STRUCTURAL ANALYSIS OF MEDICAL IMAGES AND BACTERIAL POPULATIONS BY IMAGE PROCESSING AND ARTIFICIAL INTELLIGENCE

Year 2025, Volume: 9 Issue: 2, 229 - 235, 30.08.2025

Mehmet Erhan Şahin

https://doi.org/10.46519/ij3dptdi.1624544

Abstract

This study was carried out to investigate the structural properties of medical images and bacterial populations using fractal analysis and lacunarity measurements. In the study, image processing techniques, fractal and lacunar analysis methods and artificial intelligence-based models were used together to determine the geometric complexity and irregularity levels of healthy and pathological conditions. Deep learning models such as convolutional neural networks (CNN) and U-Net have been successfully applied to the classification and segmentation of images. The results showed that fractal dimension and lacunarity measures are effective tools for detecting fibrotic changes in lung tissue and pathological growth patterns in bacterial colonies. Differences between healthy and diseased states were successfully discriminated by fractal dimension and lacunarity values. Artificial intelligence based models have attracted attention with their high accuracy and sensitivity rates in image processing. This study reveals that the integration of fractal and lacunar analysis with artificial intelligence offers a strong potential for developing fast, objective and accurate decision support systems in medical diagnosis and microbiological analysis. In the future, it is recommended to apply this method on larger data sets and different disease models.

Keywords

Convolutional Neural Networks (CNN) , U-Net , Medical Imaging , Lung X-Ray Image , Image Processing , Decision Support Systems.

References

• 1. Smith, T. G., Lange, G. D., & Marks, W. B. “Fractal methods and results in cellular morphology—Dimensions, lacunarity, and multifractals”, Journal of Neuroscience Methods, Vol. 69, Issue 2, Pages 123–136, 1996.
• 2. Gonzalez, R. C., & Woods, R. E. Digital Image Processing, Pearson Education, 2018.
• 3. Ronneberger, O., Fischer, P., & Brox, T. “U-Net: Convolutional Networks for Biomedical Image Segmentation”, MICCAI, Pages 234–241, 2015.
• 4. Mandelbrot, B. The Fractal Geometry of Nature, W.H. Freeman, San Francisco, CA, 1982.
• 5. Losa, G.A., Merlini, D., Nonnenmacher, T.F., & Weibel, E.R. (Eds.) Fractals in Biology and Medicine (Vol. 4), Birkhäuser, Basel, Switzerland, 2005.
• 6. Di Ieva, A., Grizzi, F., Jelinek, H., Pellionisz, A.J., & Losa, G.A. “Fractals in the Neurosciences, Part I: General Principles and Basic Neurosciences”, Neuroscientist, Vol. 20, Issue 4, Pages 403–417, 2014.
• 7. Karperien, A., Jelinek, H., & Milosevic, N. “Reviewing lacunarity analysis and classification of microglia in neuroscience”, European Conference on Mathematical and Theoretical Biology, 2011.
• 8. Güleç, M., Taşsöker, M., & Şener, S. “Tıpta ve diş hekimliğinde fraktal analiz”, Ege Üniversitesi Diş Hekimliği Fakültesi Dergisi, Vol. 40, Issue 1, Pages 17–31, 2019.
• 9. Arsan, E., Genç, A., Gözü, A., & Şahin, B. “Fractal analysis for differentiation of idiopathic pulmonary fibrosis and normal lung parenchyma”, Digital Medicine, Vol. 3, Issue 2, Pages 61–66, 2017.
• 10. Bayrak, N., & Kırcı, M. “Fractal and lacunarity analysis of dental radiographs to detect periodontitis”, Journal of X-Ray Science and Technology, Vol. 28, Issue 2, Pages 309–321, 2020.
• 11. Karthik, R., Menaka, R., & Singh, S. P. “Fractal Analysis of Bacterial Colony Images for Predicting the Effect of Nano-Ag on the Production of Extracellular Enzymes in Bacillus subtilis”, Journal of Nanoscience and Nanotechnology, Vol. 19, Issue 7, Pages 3933–3941, 2019.
• 12. Yap, S.Y., Yeong, C.H., Ng, K.H., & Abdul Majid, Z. “Deep Learning Algorithms for Detection of Diabetic Retinopathy in Retinal Fundus Photographs: A Systematic Review and Meta-Analysis”, Computer Methods and Programs in Biomedicine, Vol. 196, Page 105642, 2020.
• 13. Tang, Y., Zhang, Y., Chai, Y., Wang, Y., & He, X. “Fractal analysis of Actinobacillus pleuropneumoniae biofilm initial adhesion using box-counting method”, Microbial Pathogenesis, Vol. 137, Page 103732, 2019.
• 14. Rafael, C., & Richard, E. Digital Image Processing, 2nd ed., Pearson Education, Upper Saddle River, NJ, 2008.
• 15. Tomasi, C., & Manduchi, R. “Bilateral Filtering for Gray and Color Images”, Proceedings of the Sixth International Conference on Computer Vision, Pages 839–846, 1998.
• 16. Ziou, D., & Tabbone, S. “Edge Detection Techniques – An Overview”, Pattern Recognition and Image Analysis C/C of Raspoznavaniye Obrazov I Analiz Izobrazhenii, Vol. 8, Issue 4, Pages 537–559, 1998. 17. Zhang, Y., Brady, M., & Smith, S. “Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm”, IEEE Transactions on Medical Imaging, Vol. 20, Issue 1, Pages 45–57, 2001.
• 18. Mureşan, R.C., Zaharie, D., & Zaharie, M. “Fractal Dimension for Data Mining”, In: Roşu, A-L., Rebedea, T. (eds), Data Mining with Decision Trees. Intelligent Systems Reference Library, Vol. 81, Springer, Cham, Pages 81–91, 2016.
• 19. Losa, G.A., & Nonnenmacher, T.F. “Self-affinity and fractal dimension in the microarchitecture of human cancellous bone”, European Journal of Morphology, Vol. 34, Issue 3, Pages 159–167, 1996.
• 20. LeCun, Y., Bengio, Y., & Hinton, G. “Deep learning”, Nature, Vol. 521, Issue 7553, Pages 436–444, 2015.
• 21. Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T., & Ronneberger, O. “3D U-Net: learning dense volumetric segmentation from sparse annotation”, In: Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Pages 424–432, 2016.
• 22. Kohavi, R. “A study of cross-validation and bootstrap for accuracy estimation and model selection”, In: Proceedings of the 14th International Joint Conference on Artificial Intelligence, Vol. 2, Pages 1137–1143, Montreal, Canada, Morgan Kaufmann Publishers Inc., 1995.
• 23. Saito, T., & Rehmsmeier, M. “The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets”, PloS One, Vol. 10, Issue 3, Page e0118432, 2015.