186 - Multisequence MRI-based nomogram for prediction of human epidermal growth factor receptor 2 expression in breast cancer
Accurate identification of human epidermal growth factor receptor 2 (HER2) expression has a clinical significance for the diagnosis and therapy in breast cancer (BC). This study was aimed at developing a nomogram based on multi-sequence MRI (msMRI) radiomics signatures (RSs) and imaging characterist...
Saved in:
Published in | Journal of medical imaging and radiation sciences Vol. 55; no. 3 |
---|---|
Main Authors | , |
Format | Journal Article |
Language | English |
Published |
Elsevier Inc
01.10.2024
|
Online Access | Get full text |
Cover
Loading…
Summary: | Accurate identification of human epidermal growth factor receptor 2 (HER2) expression has a clinical significance for the diagnosis and therapy in breast cancer (BC). This study was aimed at developing a nomogram based on multi-sequence MRI (msMRI) radiomics signatures (RSs) and imaging characteristics to predict HER2 expression in BC.
206 consecutive women diagnosed with invasive BC were retrospectively enrolled and randomly divided into a training set (n = 144) and validation set (n = 62). Tumor segmentation and feature extraction were performed on dynamic contrast-enhanced (DCE) MRI, T2-weighted imaging (T2WI), and apparent diffusion coefficient (ADC) map. Radiomics models were constructed using RSs, and radiomics score (Rad-score) was calculated. Rad-score and significant clinical-imaging characteristics were included in the multivariate analysis to establish the nomogram. The performance was mainly evaluated via the area under the curve (AUC) of receiver operating characteristic (ROC).
Edema types on T2WI (OR = 4.480, P = 0.008), enhancement type (OR = 7.550, P = 0.002), and Rad-score (OR = 5.906, P < 0.001) were independent risk predictors for HER2 expression. Radiomics model based on msMRI (AUCs of 0.936 and 0.880 in the training and validation sets, respectively) was superior to those based on one sequence or dual sequences. With the combination of edema and enhancement types, the nomogram achieved the highest performance in the training set (AUC: 0.940) and validation set (AUC: 0.893).
Multisequence MRI-based nomogram could effectively predict the HER2 expression in BC. |
---|---|
ISSN: | 1939-8654 |
DOI: | 10.1016/j.jmir.2024.101504 |