Role of texture analysis in breast MRI as a cancer biomarker: A review

Abstract

Breast cancer is a known heterogeneous disease. Current clinically utilized histopathologic biomarkers may undersample tumor heterogeneity, resulting in higher rates of misdiagnosis for breast cancer. MRI can provide a whole-tumor sampling of disease burden and is widely utilized in clinical care. Texture analysis can provide a localized description of breast cancer, with particular emphasis on quantifying breast lesion heterogeneity. The object of this review is to provide an overview of texture analysis applications towards breast cancer diagnosis, prognosis, and treatment response evaluation and review the role of image-based texture features as noninvasive prognostic and predictive biomarkers. Level of Evidence: 5 Technical Efficacy: Stage 2 J. MAGN. RESON. IMAGING 2019;49:927-938. View this article online at wileyonlinelibrary.com. Applications in Breast Computer-Aided DiagnosisComputer-aided diagnosis (CAD) of breast tissue was one of the earliest applications of texture analysis in the breast. 41 Gibbs and Turnbull 42 were one of the first to apply texture analysis toward classifying breast lesions as benign or malignant. The authors reported using 2D DCE-MR images from a cohort of 79 women, of which 45 were diagnosed with breast cancer. An ROI was selected to encompass the entire lesion, within which gray-level intensity values were discretized to 32 levels. Within each lesion ROI, a co-occurrence matrix was determined for adjoining pixels in 0 , 45 , 90 , and 135 directions. The co-occurrence matrices of each direction were averaged and 14 GLCM texture features were extracted. Texture features of variance, sum entropy, and 928

Performance evaluation of texture analysis based on kinetic parametric maps from breast DCE‐MRI in classifying benign from malignant lesions

“…Although such studies on texture analysis were directly based on post‐contrast images, our experiment focused on quantifying the heterogeneity of breast lesions based on six kinetic parameters, namely MSI, SI slope , E initial , E peak , ESER, and SEP, which were calculated from breast DCE‐MRI in a pixel‐wise fashion. The results demonstrated an improvement in classification performance compared to the traditional direct texture analysis of lesions, 57 and all AUC values were >0.75. That means it is feasible to discriminate benign from malignant lesions based on texture features extracted from the kinetic parametric matrices.…”

“…Hence, the application of texture analysis has gained great attention in the oncology field in recent years. It is widely used in the analysis of various types of medical images to explore the relationship between texture parameters and information about the tumor 57,58 . Such studies have proved the close correlation between texture features and tumor information.…”

Peripheral Nerves: Not Only Cross-sectional Area in the Era of Radiomics

“…24,25 The evolution of nerve texture analysis is represented by the advent of radiomics, an advanced quantitative image analysis that extracts a large amount of data from medical images, with the final outcome of providing information that is not visible to the human eye. [38][39][40][41][42][43][44][45][46][47][48][49][50][51][52][53][54] The possibility of studying the phenotype of peripheral nerves on images acquired with standard proto-cols and analyzing these images with widely available radiomics software packages could open new possibilities to study peripheral nerve pathology far beyond simple CSA evaluation. 7,9,10,18 MRI of peripheral nerves is also challenging mostly due to the thin nature of the nerves, the difficulties in selecting appropriate nerve boundaries, the difficulties in image interpretation, and the complex anatomy.…”

T2 heterogeneity provides a sensitive measure of early tumor response to radiotherapy

“…It has been postulated that metrics describing the internal structure and heterogeneity within tumors may provide more information about the disease than traditional whole-tumor metrics (12,13). Characterization of tumor heterogeneity with MR imaging has been attempted previously using texture analysis (12,14,15), clustering methods (16–19), and other structural descriptors (20). However, such efforts often lack biological interpretation and clear clinical relevance.…”