Using Deep Learning to Generate and Classify Thyroid Cytopathology Reports According to The Bethesda System

Abstract

The purpose of this paper is to study approaches to the intellectual processing of Russianlanguage textual medical information concerning the thyroid cytopathology description to solve the issues of their classification and generation of the text of the medical report, as well as augmentation of descriptions in their acute shortage. Over the past decade, the field of biomedicine has not undergone significant changes. Approaches to analyzing patients' problems are mostly based on manual processing and expert knowledge of doctors. The paper considers the creation of a machine-learning pipeline containing a full cycle of data preprocessing and model training in the field of thyroid nodules fine-needle aspiration classification according to the Bethesda thyroid cytopathology reporting system. Sequential and transformer neural networks were used to design the architecture of deep learning models. The paper proposes approaches for cleaning and preprocessing raw medical descriptions to the required type. The obtained results show that sequential neural networks have greater accuracy on small data sets, and transformation architectures are superior to others when generating cytopathological reports on large amounts of data. The solution obtained in the study can be used as an additional reference tool for thyroid cytologists.