# 3D-MRI Brain Tumor Detection Model Using Modified Version of Level Set Segmentation Based on Dragonfly Algorithm

^{1}

^{2}

^{3}

^{*}

## Abstract

**:**

## 1. Introduction

#### 1.1. Problem Statement and Motivation

#### 1.2. Contribution and Methodology

## 2. Related Work

## 3. Materials and Methods

#### 3.1. Preprocessing Phase

#### 3.2. Two Steps Dragonfly-Based Clustering Phase

Algorithm 1: Two-step Dragonfly Clustering. |

Input: $\mathit{D}$ dataset contains MRI brain imagesOutput: Best solution of final cluster center (${\mathit{C}}_{\mathit{b}\mathit{e}\mathit{s}\mathit{t},\mathit{j}}$) $\mathit{j}=\mathbf{1},\mathbf{2},\mathbf{3},\mathbf{4}$BeginInitialization phaseInitialize the position of dragonfly population X _{i} (i = 1 2, ..., n).Initialize step vectors Δ X _{i}For $\mathit{i}=\mathbf{1}:{\mathit{S}}_{\mathit{N}}$ /* ${\mathit{S}}_{\mathit{N}}$ is the total number of food sources (number of clusters) */Initialize the food source within the boundary of given dataset in random order; Evaluate the better potions of food sources by applying the k-means algorithm / *Algorithm 2*/ Send the dragonflies to the food sources; / * Computed centers */ End ForDragonfly algorithm PhaseIteration = 0; Do While (the end condition is not satisfied)For i = 1:n Calculate the fitness of each dragonfly Update the food source and enemy Update w, s, a, c, f, and e Calculate S, A, C, F, and E using Equations (4) to (8) Update neighboring radius If (a dragonfly has at least one neighboring dragonfly)Update step vector (ΔX) using Equation (9) Update position vector X using Equation (10) ElseUpdate position vector using Equation (11) End ifCheck and correct the new positions based on the boundaries of variables End ForFor $\mathit{i}=\mathbf{1}:{\mathit{S}}_{\mathit{N}}$Compute the probability. /* Calculate the probability for each one */ End ForFor $\mathit{i}=\mathbf{1}:{\mathit{S}}_{\mathit{N}}$If (rand ( ) < ${\mathit{P}}_{\mathit{i}}$) /* ${\mathit{P}}_{\mathit{i}}$ denotes the probability associated with ${\mathit{i}}^{\mathit{t}\mathit{h}}$ food source */Calculate the new fitness of the new food source using Equation (14); Select the best food source by using a greedy selection between the old and new food source; Else$\mathit{i}=\mathit{i}+\mathbf{1}$; End If End ForEnd WhileOutput: Final clusters‘ centers. End |

Algorithm 2: K-means clustering [42]. |

Input: $\mathit{K}=\mathbf{4}$. // the number of clusters; $\mathit{D}$ dataset contains MRI brain images (2D slices).BeginArbitrary choose $\mathit{K}$ objects from $\mathit{D}$ as the initial cluster centers; Repeat- (re) group the most similar objects into a cluster, based on the Euclidian distance between the object and the cluster centroid (mean); - Update the cluster centroid, i.e., calculate the mean value of the objects for each cluster. Until no change. |

_{j}shows the position j-th neighboring individual.

#### 3.3. Level Set Segmentation

Algorithm 3: Level set segmentation. |

1: Insert initial contour points using two-step DA clustering output (ROI indexes). 2: Construct a signed distance function. 3: Calculate feature image using Gaussian filter and gradient. 4: Obtain the curve’s narrow band. 5: Obtain curvature and use gradient descent to minimize energy. 6: Evolve the curve. 7: Repeat step number two and stop after obtaining the segmented region. |

## 4. Experimental Results

#### 4.1. Experiment 1: Comparison with Existing Methods

#### 4.2. Experiment 2: Model Accuracy with and without k-Means

#### 4.3. Experiment 3: Role of DA to Reduce Level Set Iteration

## 5. Conclusions and Future Work

## Author Contributions

## Funding

## Conflicts of Interest

## References

- El-Melegy, M.T.; El-Magd, K.M.A.; Ali, S.A.; Hussain, K.F.; Mahdy, Y.B. Ensemble of Multiple Classifiers for Automatic Multimodal Brain Tumor Segmentation. In Proceedings of the International Conference on Innovative Trends in Computer Engineering (ITCE), Aswan, Egypt, 2–4 February 2019; pp. 58–63. [Google Scholar]
- Aparna, R.M.; Shanmugavadivu, P. A Survey of Medical Imaging, Storage and Transfer Techniques. In Proceedings of the International Conference on ISMAC in Computational Vision and Bio-Engineering, Coimbatore, India, 16–17 May 2018; pp. 17–29. [Google Scholar]
- Lu, C.; Xu, Z.; Ye, X. Evaluation of Intraoperative MRI-Assisted Stereotactic Brain Tissue Biopsy: A Single-Center Experience in China. Chin. Neurosurg. J.
**2019**, 5, 1–10. [Google Scholar] [CrossRef] [Green Version] - Bauer, S.; Wiest, R.; Nolte-P, L.; Reyes, M. A Survey of MRI-Based Medical Image Analysis For Brain Tumor Studies. Phys. Med. Biol.
**2013**, 58, 1–44. [Google Scholar] [CrossRef] [PubMed] - Mild, K.H.; Lundström, R.H.; Wilén, J.H. Non-ionizing Radiation in Swedish Health Care Exposure and Safety Aspects. Int. J. Environ. Res. Public Health
**2019**, 16, 1186. [Google Scholar] [CrossRef] [Green Version] - Zhuge, Y.; Krauze, A.V.; Ning, H.; Cheng, J.Y.; Arora, B.C.; Camphausen, K.; Miller, R.W. Brain tumor segmentation using holistically nested neural networks in MRI images. Med. Phys.
**2017**, 44, 5234–5243. [Google Scholar] [CrossRef] - Banerjee, S.; Mitra, S. Novel Volumetric Sub-region Segmentation in Brain Tumors. Front. Comput. Neurosci.
**2020**, 14, 1–13. [Google Scholar] [CrossRef] - Popoola, J.J.; Godson, T.E.; Olasoji, Y.O.; Adu, M.R. Study on Capabilities of Different Segmentation Algorithms in Detecting and Reducing Brain Tumor Size in Magnetic Resonance Imaging for Effective Telemedicine Services. Eur. J. Eng. Res. Sci.
**2019**, 4, 23–29. [Google Scholar] [CrossRef] - Angulakshmi, M.; Priya, G.L. Automated Brain Tumor Segmentation Techniques—A Review. Int. J. Imaging Syst. Technol.
**2017**, 27, 66–77. [Google Scholar] [CrossRef] [Green Version] - Shirly, S.; Ramesh, K. Review on 2D and 3D MRI Image Segmentation Techniques. Curr. Med. Imaging Former. Curr. Med. Imaging Rev.
**2019**, 15, 150–160. [Google Scholar] [CrossRef] - Sajid, S.; Hussain, S.; Sarwar, A. Brain Tumor Detection and Segmentation in MR Images Using Deep Learning. Arab. J. Sci. Eng.
**2019**, 44, 9249–9261. [Google Scholar] [CrossRef] - Wang, D. Efficient Level-Set Segmentation Model Driven by The Local GMM and Split Bregman Method. IET Image Process.
**2019**, 13, 761–770. [Google Scholar] [CrossRef] - Rahman, C.; Rashid, T. Dragonfly Algorithm and Its Applications in Applied Science Survey. Comput. Intell. Neurosci.
**2019**, 2019, 11–21. [Google Scholar] [CrossRef] - Seyedali, M. Dragonfly Algorithm: A New Meta-Heuristic Optimization Technique for Solving Single-Objective, Discrete, and Multi-Objective Problems. Neural Comput. Appl.
**2016**, 27, 1053–1073. [Google Scholar] [CrossRef] - Ranjini, K.; Murugan, S. Memory Based Hybrid Dragonfly Algorithm for Numerical Optimization Problems. Expert Syst. Appl.
**2017**, 83, 63–78. [Google Scholar] [CrossRef] - Saman, S.; Narayanan, S.J. Survey on brain tumor segmentation and feature extraction of MR images. Int. J. Multimed. Inf. Retr.
**2018**, 8, 79–99. [Google Scholar] [CrossRef] - Tiwari, A.; Srivastava, S.; Pant, M. Brain tumor segmentation and classification from magnetic resonance images: Review of selected methods from 2014 to 2019. Pattern Recognit. Lett.
**2020**, 131, 244–260. [Google Scholar] [CrossRef] - El-Baz, A.; Suri, J.S. Level Set Method in Medical Imaging Segmentation; CRC Press: Boca Raton, FL, USA, 2019. [Google Scholar]
- Al-Rifaie, M.; Aber, A.; Hemanth, J. Deploying Swarm Intelligence in Medical Imaging; Identifying Metastasis, Micro-Calcifications and Brain Image Segmentation. IET Syst. Biol.
**2015**, 9, 234–244. [Google Scholar] [CrossRef] - Rupika, N.; Menon, H.; Vikram, K. A Survey on Advanced Segmentation Techniques for Brain MRI Image Segmentation. Int. J. Adv. Sci. Eng. Inf. Technol.
**2017**, 7, 1448–1456. [Google Scholar] [CrossRef] [Green Version] - Kermi, A.; Andjouh, K.; Zidane, F. Fully automated brain tumor segmentation system in 3D-MRI using symmetry analysis of brain and level-sets. IET Image Process.
**2018**, 12, 1964–1971. [Google Scholar] [CrossRef] - Bal, A.; Banerjee, M.; Chakrabarti, A.; Sharma, P. MRI Brain Tumor Segmentation and Analysis using Rough-Fuzzy C-Means and Shape Based Properties. J. King Saud Univ. Comput. Inf. Sci.
**2018**. [Google Scholar] [CrossRef] - Anitha, V.; Murugavalli, S. Brain Tumor Classification using Two-Tier Classifier with Adaptive Segmentation Technique. IET Comput. Vis.
**2016**, 10, 9–17. [Google Scholar] [CrossRef] - Mahalakshmi, A.; Krishnappa, H.; Jayadevappa, D. A Hybrid Approach for the Segmentation of Brain Tumor using K-Means Clustering and Variational Level Set. J. Adv. Res. Dyn. Control. Syst.
**2018**, 10, 258–264. [Google Scholar] - Thapaliya, K.; Pyun, J.-Y.; Park, C.-S.; Kwon, G.-R. Level Set Method with Automatic Selective Local Statistics for Brain Tumor Segmentation in MR Images. Comput. Med. Imaging Graph.
**2013**, 37, 522–537. [Google Scholar] [CrossRef] [PubMed] - Le, T.; Gummadi, R.; Savvides, M. Deep Recurrent Level Set for Segmenting Brain Tumors. Lect. Notes Comput. Sci.
**2018**, 11072, 646–653. [Google Scholar] [CrossRef] [Green Version] - Qin, P.; Zhang, J.; Zeng, J.; Liu, H.; Cui, Y. A Framework Combining DNN and Level-Set Method to Segment Brain Tumor in Multi-Modalities MR Image. Soft Comput.
**2019**, 19, 9237–9251. [Google Scholar] [CrossRef] - Rajan, P.G.; Sundar, C. Brain Tumor Detection and Segmentation by Intensity Adjustment. J. Med. Syst.
**2019**, 43, 1–13. [Google Scholar] [CrossRef] [PubMed] - Abdel-Maksoud, E.; Elmogy, M.; Al-Awadi, R. Brain Tumor Segmentation Based on A Hybrid Clustering Technique. Egypt. Inform. J.
**2015**, 16, 71–81. [Google Scholar] [CrossRef] - Ural, B. A Computer-Based Brain Tumor Detection Approach with Advanced Image Processing and Probabilistic Neural Network Methods. J. Med. Biol. Eng.
**2017**, 38, 867–879. [Google Scholar] [CrossRef] - Ma, C.; Luo, G.; Wang, K. Concatenated and Connected Random Forests with Multiscale Patch Driven Active Contour Model for Automated Brain Tumor Segmentation of MR Images. IEEE Trans. Med. Imaging
**2018**, 37, 1943–1954. [Google Scholar] [CrossRef] - Hancer, E.; Ozturk, C.; Karaboga, D. Extraction of Brain Tumors from MRI Images with Artificial Bee Colony-Based Segmentation Methodology. In Proceedings of the 8th International Conference on Electrical and Electronics Engineering (ELECO), Bursa, Turkey, 28–30 November 2019; pp. 516–520. [Google Scholar]
- Christ, J.; Subramanian, R. Clown Fish Queuing and Switching Optimization Algorithm for Brain Tumor Segmentation. Biomed. Res.
**2016**, 27, 65–69. [Google Scholar] - Narayanan, B.; Hardie, R. A Computationally Efficient U-Net Architecture for Lung Segmentation in Chest Radiographs. In Proceedings of the IEEE National Aerospace and Electronics Conference (NAECON), Dayton, OH, USA, 20–24 July 2020; pp. 279–284. [Google Scholar]
- Jin, L.; Pan, Y.; Li, M.; Chen, Z.; Tang, L.; Lu, C.; Wang, J. Applications of Deep Learning to MRI Images: A Survey. Big Data Min. Anal.
**2018**, 1, 1–18. [Google Scholar] [CrossRef] - Mohammad, H.; Davy, A.; Warde-Farley, D.; Biard, A.; Courville, A.; Bengio, Y.; Pal, C.; Jodoin, P.-M.; Larochelle, H. Brain Tumor Segmentation with Deep Neural Networks. Med. Image Anal.
**2017**, 35, 18–31. [Google Scholar] [CrossRef] [Green Version] - Iglesias, J.E.; Liu, C.-Y.; Thompson, P.; Tu, Z. Robust brain extraction across datasets and comparison with publicly available methods. IEEE Trans. Med. Imaging
**2011**, 30, 1617–1634. [Google Scholar] [CrossRef] [PubMed] - Nair, R.; David, E.; Rajagopal, S. A robust anisotropic diffusion filter with low arithmetic complexity for images. EURASIP J. Image Video Process.
**2019**, 48, 1–14. [Google Scholar] [CrossRef] - Chen, J.; Gong, Y. Particle swarm optimization for two-echelon location-routing problem. J. Comput. Appl.
**2013**, 33, 2261–2264. [Google Scholar] [CrossRef] - Kumar, Y.; Sahoo, G. A two-step artificial bee colony algorithm for clustering. Neural Comput. Appl.
**2015**, 28, 537–551. [Google Scholar] [CrossRef] - Zhang, C.; Shen, X.; Cheng, H.; Qian, Q. Brain tumor segmentation based on hybrid clustering and morphological operations. Int. J. Biomed. Imaging
**2019**, 2019, 1–111. [Google Scholar] [CrossRef] - Armano, G.; Farmani, M.R. Clustering analysis with combination of artificial bee colony algorithm and k-means technique. Int. J. Comput. Theory Eng.
**2014**, 6, 141–145. [Google Scholar] [CrossRef] [Green Version] - Arunprasath, S. Internet of medical things-load optimization of power flow based on hybrid enhanced grey wolf optimization and dragonfly algorithm. Future Gener. Comput. Syst.
**2019**, 98, 319–330. [Google Scholar] [CrossRef] - Bao, X.; Jia, H.; Lang, C. Dragonfly algorithm with opposition-based learning for multilevel thresholding Color Image Segmentation. Symmetry
**2019**, 11, 716. [Google Scholar] [CrossRef] [Green Version] - Li, C.; Xu, C.; Gui, C.; Fox, M.D. Distance regularized level set evolution and its application to image segmentation. IEEE Trans. Image Process.
**2010**, 19, 3243–3254. [Google Scholar] [CrossRef] - Belaid, A.; Boukerroui, D.; Maingourd, Y.; Lerallut, J.F. Phase-based level set segmentation of ultrasound images. IEEE Trans. Inf. Technol. Biomed.
**2010**, 15, 138–147. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Menze, B.; Jakab, A.; Bauer, S.; Cramer, J.K.; Farahani, K.; Kirby, J.; Burren, Y.; Porz, N.; Slotboom, J.; Wiest, R.; et al. The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans. Med. Imaging
**2015**, 34, 1993–2024. [Google Scholar] [CrossRef] [PubMed] - James, J.A.; Dasarathy, B. Medical image fusion: A survey of the state of the art. Int. J. Inf. Fusion
**2014**, 19, 4–19. [Google Scholar] [CrossRef] [Green Version] - Lefkovits, L.; Lefkovits, S.; Vaida, M. Brain tumor segmentation based on random forest. Mem. Sci. Sect. Rom. Acad.
**2016**, 39, 83–93. [Google Scholar] - Ayachi, R.; Amor, N.B. Brain tumor segmentation using support vector machines. Lect. Notes Comput. Sci. Book Ser. (LNCS)
**2009**, 5590, 736–747. [Google Scholar] [CrossRef] - Zhang, K.; Zhang, L.; Song, H.; Zhou, W. Active contours with selective local or global segmentation: A new formulation and level set method. Image Vis. Comput.
**2010**, 28, 668–676. [Google Scholar] [CrossRef]

**Figure 6.**Dragonfly algorithm flowchart [43].

**Figure 9.**Brain tumor segmentation. (

**a**) 2D slice. (

**b**) Final segmentation based on the Dragonfly Algorithm (DA). (

**c**) Final segmentation based on the Clown Fish (CF) Algorithm.

**Figure 10.**Brain tumor segmentation for BRATS 2017 dataset. (

**a**) 2D slice. (

**b**) Final segmentation with the modified level set.

**Figure 11.**Brain tumor segmentation for BRATS 2017 dataset. (

**a**) 2D slice. (

**b**) Final segmentation with the modified level set. (

**c**) Ground truth.

**Table 1.**Results of the comparison between the proposed model and state-of-the-art brain segmentation methods (average over 285 subjects).

Methods | Accuracy | Recall | Precision |
---|---|---|---|

Proposed Model (Two-step DA, Level Set) | 98.20 | 95.13 | 93.21 |

Symmetry Analysis, Level Set [21] | 93.63 | 89.10 | 90.45 |

Fuzzy C-Means [22] | 85.7 | 87.6 | 72.3 |

Rough Fuzzy C-Means [22] | 91.50 | 90 | 92 |

K-means, Level Set [24] | 89.30 | 92.7 | 75.8 |

Random Forest [49] | 85.60 | 91.85 | 78.3 |

Support Vector Machine (SVM) [50] | 94.25 | 92.15 | 91.21 |

**Table 2.**Results of the comparison between the proposed model and Deep Neural Network (DNN)-based brain segmentation methods (average over 285 subjects).

DNN Methods | Accuracy | Recall | Precision |
---|---|---|---|

Proposed Model (Two-step DA, Level Set) | 98.15 | 95.40 | 93.57 |

Two-pathway CNN [36] | 96.24 | 89.67 | 82.56 |

DNN, level set [26] | 91.58 | 96.40 | 93.23 |

**Table 3.**Results of the comparison between combinations of different nature-inspired metaheuristic algorithms with level set for brain tumor segmentation (average over 285 subjects).

Nature-Inspired Metaheuristic | Accuracy | Recall | Precision |
---|---|---|---|

DA, Level Set | 98.15 | 95.40 | 93.57 |

ABC, Level Set | 95.90 | 92.13 | 91.40 |

PSO, Level Set | 93.58 | 92.40 | 89.23 |

CF, Level Set | 96.85 | 94.32 | 92.55 |

**Table 4.**Comparison of accuracy with and without k-means (average over 285 subjects with repeating each experiment 5 times).

Methods | Accuracy | Mean | Standard Deviation |
---|---|---|---|

k-means, DA and level set | 98.10 | 95.67 | 0.02 |

DA, level set | 85.67 | 82.56 | 0.04 |

Methods | Patient No.1 | Patient No.2 | Patient No.3 | Patient No.4 | Patient No.5 |
---|---|---|---|---|---|

Level set with DA clustering | 15 | 18 | 16 | 15 | 20 |

Level set without DA clustering | 252 | 330 | 371 | 266 | 407 |

© 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**

Khalil, H.A.; Darwish, S.; Ibrahim, Y.M.; Hassan, O.F.
3D-MRI Brain Tumor Detection Model Using Modified Version of Level Set Segmentation Based on Dragonfly Algorithm. *Symmetry* **2020**, *12*, 1256.
https://doi.org/10.3390/sym12081256

**AMA Style**

Khalil HA, Darwish S, Ibrahim YM, Hassan OF.
3D-MRI Brain Tumor Detection Model Using Modified Version of Level Set Segmentation Based on Dragonfly Algorithm. *Symmetry*. 2020; 12(8):1256.
https://doi.org/10.3390/sym12081256

**Chicago/Turabian Style**

Khalil, Hassan A., Saad Darwish, Yasmine M. Ibrahim, and Osama F. Hassan.
2020. "3D-MRI Brain Tumor Detection Model Using Modified Version of Level Set Segmentation Based on Dragonfly Algorithm" *Symmetry* 12, no. 8: 1256.
https://doi.org/10.3390/sym12081256