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

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.