Eigentumors for prediction of treatment failure in patients with early-stage breast cancer using dynamic contrast-enhanced MRI: a feasibility study

Abstract

We present a radiomics model to discriminate between patients at low risk and those at high risk of treatment failure at long-term follow-up based on eigentumors: principal components computed from volumes encompassing tumors in washin and washout images of pre-treatment dynamic contrast-enhanced (DCE-) MR images. Eigentumors were computed from the images of 563 patients from the MARGINS study. Subsequently, a least absolute shrinkage selection operator (LASSO) selected candidates from the components that contained 90% of the variance of the data. The model for prediction of survival after treatment (median follow-up time 86 months) was based on logistic regression. Receiver operating characteristic (ROC) analysis was applied and area-under-the-curve (AUC) values were computed as measures of training and cross-validated performances. The discriminating potential of the model was confirmed using Kaplan-Meier survival curves and log-rank tests. From the 322 principal components that explained 90% of the variance of the data, the LASSO selected 28 components. The ROC curves of the model yielded AUC values of 0.88, 0.77 and 0.73, for the training, leave-one-out cross-validated and bootstrapped performances, respectively. The bootstrapped Kaplan-Meier survival curves confirmed significant separation for all tumors (P < 0.0001). Survival analysis on immunohistochemical subgroups shows significant separation for the estrogen-receptor subtype tumors (P < 0.0001) and the triple-negative subtype tumors (P = 0.0039), but not for tumors of the HER2 subtype (P = 0.41). The results of this retrospective study show the potential of early-stage pre-treatment eigentumors for use in prediction of treatment failure of breast cancer.

Contralateral parenchymal enhancement on dynamic contrast-enhanced MRI reproduces as a biomarker of survival in ER-positive/HER2-negative breast cancer patients

“…While Hattangadi et al [ 12 ] focused on tumour-induced changes to the parenchyma directly around the index tumour, CPE focuses on the properties of the healthy parenchyma prior to tumourigenesis. Texture analysis of parenchymal tissue has been associated with signalling pathways and patient survival [ 37 , 38 ].…”

Preoperative prediction of lymphovascular invasion in invasive breast cancer with dynamic contrast‐enhanced‐MRI‐based radiomics

“…Dynamic contrast‐enhanced (DCE)‐MRI is essential in breast MRI applications, as it provides anatomical and hemodynamic information regarding the tumor with a high spatial resolution. DCE‐MRI‐based radiomics have been used for differentiating malignancy, classifying molecular subtypes, assessing Ki67 status, evaluating the risk of recurrence, predicting the response to treatment, and predicting sentinel lymph node metastasis in breast cancer . However, DCE‐MRI‐based radiomics for LVI prediction remains underinvestigated.…”

MRI-based radiomics model for preoperative prediction of 5-year survival in patients with hepatocellular carcinoma

“…Accumulating evidence also suggests the predictive value of an MRI-based radiomics model in nasopharyngeal carcinoma, breast cancer, glioma and cervical cancer. [29][30][31][32][33][34] Given the widespread application and predictive value of MRI, it is necessary to build an MRI-based prognosis model for treatment guidance in resectable HCC.…”