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

Abstract

Purpose: To 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. Procedures: In 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), cooccurrence 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 Sunitha B. Thakur and Katja Pinker contributed equally to this work.

Quantitative Analysis of Enhancement Intensity and Patterns on Contrast-enhanced Spectral Mammography

“…Marino et al 18 had found that CESM and radiomics analysis had differential value in hormonal receptor status with accuracy of 78.4% to 100%. This study analysed CNR differences between receptor positive and negative lesions and concluded that enhancement intensity was related to hormonal receptor status.…”

Diffusion-weighted imaging of the breast—a consensus and mission statement from the EUSOBI International Breast Diffusion-Weighted Imaging working group

“…While the basic monoexponential diffusion model and resulting ADC values providing a simple and technically reproducible parameter are currently preferable in clinical practice, the working group explicitly acknowledges continuous developments in the field of DWI that hold promise and should be pursued in parallel with ADC standardization. For example, the heterogeneity of ADC values within lesions may be measured using histogram analysis and more advanced artificial intelligence techniques [75][76][77]. Furthermore, DWI techniques "beyond the ADC" [26], such as diffusion tensor imaging (DTI), which allows the analysis of diffusion anisotropy [78][79][80][81][82][83]; intravoxel incoherent motion (IVIM) imaging, which distinguishes between intravascular perfusion and extravascular microstructural diffusion components [84][85][86][87][88][89]; and non-Gaussian diffusion, which provides enhanced sensitivity to tissue complexity, for instance from the kurtosis model [11,[84][85][86][87][88][90][91][92][93], may enhance the value of DWI.…”

Magnetic resonance imaging-derived radiomic signature predicts locoregional failure after organ preservation therapy in patients with hypopharyngeal squamous cell carcinoma

“…Further study is warranted to assess whether DWI-driven radiomic signatures can predict 1-year LRF in patients with advanced HPSCC who want to receive OPT. Taken together, these findings suggest that a combination of image features through the analysis of CT images, MRI images (included DWI), and 18 F-FDG PET might provide enormous information about the tumor phenotypic features [40][41][42][43][44], and the aforementioned approach should be confirmed in future studies for patients with HPSCC who received CCRT for organ preservation.…”

“…Combining radiomic analysis and functional MRI modalities such as diffusion-weighted imaging (DWI) would have the potential effect of providing more information about the prognostic imaging phenotype in patients with advanced HPSCC. Recently, Leithner et al reported that radiomic analysis derived from DWI imaging can provide high accuracy in subclassifying the molecular subtypes of breast cancer (luminals A and B, and HER2 enriched) [40]. Dulhanty et al also demonstrated that radiomics-driven DWI can be used as a forcefully sensing strategy to help physicians precisely screen zone-level prostate cancers for further targeted biopsy treatment [41].…”