Application of artificial intelligence in ultrasound diagnostics of thyroid nodules

BACKGROUND: the use of artificial intelligence in ultrasound diagnosis of thyroid nodules is expected and quite promising. However, in order to understand this, it is necessary to see how a doctor works with its help, diagnosing diseases step by step, and how exactly this intelligence is implemented in practical healthcare. The current publication provides an overview of existing intelligent systems for supporting medical decisions in thyroidology, and describes in detail the capabilities of the Russian intelligent computer assistant for ultrasound diagnostics - a system for stratifying thyroid nodules by EU-TIRADS categories.

AIM: increasing the accuracy and reducing the time of ultrasound diagnostics in the study of thyroid nodules through the use of an intelligent system for assisting the ultrasound doctor at various stages of his activity with demonstration of the actions of the “assistant”.

MATERIALS AND METHODS: to understand the possibilities of ultrasound doctors using artificial intelligence in their work, the proposed solution is divided into stages, each of which demonstrates the additional capabilities that a doctor has when using intelligent computer vision methods. Various artificial neural network architectures are used as an intellectual base, which can be further trained like a human on new medical data.

RESULTS: the proposed intelligent solution allows the ultrasound doctor to have a “second opinion” at his workplace, which, by processing ultrasound cine loops, allows him to solve the problems of segmentation and stratification of thyroid nodules according to EU-TIRADS categories with an accuracy of 70%, i.e. at the level of a doctor with 5 years of experience. The proposed data driven approach will improve its accuracy as new patient loops are processed.

CONCLUSION: the narrative leads the reader to understand in what diagnostic processes it is useful to use artificial intelligence methods in the ultrasound diagnosis of thyroid nodules, and how natural and artificial intelligence can effectively interact within the framework of a software web application.

1. Mathur P, Mishra S, Awasthi R, Khanna A, Maheshwari K, et al. Artificial Intelligence in Healthcare: 2021 Year in Review. doi: https://doi.org/10.13140/RG.2.2.25350.24645/1

2. Słowińska-Klencka D, Popowicz B, Klencki M. Real-Time Ultrasonography and the Evaluation of Static Images Yield Different Results in the Assessment of EU-TIRADS Categories. J Clin Med. 2023;12(18):5809. doi: https://doi.org/10.3390/jcm12185809

3. Peng S, Liu Y, Lv W, et al. Deep learning-based artificial intelligence model to assist thyroid nodule diagnosis and management: a multicentre diagnostic study. Lancet Digit Heal. 2021. doi: https://doi.org/10.1016/S2589-7500(21)00041-8

4. Ha EJ, Lee JH, Lee DH, et al. Artificial Intelligence Model Assisting Thyroid Nodule Diagnosis and Management: A Multicenter Diagnostic Study. J Clin Endocrinol Metab. 2024;109(2):527-535. doi: https://doi.org/10.1210/clinem/dgad503

5. Трухин А.А., Захарова С.М., Дунаев М.Е., Исаева М.П., Гармаш А.А., Трошина Е.А. Роль искусственного интеллекта в дифференциальной ультразвуковой диагностике узловых образований щитовидной железы. Клиническая и экспериментальная тиреоидология. — 2022. — Т.18. — №2. С. 32-38. https://doi.org/10.14341/ket12730

6. Фартушный Э.Н., Сыч Ю.П., Фартушный И.Э., Кошечкин К.А., Лебедев Г.С. Стратификация узловых образований щитовидной железы по категориям Eu-TIRADS с использованием трансферного обучения свёрточных нейронных сетей // Клиническая и экспериментальная тиреоидология. — 2022. — Т.18. — №2. https://doi.org/10.14341/ket12724.

7. Manaev AV, Trukhin AA, Zakharova SM, Troshina EA, Mokrysheva NG, Garmash AA. Textural Statistical Features of Ultrasound Imaging of Thyroid Nodules in the Assessment of Malignancy Status. Phys At Nucl. 2023;86(11):2500-2506. doi: https://doi.org/10.1134/S1063778823110297

8. Цыгулева К.В., Ложкин И.А., Королев Д.В., Зайцев К.С., Дунаев М.Е., Гармаш А.А., и др. Исследование применения нейросетевых моделей в классификации узлов щитовидной железы по категориям EU-TIRADS для персонализации ультразвуковой диагностики щитовидной железы // Клиническая и экспериментальная тиреоидология. — 2023. — Т. 19. — №1. doi: https://doi.org/10.14341/ket12757

9. Jhade S, Gangavarapu S, Channabasamma Rozhdestvenskiy O. Smart Medicine: Exploring the Landscape of AI-Enhanced Clinical Decision Support Systems. MATEC Web of Conferences. 2024:392. doi: https://doi.org/10.1051/matecconf/202439201083

10. Hong N, Park H, Rhee Y. Machine Learning Applications in Endocrinology and Metabolism Research: An Overview. Endocrinol Metab. 2020;35(1):71-84

11. Гусев А.В., Владзимирский А.В., Шарова Д.Е., Арзамасов К.М., Храмов А.Е. Развитие исследований и разработок в сфере технологий искусственного интеллекта для здравоохранения в Российской Федерации: итоги 2021 года. 2022. — Т. 3. doi: https://doi.org/10.17816/DD107367

12. Комарь П.А., Дмитриев В.С., Ледяева А.М., Шадеркин И.А., Зеленский М.М. Рейтинг стартапов искусственного интеллекта: перспективы для здравоохранения России. // Журнал телемедицины и электронного здравоохранения. — 2021 г. — Т. 3. URL: https://cyberleninka.ru/article/n/reyting-startapov-iskusstvennogo-intellekta-perspektivy-dlya-zdravoohraneniya-rossii

13. Afridi A, Khan S. Digital transformation in healthcare rehabilitation: a narrative review. 2024;12:16-30. doi: https://doi.org/10.5937/jpmnt12-48336

14. Grigorieva N, Demkina A, Korobeynikova A. Digitalization in the Russian healthcare: barriers to digital maturity. Population and Economics. 2024;8:1-14. doi: https://doi.org/10.3897/popecon.8.e111793

15. Toldo M, Maracani A, Michieli U, Zanuttigh P. Unsupervised Domain Adaptation in Semantic Segmentation: A Review. Technologies. 2020;8:35. doi: https://doi.org/10.3390/technologies8020035

16. База данных №2023624099. База размеченных данных для решения задач классификации EU-TIRADS, автоматических детекции (локализации) и сегментации узловых образований щитовидной железы, дата государственной регистрации 21.10.2023 г.

17. Программа для ЭВМ №2023685308. Интеллектуальный ассистент врача ультразвуковой диагностики узловых образований щитовидной железы, дата государственной регистрации 24.10.2023 г.