Breast cancer subtype intertumor heterogeneity: MRI-based features predict results of a genomic assay

Evaluation of tumor-derived MRI-texture features for discrimination of molecular subtypes and prediction of 12-month survival status in glioblastoma

PURPOSE

Glioblastoma multiforme (GBM) is the most common and aggressive primary brain cancer. Four molecular subtypes of GBM have been described but can only be determined by an invasive brain biopsy. The goal of this study is to evaluate the utility of texture features extracted from magnetic resonance imaging (MRI) scans as a potential noninvasive method to characterize molecular subtypes of GBM and to predict 12-month overall survival status for GBM patients.

METHODS

The authors manually segmented the tumor regions from postcontrast T1 weighted and T2 fluid-attenuated inversion recovery (FLAIR) MRI scans of 82 patients with de novo GBM. For each patient, the authors extracted five sets of computer-extracted texture features, namely, 48 segmentation-based fractal texture analysis (SFTA) features, 576 histogram of oriented gradients (HOGs) features, 44 run-length matrix (RLM) features, 256 local binary patterns features, and 52 Haralick features, from the tumor slice corresponding to the maximum tumor area in axial, sagittal, and coronal planes, respectively. The authors used an ensemble classifier called random forest on each feature family to predict GBM molecular subtypes and 12-month survival status (a dichotomized version of overall survival at the 12-month time point indicating if the patient was alive or not at 12 months). The performance of the prediction was quantified and compared using receiver operating characteristic (ROC) curves.

RESULTS

With the appropriate combination of texture feature set, image plane (axial, coronal, or sagittal), and MRI sequence, the area under ROC curve values for predicting different molecular subtypes and 12-month survival status are 0.72 for classical (with Haralick features on T1 postcontrast axial scan), 0.70 for mesenchymal (with HOG features on T2 FLAIR axial scan), 0.75 for neural (with RLM features on T2 FLAIR axial scan), 0.82 for proneural (with SFTA features on T1 postcontrast coronal scan), and 0.69 for 12-month survival status (with SFTA features on T1 postcontrast coronal scan).

CONCLUSIONS

The authors evaluated the performance of five types of texture features in predicting GBM molecular subtypes and 12-month survival status. The authors' results show that texture features are predictive of molecular subtypes and survival status in GBM. These results indicate the feasibility of using tumor-derived imaging features to guide genomically informed interventions without the need for invasive biopsies.

Molecular subtypes and imaging phenotypes of breast cancer

During the last 15 years, traditional breast cancer classifications based on histopathology have been reorganized into the luminal A, luminal B, human epidermal growth factor receptor 2 (HER2), and basal-like subtypes based on gene expression profiling. Each molecular subtype has shown varying risk for progression, response to treatment, and survival outcomes. Research linking the imaging phenotype with the molecular subtype has revealed that non-calcified, relatively circumscribed masses with posterior acoustic enhancement are common in the basal-like subtype, spiculated masses with a poorly circumscribed margin and posterior acoustic shadowing in the luminal subtype, and pleomorphic calcifications in the HER2-enriched subtype. Understanding the clinical implications of the molecular subtypes and imaging phenotypes could help radiologists guide precision medicine, tailoring medical treatment to patients and their tumor characteristics.

How Can Advanced Imaging Be Used to Mitigate Potential Breast Cancer Overdiagnosis?

Radiologists, as administrators and interpreters of screening mammography, are considered by some to be major contributors to the potential harms of screening, including overdiagnosis and overtreatment. In this article, we outline current efforts within the breast imaging community toward mitigating screening harms, including the widespread adoption of tomosynthesis and potentially adjusting screening frequency and thresholds for image-guided breast biopsy. However, the emerging field of breast radiomics may offer the greatest promise for reducing overdiagnosis by identifying imaging-based biomarkers strongly associated with tumor biology, and therefore helping prevent the harms of unnecessary treatment for indolent cancers.

Association between partial-volume corrected SUVmax and Oncotype DX recurrence score in early-stage, ER-positive/HER2-negative invasive breast cancer

PURPOSE

Oncotype DX, a 21-gene expression assay, provides a recurrence score (RS) which predicts prognosis and the benefit from adjuvant chemotherapy in patients with early-stage, estrogen receptor-positive (ER-positive), and human epidermal growth factor receptor 2-negative (HER2-negative) invasive breast cancer. However, Oncotype DX tests are expensive and not readily available in all institutions. The purpose of this study was to investigate whether metabolic parameters on (18)F-FDG PET/CT are associated with the Oncotype DX RS and whether (18)F-FDG PET/CT can be used to predict the Oncotype DX RS.

METHODS

The study group comprised 38 women with stage I/II, ER-positive/HER2-negative invasive breast cancer who underwent pretreatment (18)F-FDG PET/CT and Oncotype DX testing. On PET/CT, maximum (SUVmax) and average standardized uptake values, metabolic tumor volume, and total lesion glycolysis were measured. Partial volume-corrected SUVmax (PVC-SUVmax) determined using the recovery coefficient method was also evaluated. Oncotype DX RS (0 - 100) was categorized as low (<18), intermediate (18 - 30), or high (≥31). The associations between metabolic parameters and RS were analyzed. Multivariate logistic regression was used to identify significant independent predictors of low versus intermediate-to-high RS.

RESULTS

Of the 38 patients, 22 (58 %) had a low RS, 13 (34 %) had an intermediate RS, and 3 (8 %) had a high RS. In the analysis with 38 index tumors, PVC-SUVmax was higher in tumors in patients with intermediate-to-high RS than in those with low RS (5.68 vs. 4.06; P = 0.067, marginally significant). High PVC-SUVmax (≥4.96) was significantly associated with intermediate-to-high RS (odds ratio, OR, 10.556; P = 0.004) in univariate analysis. In multivariate analysis with clinicopathologic factors, PVC-SUVmax ≥4.96 (OR 8.459; P = 0.013) was a significant independent predictor of intermediate-to-high RS.

CONCLUSIONS

High PVC-SUVmax on (18)F-FDG PET/CT was significantly associated with an intermediate-to-high Oncotype DX RS. PVC metabolic parameters on (18)F-FDG PET/CT can be used to predict the Oncotype DX RS in patients with early-stage, ER-positive/HER2-negative breast cancer.

A Radio-genomics Approach for Identifying High Risk Estrogen Receptor-positive Breast Cancers on DCE-MRI: Preliminary Results in Predicting OncotypeDX Risk Scores

To identify computer extracted imaging features for estrogen receptor (ER)-positive breast cancers on dynamic contrast en-hanced (DCE)-MRI that are correlated with the low and high OncotypeDX risk categories. We collected 96 ER-positivebreast lesions with low (<18, N = 55) and high (>30, N = 41) OncotypeDX recurrence scores. Each lesion was quantitatively charac-terize via 6 shape features, 3 pharmacokinetics, 4 enhancement kinetics, 4 intensity kinetics, 148 textural kinetics, 5 dynamic histogram of oriented gradient (DHoG), and 6 dynamic local binary pattern (DLBP) features. The extracted features were evaluated by a linear discriminant analysis (LDA) classifier in terms of their ability to distinguish low and high OncotypeDX risk categories. Classification performance was evaluated by area under the receiver operator characteristic curve (Az). The DHoG and DLBP achieved Az values of 0.84 and 0.80, respectively. The 6 top features identified via feature selection were subsequently combined with the LDA classifier to yield an Az of 0.87. The correlation analysis showed that DHoG (ρ = 0.85, P < 0.001) and DLBP (ρ = 0.83, P < 0.01) were significantly associated with the low and high risk classifications from the OncotypeDX assay. Our results indicated that computer extracted texture features of DCE-MRI were highly correlated with the high and low OncotypeDX risk categories for ER-positive cancers.

Imaging genomics in cancer research: limitations and promises

Recently, radiogenomics or imaging genomics has emerged as a novel high-throughput method of associating imaging features with genomic data. Radiogenomics has the potential to provide comprehensive intratumour, intertumour and peritumour information non-invasively. This review article summarizes the current state of radiogenomic research in tumour characterization, discusses some of its limitations and promises and projects its future directions. Semi-radiogenomic studies that relate specific gene expressions to imaging features will also be briefly reviewed.

Breast cancer molecular subtype classifier that incorporates MRI features

PURPOSE

To use features extracted from magnetic resonance (MR) images and a machine-learning method to assist in differentiating breast cancer molecular subtypes.

MATERIALS AND METHODS

This retrospective Health Insurance Portability and Accountability Act (HIPAA)-compliant study received Institutional Review Board (IRB) approval. We identified 178 breast cancer patients between 2006-2011 with: 1) ERPR + (n = 95, 53.4%), ERPR-/HER2 + (n = 35, 19.6%), or triple negative (TN, n = 48, 27.0%) invasive ductal carcinoma (IDC), and 2) preoperative breast MRI at 1.5T or 3.0T. Shape, texture, and histogram-based features were extracted from each tumor contoured on pre- and three postcontrast MR images using in-house software. Clinical and pathologic features were also collected. Machine-learning-based (support vector machines) models were used to identify significant imaging features and to build models that predict IDC subtype. Leave-one-out cross-validation (LOOCV) was used to avoid model overfitting. Statistical significance was determined using the Kruskal-Wallis test.

RESULTS

Each support vector machine fit in the LOOCV process generated a model with varying features. Eleven out of the top 20 ranked features were significantly different between IDC subtypes with P < 0.05. When the top nine pathologic and imaging features were incorporated, the predictive model distinguished IDC subtypes with an overall accuracy on LOOCV of 83.4%. The combined pathologic and imaging model's accuracy for each subtype was 89.2% (ERPR+), 63.6% (ERPR-/HER2+), and 82.5% (TN). When only the top nine imaging features were incorporated, the predictive model distinguished IDC subtypes with an overall accuracy on LOOCV of 71.2%. The combined pathologic and imaging model's accuracy for each subtype was 69.9% (ERPR+), 62.9% (ERPR-/HER2+), and 81.0% (TN).

CONCLUSION

We developed a machine-learning-based predictive model using features extracted from MRI that can distinguish IDC subtypes with significant predictive power. J. Magn. Reson. Imaging 2016;44:122-129.

Breast MRI radiogenomics: Current status and research implications

Breast magnetic resonance imaging (MRI) radiogenomics is an emerging area of research that has the potential to directly influence clinical practice. Clinical MRI scanners today are capable of providing excellent temporal and spatial resolution, which allows extraction of numerous imaging features via human extraction approaches or complex computer vision algorithms. Meanwhile, advances in breast cancer genetics research has resulted in the identification of promising genes associated with cancer outcomes. In addition, validated genomic signatures have been developed that allow categorization of breast cancers into distinct molecular subtypes as well as predict the risk of cancer recurrence and response to therapy. Current radiogenomics research has been directed towards exploratory analysis of individual genes, understanding tumor biology, and developing imaging surrogates to genetic analysis with the long-term goal of developing a meaningful tool for clinical care. The background of breast MRI radiogenomics research, image feature extraction techniques, approaches to radiogenomics research, and promising areas of investigation are reviewed. J. Magn. Reson. Imaging 2016;43:1269-1278.