EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

The role of artificial intelligence in radiofrequency ablation of thyroid nodules: a review

Viacheslav A. Solovov, Andrey A. Fedulov, Olga N. Ablekova

Digital Diagnostics · 06.08.2026 · 7 (3) · 336-350

DOI: 10.17816/dd704814 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Digital Diagnostics, online erschienen am 06.08.2026. Verfasst von Viacheslav A. Solovov und 2 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The prevalence of thyroid nodules is relatively high, according to various studies, affecting a significant portion of the adult population—up to 68%. Although most nodules are benign and do not require a treatment, in certain cases, if clinical symptoms are present, such as a compression syndrome, a cosmetic defect, or manifestations of thyrotoxicosis, a therapy becomes necessary. Minimally invasive techniques, primarily ultrasound-guided radiofrequency ablation, are gradually taking on an important role in treating patients with thyroid nodules, demonstrating a favorable efficacy and safety. Given the high operator dependence of ultrasound examination and the technical specifics of radiofrequency ablation, the interest in implementing objective, artificial Intelligence-based tools supporting clinical decision-making at all stages of the procedure is growing. A literature search was conducted in PubMed/MEDLINE, Embase, Web of Science, Scopus, IEEE Xplore, CNKI, Wanfang, CiNii, KoreaMed, KISS, and DBpia databases. The review included clinical guidelines, systematic reviews and meta-analyses, narrative reviews, prospective and retrospective clinical studies, as well as original research and technical developments addressing the application of machine learning and computer vision methods in the radiofrequency ablation of thyroid nodules. In preprocedural diagnostics, artificial Intelligence systems demonstrate high diagnostic efficacy comparable to that of expert radiologists and are capable of reducing the number of unnecessary invasive interventions. Models for predicting the efficacy of radiofrequency ablation have been developed, integrating clinical and ultrasound predictors. New ultrasound navigation technologies have been proposed to provide the intra-procedural support. In the post-ablation period, the main challenge remains the objective assessment of ablation completeness. Despite the development of algorithmic approaches and automated methods for measuring ablation zones, the availability of clinically validated models for segmenting post-ablation changes in thyroid nodules remains limited. Thus, artificial Intelligence technologies demonstrate the highest clinical applicability in the preprocedural diagnostic stage. At the same time, solutions for the intra- and postprocedural use require further research, a confirmation of their impact on long-term clinical outcomes, and integration into routine clinical practice.

Zitieren

APA

Solovov, V. A., Fedulov, A. A., & Ablekova, O. N. (2026). The role of artificial intelligence in radiofrequency ablation of thyroid nodules: a review. Digital Diagnostics, 7(3), 336-350. https://doi.org/10.17816/dd704814

Vancouver

Solovov VA, Fedulov AA, Ablekova ON. The role of artificial intelligence in radiofrequency ablation of thyroid nodules: a review. Digital Diagnostics. 2026;7(3):336-350. doi:10.17816/dd704814

BibTeX
@article{Solovov2026,
  author = {Solovov, Viacheslav A. and Fedulov, Andrey A. and Ablekova, Olga N.},
  title = {The role of artificial intelligence in radiofrequency ablation of thyroid nodules: a review},
  journal = {Digital Diagnostics},
  year = {2026},
  volume = {7},
  number = {3},
  pages = {336--350},
  doi = {10.17816/dd704814}
}
Kostenlos starten →