

#### 2.3. Rough Sets Theory

## 3. Materials and Proposed System

#### 3.1. Medical Image Datasets

#### 3.1.1. LIDC Image Dataset

#### 3.1.2. RTH Image Dataset

#### 3.2. Proposed System

#### 3.2.1. Image Processing Block (A)

#### 3.2.2. Reconstruction Block (B)

#### 3.2.3. Feature Extraction Block (C)

#### 3.2.4. Classification Block (D)

#### 3.3. Proposed Procedure

**Step 1:**Adjusting Image Contrast

**Step 2:**Outlining the Lung Area

#### 3.3.1. Segmenting the Chest CT Image

Algorithm 1: Segmenting chest CT image |

Input: image I (size of I is 512 × 512)beginfor i ⃪ 1 to 512 doif $\sum}_{j=1}^{512}I\left(i,j\right)$ > ${T}_{chest}$x = i breakendendfor j ⃪ 1 to 512 doif $\sum}_{i=1}^{512}I\left(i,j\right)$ > ${T}_{chest}$y = j break endendfor i ⃪ 512 to 1 doif $\sum}_{j=1}^{512}I\left(i,j\right)$ > ${T}_{chest}$W = i breakendendfor j ⃪ 512 to 1 doif $\sum}_{i=1}^{512}I\left(i,j\right)$ > ${T}_{chest}$H = j breakendendendOutput: image I crop from I$\left(x,y\right)$, width is W-x, and height is H-y |

#### 3.3.2. Removing Irrelevant Background Areas

#### 3.3.3. Outlining the Lung Areas with a Box Field

**Step 3:**Reconstructing the Image by SVD

Algorithm 2: Removing irrelevant background areas |

Input: image I (size of I is width × height)beginfor i ⃪ 1 to width dofor j ⃪ 1 to heightif $\mathit{I}\left(i,j\right)$ < 1$\mathit{I}\left(i,j\right)$ = 1 else if $\mathit{I}\left(i,j\right)$ = 1 and $\sum}_{j=j}^{j+9}I\left(i,j\right)$ < 10continue;elsebreak;endendendfor i ⃪ 1 to width dofor j ⃪ height to 1if $\mathit{I}\left(i,j\right)$ < 1$\mathit{I}\left(i,j\right)$ = 1 else if $\mathit{I}\left(i,j\right)$ = 1 and $\sum}_{j=j}^{j-9}I\left(i,j\right)$ < 10continue;elsebreak;endendendfor j ⃪ 1 to height dofor i ⃪ 1 to width doif $\mathit{I}\left(i,j\right)$ < 1$\mathit{I}\left(i,j\right)$ = 1 else if $\mathit{I}\left(i,j\right)$= 1 and $\sum}_{i=i}^{i+9}I\left(i,j\right)$ < 10continue;elsebreak;endendendfor j ⃪ 1 to height dofor i ⃪ width to 1 doif $\mathit{I}\left(i,j\right)$ < 1$\mathit{I}\left(i,j\right)$ = 1 else if $\mathit{I}\left(i,j\right)$ = 1 and $\sum}_{i=i}^{i-9}I\left(i,j\right)$ < 10continue;elsebreak;endendendendOutput: image I |

Algorithm 3: Outlining the lung areas with a box field |

Input: image I (size of I is width × height)beginx = 0, y = 0, W = 0, H = 0 for i ⃪ 1 to width dofor j ⃪ 1 to heightif $\mathit{I}\left(i,j\right)$ < 0.8x = i breakendendif x $\ne $ 0breakendendfor i ⃪ width to 1 dofor j ⃪ 1 to heightif $\mathit{I}\left(i,j\right)$ < 0.8W = i breakendendif W $\ne $ 0breakendendfor j ⃪ 1 to height dofor i ⃪ 1 to width doif $\mathit{I}\left(i,j\right)$ < 0.8y = j breakendendif y $\ne $ 0breakendendfor j ⃪ height to 1 dofor i ⃪ 1 to width doif $\mathit{I}\left(i,j\right)$ < 0.8H = j breakendendif H $\ne $ 0breakendendendOutput: image I crop from I$\left(x,y\right)$, width is W-x, and height is H-y |

**Step 4:**Generating the Coefficient by DWPT

#### 3.3.4. The DWPT Decomposition Process

#### 3.3.5. Wavelet Packet Entropy

**Step 5:**Computing the Feature Values and Reducing Attributes

**Step 6:**Classifying the Lung Image Dataset

## 4. Experimental Results and Discussions

## 5. Conclusions

## Author Contributions

## Funding

## Acknowledgments

## Conflicts of Interest

## Appendix A

## References

- Sousa, J.R.; Silva, A.C.; De Paiva, A.C.; Nunes, R.A. Methodology for automatic detection of lung nodules in computerized tomography images. Comput. Methods Programs Biomed.
**2010**, 98, 1–14. [Google Scholar] [CrossRef] [PubMed] - Souto, M.; Correa, J.; Tahoces, P.G.; Tucker, D.; Malagari, K.S.; Vidal, J.J.; Fraser, R.G. Enhancement of Chest Images by Automatic Adaptive Spatial Filtering. J. Digit. Imaging
**1992**, 4, 1–7. [Google Scholar] [CrossRef] - Correa, J.; Souto, M.; Tahoces, P.G.; Malagari, K.; Tucker, D.; Larkin, J.; Kuhlman, J.; Barnes, G.T.; Zerhouni, E.; Fraser, R.G.; et al. Digital chest radiography: A comparison between unprocessed and processed images in the detection of solitary pulmonary nodules. Radiology
**1995**, 195, 253–258. [Google Scholar] [CrossRef] [PubMed] - Helen, H.; Jeongjin, L.; Yeny, Y. Automatic lung nodule matching on sequential CT images. Comput. Biol. Med.
**2008**, 38, 623–634. [Google Scholar] - Armato, S.G.; McLennan, G.; McNitt-Gray, M.F.; Meyer, C.R.; Yankelevitz, D.; Aberle, D.R.; Clarke, L.P. Lung image database consortium developing a resource for the medical imaging research community. Radiology
**2004**, 232, 739–748. [Google Scholar] [CrossRef] [PubMed] - Lee, S.L.A.; Kouzani, A.Z.; Hu, E.J. Random forest based lung nodule classification aided by clustering. Comput. Med. Imaging Graph.
**2010**, 34, 535–542. [Google Scholar] [CrossRef] - Mullaly, W.; Betke, M.; Hong, H.; Wang, J.; Mann, K.; Ko, J.P. Multi-criterion 3D segmentation and registration of pulmonary nodules on CT: A preliminary investigation. In Proceedings of the International Conference on Diagnostic Imaging and Analysis (ICDIA 2002), Shanghai, China, 18–20 August 2002; pp. 176–181. [Google Scholar]
- Dehmeshki, J.; Ye, X.; Lin, X.Y.; Valdivieso, M.; Amin, H. Automated detection of lung nodules in CT images using shape-based genetic algorithm. Comput. Med. Imaging Graph.
**2007**, 31, 408–417. [Google Scholar] [CrossRef] - Yeny, Y.; Helen, H. Correction of segmented lung boundary for inclusion of pleural nodules and pulmonary vessels in chest CT images. Comput. Biol. Med.
**2008**, 38, 845–857. [Google Scholar] - Mallat, S. A Wavelet Tour of Signal Processing; Academic Press: New York, NY, USA, 1999. [Google Scholar]
- Avci, E. An expert system based on Wavelet Neural Network-Adaptive Norm Entropy for scale invariant texture classification. Expert Syst. Appl.
**2007**, 32, 919–926. [Google Scholar] [CrossRef] - Vozalis, M.G.; Margaritis, K.G. Using SVD and demographic data for the enhancement of generalized Collaborative Filtering. Inf. Sci.
**2007**, 177, 3017–3037. [Google Scholar] [CrossRef] - Pawlak, Z. Rough sets. Int. J. Comput. Inf. Sci.
**1982**, 11, 341–356. [Google Scholar] [CrossRef] - Pawlak, Z. Rough Sets: Theoretical Aspects of Reasoning about Data; Kluwer Academic Publisher: Boston, MA, USA, 1991. [Google Scholar]
- Pawlak, Z.; Skowron, A. Rudiments of rough sets. Inf. Sci.
**2007**, 177, 3–27. [Google Scholar] [CrossRef] - Jothi, G.; Hannah Inbarani, H. Hybrid Tolerance Rough Set–Firefly based supervised feature selection for MRI brain tumor image classification. Appl. Soft Comput.
**2016**, 46, 639–651. [Google Scholar] - Chung, K.L.; Yang, W.N.; Huang, Y.H.; Wu, S.T.; Hsu, Y.C. On SVD-based watermarking algorithm. Appl. Math. Comput.
**2007**, 188, 54–57. [Google Scholar] [CrossRef] - Avci, E. Comparison of wavelet families for texture classification by using wavelet packet entropy adaptive network based fuzzy inference system. Appl. Soft Comput.
**2008**, 8, 225–231. [Google Scholar] [CrossRef] - Avci, E.; Turkoglu, I.; Poyraz, M. A new approach based on scalogram for automatic target recognition with X-band Doppler radar. Asian J. Inf. Technol.
**2005**, 4, 133–140. [Google Scholar] - Avci, E.; Turkoglu, I.; Poyraz, M. Intelligent target recognition based on wavelet packet neural network. Expert Syst. Appl.
**2005**, 29, 175–182. [Google Scholar] [CrossRef] - Mallat, S.; Zhong, S. Characterization of signals from multiscale edges. IEEE Trans. Pattern Anal. Mach. Intell.
**1992**, 14, 710–732. [Google Scholar] [CrossRef] [Green Version] - Huang, K.; Aviyente, S. Information-theoretic wavelet packet subband selection for texture classification. Signal Process.
**2006**, 86, 1410–1420. [Google Scholar] [CrossRef] - Muneeswaran, K.; Ganesan, L.; Arumugam, S.; Soundar, K.R. Texture classification with combined rotation and scale invariant wavelet features. Pattern Recognit.
**2005**, 38, 1495–1506. [Google Scholar] [CrossRef] - 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] - Gonzalez, R.C.; Woods, R.E. Digital Image Processing, 2nd ed.; Prentice-Hall: Englewood Cliffs, NJ, USA, 2002. [Google Scholar]
- Kroon, D.-J. Region Growing, MATLAB Central File Exchange. Available online: https://www.mathworks.com/matlabcentral/fileexchange/19084-region-growing (accessed on 25 February 2020).
- Grzymala-Busse, J.W. A new version of the rule induction system LERS. Fundam. Inform.
**1997**, 31, 27–39. [Google Scholar] [CrossRef] - Arivazhagan, S.; Ganesan, L. Texture classification using wavelet transform. Pattern Recognit. Lett.
**2003**, 24, 1513–1521. [Google Scholar] [CrossRef] - Witten, I.H.; Frank, E.; Hall, M.A.; Christopher, J.P. Data Mining: Practical Machine Learning Tools and Techniques, 4th ed.; Elsevier: Amsterdam, The Netherlands, 2017; pp. 67–89. [Google Scholar]
- Klement, W.; Wilk, S.; Michalowski, W.; Farion, K.J.; Osmond, M.H.; Verter, V. Predicting the need for CT imaging in children with minor head injury using an ensemble of Naive Bayes classifiers. Artif. Intell. Med.
**2012**, 54, 163–170. [Google Scholar] [CrossRef] - Mohan, G.; Subashini, M.M. MRI based medical image analysis: Survey on brain tumor grade classification. Biomed. Signal Process. Control
**2018**, 39, 139–161. [Google Scholar] [CrossRef] - Li, S.; Jiang, H.; Wang, Z.; Zhang, G.; Yao, Y.D. An effective computer aided diagnosis model for pancreas cancer on PET/CT images. Comput. Methods Programs Biomed.
**2018**, 165, 205–214. [Google Scholar] [CrossRef] - Xie, H.T.; Yang, D.B.; Sun, N.N.; Chen, Z.N.; Zhang, Y.D. Automated pulmonary nodule detection in CT images using deep convolutional neural networks. Pattern Recognit.
**2019**, 85, 109–119. [Google Scholar] [CrossRef]

**Figure 12.**The image (IMG-A) for the singular value decomposition (SVD) image reconstruction process.

**Figure 15.**Lung images with various discrete wavelet packets transform (DWPT) coefficients (m = 1, the amount of DWPT coefficient = 4).

**Figure 16.**Lung images based on various DWPT coefficients (m = 1, the amount of DWPT coefficient = 16).

(1–6) | Size | Pos.Reg. | SC | Reducts |
---|---|---|---|---|

1 | 1 | 1 | 1 | {range} |

2 | 1 | 1 | 1 | {mean} |

3 | 1 | 1 | 1 | {min} |

4 | 1 | 1 | 1 | {max} |

5 | 1 | 1 | 1 | {standard-deviation} |

6 | 1 | 1 | 1 | {mean-absolute-deviation } |

Method | Proposed | Trees | Naïve Bayes | Multilayer Perception | SMO |
---|---|---|---|---|---|

Region growing | 97.80% (0.038) | 79.40% (11.53) | 80.10% (12.35) | 79.80% (9.95) | 77.40% (10.21) |

Proposed algorithm | * 99.41% (0.018) | 87.42% (9.68) | 83.18% (10.51) | 84.48% (11.16) | 81.13% (10.91) |

Method | Proposed | Trees | Naïve Bayes | Multilayer Perception | SMO |
---|---|---|---|---|---|

Region growing | 97.51% (0.043) | 81.50% (12.58) | 67.40% (14.33) | 89.00% (10.68) | 71.00% (13.82) |

Proposed algorithm | * 98.80% (0.037) | 87.00%(10.78) | 62.90% (13.73) | 89.50% (9.36) | 71.40% (13.41) |

Method | Rough Sets | Trees.J48 | Naïve Bayes | Multilayer Perception | SMO | |
---|---|---|---|---|---|---|

Proposed system | DWPT | 99.17% (0.026) | 86.90% (9.40) | 82.10% (11.83) | 84.70% (11.59) | 80.90% (10.55) |

DWPT-SVD | * 99.41% (0.018) | 87.42% (9.68) | 83.18% (10.51) | 84.48% (11.16) | 81.13% (10.91) |

Method | Rough Sets | Trees.J48 | Naïve Bayes | Multilayer Perception | SMO | |
---|---|---|---|---|---|---|

Proposed system | DWPT | 98.66% (0.030) | 84.80% (11.05) | 62.90% (13.43) | 89.50% (9.47) | 71.60% (13.61) |

DWPT-SVD | * 98.80% (0.037) | 87.00% (10.78) | 62.90% (13.73) | 89.50% (9.36) | 71.40% (13.41) |

© 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**

Cheng, C.-H.; Chen, H.-H.; Chen, T.-L.
A Clinical Decision-Support System Based on Three-Stage Integrated Image Analysis for Diagnosing Lung Disease. *Symmetry* **2020**, *12*, 386.
https://doi.org/10.3390/sym12030386

**AMA Style**

Cheng C-H, Chen H-H, Chen T-L.
A Clinical Decision-Support System Based on Three-Stage Integrated Image Analysis for Diagnosing Lung Disease. *Symmetry*. 2020; 12(3):386.
https://doi.org/10.3390/sym12030386

**Chicago/Turabian Style**

Cheng, Ching-Hsue, Hsien-Hsiu Chen, and Tai-Liang Chen.
2020. "A Clinical Decision-Support System Based on Three-Stage Integrated Image Analysis for Diagnosing Lung Disease" *Symmetry* 12, no. 3: 386.
https://doi.org/10.3390/sym12030386