RSS-Feed abonnieren
DOI: 10.1055/a-2122-5585
Stratifying High-Risk Thyroid Nodules Using a Novel Deep Learning System
Funding This work was supported by grants from the Ministry of Science and Technology of Taiwan (MOST 110–2221-E-002–122-MY3 and MOST 110–2221-E-002–123-MY3).
Abstract
Introduction The current ultrasound scan classification system for thyroid nodules is time-consuming, labor-intensive, and subjective. Artificial intelligence (AI) has been shown to increase the accuracy of predicting the malignancy rate of thyroid nodules. This study aims to demonstrate the state-of-the-art Swin Transformer to classify thyroid nodules.
Materials and Methods Ultrasound images were collected prospectively from patients who received fine needle aspiration biopsy for thyroid nodules from January 2016 to June 2021. One hundred thirty-nine patients with malignant thyroid nodules were enrolled, while 235 patients with benign nodules served as controls. Images were fed to Swin-T and ResNeSt50 models to classify the thyroid nodules.
Results Patients with malignant nodules were younger and more likely male compared to those with benign nodules. The average sensitivity and specificity of Swin-T were 82.46% and 84.29%, respectively. The average sensitivity and specificity of ResNeSt50 were 72.51% and 77.14%, respectively. Receiver operating characteristics analysis revealed that the area under the curve of Swin-T was higher (AUC=0.91) than that of ResNeSt50 (AUC=0.82). The McNemar test evaluating the performance of these models showed that Swin-T had significantly better performance than ResNeSt50.
Swin-T classifier can be a useful tool in helping shared decision-making between physicians and patients with thyroid nodules, particularly in those with high-risk characteristics of sonographic patterns.
Publikationsverlauf
Eingereicht: 26. März 2023
Eingereicht: 15. Juni 2023
Angenommen: 28. Juni 2023
Artikel online veröffentlicht:
21. August 2023
© 2023. Thieme. All rights reserved.
Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany
-
References
- 1 Welker MJ, Orlov D. Thyroid nodules. Am Fam Physician 2003; 67: 559-566
- 2 Wiltshire JJ, Drake TM, Uttley L. et al. Systematic review of trends in the incidence rates of thyroid cancer. Thyroid 2016; 26: 1541-1552 DOI: 10.1089/thy.2016.0100.
- 3 Hagag P, Strauss S, Weiss M. Role of ultrasound-guided fine-needle aspiration biopsy in evaluation of nonpalpable thyroid nodules. Thyroid 1998; 8: 989-995 DOI: 10.1089/thy.1998.8.989.
- 4 Brito JP, Gionfriddo MR, Al Nofal A. et al. The accuracy of thyroid nodule ultrasound to predict thyroid cancer: Systematic review and meta-analysis. J Clin Endocrinol Metab 2014; 99: 1253-1263 DOI: 10.1210/jc.2013-2928.
- 5 Wu HH, Jones JN, Osman J. Fine-needle aspiration cytology of the thyroid: Ten years experience in a community teaching hospital. Diagn Cytopathol 2006; 34: 93-96 DOI: 10.1002/dc.20389.
- 6 Hegedus L. Clinical practice. The thyroid nodule. N Engl J Med 2004; 351: 1764-1771 DOI: 10.1056/NEJMcp031436.
- 7 Haugen BR, Alexander EK, Bible KC. et al. 2015 American Thyroid Association Management Guidelines for Adult Patients with Thyroid Nodules and Differentiated Thyroid Cancer: The American Thyroid Association Guidelines task force on thyroid nodules and differentiated thyroid cancer. Thyroid 2016; 26: 1-133 DOI: 10.1089/thy.2015.0020.
- 8 Horvath E, Majlis S, Rossi R. et al. An ultrasonogram reporting system for thyroid nodules stratifying cancer risk for clinical management. J Clin Endocrinol Metab 2009; 94: 1748-1751 DOI: 10.1210/jc.2008-1724.
- 9 Choi SH, Kim EK, Kwak JY. et al. Interobserver and intraobserver variations in ultrasound assessment of thyroid nodules. Thyroid 2010; 20: 167-172 DOI: 10.1089/thy.2008.0354.
- 10 Tessler FN, Middleton WD, Grant EG. et al. ACR Thyroid Imaging, Reporting and Data System (TI-RADS): White Paper of the ACR TI-RADS Committee. J Am Coll Radiol 2017; 14: 587-595 DOI: 10.1016/j.jacr.2017.01.046.
- 11 Russ G, Bonnema SJ, Erdogan MF. et al. European Thyroid Association Guidelines for Ultrasound Malignancy Risk Stratification of Thyroid Nodules in Adults: The EU-TIRADS. Eur Thyroid J 2017; 6: 225-237 DOI: 10.1159/000478927.
- 12 Tulecke MA, Wang HH. ThinPrep for cytologic evaluation of follicular thyroid lesions: correlation with histologic findings. Diagn Cytopathol 2004; 30: 7-13 DOI: 10.1002/dc.10391.
- 13 NCI Thyroid FNA State of the Science Conference. Cibas ES, Ali SZ. The Bethesda System For Reporting Thyroid Cytopathology. Am J Clin Pathol 2009; 132: 658-665 DOI: 10.1309/AJCPPHLWMI3JV4LA.
- 14 Liu Z, Lin Y, Cao Y et al. Swin Transformer: Hierarchical Vision Transformer using Shifted Windows Available at: https://ui.adsabs.harvard.edu/abs/2021arXiv210314030L; Date Accessed: March 01, 2021
- 15 Kornelius E, Lo SC, Huang CN. et al. The risk of thyroid cancer in patients with thyroid nodule 3 Cm or larger. Endocr Pract 2020; 26: 1286-1290 DOI: 10.4158/EP-2020-0136.
- 16 Shayganfar A, Hashemi P, Esfahani MM. et al. Prediction of thyroid nodule malignancy using thyroid imaging reporting and data system (TIRADS) and nodule size. Clin Imaging 2020; 60: 222-227 DOI: 10.1016/j.clinimag.2019.10.004.
- 17 Schiffmann L, Kostev K, Kalder M. Association between various thyroid gland diseases, TSH values and thyroid cancer: A case-control study. J Cancer Res Clin Oncol 2020; 146: 2989-2994 DOI: 10.1007/s00432-020-03283-x.
- 18 Haymart MR, Repplinger DJ, Leverson GE. et al. Higher serum thyroid stimulating hormone level in thyroid nodule patients is associated with greater risks of differentiated thyroid cancer and advanced tumor stage. J Clin Endocrinol Metab 2008; 93: 809-814 DOI: 10.1210/jc.2007-2215.
- 19 Boelaert K, Horacek J, Holder RL. et al. Serum thyrotropin concentration as a novel predictor of malignancy in thyroid nodules investigated by fine-needle aspiration. J Clin Endocrinol Metab 2006; 91: 4295-4301 DOI: 10.1210/jc.2006-0527.
- 20 Mekraksakit P, Rattanawong P, Karnchanasorn R. et al. Prognosis of differentiated thyroid carcinoma in patients with Graves disease: A systematic review and meta-analysis. Endocr Pract 2019; 25: 1323-1337 DOI: 10.4158/EP-2019-0201.
- 21 Staniforth JUL, Erdirimanne S, Eslick GD. Thyroid carcinoma in Graves’ disease: A meta-analysis. Int J Surg 2016; 27: 118-125 DOI: 10.1016/j.ijsu.2015.11.027.
- 22 Feldt-Rasmussen U. Hashimoto’s thyroiditis as a risk factor for thyroid cancer. Curr Opin Endocrinol Diabetes Obes 2020; 27: 364-371 DOI: 10.1097/MED.0000000000000570.
- 23 Negro R, Valcavi R, Toulis KA. Incidental thyroid cancer in toxic and nontoxic goiter: Is TSH associated with malignanCy rate? Results of a meta-analysis. Endocr Pract 2013; 19: 212-218 DOI: 10.4158/EP12234.OR.
- 24 Zhang H, Wu C, Zhang Z et al. ResNeSt: Split-attention networks. Available at: https://ui.adsabs.harvard.edu/abs/2020arXiv200408955Z; Date Accessed: April 01, 2020
- 25 Dai Y, Gao Y, Liu F. TransMed: Transformers advance multi-modal medical image classification. Diagnostics (Basel) 2021; 11 DOI: 10.3390/diagnostics11081384.
- 26 Dosovitskiy A, Beyer L, Kolesnikov A et al. An image is worth 16x16 words: Transformers for image recognition at scale. Available at: https://ui.adsabs.harvard.edu/abs/2020arXiv201011929D; Date Accessed: October 01, 2020
- 27 Thomas J, Haertling T. AIBx, artificial intelligence model to risk stratify thyroid nodules. Thyroid 2020; 30: 878-884 DOI: 10.1089/thy.2019.0752.
- 28 Ko SY, Lee JH, Yoon JH. et al. Deep convolutional neural network for the diagnosis of thyroid nodules on ultrasound. Head Neck 2019; 41: 885-891 DOI: 10.1002/hed.25415.
- 29 Bomhof-Roordink H, Gartner FR, Stiggelbout AM. et al. Key components of shared decision making models: A systematic review. BMJ Open 2019; 9: e031763 DOI: 10.1136/bmjopen-2019-031763.
- 30 Singh ONM, Bagautdinova D, Hargraves I. et al. Development and pilot testing of a conversation aid to support the evaluation of patients with thyroid nodules. Clin Endocrinol 2022; 96: 627-636 DOI: 10.1111/cen.14599.