ARTIFICIAL INTELLIGENCE FOR ULTRASOUND‑BASED DIAGNOSIS AND RISK STRATIFICATION OF THYROID NODULES: EVIDENCE, HUMAN FACTORS, AND HEALTH‑IT IMPLICATIONS

Joanna Ślusarczyk; Beata Szreder; Piotr Pietrzyk; Natalia Stanek; Patrycja Krawczyk; Maja Łapaj; Aleksandra Jagiełło; Zuzanna Noweta; Milena Lewicka; Tamara Chadań

doi:10.31435/ijitss.2(50).2026.5276

Authors

Joanna Ślusarczyk Provincial Hospital in Kielce, Poland https://orcid.org/0009-0008-6405-5963
Beata Szreder Medical University of Gdansk, Gdansk, Poland https://orcid.org/0009-0008-7876-2159
Piotr Pietrzyk Mazovian Bródno Hospital in Warsaw, Poland
Natalia Stanek Hospital of the Ministry of Interior and Administration in Katowice, Poland https://orcid.org/0009-0009-5745-5253
Patrycja Krawczyk Provincial Hospital in Kielce, Poland https://orcid.org/0009-0001-0536-4570
Maja Łapaj Hospital of the Ministry of Interior and Administration in Katowice, Poland https://orcid.org/0009-0006-8285-6997
Aleksandra Jagiełło Mazovian Bródno Hospital in Warsaw, Poland https://orcid.org/0009-0005-6310-6755
Zuzanna Noweta Collegium Medicum of the Nicolaus Copernicus University in Bydgoszcz, Poland https://orcid.org/0009-0009-8086-8101
Milena Lewicka Medical University of Gdansk, Gdansk, Poland https://orcid.org/0009-0006-2919-9537
Tamara Chadań Collegium Medicum of the Nicolaus Copernicus University in Bydgoszcz, Poland https://orcid.org/0009-0001-5891-7925

DOI:

https://doi.org/10.31435/ijitss.2(50).2026.5276

Keywords:

Thyroid Nodules, Ultrasound, Artificial Intelligence, Deep Learning, Computer-Aided Diagnosis, TI‑RADS

Abstract

Background: Thyroid ultrasound is the cornerstone of thyroid nodule assessment, yet image capture and interpretation remain operator‑dependent. Artificial intelligence (AI) is increasingly proposed to support malignancy risk stratification, align reporting with TI‑RADS frameworks, and reduce unnecessary fine‑needle aspiration biopsy (FNA).

Objective: To synthesize evidence from the last five years on AI-assisted thyroid nodule assessment using ultrasound, with emphasis on validation, generalizability, human–AI interaction, and health‑IT implications.

Methodology: Structured narrative review prioritizing multicenter or externally validated studies, workflow-oriented evaluations, and systematic reviews/meta‑analyses.

Results: AI may improve consistency among less experienced users in retrospective studies, but a prospective trial showed no workflow improvement and strong operator dependence. Recent multicenter studies increasingly use multi‑view images, cine/video, and multimodal copilots. Meta‑analyses highlight heterogeneity and the need for robust external validation.

Conclusion: Translation requires prospective decision-endpoint studies, standardized ultrasound scanning, uncertainty-aware outputs, and integration into structured reporting and monitoring systems.

References

Broomand Lomer, N., Ahmadzadeh, A. M., Ashoobi, M. A., Abdi, S., Ghasemi, A., & Gholamrezanezhad, A. (2026). CT-based radiomics and deep learning for preoperative thyroid nodule classification: A systematic review, meta-analysis, and radiologist comparison. Academic Radiology, 33(1), 98–116. https://doi.org/10.1016/j.acra.2025.09.045

Ni, J., You, Y., Wu, X., Chen, X., Wang, J., & Li, Y. (2025). Performance evaluation of deep learning for the detection and segmentation of thyroid nodules: Systematic review and meta-analysis. Journal of Medical Internet Research, 27, e73516. https://doi.org/10.2196/73516

Potipimpanon, P., Charakorn, N., & Hirunwiwatkul, P. (2022). A comparison of artificial intelligence versus radiologists in the diagnosis of thyroid nodules using ultrasonography: A systematic review and meta-analysis. European Archives of Oto-Rhino-Laryngology, 279(11), 5363–5373. https://doi.org/10.1007/s00405-022-07436-1

Xu, J., Xu, H.-L., Cao, Y.-N., Huang, Y., Gao, S., Wu, Q.-J., & Gong, T.-T. (2023). The performance of deep learning on thyroid nodule imaging predicts thyroid cancer: A systematic review and meta-analysis of epidemiological studies with independent external test sets. Diabetes & Metabolic Syndrome, 17(11), 102891. https://doi.org/10.1016/j.dsx.2023.102891

Chen, C., Jiang, Y., Yao, J., Lai, M., Liu, Y., Jiang, X., Ou, D., Feng, B., Zhou, L., Xu, J., Wu, L., Zhou, Y., Yue, W., Dong, F., & Xu, D. (2024). Deep learning to assist composition classification and thyroid solid nodule diagnosis: A multicenter diagnostic study. European Radiology, 34(4), 2323–2333. https://doi.org/10.1007/s00330-023-10269-z

Edström, A. B., Makouei, F., Wennervaldt, K., Lomholt, A. F., Kaltoft, M., Melchiors, J., Hvilsom, G. B., Bech, M., Tolsgaard, M., & Todsen, T. (2025). Human–AI collaboration for ultrasound diagnosis of thyroid nodules: A clinical trial. European Archives of Oto-Rhino-Laryngology, 282(6), 3221–3231. https://doi.org/10.1007/s00405-025-09236-9

Gatta, E., Gatta, R., Morandi, R., Isoli, S., Corvaglia, S., Vetrugno, S., Maltese, V., Pirola, I., Casella, C., & Cappelli, C. (2025). Machine learning for diagnosis of malignant thyroid nodules based on thyroid ultrasound: Systematic review and meta-analysis of studies with external datasets. European Journal of Radiology Open. Advance online publication. https://doi.org/10.1016/j.ejro.2025.100716

Haugen, B. R., Alexander, E. K., Bible, K. C., Doherty, G. M., Mandel, S. J., Nikiforov, Y. E., Pacini, F., Randolph, G. W., Sawka, A. M., Schlumberger, M., Schuff, K. G., Sherman, S. I., Sosa, J. A., Steward, D. L., Tuttle, R. M., & Wartofsky, L. (2016). 2015 American Thyroid Association management guidelines for adult patients with thyroid nodules and differentiated thyroid cancer. Thyroid, 26(1), 1–133. https://doi.org/10.1089/thy.2015.0020

Hou, X., Hua, M., Zhang, W., Ji, J., Zhang, X., Jiang, H., Li, M., Wu, X., Zhao, W., Sun, S., Cao, L., & Wang, L. (2024). An ultrasonography of thyroid nodules dataset with pathological diagnosis annotation for deep learning. Scientific Data, 11(1), 1272. https://doi.org/10.1038/s41597-024-04156-5

Huang, P., Zheng, B., Li, M., Xu, L., Rabbani, S., Mayet, A. M., Chen, C., Zhan, B., & Jun, H. (2022). The diagnostic value of artificial intelligence ultrasound S-Detect technology for thyroid nodules. Computational Intelligence and Neuroscience, 2022, 3656572. https://doi.org/10.1155/2022/3656572

Kang, S., Lee, E., Chung, C. W., Jang, H. N., Moon, J. H., Shin, Y., Kim, K., Li, Y., Shin, S. M., Kim, Y. H., Kwon, S. K., Ahn, C. H., Jung, K. Y., Hong, A. R., Park, Y. J., Park, D. J., Kwak, J. Y., & Cho, S. W. (2021). A beneficial role of computer-aided diagnosis system for less experienced physicians in the diagnosis of thyroid nodule on ultrasound. Scientific Reports, 11, 20448. https://doi.org/10.1038/s41598-021-99983-6

Russ, G., Bonnema, S. J., Erdogan, M. F., Durante, C., Ngu, R., & Leenhardt, L. (2017). European Thyroid Association guidelines for ultrasound malignancy risk stratification of thyroid nodules in adults: The EU-TIRADS. European Thyroid Journal, 6(5), 225–237. https://doi.org/10.1159/000478927

See-Mode Technologies Pte. Ltd. (2024). 510(k) summary: See-Mode Augmented Reporting Tool, Thyroid (SMART-T) (K240697). U.S. Food and Drug Administration. https://www.accessdata.fda.gov/cdrh_docs/pdf24/K240697.pdf

Tessler, F. N., Middleton, W. D., Grant, E. G., Hoang, J. K., Berland, L. L., Teefey, S. A., Cronan, J. J., Beland, M. D., Desser, T. S., Frates, M. C., Hammers, L. W., Hamper, U. M., Langer, J. E., Reading, C. C., Scoutt, L. M., & Stavros, A. T. (2017). ACR thyroid imaging, reporting and data system (TI-RADS): White paper of the ACR TI-RADS committee. Journal of the American College of Radiology, 14(5), 587–595. https://doi.org/10.1016/j.jacr.2017.01.046

Vahdati, S., Khosravi, B., Robinson, K. A., Rouzrokh, P., Moassefi, M., Akkus, Z., & Erickson, B. J. (2024). A multi-view deep learning model for thyroid nodules detection and characterization in ultrasound imaging. Bioengineering, 11(7), 648. https://doi.org/10.3390/bioengineering11070648

Wildman-Tobriner, B., Taghi-Zadeh, E., & Hoang, J. K. (2022). Artificial intelligence (AI) tools for thyroid nodules on ultrasound, from the AJR Special Series on AI applications. AJR American Journal of Roentgenology, 219(4), 1–8. https://doi.org/10.2214/AJR.22.27430

Yang, L., Li, C., Chen, Z., He, S., Wang, Z., & Liu, J. (2023). Diagnostic efficiency among EU-/C-/ACR-TIRADS and S-Detect for thyroid nodules: A systematic review and network meta-analysis. Frontiers in Endocrinology, 14, 1227339. https://doi.org/10.3389/fendo.2023.1227339

Yao, J., Wang, Y., Lei, Z., Wang, K., Feng, N., Dong, F., Zhou, J., Li, X., Hao, X., Shen, J., Zhao, S., Gao, Y., Wang, V., Ou, D., Li, W., Lu, Y., Chen, L., Yang, C., Wang, L., Feng, B., Zhou, Y., Chen, C., Yan, Y., Wang, Z., Ru, R., Chen, Y., Zhang, Y., & Xu, D. (2025). Multimodal GPT model for assisting thyroid nodule diagnosis and management. npj Digital Medicine, 8, 245. https://doi.org/10.1038/s41746-025-01652-9

Zhan, J., Zhang, J., Zhu, S., Ni, L., Zhang, C., & Hu, J. (2025). Diagnostic performance of ultrasound characteristics-based artificial intelligence models for thyroid nodules: A systematic review and meta-analysis. Frontiers in Oncology, 15, 1614603. https://doi.org/10.3389/fonc.2025.1614603

Zhou, Y., Chen, C., Yao, J., Yu, J., Feng, B., Sui, L., Yan, Y., Chen, X., Liu, Y., Zhang, X., Wang, H., Pan, Q., Zou, W., Zhang, Q., Lin, L., Xu, C., Yuan, S., He, Q., Ding, X., Liang, P., Wang, V. Y., & Xu, D. (2025). A deep learning based ultrasound diagnostic tool driven by 3D visualization of thyroid nodules. npj Digital Medicine, 8, 126. https://doi.org/10.1038/s41746-025-01455-y