Radiomic Signatures Derived from Diffusion-Weighted Imaging for the Assessment of Breast Cancer Receptor Status and Molecular Subtypes

Doris Leithner,Blanca Bernard-Davila,Maria Adele Marino,Joao V Horvat,Elizabeth A Morris,Maxine S Jochelson,Elizabeth J Sutton,R Elena Ochoa-Albiztegui,Sunitha B Thakur,Daly Avendano,Katja Pinker,Danny F Martinez

doi:10.1007/s11307-019-01383-w

Abstract

PurposeTo compare annotation segmentation approaches and to assess the value of radiomics analysis applied to diffusion-weighted imaging (DWI) for evaluation of breast cancer receptor status and molecular subtyping.ProceduresIn this IRB-approved HIPAA-compliant retrospective study, 91 patients with treatment-naïve breast malignancies proven by image-guided breast biopsy, (luminal A, n = 49; luminal B, n = 8; human epidermal growth factor receptor 2 [HER2]-enriched, n = 11; triple negative [TN], n = 23) underwent multiparametric magnetic resonance imaging (MRI) of the breast at 3 T with dynamic contrast-enhanced MRI, T2-weighted and DW imaging. Lesions were manually segmented on high b-value DW images and segmentation ROIS were propagated to apparent diffusion coefficient (ADC) maps. In addition in a subgroup (n = 79) where lesions were discernable on ADC maps alone, these were also directly segmented there. To derive radiomics signatures, the following features were extracted and analyzed: first-order histogram (HIS), co-occurrence matrix (COM), run-length matrix (RLM), absolute gradient, autoregressive model (ARM), discrete Haar wavelet transform (WAV), and lesion geometry. Fisher, probability of error and average correlation, 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 applied for pairwise differentiation of receptor status and molecular subtyping. Histopathologic results were considered the gold standard.ResultsFor lesion that were segmented on DWI and segmentation ROIs were propagated to ADC maps the following classification accuracies > 90% were obtained: luminal B vs. HER2-enriched, 94.7 % (based on COM features); luminal B vs. others, 92.3 % (COM, HIS); and HER2-enriched vs. others, 90.1 % (RLM, COM). For lesions that were segmented directly on ADC maps, better results were achieved yielding the following classification accuracies: luminal B vs. HER2-enriched, 100 % (COM, WAV); luminal A vs. luminal B, 91.5 % (COM, WAV); and luminal B vs. others, 91.1 % (WAV, ARM, COM).ConclusionsRadiomic signatures from DWI with ADC mapping allows evaluation of breast cancer receptor status and molecular subtyping with high diagnostic accuracy. Better classification accuracies were obtained when breast tumor segmentations could be performed on ADC maps.

Highlights

With the revelation that breast cancer is a genetic disease, it has become evident that traditional classifications based on tumor histology, size, grade, and receptor status cannot fully capture its characteristics
Of the 91 lesions, in 79 lesions, areas of decreased apparent diffusion coefficient (ADC) values were confidently identifiable on ADC maps alone without the need for correlation with the high b-value images (41 luminal A, 6 luminal B, 10 human epidermal growth factor receptor 2 (HER2)-enriched, 22 triple negative (TN))
In these 79/91 lesions, tumor segmentation was performed using region of interest (ROI) constructed on diffusion-weighted imaging (DWI) on the one hand, and using ROIs directly drawn on the ADC maps on the other hand, for comparative analysis

Summary

Introduction

With the revelation that breast cancer is a genetic disease, it has become evident that traditional classifications based on tumor histology, size, grade, and receptor status cannot fully capture its characteristics. The assessment of molecular subtypes to guide treatment selection is currently performed by gene expression profiling or immunohistochemical surrogates from tissue samples [8,9,10]. This approach can be limited, as biopsy can only capture a small part of a potentially heterogeneous lesion. Previous radiomic studies in breast cancer have primarily focused on features derived from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and their utility for the prediction of molecular subtype [12,13,14,15], as well as tumor histology [16], risk of recurrence [17, 18], response to chemotherapy [19], and potential to metastasize [20, 21]. DWI with apparent diffusion coefficient (ADC) mapping visualizes diffusivity, which indirectly reflects cell density in solid tumors

Objectives

Methods

Results

Discussion

Conclusion