This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Artificial Intelligence in Thyroid Cytopathology: Diagnostic and Technical Insights
by
, , , , , , , , , , , ,
Mariachiara Negrelli
1,†
,
Chiara Frascarelli
1,2,†,
Fausto Maffini
1,
Elisa Mangione
1,
Clementina Di Tonno
1,
Mariano Lombardi
1,
Francesca Maria Porta
1,
Mario Urso
3,
Vincenzo L’Imperio
3
,
Fabio Pagni
3,
Claudio Bellevicine
4
,
Mariantonia Nacchio
4,
Umberto Malapelle
4
,
Giancarlo Troncone
4
,
Antonio Marra
2,5,
Giuseppe Curigliano
2,5,
Konstantinos Venetis
1,*,
Elena Guerini-Rocco
1,2,‡ and
Nicola Fusco
1,2,‡
1
Division of Pathology, European Institute of Oncology IRCCS, 20139 Milan, Italy
2
Department of Oncology and Hemato-Oncology, University of Milan, 20133 Milan, Italy
3
Department of Medicine and Surgery, Pathology, IRCCS Fondazione San Gerardo dei Tintori, University of Milano-Bicocca, 20900 Monza, Italy
4
Department of Public Health, University of Naples Federico II, 80131 Naples, Italy
5
Division of New Drugs and Early Drug Development for Innovative Therapies, European Institute of Oncology IRCCS, Via G. Ripamonti 435, 20141 Milan, Italy
*
Author to whom correspondence should be addressed.
†
These authors contributed equally to this work.
‡
These authors also contributed equally to this work.
Cancers 2025, 17(21), 3525; https://doi.org/10.3390/cancers17213525 (registering DOI)
Submission received: 22 August 2025
/
Revised: 22 October 2025
/
Accepted: 27 October 2025
/
Published: 31 October 2025
(This article belongs to the Special Issue Molecular Pathology and Human Cancers)
Simple Summary
Thyroid nodules are very common, and fine-needle aspiration cytology is the main test used to decide whether a nodule is benign or not. While this test is reliable in most cases, many samples fall into an “indeterminate” category, often leading to unnecessary operations or delays in treatment. New computer-based methods, known as deep learning, can analyze digital images of thyroid cytology slides and may help reduce this uncertainty. By learning patterns that even experienced specialists may overlook, these systems could support pathologists in making faster and more accurate decisions, especially in difficult cases. In this article, we discuss how deep learning has been applied to thyroid cytology, the technical and practical challenges it faces, and how it could eventually help make thyroid cancer diagnosis more precise, consistent, and accessible worldwide.
Abstract
Fine-needle aspiration cytology (FNAC) is the cornerstone of thyroid nodule evaluation, standardized by the Bethesda System. However, indeterminate categories (Bethesda III–IV) remain a major challenge, often leading to unnecessary surgery or delayed molecular testing. Deep learning (DL) has recently emerged as a promising adjunct in thyroid cytopathology, with applications spanning triage support, Bethesda category classification, and integration with molecular data. Yet, routine adoption is limited by preanalytical variability (staining, slide preparation, Z-stack acquisition, scanner heterogeneity), annotation bias, and domain shift, which reduce generalizability across centers. Most studies remain retrospective and single-institution, with limited external validation. This article provides a technical overview of DL in thyroid cytology, emphasizing preanalytical sources of variability, architectural choices, and potential clinical applications. We argue that standardized datasets, multicenter prospective trials, and robust explainability frameworks are essential prerequisites for safe clinical deployment. Looking forward, DL systems are most likely to enter practice as diagnostic co-pilots, Bethesda classifiers, and multimodal risk-stratification tools. With rigorous validation and ethical oversight, these technologies may augment cytopathologists, reduce interobserver variability, and help transform thyroid cytology into a more standardized and data-driven discipline.
