Predictive value of MRI-based deep learning model for lymphovascular invasion status in node-negative invasive breast cancer

Abstract

To retrospectively assess the effectiveness of deep learning (DL) model, based on breast magnetic resonance imaging (MRI), in predicting preoperative lymphovascular invasion (LVI) status in patients diagnosed with invasive breast cancer who have negative axillary lymph nodes (LNs). Data was gathered from 280 patients, including 148 with LVI-positive and 141 with LVI-negative lesions. These patients had undergone preoperative breast MRI and were histopathologically confirmed to have invasive breast cancer without axillary LN metastasis. The cohort was randomly split into training and validation groups in a 7:3 ratio. Radiomics features for each lesion were extracted from the first post-contrast dynamic contrast-enhanced (DCE)-MRI. The Least Absolute Shrinkage and Selection Operator (LASSO) regression method and logistic regression analyses were employed to identify significant radiomic features and clinicoradiological variables. These models were established using four machine learning (ML) algorithms and one DL algorithm. The predictive performance of the models (radiomics, clinicoradiological, and combination) was assessed through discrimination and compared using the DeLong test. Four clinicoradiological parameters and 10 radiomic features were selected by LASSO for model development. The Multilayer Perceptron (MLP) model, constructed using both radiomic and clinicoradiological features, demonstrated excellent performance in predicting LVI, achieving a high area under the curve (AUC) of 0.835 for validation. The DL model (MLP-radiomic) achieved the highest accuracy (AUC = 0.896), followed by DL model (MLP-combination) with an AUC of 0.835. Both DL models were significantly superior to the ML model (RF-clinical) with an AUC of 0.720. The DL model (MLP), which integrates radiomic features with clinicoradiological information, effectively aids in the preoperative determination of LVI status in patients with invasive breast cancer and negative axillary LNs. This is beneficial for making informed clinical decisions.

Keywords: Breast cancer; Deep learning; Lymphovascular invasion; Magnetic resonance imaging.

Figure 1

The overall workflow of the study. The patient recruitment and random grouping is displayed in the left dotted box. The radiomics workflow is displayed in the right dotted box.

Figure 2

Significant clinicoradiological features. (A) patient age, (B) TTP, (C) peritumor edema, and (D) IMPCs selected by logistic regression analysis.

Figure 3

Feature-weighted diagram of LASSO model with 10 features included in model (A) and feature correlation plot (B). *The LASSO coefficient is a negative value, and the radiomic features are arranged in descending order according to the absolute value of the LASSO coefficient.

Figure 4

The ROC curves of radiomics models based on five classifiers in (A) the training cohorts and (B) the validation cohorts.

Figure 5

The ROC curves of combined models based on five classifiers in (A) the training cohorts and (B) the validation cohorts.

Figure 6

The ROC curves of the optimal models based on radiomic signatures alone (Model 1), clinicoradiological variables (Model 2) and combined features including the above two (Model 3) in (A) the training cohorts and (B) the validation cohorts.