Texture analysis on MR images helps predicting non-response to NAC in breast cancer

Abstract

BackgroundTo assess the performance of a predictive model of non-response to neoadjuvant chemotherapy (NAC) in patients with breast cancer based on texture, kinetic, and BI-RADS parameters measured from dynamic MRI.MethodsSixty-nine patients with invasive ductal carcinoma of the breast who underwent pre-treatment MRI were studied. Morphological parameters and biological markers were measured. Pathological complete response was defined as the absence of invasive and in situ cancer in breast and nodes. Pathological non-responders, partial and complete responders were identified. Dynamic imaging was performed at 1.5 T with a 3D axial T1W GRE fat-suppressed sequence. Visual texture, kinetic and BI-RADS parameters were measured in each lesion. ROC analysis and leave-one-out cross-validation were used to assess the performance of individual parameters, then the performance of multi-parametric models in predicting non-response to NAC.ResultsA model based on four pre-NAC parameters (inverse difference moment, GLN, LRHGE, wash-in) and k-means clustering as statistical classifier identified non-responders with 84 % sensitivity. BI-RADS mass/non-mass enhancement, biological markers and histological grade did not contribute significantly to the prediction.ConclusionPre-NAC texture and kinetic parameters help predicting non-benefit to NAC. Further testing including larger groups of patients with different tumor subtypes is needed to improve the generalization properties and validate the performance of the predictive model.

Multivariate machine learning models for prediction of pathologic response to neoadjuvant therapy in breast cancer using MRI features: a study using an independent validation set

“…One trial reported up to 23% of patients with primary operable breast cancer can have breast conserving surgery instead of mastectomy if treated with neoadjuvant therapy 7 . However, response rates to NAT vary among patients and have been shown to depend on subtype 8–16 . In fact, up to 30% of patients may not respond to NAT 17 .…”

“…In fact, up to 30% of patients may not respond to NAT 17 . These patients incur toxicities and costs of treatment but gain proportionally less benefit 7,8 . Identifying a method to predict which breast cancer patients will achieve pCR and which will have residual invasive disease (RD) following NAT would allow for improved stratification of patients to more appropriate treatment regimens 18 .…”

“…Among other means of predicting response to NAT, such as using tumor stage and receptor status 19 , features extracted from pre-treatment MRI have shown promise for this purpose 8,18,20–28 . Using MRI could provide a fast and noninvasive way to further stratify patients at no additional cost to patients who already require MRI as part of a standard preoperative workup for breast cancer.…”

Differentiating axillary lymph node metastasis in invasive breast cancer patients: A comparison of radiomic signatures from multiparametric breast MR sequences

“…Quantitative radiomic features extracted from breast dynamic contrast‐enhanced magnetic resonance imaging (DCE‐MRI) have been shown to be associated with genetic expression profiles in breast cancer . Radiomic breast MRI features have also been shown to be predictive of the response of neoadjuvant chemotherapy, recurrence risk, and recurrence‐free survival for breast cancer patients …”

Is the whole larger than the sum of the parts? Integrated PET/MRI as a tool for response prediction

“…Already the first valuable study showed a very good correlation of two different PET parameters with the final pathological response in primary tumors receiving neoadjuvant chemotherapy [18]. Also, for dedicated breast MRI, different parameters (diffusion-weighted imaging, perfusion changes, or functional tumor volume) were evaluated and have been shown to be of value for response assessment in neoadjuvant chemotherapy [21][22][23][24].…”