Abstract
Radiomic features hold potential to improve prediction of disease-free survival (DFS) in triple-negative breast cancer (TNBC) and may show better performance if developed from TNBC patients. We aimed to develop a radiomics score based on MRI features to estimate DFS in patients with TNBC. A total of 228 TNBC patients who underwent preoperative MRI and surgery between April 2012 and December 2016 were included. Patients were temporally divided into the training (n = 169) and validation (n = 59) set. Radiomic features of the tumor were extracted from T2-weighted and contrast-enhanced T1- weighted MRI. Then a radiomics score was constructed with the least absolute shrinkage and selection operator regression in the training set. Univariate and multivariate Cox proportional hazards models were used to determine what associations the radiomics score and clinicopathologic variables had with DFS. A combined clinicopathologic-radiomic (CCR) model was constructed based on multivariate Cox analysis. The incremental values of the radiomics score were evaluated by using the integrated area under the receiver operating characteristic curve (iAUC) and bootstrapping (n = 1000). The radiomics score, which consisted of 5 selected MRI features, was significantly associated with worse DFS in both the training and validation sets (p = 0.002, p = 0.033, respectively). In both the training and validation set, the radiomics score showed comparable performance with the clinicopathologic model. The CCR model demonstrated better performance than the clinicopathologic model in the training set (iAUC, 0.844; difference in iAUC, p < 0.001) and validation set (iAUC, 0.765, difference in iAUC, p < 0.001). In conclusion, MRI-based radiomic features can improve the prediction of DFS when integrated with clinicopathologic data in patients with TNBC.
Highlights
Breast cancer is a heterogeneous disease, and comprehensive genomic analysis has revealed the existence of four main breast cancer classes[1], similar to the intrinsic subtypes characterised by microarray-based gene expression profiling[2]
In this study we showed that the radiomics score was associated with disease-free survival (DFS) in both the training and validation data set, and that it remained an independent prognostic factor at multivariate analysis
As the clinicopathologic model was determined by the entire data set (n = 228), this approach would have provided a larger advantage to the clinicopathologic model
Summary
Breast cancer is a heterogeneous disease, and comprehensive genomic analysis has revealed the existence of four main breast cancer classes[1], similar to the intrinsic subtypes characterised by microarray-based gene expression profiling[2]. Radiomic features observed at preoperative staging magnetic resonance imaging (MRI) were reported to be independent biomarkers for disease-free survival (DFS) in patients with invasive breast cancer[12]. The majority of breast cancers included in this previous study were luminal subtype tumors, with the radiomics signature and the triple-negative subtype being identified as Characteristics Age, years* Tumor size on MRI, mm* Pathological T category pT1 pT2 pT3 Pathological N category pN0 pN1 pN2 Type of surgery Breast-conserving surgery Mastectomy Adjuvant radiation therapy No Yes Neoadjuvant chemotherapy No Yes Adjuvant chemotherapy No Yes Histological grade 1 or 2 3 Lymphovascular invasion No Yes. independent prognostic factors for DFS12. The imaging features of TNBC differ from non-TNBC subtypes, and semantic MRI features that are associated with worse survival differ between breast cancer subtypes[8,13,14].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
