Fractal geometry applied to the analysis of cervix biopsy.

Background: the measurement of the spaces of occupation of irregular objects in the context of fractal geometry has had some applications at a cellular morphometric level, where characterizations of normality and disease have been established. The objective of the present study is to apply a fractal methodology to characterize images from cervical colposcopy.

Materials And Methods: a mathematical and geometrical characterization of 67 cell samples was performed by measuring cellular fractal characteristics through the Box-Counting method, being nine normal, eight low-intraepithelial lesions, 16 high-intraepithelial lesions, eight carcinomas in situ, 20 squamous cell carcinomas and six endocervical carcinomas.

Results: the values of fractal dimension of the nuclear and cytoplasmic borders with respect to the totality varied between 0.719 to 1128 and 0.81 to 1024 while the occupation spaces in the 2 pixels grid were between 293 to 1606 and 64 to 693 respectively and in the 4 pixels grid oscillated between 153 to 894 and 36 to 361, respectively. Exocervical cells values had sensitivities between 78.3% to 100% in order to differentiate them from different types of cervical lesions.

Conclusions: according to the results obtained, the mathematical values found are suggestive of being able to differentiate between normality and some colposcopy-guided cervical biopsy lesions.