Skip to main content

Advertisement

SpringerLink
Log in

A Hybrid Approach using the Fuzzy Logic System and the Modified Genetic Algorithm for Prediction of Skin Cancer

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

In recent years the death rate from skin cancer (SC) disease tends to grow enormously. Various studies demonstrated that skin malignancy may rank third as a reason for death for each age gathering, after breast and lung cancer. It becomes necessary to diagnose this skin malignancy at an early stage. The objective of this study was to combine machine learning and soft computing techniques to achieve higher accuracy in the prediction of SC. To play out the exploration work we utilized two datasets, one from “111 Save Life hospital”, Jamshedpur, India, and the other is the UCI repository skin cancer dataset. In this paper, a hybrid technique was utilized that combined the advantages of the fuzzy logic system (FLS) and the genetic algorithm (GA). Classifiers such as support vector machine (SVM) and Naive Bayes (NB) were implemented. The modified genetic algorithm (Modified_GA) is used to select the best features which will participate in the fuzzy rules generation process. The modified GA selects the best features along with the calculation of the accuracy of the system based on the selected features. A new rule reduction algorithm (RR_algorithm) is then utilized to reduce the certain number of rules to decrease the complexity of the rule base of the fuzzy system. For the SCC_dataset, the Modified_GA algorithm selects four features with an increased accuracy value of 89.6552%. The RR_algorithm reduces 20 rules from the rule base of the FLS with a constant accuracy value of 98% compared with the FLS with a larger number of rules. For the UCI_dataset, the Modified_GA algorithm selects 19 features with an increased accuracy value of 97.3684%. The selected features were further reduced with the help of sequentialfs() function. Now, the total selected features were 15 with an increased accuracy value of 97.3684% (obtained by the SVM classifier) and 98.6842% (obtained by the NB classifier). Experimental results on the two datasets show that the proposed strategies strikingly improves the forecast precision of skin malignancy.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  1. Skin cancer statistics, melanoma of the skin is the 19th most common cancer world wide (2019). https://www.wcrf.org/dietandcancer/cancer-trends/skin-cancer-statistics

  2. Jha S, Mehta AK, Azad C (2020) A fuzzy logic based approach for prediction of squamous cell carcinoma. Soft Comput Theor Appl 1154:325–334

    Google Scholar 

  3. Aherne NJ, Dhawan A et al (2020) Mathematical oncology and its application in non melanoma skin cancer—a primer for radiation oncology professionals. Oral Oncol, 103

  4. Davis J, Bordeaux J (2013) Squamous cell carcinoma. JAMA Dermatol, 149

  5. Jha S , Mehta AK, Azad C (2019) A fuzzy logic based approach for prediction of basal cell carcinoma and squamous cell carcinoma among the data of skin cancer. EAI endorsed transaction on pervasive health and technology 5

  6. Chen M, Zhou P, Di W et al (2020) AI-skin: skin disease recognition based on self-learning and wide data collection through a closed-loop framework. Inf Fusion 54:1–9

    Article  Google Scholar 

  7. Zimmermann HJ (2001) Fuzzy set theory-and its applications. Kluwer Academy Publication, London

    Book  Google Scholar 

  8. Zadeh LA (1996) Fuzzy sets, fuzzy logic, and fuzzy systems. World Scientific Publication, New York

    Book  Google Scholar 

  9. Genetic algorithm (2019). https://www.sciencedirect.com/topics/engineering/genetic-algorithm

  10. Hilali-Jaghdam I, Ishak AB et al (2020) Quantum and classical genetic algorithms for multilevel segmentation of medical images: a comparative study. Comput Commun 162:83–93

    Article  Google Scholar 

  11. Kadampur MA et al (2020) Skin cancer detection: applying a deep learning based model driven architecture in the cloud for classifying dermal cell images. Inform Med Unlocked, 18

  12. Sajadimajd S, Bahramsoltani R et al (2020) Advances on natural polyphenols as anticancer agents for skin cancer. Pharmacol Res, 151

  13. Geller AC, Dickerman BA et al (2018) Skin cancer interventions across the cancer control continuum: a review of experimental evidence and future research directions. Prevent Med 111:442–450

    Article  Google Scholar 

  14. Marc B, Nupur K et al (2020) A panel of criteria for comprehensive assessment of severity of ultraviolet B radiation-induced non-melanoma skin cancers in SKH-1 mice. J Photochem Photobiol B Biol 205

  15. Ma YP et al (2020) The association between non steroidal anti-inflammatory drugs and skin cancer: different responses in American and European populations. Pharmacol Res 152

  16. OSullivan DE, et al (2019) Indoor tanning and skin cancer in Canada: a meta-analysis and attributable burden estimation. Cancer Epidemiol 59:1–7

  17. Lunsford NB et al (2018) Skin cancer knowledge, awareness, beliefs and preventive behaviors among black and Hispanic men and women. Prevent Med Rep 12:203–209

    Article  Google Scholar 

  18. Gandini S, Palli D et al (2018) Anti-hypertensive drugs and skin cancer risk: a review of the literature and meta-analysis. Crit Rev Oncol/Hematol 122:1–9

    Article  Google Scholar 

  19. Heaton H, Lawrence N (2019) Non-melanoma skin cancer in women. Int J Womens Dermatol 5:2–7

    Article  Google Scholar 

  20. Gandini S et al (2016) Atopic dermatitis, naevi count and skin cancer risk: a meta-analysis. J Dermatol Sci 84:137–143

    Article  Google Scholar 

  21. Attia ABE et al (2017) Noninvasive real-time characterization of non-melanoma skin cancers with handheld opt acoustic probes. Photo Acoust 7:20–26

    Google Scholar 

  22. Verma AK et al (2019) Comparison of skin disease prediction by feature selection using ensemble data mining techniques. Inform Med Unlocked, 16

  23. Caini S et al (2014) Vitamin D and melanoma and non-melanoma skin cancer risk and prognosis: a comprehensive review and meta-analysis. Eur J Cancer 50:2649–2658

    Article  Google Scholar 

  24. Alfed N, Khelifi F (2017) Bagged textural and color features for melanoma skin cancer detection in dermoscopic and standard images. Exp Syst Appl 90:101–110

    Article  Google Scholar 

  25. Hoshyar AN et al (2014) The beneficial techniques in preprocessing step of skin cancer detection system comparing. Procedia Comput Sci 42:25–31

    Article  Google Scholar 

  26. Jain S et al (2015) Computer aided melanoma skin cancer detection using image processing. Procedia Comput Sci 48:735–740

    Article  Google Scholar 

  27. Mahbod A et al (2020) Transfer learning using a multi-scale and multi-network ensemble for skin lesion classification. Comput Methods Prog Biomed, 193

  28. Pour MP et al (2020) Transform domain representation-driven convolutional neural networks for skin lesion segmentation. Exp Syst Appl 144

  29. Glanz K, Mayer JA (2005) Reducing ultraviolet radiation exposure to prevent skin cancer: methodology and measurement. Am J Prevent Med 29:131–142

    Article  Google Scholar 

  30. Tang J (2009) A multi-direction GVF snake for the segmentation of skin cancer images. Pattern Recognit 42:1172–1179

    Article  Google Scholar 

  31. Ksiazek W, Abdar M et al (2019) A novel machine learning approach for early detection of hepatocellular carcinoma patients. Cogn Syst Res 54:116–127

    Article  Google Scholar 

  32. Iraji MS (2017) Multi-layer architecture for adaptive fuzzy inference system with a large number of input features. Cogn Syst Res 42:23–41

    Article  Google Scholar 

  33. Sreejith S, Khanna Nehemiah H et al (2020) A classification framework using a diverse intensified strawberry optimized neural network (DISON) for clinical decision-making. Cogn Syst Res 64:98–116

    Article  Google Scholar 

  34. Chu Y, Zhao Y (2018) Bidirectional feature selection with global and local structure preservation for small size samples. Cogn Syst Res 52:756–764

    Article  Google Scholar 

  35. He K, Cao X, Shi Y, Nie D, Gao Y, Shen D (2019) Pelvic organ segmentation using distinctive curve guided fully convolutional networks. IEEE Trans Med Imaging 38(2):585–595

    Article  Google Scholar 

  36. Yu X, Ye X, Gao Q (2019) Pipeline image segmentation algorithm and heat loss calculation based on gene-regulated apoptosis mechanism. Int J Press Vess Pip 172:329–336

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Compter Applications, National Institute of Technology, Jamshedpur, India

    Saurabh Jha & Ashok Kumar Mehta

Authors
  1. Saurabh Jha
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ashok Kumar Mehta
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Saurabh Jha.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jha, S., Mehta, A.K. A Hybrid Approach using the Fuzzy Logic System and the Modified Genetic Algorithm for Prediction of Skin Cancer. Neural Process Lett 54, 751–784 (2022). https://doi.org/10.1007/s11063-021-10656-x

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11063-021-10656-x

Keywords

Search

Navigation