Establishment of logistic regression analysis model of ultrasound characteristics of nodular goiter and thyroid cancer and its predictive value

Yang Liu; Mengqi Xiao; Yuanchun Li; Huilin Liu; Jinfeng Huang; Yuehui Jia

doi:10.1117/12.2636652

10 June 2022 Establishment of logistic regression analysis model of ultrasound characteristics of nodular goiter and thyroid cancer and its predictive value

Yang Liu, Mengqi Xiao, Yuanchun Li, Huilin Liu, Jinfeng Huang, Yuehui Jia

Author Affiliations +

Proceedings Volume 12179, Second International Conference on Medical Imaging and Additive Manufacturing (ICMIAM 2022); 1217905 (2022) https://doi.org/10.1117/12.2636652
Event: Second International Conference on Medical Imaging and Additive Manufacturing (ICMIAM 2022), 2022, Xiamen, China

Abstract

This study was aimed to investigate the value of logistic regression analysis model of ultrasound characteristics in differentiating nodular goiter and papillary thyroid carcinoma. Methods: A total of 184 patients with nodular goiter and thyroid cancer confirmed by surgery and pathology in our hospital were collected. Among them, 102 patients with nodular goiter and 82 patients with papillary thyroid carcinoma. All patients underwent conventional ultrasonography and contrast enhanced ultrasonography before surgery. The ultrasound image features were compared and analyzed, and univariate analysis was performed by χ2 test. With statistically significant indicators as independent variables, then multiple logistic regression analysis was performed, and receiver operating characteristic (ROC) curves were constructed to analyze the diagnostic performance of the logistic regression model. Results: Univariate analysis showed that age, lesion number, shape, margin, aspect ratio, calcification, micro calcification, enhancement mode, internal echo, internal structure, cystic degeneration and other factors were statistical significance (P<0.05).Multivariate analysis showed that irregular shape, mass effect, aspect ratio greater than 1, internal nodule echo, micro calcification and contrast-enhanced ultrasound were independent predictors for differentiating nodular goiter from thyroid cancer (P<0.05). The area under the ROC curve constructed by the independent predictors was 0.954, and the sensitivity and specificity were 95.1% and 83.3%, respectively. Conclusion: The logistic regression analysis model of ultrasound features has important value in the identification of nodular goiter and thyroid cancer.

Citation Download Citation

Yang Liu, Mengqi Xiao, Yuanchun Li, Huilin Liu, Jinfeng Huang, and Yuehui Jia "Establishment of logistic regression analysis model of ultrasound characteristics of nodular goiter and thyroid cancer and its predictive value", Proc. SPIE 12179, Second International Conference on Medical Imaging and Additive Manufacturing (ICMIAM 2022), 1217905 (10 June 2022); https://doi.org/10.1117/12.2636652

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Ultrasonography

Statistical analysis

Tumor growth modeling

Tissues

Tumors

Cancer

Solids

Show All Keywords

Keywords/Phrases

Search In:

Publication Years