Algorithm for Calculating the Fractal Dimension of Medical Images Using Neutrophil Nuclei as an Example: Integration with Neural Network Segmentation to Simplify Training
Abstract A hybrid algorithm for automated analysis of blood smears is proposed, combining the localization of neutrophil nuclei using the U-Net convolutional neural network and the subsequent calculation of their fractal dimension via the box-counting method along the contour highlighted by the color method (HSV segmentation). The approach allows for dividing the task into two stages: highlighting the area of interest and classification by scalar feature, which reduces the requirements for the volume and complexity of the the training dataset required for neural network training. Experiments on a dataset of 300 images demonstrated satisfactory segmentation quality (IoU ≈ 0.44) and a correlation between fractal dimension values and neutrophil maturation stages (ρ = 0.9350, p < 0.001). The method eliminates the need for manual contour delineation and ensures reproducibility of the analysis, which makes it promising for laboratory diagnostics.
Algorithm for Calculating the Fractal Dimension of Medical Images Using Neutrophil Nuclei as an Example: Integration with Neural Network Segmentation to Simplify Training. // Measurement Techniques. – 2026. – DOI: 10.1134/S000635092670048X. – URL: https://link.springer.com/article/10.1134/S000635092670048X
(2026). Algorithm for Calculating the Fractal Dimension of Medical Images Using Neutrophil Nuclei as an Example: Integration with Neural Network Segmentation to Simplify Training. Measurement Techniques. https://doi.org/10.1134/S000635092670048X
“Algorithm for Calculating the Fractal Dimension of Medical Images Using Neutrophil Nuclei as an Example: Integration with Neural Network Segmentation to Simplify Training.” Measurement Techniques, 2026. doi:10.1134/S000635092670048X.
@article{article35876,
title = {Algorithm for Calculating the Fractal Dimension of Medical Images Using Neutrophil Nuclei as an Example: Integration with Neural Network Segmentation to Simplify Training},
journal = {Measurement Techniques},
year = {2026},
doi = {10.1134/S000635092670048X},
url = {https://link.springer.com/article/10.1134/S000635092670048X}
}
Abstract— The effective thermal conductivity of a pulsating heat pipe (also referred to as a dream pipe) is studied. In heat pipes of this type, longitudinal heat transfer is enhanced owing to forced working fluid pulsations. The...
Abstract— This work presents an exergetic analysis of the commercial parabolic trough collector (PTC) used for the water desalination that has a dimensions similar to Solar Electric Generating System parabolic trough collector Model...
Abstract— The article presents the results of numerically simulating a submerged jet flow of liquid metal (mercury) in a round tube under the effect of longitudinal magnetic field. The submerged jet is produced when liquid metal flows...
Abstract Scaling of slightly soluble compounds is a key problem of water treatment in heat supply and circulation cooling water systems, as well as in the use of membrane technologies. The problem of minimizing the risks of slightly...
Abstract The article presents the results of elaborating a compact small gas turbine power unit relating to the 180 kW capacity class intended for a wide use in various industry branches. The design solutions for and technical...