Current status of machine learning in thyroid cytopathology

Abstract

The implementation of Digital Pathology has allowed the development of computational Pathology. Digital image-based applications that have received FDA Breakthrough Device Designation have been primarily focused on tissue specimens. The development of Artificial Intelligence-assisted algorithms using Cytology digital images has been much more limited due to technical challenges and a lack of optimized scanners for Cytology specimens. Despite the challenges in scanning whole slide images of cytology specimens, there have been many studies evaluating CP to create decision-support tools in Cytopathology. Among different Cytology specimens, thyroid fine needle aspiration biopsy (FNAB) specimens have one of the greatest potentials to benefit from machine learning algorithms (MLA) derived from digital images. Several authors have evaluated different machine learning algorithms focused on thyroid cytology in the past few years. The results are promising. The algorithms have mostly shown increased accuracy in the diagnosis and classification of thyroid cytology specimens. They have brought new insights and demonstrated the potential for improving future cytopathology workflow efficiency and accuracy. However, many issues still need to be addressed to further build on and improve current MLA models and their applications. To optimally train and validate MLA for thyroid cytology specimens, larger datasets obtained from multiple institutions are needed. MLAs hold great potential in improving thyroid cancer diagnostic speed and accuracy that will lead to improvements in patient management.

Keywords: Computational pathology; Cytology; Digital pathology; Machine learning algorithms; Thyroid.

Fig. 1

Whole slide image of a fine needle aspiration biopsy of a thyroid papillary carcinoma smear.