Intratumoral and peritumoral-based radiomics for assessment of lymphovascular invasion in invasive breast cancer: model development and validation.
AI interpretation is pending for this paper.
Open original publication →What the AI sees
Not AI summarized yet.
Research significance
Pending deeper interpretation.
Source abstract
BACKGROUND: Preoperative non-invasive assessment of lymphovascular invasion (LVI) is critical for optimizing surgical strategy and risk stratification in breast cancer patients, yet reliable preoperative predictive tools remain insufficient. Current radiomics studies for breast cancer LVI prediction predominantly focus on intratumoral region (ITR) features, while emerging evidence indicates that the peritumoral region (PTR) harbors tumor microenvironmental alterations closely related to tumor invasion and metastasis and possesses unique diagnostic potential. However, existing studies rarely explore the predictive value of magnetic resonance imaging (MRI)-based radiomics features from different peritumoral subregions for breast cancer LVI, and there is no unified consensus on the optimal effective peritumoral expansion range for LVI prediction. This study aimed to explore the predictive value of multi‑range peritumoral MRI radiomics features for LVI in breast cancer and identify the optimal peritumoral margin. METHODS: A total of 291 patients with invasive breast carcinoma who received preoperative dynamic contrast-enhanced MRI (DCE-MRI) at Gansu Provincial Maternity and Child-Care Hospital (Gansu Provincial Central Hospital) between December 2019 and August 2023 were enrolled and divided into training (n=204) and testing (n=87) cohorts. Radiomics features were extracted from ITR, PTR-5 mm, PTR-10 mm, combined ITR and PTR-5 mm (ITR+PTR-5 mm), and combined ITR and PTR-10 mm (ITR+PTR-10 mm) on preoperative DCE-MRI images. Feature consistency screening, dimensionality reduction, and optimization were sequentially performed via intra-class correlation coefficients (ICCs), Spearman correlation analysis, and least absolute shrinkage and selection operator (LASSO) regression with 10-fold cross-validation. Five radiomics prediction models based on the random forest (RF) algorithm were constructed corresponding to the five feature regions. The predictive performance of each model was comprehensively assessed using receiver operating characteristic (ROC) curves, from which the area under the curve (AUC), sensitivity, specificity, and accuracy were calculated, calibration curve with the Hosmer-Lemeshow test, and decision curve analysis (DCA). The clinically meaningful threshold ranges of model efficacy indicators were further clarified for clinical decision-making reference. RESULTS: The ITR+PTR-5 mm radiomics model yielded the optimal and most stable predictive efficacy with AUC values of 0.920 (training cohort) and 0.794 (test cohort). The calibration curve of this model showed excellent consistency between predicted probabilities and actual observed LVI status. DCA verified that this model provided the highest clinical net benefit across a wide range of threshold probabilities compared with other models. CONCLUSIONS: The DCE-MRI-based ITR+PTR-5 mm radiomics model can serve as a potential noninvasive auxiliary tool for preoperative LVI risk assessment, providing tentative evidence for individualized clinical treatment decision-making.