Radiomic signatures with contrast-enhanced magnetic resonance imaging for the assessment of breast cancer receptor status and molecular subtypes: initial results

Abstract

Background To evaluate the diagnostic performance of radiomic signatures extracted from contrast-enhanced magnetic resonance imaging (CE-MRI) for the assessment of breast cancer receptor status and molecular subtypes. Methods One hundred and forty-three patients with biopsy-proven breast cancer who underwent CE-MRI at 3 T were included in this IRB-approved HIPAA-compliant retrospective study. The training dataset comprised 91 patients (luminal A, n = 49; luminal B, n = 8; HER2-enriched, n = 11; triple negative, n = 23), while the validation dataset comprised 52 patients from a second institution (luminal A, n = 17; luminal B, n = 17; triple negative, n = 18). Radiomic analysis of manually segmented tumors included calculation of features derived from the first-order histogram (HIS), co-occurrence matrix (COM), run-length matrix (RLM), absolute gradient (GRA), autoregressive model (ARM), discrete Haar wavelet transform (WAV), and lesion geometry (GEO). Fisher, probability of error and average correlation (POE + ACC), and mutual information coefficients were used for feature selection. Linear discriminant analysis followed by k-nearest neighbor classification (with leave-one-out cross-validation) was used for pairwise radiomic-based separation of receptor status and molecular subtypes. Histopathology served as the standard of reference. Results In the training dataset, radiomic signatures yielded the following accuracies > 80%: luminal B vs. luminal A, 84.2% (mainly based on COM features); luminal B vs. triple negative, 83.9% (mainly based on GEO features); luminal B vs. all others, 89% (mainly based on COM features); and HER2-enriched vs. all others, 81.3% (mainly based on COM features). Radiomic signatures were successfully validated in the separate validation dataset for luminal A vs. luminal B (79.4%) and luminal B vs. triple negative (77.1%). Conclusions In this preliminary study, radiomic signatures with CE-MRI enable the assessment of breast cancer receptor status and molecular subtypes with high diagnostic accuracy. These results need to be confirmed in future larger studies.

A rapid volume of interest-based approach of radiomics analysis of breast MRI for tumor decoding and phenotyping of breast cancer

“…Again, these numbers lie within the 95% CI of our models, differing strongest in prediction of ER (AUC 0.79 vs 0.67). Our results in differentiation of molecular subtypes also go in line with a previous publication by Leithner et al [29], revealing comparable results for the differentiation of luminal A from HER2-enriched, luminal B from triple-negative and superior results for distinguishing HER2-enriched from triple-negative cancers.…”

Radiomics for Tumor Characterization in Breast Cancer Patients: A Feasibility Study Comparing Contrast-Enhanced Mammography and Magnetic Resonance Imaging

“…They therefore concluded that CAD-CEDM can provide complementary information to radiologists, mainly by reducing the number of false-positive findings. In a different study from the same group, Danala et al [23] used the CAD scheme of CEDM images to classify breast masses. The authors used the segmentation results obtained from dual-energy subtracted images of a CEDM dataset of 111 breast lesions to build a multilayer perceptron machine learning system able to classify mass lesions.…”

“…Several studies have already reported the value of radiomics analyses of DCE-MRI, including the value of DCE-MRI morphologic and functional radiomic features to provide insight into individual genomic signatures, breast cancer molecular subtypes, and clinically used recurrence scores [7,[20][21][22][23]. There are fewer studies on the value of radiomics analyses of CEM; nevertheless, based on these limited studies, the results have been encouraging [23][24][25]. Recently, we reported preliminary results on the potential of CEM radiomics analysis of 100 patients in a larger-scale CEM-only study [25].…”

MRI Radiomic Features: Association with Disease-Free Survival in Patients with Triple-Negative Breast Cancer

“…In the last few years, researchers have used various approaches when applying MRI-based radiomic features in breast imaging, but most studies have focused on the differential diagnosis of breast lesions, the prediction of pathological characteristics, and response to neoadjuvant chemotherapy [15][16][17][18][19][20][21][22] . Recently, one study reported that a MRI-based radiomics signature was an independent predictor of DFS 12 .…”

“…www.nature.com/scientificreports www.nature.com/scientificreports/ which investigated the role of radiomics in differentiating breast cancer subtypes have also shown that radiomic features related to lesion shape contribute the most among other features when discriminating TNBC from other subtypes 19,23 . Interestingly, whereas one shape-related radiomic feature was selected in the aforementioned study from Park et al 12 , none of the shape-related features were selected in our study.…”