"Balina Optimizasyon Algoritması"nı İçeren Yeni Bir Hibrit Görüntü Segmentasyon Modeli Kullanılarak Siyah Mantar (Mukormikozis) ile Sağlık Davranışı Etkisinin ve Covid-19'un Tespiti

Öz

Covid-19 çeşitli ciddi sağlık sorunlarına yol açabilen ve ilişkili bireylerin sağlık davranışlarını etkileyebilen çeşitli mantar ve bakteri enfeksiyonlarıyla da ilişkilendirilmiştir. Bu bağlamda, mukormikoz olarak da bilinen siyah mantarın (BF) dahil edilmesinin yaygın olduğu bulunmuştur. Bu nedenle, BF'li covid-19 hastasının erken tespiti, ciddi hasarları önlemek için çok önemli kabul edilir. Bu nedenle, bu çalışmanın amacı, BF'li covid-19'un otomatik ve erken teşhisi için etkili bir yeni hibrit görüntü segmentasyon modeli önermektir. Bu amaçla, işlem görüntülerine uygulanan bir hibrit model önerildi. Ancak, görüntülerin segmentasyonu için "Otsu'nun eşikleme" ve "uyarlanabilir yöntem" kullanıldı ve optimizasyon için "Balina Optimizasyon Algoritması" (WOA) kullanıldı ve performans analizi yapıldı. Bu çalışmadan elde edilen sonuçlar, önerilen hibrit modelin diğer modellere kıyasla yüksek oranda doğruluk, kesinlik, duyarlılık, geri çağırma ve özgüllüğe sahip olduğunu göstermiştir. Bu çalışma aynı zamanda BF'li covid-19 hastaları bağlamında farklı sağlık davranışı çıkarımları da sunmaktadır.

Anahtar Kelimeler

• Kara Mantar
• Balina Optimizasyon Algoritması
• Hibrit Model
• COVID-19
• Görüntü Segmentasyonu
• Sağlık Davranışı

DETECTION OF HEALTH BEHAVIOR IMPACT AND COVID-19 WITH BLACK FUNGUS (MUCORMYCOSIS), USING A NOVEL HYBRID MODEL OF IMAGE SEGMENTATION, INCORPORATING “WHALE OPTIMIZATION ALGORITHM”

Öz

Covid-19 has also been linked to other fungal and bacterial infections which can lead to various serious health-related conditions, impacting the health behavior of the associated individuals. In this regard, the incorporation of black fungus (BF), also known as mucormycosis, is found to be common. Therefore, the early detection of covid-19 patient with BF is considered to be crucial to prevent any serious damages. Thus, the aim of this study is to propose an effective novel hybrid model of image segmentation for automated and early diagnosis of covid-19 with BF. For this purpose, a hybrid model was proposed which was applied to the processes images. However, the “Otsu’s thresholding” and the “adaptive method” were used for the segmentation of images and the “Whale Optimization Algorithm” (WOA) was used for optimization and performance analysis was conducted. The results obtained from this study showed that the proposed hybrid model has high percentage of accuracy, precision, sensitivity, recall and specificity as compared to other models. This study also provides different health behavior implications within the context of covid-19 patients with BF.

Anahtar Kelimeler

• Black Fungus
• Whale Optimization Algorithm
• Hybrid Model
• Covid-19
• Image Segmentation
• Health Behaviour

Kaynakça

1. Abd Elaziz, M., Lu, S., & He, S. (2021). A multi-leader whale optimization algorithm for global optimization and image segmentation. Expert Systems with Applications, 175, 114841.
2. Abdel-Basset, M., Mohamed, R., AbdelAziz, N. M., & Abouhawwash, M. (2022). HWOA: A hybrid whale optimization algorithm with a novel local minima avoidance method for multi-level thresholding color image segmentation. Expert Systems with Applications, 190, 116145.
3. Abualigah, L., Diabat, A., Sumari, P., & Gandomi, A. H. (2021). A novel evolutionary arithmetic optimization algorithm for multilevel thresholding segmentation of covid-19 ct images. Processes, 9(7), 1155.
4. Budhiraja, I., Garg, D., Kumar, N., & Sharma, R. (2022). A comprehensive review on variants of SARS-CoVs-2: Challenges, solutions and open issues. Computer Communications.
5. Charan, P. S., & Ramkumar, G. (2023). Mucormycosis Detection using Hybrid Convolutional Neural Network with Support Vector Machine and Compare the performance with Support Vector Machine. 2023 International Conference on Artificial Intelligence and Knowledge Discovery in Concurrent Engineering (ICECONF),
6. Charan, P. V. S., & Ramkumar, G. (2022a). Black Fungus Classification using Adaboost with SVM-based classifier and Compare accuracy with Support Vector Machine. 2022 5th International Conference on Contemporary Computing and Informatics (IC3I),
7. Charan, P. V. S., & Ramkumar, G. (2022b). A Novel Deep Learning based Black Fungus Detection using the Bagging Ensemble with K-Nearest Neighbor. 2022 5th International Conference on Contemporary Computing and Informatics (IC3I),
8. Chaudhari, V., Vairagade, V., Thakkar, A., Shende, H., & Vora, A. (2023). Nanotechnology-based fungal detection and treatment: current status and future perspective. Naunyn-Schmiedeberg's Archives of Pharmacology, 1-21.

9. Chavda, V. P., Vuppu, S., Mishra, T., Kamaraj, S., Patel, A. B., Sharma, N., & Chen, Z.-S. (2022). Recent review of COVID-19 management: Diagnosis, treatment and vaccination. Pharmacological Reports, 74(6), 1120-1148.
10. Cornely, O. A., Alastruey-Izquierdo, A., Arenz, D., Chen, S. C., Dannaoui, E., Hochhegger, B., Hoenigl, M., Jensen, H.
11. E., Lagrou, K., & Lewis, R. E. (2019). Global guideline for the diagnosis and management of mucormycosis: an initiative of the European Confederation of Medical Mycology in cooperation with the Mycoses Study Group
12. Education and Research Consortium. The Lancet infectious diseases, 19(12), e405-e421.
13. Got, A., Moussaoui, A., & Zouache, D. (2021). Hybrid filter-wrapper feature selection using whale optimization algorithm: A multi-objective approach. Expert Systems with Applications, 183, 115312.
14. Gurunathan, S., Lee, A. R., & Kim, J. H. (2022). Antifungal effect of nanoparticles against COVID-19 linked black fungus: a perspective on biomedical applications. International Journal of Molecular Sciences, 23(20), 12526.
15. Hoenigl, M. (2021). Invasive fungal disease complicating coronavirus disease 2019: when it rains, it spores. In (Vol. 73, pp. e1645-e1648): Oxford University Press US.
16. John, T. M., Jacob, C. N., & Kontoyiannis, D. P. (2021). When uncontrolled diabetes mellitus and severe COVID-19 converge: the perfect storm for mucormycosis. Journal of Fungi, 7(4), 298.
17. Karthikeyan, S., Ramkumar, G., Aravindkumar, S., Tamilselvi, M., Ramesh, S., & Ranjith, A. (2022). A novel deep learning-based black fungus disease identification using modified hybrid learning methodology. Contrast Media & Molecular Imaging, 2022.
18. Kumar, A., Kaur, S., & Kaur, H. (2021). EMERGENCE OF BLACK FUNGUS AND THE COVID-19 PANDEMIC. INNOVATIVE AND CURRENT ADVANCES IN AGRICULTURE AND ALLIED SCIENCES.
19. LeibundGut-Landmann, S., Wüthrich, M., & Hohl, T. M. (2012). Immunity to fungi. Current opinion in immunology, 24(4), 449-458.
20. Mahalakshmi, V., Balobaid, A., Kanisha, B., Sasirekha, R., & Ramkumar Raja, M. (2023). Artificial Intelligence: A Next-Level Approach in Confronting the COVID-19 Pandemic. Healthcare,
21. Prakash, H., Skiada, A., Paul, R. A., Chakrabarti, A., & Rudramurthy, S. M. (2021). Connecting the dots: interplay of pathogenic mechanisms between COVID-19 disease and mucormycosis. Journal of Fungi, 7(8), 616.
22. Raut, A., & Huy, N. T. (2021). Rising incidence of mucormycosis in patients with COVID-19: another challenge for India amidst the second wave? The Lancet Respiratory Medicine, 9(8), e77.
23. Rawson, T. M., Wilson, R. C., & Holmes, A. (2021). Understanding the role of bacterial and fungal infection in COVID-19. Clinical Microbiology and Infection, 27(1), 9-11.
24. Segrelles-Calvo, G., de S Araujo, G. R., & Frases, S. (2020). Systemic mycoses: a potential alert for complications in COVID-19 patients. Future Microbiology, 15(14), 1405-1413.
25. Spellberg, B., Edwards Jr, J., & Ibrahim, A. (2019). Novel perspectives on mucormycosis: pathophysiology, presentation, and management. Clinical microbiology reviews, 18(3), 556-569.
26. Tolle, L. B., & Standiford, T. J. (2019). Danger‐associated molecular patterns (DAMPs) in acute lung injury. The Journal of pathology, 229(2), 145-156.
27. Tongbram, S., Shimray, B. A., Singh, L. S., & Dhanachandra, N. (2021). A novel image segmentation approach using fcm and whale optimization algorithm. Journal of ambient intelligence and humanized computing, 1-15.
28. Wang, Q., Wu, M., Zheng, S., & Tian, X. (2018). The research of the enzymatic hydrolysis of black fungus beverage preparation technology. Food Research and Development, 39(24), 71-77.