Medical image segmentation based on 2D maximum fuzzy entropy and improved genetic algorithm

AbstractIn this study, an effective means for detecting cancer region through different types of medical image segmentation are presented and explained. We proposed a new method for cancer segmentation on the basis of fuzzy entropy with a level set (FELs) thresholding. The proposed method was successfully utilized to segment cancer images and then efficiently performed the segmentation of test ultrasound image, brain MRI, and dermoscopy image compared with algorithms proposed in previous studies. Results showed an excellent performance of the proposed method in detecting cancer image segmentation in terms of accuracy, precision, specificity, and sensitivity measures.

Download Full-text

Incorporating priors for medical image segmentation using a genetic algorithm

Neurocomputing ◽

10.1016/j.neucom.2015.09.123 ◽

2016 ◽

Vol 195 ◽

pp. 181-194 ◽

Cited By ~ 31

Author(s):

Payel Ghosh ◽

Melanie Mitchell ◽

James A. Tanyi ◽

Arthur Y. Hung

Keyword(s):

Genetic Algorithm ◽

Image Segmentation ◽

Medical Image ◽

Medical Image Segmentation

Download Full-text

Medical Image Thresholding Using Genetic Algorithm and Fuzzy Membership Functions

International Journal of Fuzzy System Applications ◽

10.4018/ijfsa.2019100103 ◽

2019 ◽

Vol 8 (4) ◽

pp. 39-59

Author(s):

Shashwati Mishra ◽

Mrutyunjaya Panda

Keyword(s):

Genetic Algorithm ◽

Fuzzy Logic ◽

Image Segmentation ◽

Medical Image ◽

Medical Image Segmentation ◽

Hybrid Technique ◽

Membership Functions ◽

Novel Approach ◽

Fitness Value ◽

Sensitivity Specificity

Thresholding is one of the important steps in image analysis process and used extensively in different image processing techniques. Medical image segmentation plays a very important role in surgery planning, identification of tumours, diagnosis of organs, etc. In this article, a novel approach for medical image segmentation is proposed using a hybrid technique of genetic algorithm and fuzzy logic. Fuzzy logic can handle uncertain and imprecise information. Genetic algorithms help in global optimization, gives good results in noisy environments and supports multi-objective optimization. Gaussian, trapezoidal and triangular membership functions are used separately for calculating the entropy and finding the fitness value. CPU time, Root Mean Square Error, sensitivity, specificity, and accuracy are calculated using the three membership functions separately at threshold levels 2, 3, 4, 5, 7 and 9. MRI images are considered for applying the proposed method and the results are analysed. The experimental results obtained prove the effectiveness and efficiency of the proposed method.

Download Full-text

Medical Image Thresholding Using Genetic Algorithm and Fuzzy Membership Functions

Research Anthology on Multi-Industry Uses of Genetic Programming and Algorithms ◽

10.4018/978-1-7998-8048-6.ch045 ◽

2021 ◽

pp. 896-916

Author(s):

Shashwati Mishra ◽

Mrutyunjaya Panda

Keyword(s):

Genetic Algorithm ◽

Fuzzy Logic ◽

Image Segmentation ◽

Medical Image ◽

Medical Image Segmentation ◽

Hybrid Technique ◽

Membership Functions ◽

Novel Approach ◽

Sensitivity Specificity ◽

Processing Techniques

Thresholding is one of the important steps in image analysis process and used extensively in different image processing techniques. Medical image segmentation plays a very important role in surgery planning, identification of tumours, diagnosis of organs, etc. In this article, a novel approach for medical image segmentation is proposed using a hybrid technique of genetic algorithm and fuzzy logic. Fuzzy logic can handle uncertain and imprecise information. Genetic algorithms help in global optimization, gives good results in noisy environments and supports multi-objective optimization. Gaussian, trapezoidal and triangular membership functions are used separately for calculating the entropy and finding the fitness value. CPU time, Root Mean Square Error, sensitivity, specificity, and accuracy are calculated using the three membership functions separately at threshold levels 2, 3, 4, 5, 7 and 9. MRI images are considered for applying the proposed method and the results are analysed. The experimental results obtained prove the effectiveness and efficiency of the proposed method.

Download Full-text