Multiparametric MR-based feature fusion radiomics combined with ADC maps-based tumor proliferative burden in distinguishing TNBC versus non-TNBC

To investigate the incremental value of quantitative stratified apparent diffusion coefficient (ADC) defined tumor habitats for differentiating triple negative breast cancer (TNBC) from non-TNBC on multiparametric MRI (mpMRI) based feature-fusion radiomics (R ) model. 466 breast cancer patients (54 TNBC, 412 non-TNBC) who underwent routine breast MRIs in our hospital were retrospectively analyzed. Radiomics features were extracted from whole tumor on T2WI, diffusion-weighted imaging, ADC maps and the 2nd phase of dynamic contrast-enhanced MRI. Four models including the R model (fused features from all MRI sequences), R model (ADC radiomics feature), Stratified model (tumor habitas defined on stratified ADC parameters) and combinational R -Stratified model were constructed to distinguish TNBC versus non-TNBC. All cases were randomly divided into a training ( = 337) and test set ( = 129). The four competing models were validated using the area under the curve (AUC), sensitivity, specificity and accuracy. Both the R and Stratified models demonstrated good performance in distinguishing TNBC from non-TNBC, with best AUCs of 0.818 and 0.773 in the training and test sets. Stratified model revealed significant different tumor habitats (necrosis/cysts habitat, chaotic habitat or proliferative tumor core) between TNBC and non-TNBC with its top three discriminative parameters ( 0.05). The integrated R -Stratified model demonstrated superior accuracy over the other three models, with higher AUCs of 0.832 and 0.784 in the training and test set, respectively ( 0.05). The R -Stratified model through integrating various tumor habitats' information from whole-tumor ADC maps-based Stratified model and radiomics information from mpMRI-based R model, exhibits tremendous promise for identifying TNBC.