1. Intratumoral and Peritumoral Radiomics Based on Preoperative MRI for Evaluation of Programmed Cell Death Ligand-1 Expression in Breast Cancer.
- Author
-
Wu Z, Lin Q, Wang H, Chen J, Wang G, Fu G, Li L, and Bian T
- Subjects
- Humans, Female, Retrospective Studies, Middle Aged, Adult, Aged, ROC Curve, Image Processing, Computer-Assisted methods, Breast diagnostic imaging, Radiomics, Breast Neoplasms diagnostic imaging, Magnetic Resonance Imaging methods, B7-H1 Antigen metabolism, Contrast Media
- Abstract
Background: Programmed cell death ligand-1 (PD-L1) is a promising target for immune checkpoint blockade therapy in breast cancer. However, the preoperative evaluation of PD-L1 expression in breast cancer is rarely explored., Purpose: To determine the ability of radiomics signatures based on preoperative dynamic contrast-enhanced (DCE) MRI to evaluate PD-L1 expression in breast cancer., Study Type: Retrospective., Population: 196 primary breast cancer patients with preoperative MRI and postoperative pathological evaluation of PD-L1 expression, divided into training (n = 137, 28 PD-L1-positive) and test cohorts (n = 59, 12 PD-L1-positive)., Field Strength/sequence: 3.0T; volume imaging for breast assessment DCE sequence., Assessment: Radiomics features were extracted from the first phase of DCE-MRI by using the minimum redundancy maximum relevance method and least absolute shrinkage and selection operator algorithm. Three radiomics signatures were constructed based on the intratumoral, peritumoral, and combined intra- and peritumoral regions. The performance of the signatures was assessed using area under the receiver operating characteristic (ROC) curve (AUC), sensitivity, specificity, and accuracy., Statistical Tests: Univariable and multivariable logistic regression analysis, t-tests, chi-square tests, Fisher exact test or Yates correction, ROC analysis, and one-way analysis of variance. P < 0.05 was considered significant., Results: In the test cohort, the combined radiomics signature (AUC, 0.853) exhibited superior performance compared to the intratumoral (AUC, 0.816; P = 0.528) and peritumoral radiomics signatures (AUC, 0.846; P = 0.905) in PD-L1 status evaluation, although the differences did not reach statistical significance., Data Conclusion: Intratumoral and peritumoral radiomics signatures based on preoperative breast MRI showed some potential accuracy for the non-invasive evaluation of PD-L1 status in breast cancer., Level of Evidence: 4 TECHNICAL EFFICACY: Stage 2., (© 2023 International Society for Magnetic Resonance in Medicine.)
- Published
- 2024
- Full Text
- View/download PDF