ABSTRACT
The quantitative studies of follicular thyroid tumors were applied for their morphological differentiation. The computer-aided analysis of the images permits objective and prompt estimation of the quantitative parameters of the structural components of a tumor in the histological sections. The comparison of the values obtained in the tissue samples could identify the most typical differentially diagnostic criteria that could help to define the type of a tumor, by replacing a routine morphological study based on the analysis of qualitative morphological signs. Its effectiveness is largely determined by the skill of a physician and the subjectivity of assessments of observed phenomena.
Subject(s)
Adenoma/diagnosis , Carcinoma, Papillary, Follicular/diagnosis , Diagnosis, Computer-Assisted , Thyroid Neoplasms/diagnosis , Adenoma/pathology , Carcinoma, Papillary, Follicular/pathology , Diagnosis, Differential , Humans , Thyroid Neoplasms/pathologyABSTRACT
Artificial neural network is a complex system capable of gathering and synthesizing data and capable of learning using particular given parameters. This technology was applied to studying cytological diagnostics of thyroid diseases to differentiate between follicular cancer and follicular adenoma. A complex of quantitative cytological characteristics was used to describe cytological preparations by examples of known cytological diagnosis to train the neural network. Among offered cytological examples, 96% were recognized correctly during testing.
Subject(s)
Adenocarcinoma, Follicular/pathology , Adenoma/pathology , Diagnosis, Computer-Assisted/methods , Neural Networks, Computer , Thyroid Neoplasms/pathology , Biopsy , Diagnosis, Differential , Humans , Reproducibility of Results , Retrospective StudiesABSTRACT
To establish the objective quantitative cytological parameters of thyroid follicular tumor cells for their further use as criteria for differential cytological diagnosis, the authors made a mathematical analysis of their values obtained by computer-aided karyocytometry of thyroid follicular tumors. It is recommended that the arithmetic mean values of nuclear areas, perimeters, and optic densities should be used as criteria for differential diagnosis when there are qualitative cytological signs indicating that the tumor under study may belong to the follicular type of papillary carcinoma.
