Linear Regression Modeling Based Scoring System to Reduce Benign Breast Biopsies Using Multi-parametric US with Color Doppler and SWE

Burcu Özdemir Demirci M.D; Onur Buğdaycı M.D; Gökhan Ertaş; Deniz E T Şanlı M.D; Handan Kaya M.D; Erkin Arıbal M.D

doi:10.1016/j.acra.2023.01.024

Linear Regression Modeling Based Scoring System to Reduce Benign Breast Biopsies Using Multi-parametric US with Color Doppler and SWE

Acad Radiol. 2023 Sep:30 Suppl 2:S143-S153. doi: 10.1016/j.acra.2023.01.024. Epub 2023 Feb 16.

Authors

Burcu Özdemir Demirci M.D¹, Onur Buğdaycı M.D², Gökhan Ertaş³, Deniz E T Şanlı M.D⁴, Handan Kaya M.D⁵, Erkin Arıbal M.D⁶

Affiliations

¹ Department of Radiology, Marmara University, Istanbul, Türkiye.
² Department of Radiology, Marmara University, Istanbul, Türkiye. Electronic address: onur.bugdayci@marmara.edu.tr.
³ Department of Biomedical Engineering, Yeditepe University, Istanbul, Türkiye.
⁴ Department of Radiology, Acibadem Kozyatagi Hospital, Istanbul, Türkiye; Department of Radiology, Gaziantep University, Gaziantep, Türkiye.
⁵ Department of Pathology, Marmara University, Istanbul, Türkiye.
⁶ Department of Radiology, Marmara University, Istanbul, Türkiye; Department of Radiology, Acıbadem University Medical School, Istanbul, Türkiye.

PMID: 36804295
DOI: 10.1016/j.acra.2023.01.024

Abstract

Rationale and objectives: To develop a simple ultrasound (US) based scoring system to reduce benign breast biopsies.

Materials and methods: Women with BI-RADS 4 or 5 breast lesions underwent shear-wave elastography (SWE) imaging before biopsy. Standard US and color Doppler US (CDUS) parameters were recorded, and the size ratio (Sz_R=longest/shortest diameter) was calculated. Measured/calculated SWE parameters were minimum (SWV_Min) and maximum (SWV_Max) shear velocity, velocity heterogeneity (SWV_H=SWV_Max-SWV_Min), velocity ratio (SWV_R=SWV_Min/SWV_Max), and normalized SWV_R (SWV_Rn=(SWV_Max-SWV_Min)/SWV_Min). Linear regression analysis was performed by converting continuous parameters into categorical corresponding equivalents using decision tree analyses. Linear regression models were fitted using stepwise regression analysis and optimal coefficients for the predictors in the models were determined. A scoring model was devised from the results and validated using a different data set from another center consisting of 187 cases with BI-RADS 3, 4, and 5 lesions.

Results: A total of 418 lesions (238 benign, 180 malignant) were analyzed. US and CDUS parameters exhibited poor (AUC=0.592-0.696), SWE parameters exhibited poor-good (AUC=0.607-0.816) diagnostic performance in benign/malignant discrimination. Linear regression models of US+CDUS and US+SWE parameters revealed an AUC of 0.819 and 0.882, respectively. The developed scoring system could have avoided biopsy in 37.8% of benign lesions while missing 1.1% of malignant lesions. The scoring system was validated with a 100% NPV rate with a specificity of 74.6%.

Conclusion: The linear regression model using US+SWE parameters performed better than any single parameter alone. The developed scoring method could lead to a significant decrease in benign biopsies.

Keywords: Breast Neoplasms; Decision Trees; Elasticity Imaging Techniques; Ultrasonography, Mammary.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Biopsy
Breast / diagnostic imaging
Breast / pathology
Breast Neoplasms* / diagnostic imaging
Breast Neoplasms* / pathology
Diagnosis, Differential
Elasticity Imaging Techniques* / methods
Female
Humans
Linear Models
Reproducibility of Results
Sensitivity and Specificity
Ultrasonography, Mammary / methods