Comparison of the diagnostic effectiveness of ultrasound imaging coupled with three mathematical models for discriminating thyroid nodules

Abstract

Background

The overlapping nature of thyroid lesions visualized on ultrasound (US) images could result in misdiagnosis and missed diagnoses in clinical practice.

Purpose

To compare the diagnostic effectiveness of US coupled with three mathematical models, namely logistic regression (Logistics), partial least-squares discriminant analysis (PLS-DA), and support vector machine (SVM), in discriminating between malignant and benign thyroid nodules.

Material and Methods

A total of 588 thyroid nodules (287 benign and 301 malignant) were collected, among which 80% were utilized for constructing the mathematical models and the remaining 20% were used for internal validation. In addition, an external validation cohort comprising 160 nodules (80 benign and 80 malignant) was employed to validate the accuracy of these mathematical models.

Results

Our study demonstrated that all three models exhibited effective predictive capabilities for distinguishing between benign and malignant nodules, whose diagnostic effectiveness surpassed that of the TI-RADS classification, particularly in terms of true negative diagnoses. SVM achieved a higher diagnostic rate for malignant thyroid nodules (93.8%) compared to Logistics (91.5%) and PLS-DA (91.6%). PLS-DA exhibited higher diagnostic rates for benign thyroid nodules (91.9%) compared to Logistics (86.7%) and SVM (88.7%). Both the area under the receiver operating characteristic curve (AUC) values of PLS-DA (0.917) and SVM (0.913) were higher than that of Logistics (0.891).

Conclusion

Our findings indicate that SVM had significantly higher rates of true positive diagnoses and PLS-DA exhibited significantly higher rates of true negative diagnoses. All three models outperformed the TI-RADS classification in discriminating between malignant and benign thyroid nodules.

Keywords

Ultrasound thyroid nodule mathematical model logistic regression partial least squares discriminant analysis support vector machine

Get full access to this article

View all access options for this article.

References

Nguyen

Kang

Pham

, et al. Ultrasound image-based diagnosis of malignant thyroid nodule using artificial intelligence. Sensors 2020;20:1822.

Sheu

Levin

Schmid

. Therapy related alterations to the thyroid gland. Pathologe 2006;27:13–18.

Alexander

. Understanding the ability, and inability, of high-resolution ultrasound to guide thyroid nodule evaluation. Cancer Cytopathol 2020;128:236–237.

Haugen

Alexander

Bible

, 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.

Tessler

Middleton

Grant

, 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.

Chung

Baek

Choi

, et al. The relationship of thyroid nodule size on malignancy risk according to histological type of thyroid cancer. Acta Radiol 2020;61:620–628.

Dobruch-Sobczak

Jędrzejowski

Jakubowski

, et al. Errors and mistakes in ultrasound diagnostics of the thyroid gland. J Ultrasound 2014;14:61–73.

Melany

Chen

. Thyroid cancer: ultrasound imaging and fine-needle aspiration biopsy. Endocrinol Metab Clin North Am 2017;46:691–711.

Onenerk

Pusztaszeri

Canberk

, et al.

Triage of the indeterminate thyroid aspirate: what are the options for the practicing cytopathologist?

Cancer Cytopathol 2017;125:477–485.

10.

Hess

. Logistic regression. Transfusion 2019;59:2197–2198.

11.

Nick

Campbell

. Logistic regression. Methods Mol Biol 2007;404:273–301.

12.

Schober

Vetter

. Logistic regression in medical research. Anesth Analg 2021;132:365–366.

13.

El Sanharawi

Naudet

. Understanding logistic regression. J Fr Ophtalmol 2013;36:710–715.

14.

Sayeed

Rafeeq Ahmed

Vinmathi

, et al. Classification of transgenic mice by retinal imaging using SVMS. Comput Intell Neurosci 2022;2022:9063880. doi:10.1155/2022/9063880.

15.

Huang

Cai

Pacheco

, et al. Applications of support vector machine (SVM) learning in cancer genomics. Cancer Genomics Proteomics 2018;15:41–51.

16.

Huang

Chen

Lin

, et al. SVM and SVM ensembles in breast cancer prediction. PLoS One 2017;12:e0161501.

17.

Górski

Sordoń

Ciepiela

, et al. Voltammetric classification of ciders with PLS-DA. Talanta 2016;146:231–236.

18.

Ruiz-Perez

Guan

Madhivanan

, et al.

So you think you can PLS-DA?

BMC Bioinformatics 2020;21:2.

19.

Fathi

Oskouie

Tafazzoli

, et al. Metabonomics based NMR in Crohn’s disease applying PLS-DA. Gastroenterol Hepatol Bed Bench 2013;6:S82–S86.

20.

Gastaldelli

Sabatini

Carli

, et al. PPAR-γ-induced changes in visceral fat and adiponectin levels are associated with improvement of steatohepatitis in patients with NASH. Liver Int 2021;41:2659–2670.

21.

Cibas

Ali

. The 2017 Bethesda system for reporting thyroid cytopathology. Thyroid 2017;27:1341–1346.

22.

Hee

Hwan

Jin

, et al. Ultrasonography diagnosis and imaging-based management of thyroid nodules: revised Korean Society of Thyroid Radiology consensus statement and recommendations. Korean J Radiol 2016;17:370–395.

23.

Kim

Lee

Jung

, et al. Ultrasound assessment of synchronous thyroid nodules in patients with papillary thyroid cancer: a nodule-by-nodule analysis between ultrasound and pathology. Anticancer Res 2020;40:1779–1786.

24.

Zhang

Oluwo

Castillo

, et al. Thyroid nodule location on ultrasonography as a predictor of malignancy. Endocr Pract 2019;25:131–137.

25.

Ramundo

Lamartina

Falcone

, et al.

Is thyroid nodule location associated with malignancy risk?

Ultrasonography 2019;38:231–235.

26.

Grant

Tessler

Hoang

, et al. Thyroid ultrasound reporting lexicon: white paper of the ACR Thyroid Imaging, Reporting and Data System (TIRADS) committee. J Am Coll Radiol 2015;12:1272–1279.

27.

Yang

Song

Xue

, et al. Suggested amendment of TI-RADS classification of thyroid nodules by shear wave elastography. Acta Radiol 2020;61:1026–1033.

28.

Chen

Zhu

, et al. Diagnosis of thyroid nodules for ultrasonographic characteristics indicative of malignancy using random forest. BioData Min 2020;13:14.

29.

Akkus

Cai

Boonrod

, et al. A survey of deep-learning applications in ultrasound: artificial intelligence-powered ultrasound for improving clinical workflow. J Am Coll Radiol 2019;16:1318–1328.

30.

Jiang

, et al. Ultrasound image-based thyroid nodule automatic segmentation using convolutional neural networks. Int J Comput Assist Radiol Surg 2017;12:1895–1910.

31.

Zhang

, et al. Multivariate evaluation of Thyroid Imaging Reporting and Data System (TI-RADS) in diagnosis malignant thyroid nodule: application to PCA and PLS-DA analysis. Int J Clin Oncol 2017;22:448–454.

32.

Huang

Cai

Pacheco

, et al. Applications of support vector machine (SVM) learning in cancer genomics. Cancer Genomics Proteomics 2018;15:41–51.

33.

Aswathy

Jagannath

. An SVM approach towards breast cancer classification from H&E-stained histopathology images based on integrated features. Nat Rev Drug Discov 2021;59:1773–1783.

34.

Vadhiraj

Simpkin

O’Connell

, et al. Ultrasound image classification of thyroid nodules using machine learning techniques. Medicina (Kaunas) 2021;57:527.

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.02 MB