AUTHOR=Xu Xiaojing , Lu Liren , Zhu Luoxi , Tan Yanjuan , Yu Lifang , Bao Lingyun 

TITLE=Predicting the molecular subtypes of breast cancer using nomograms based on three-dimensional ultrasonography characteristics

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.838787

DOI=10.3389/fonc.2022.838787

ISSN=2234-943X

ABSTRACT=Purpose:Molecular subtyping of breast cancer is a common practice for individualised cancer management because the molecular classification determines the prognosis and treatment. Therefore, the ability to identify different molecular subtypes of breast cancer preoperatively can be of great significance in clinical practice. The aims of this retrospective study were to investigate characteristic three-dimensional ultrasonographic imaging parameters of breast cancer that are associated with molecular subtypes and to establish nomograms to predict the molecular subtypes of breast cancers.
Methods:A total of 309 patients diagnosed with breast cancer between January 2017and December 2019 were enrolled. Sonographic features were compared between the different molecular subtypes. A multinomial logistic regression model was developed, and nomograms were constructed based on this model. 
Results:We evaluated the performance of the nomograms in terms of discrimination and calibration.Maximum diameter, irregular shape, non-parallel growth, heterogeneous internal echo, enhanced posterior echo, lymph node metastasis, retraction phenomenon, calcification, and elasticity score were entered into the multinomial model. We constructed three nomograms to visualize the final model. The probabilities of the different molecular subtypes could be calculated based on these nomograms. Based on the receiver operating characteristic curves of the model, the macro-area under the curve (AUC) was 0.744, and the micro-AUC was 0.787. The AUC was 0.759, 0.683, 0.747, and 0.785 for luminal A, luminal B, human epidermal growth factor receptor 2-positive, and triple-negative, respectively . The nomograms for the LA, HER2, and TN subtypes provided good calibration.
Conclusions:Sonographic features such as calcification and posterior acoustic features were significantly associated with the molecular subtype of breast cancer.The presence of the retraction phenomenon was the most important predictor for the LA subtype.Nomograms to predict the molecular subtype were established, and the calibration curves and receiver operating characteristic curves proved that the models had good performance.