Development of an algorithm for recognition of Toxoplasma gondii brain cysts in microscopic images based on fractal dimension

Toxoplasma gondii is an obligate intracellular parasite infecting up to one-third of the human population. There are currently no treatment options which could eradicate the parasite from the infected host. A gold-standard, confirmatory diagnostic bioassay test for toxoplasmosis uses microscopic identification of T. gondii cysts in brain samples of mice inoculated with biological samples under investigation, which is time-consuming and requires experienced microscopist. We upgrade the bioassay by applying computational image analysis. Choosing fractal dimension (FD) for automated cyst recognition is convenient, as this parameter is relatively stable for different parasite strains, cyst age, or mice genetic background. It is also convenient to have FD immediately calculated for each cyst found. We employ a block-based multiscale analysis to detect regions in high-resolution microscopic images, fulfilling the conditions to be classified as T. gondii brain cysts. Block size cannot be too small, as (i) it could reduce the FD calculation accuracy and (ii) significantly increase the computational burden of analysis which is meant to be objective, accurate, but also computationally efficient. Rather, the robustness of cyst recognition stems from the proposed framework and also relies in part on the inherent properties of brain cysts and typical cyst surroundings. We evaluate our approach on a number of microscopic images and show the performance estimates. The method could also be used for other objects well characterized by FD or another differentiating parameter.

Ilić, A.Ž., Trajković, J., Srbljanović, J. et al. Development of an algorithm for recognition of Toxoplasma gondii brain cysts in microscopic images based on fractal dimension. Eur. Phys. J. Spec. Top. (2025). https://doi.org/10.1140/epjs/s11734-025-01944-x