Hugo J.W.L. Aerts

Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach.

Human cancers exhibit strong phenotypic differences that can be visualized noninvasively by medical imaging. Radiomics refers to the comprehensive quantification of tumour phenotypes by applying a large number of quantitative image features. Here we present a radiomic analysis of 440 features quantifying tumour image intensity, shape and texture, which are extracted from computed tomography data of 1,019 patients with lung or head-and-neck cancer. We find that a large number of radiomic features have prognostic power in independent data sets of lung and head-and-neck cancer patients, many of which were not identified as significant before. Radiogenomics analysis reveals that a prognostic radiomic signature, capturing intratumour heterogeneity, is associated with underlying gene-expression patterns. These data suggest that radiomics identifies a general prognostic phenotype existing in both lung and head-and-neck cancer. This may have a clinical impact as imaging is routinely used in clinical practice, providing an unprecedented opportunity to improve decision-support in cancer treatment at low cost.

Radiomics: Extracting more information from medical images using advanced feature analysis

Solid cancers are spatially and temporally heterogeneous. This limits the use of invasive biopsy based molecular assays but gives huge potential for medical imaging, which has the ability to capture intra-tumoural heterogeneity in a non-invasive way. During the past decades, medical imaging innovations with new hardware, new imaging agents and standardised protocols, allows the field to move towards quantitative imaging. Therefore, also the development of automated and reproducible analysis methodologies to extract more information from image-based features is a requirement. Radiomics--the high-throughput extraction of large amounts of image features from radiographic images--addresses this problem and is one of the approaches that hold great promises but need further validation in multi-centric settings and in the laboratory.

Inconsistency in large pharmacogenomic studies

Two large-scale pharmacogenomic studies were published recently in this journal. Genomic data are well correlated between studies; however, the measured drug response data are highly discordant. Although the source of inconsistencies remains uncertain, it has potential implications for using these outcome measures to assess gene–drug associations or select potential anticancer drugs on the basis of their reported results.

Predicting outcomes in radiation oncology —multifactorial decision support systems

With the emergence of individualized medicine and the increasing amount and complexity of available medical data, a growing need exists for the development of clinical decision-support systems based on prediction models of treatment outcome. In radiation oncology, these models combine both predictive and prognostic data factors from clinical, imaging, molecular and other sources to achieve the highest accuracy to predict tumour response and follow-up event rates. In this Review, we provide an overview of the factors that are correlated with outcome—including survival, recurrence patterns and toxicity—in radiation oncology and discuss the methodology behind the development of prediction models, which is a multistage process. Even after initial development and clinical introduction, a truly useful predictive model will be continuously re-evaluated on different patient datasets from different regions to ensure its population-specific strength. In the future, validated decision-support systems will be fully integrated in the clinic, with data and knowledge being shared in a standardized, instant and global manner.

CT-based radiomic signature predicts distant metastasis in lung adenocarcinoma

BACKGROUND AND PURPOSE Radiomics provides opportunities to quantify the tumor phenotype non-invasively by applying a large number of quantitative imaging features. This study evaluates computed-tomography (CT) radiomic features for their capability to predict distant metastasis (DM) for lung adenocarcinoma patients. MATERIAL AND METHODS We included two datasets: 98 patients for discovery and 84 for validation. The phenotype of the primary tumor was quantified on pre-treatment CT-scans using 635 radiomic features. Univariate and multivariate analysis was performed to evaluate radiomics performance using the concordance index (CI). RESULTS Thirty-five radiomic features were found to be prognostic (CI>0.60, FDR<5%) for DM and twelve for survival. It is noteworthy that tumor volume was only moderately prognostic for DM (CI=0.55, p-value=2.77×10(-5)) in the discovery cohort. A radiomic-signature had strong power for predicting DM in the independent validation dataset (CI=0.61, p-value=1.79×10(-17)). Adding this radiomic-signature to a clinical model resulted in a significant improvement of predicting DM in the validation dataset (p-value=1.56×10(-11)). CONCLUSIONS Although only basic metrics are routinely quantified, this study shows that radiomic features capturing detailed information of the tumor phenotype can be used as a prognostic biomarker for clinically-relevant factors such as DM. Moreover, the radiomic-signature provided additional information to clinical data.

Disparity Between In Vivo EGFR Expression and 89Zr-Labeled Cetuximab Uptake Assessed with PET

The epidermal growth factor receptor (EGFR) is highly expressed in a significant number of human malignancies, and its expression is associated with tumor aggressiveness and overall treatment resistance. The monoclonal antibody cetuximab is increasingly used in clinical settings as a treatment modality in combination with more conventional therapies, such as radio- and chemotherapy. Currently, little is known about tumor-specific uptake and overall pharmacokinetics. Noninvasive quantification of cetuximab uptake could provide important diagnostic information for patient selection and therapy evaluation. To this end, we have developed and validated a novel probe using cetuximab labeled with the long-lived positron emitter 89Zr for PET imaging. Methods: Tumor cell lines with varying EGFR expression levels were used for in vivo tumor imaging experiments. PET with 89Zr-labeled cetuximab (3.75 ± 0.14 MBq) was performed on tumor-bearing NMRI-nu mice at multiple time points after injection (ranging from 1 to 120 h) and quantified by drawing regions of interest on selected tissues. Uptake was compared by biodistribution γ-counting, and ex vivo EGFR expression levels were quantified using Western blot analysis. Results: Uptake of 89Zr-labeled cetuximab was demonstrated in the EGFR-positive tumors. However, the EGFR levels measured in vivo did not correlate with the relative signal obtained by PET. Tumor-to-blood ratios were significantly higher in the cell lines with intermediate (compared with the high) EGFR expression starting from 24 h after injection. Normal tissue uptake was unaffected by the different tumor types. Ex vivo γ-counting experiments confirmed the observed in vivo PET results. A similar disparity was found between 89Zr-labeled cetuximab tumor uptake and in vivo EGFR expression levels as demonstrated by Western blotting. Conclusion: The 89Zr-labeled cetuximab imaging probe is a promising tool for noninvasive evaluation of cetuximab uptake. Our results demonstrate a disparity between in vivo EGFR expression levels and cetuximab uptake. In a general sense, the results indicate a disparity between antibody uptake and expression levels of a biologic target in a tumor, suggesting that additional pharmacokinetic or pharmacodynamic mechanisms influence tumor delivery of this therapy. These additional mechanisms may explain why receptor expression levels alone are not sufficient to predict patient response.

Identification of residual metabolic-active areas within individual NSCLC tumours using a pre-radiotherapy 18Fluorodeoxyglucose-PET-CT scan

BACKGROUND AND PURPOSE Non-small cell lung cancer (NSCLC) tumours are mostly heterogeneous. We hypothesized that areas within the tumour with a high pre-radiation (18)F-deoxyglucose (FDG) uptake, could identify residual metabolic-active areas, ultimately enabling selective-boosting of tumour sub-volumes. MATERIAL AND METHODS Fifty-five patients with inoperable stage I-III NSCLC treated with chemo-radiation or with radiotherapy alone were included. For each patient one pre-radiotherapy and one post-radiotherapy FDG-PET-CT scans were available. Twenty-two patients showing persistent FDG uptake in the primary tumour after radiotherapy were analyzed. Overlap fractions (OFs) were calculated between standardized uptake value (SUV) threshold-based auto-delineations on the pre- and post-radiotherapy scan. RESULTS Patients with residual metabolic-active areas within the tumour had a significantly worse survival compared to individuals with a complete metabolic response (p=0.002). The residual metabolic-active areas within the tumour largely corresponded (OF>70%) with the 50%SUV high FDG uptake area of the pre-radiotherapy scan. The hotspot within the residual area (90%SUV) was completely within the GTV (OF=100%), and had a high overlap with the pre-radiotherapy 50%SUV threshold (OF>84%). CONCLUSIONS The location of residual metabolic-active areas within the primary tumour after therapy corresponded with the original high FDG uptake areas pre-radiotherapy. Therefore, a single pre-treatment FDG-PET-CT scan allows for the identification of residual metabolic-active areas.

Stability of FDG-PET Radiomics features: an integrated analysis of test-retest and inter-observer variability.

Abstract Purpose. Besides basic measurements as maximum standardized uptake value (SUV)max or SUVmean derived from 18F-FDG positron emission tomography (PET) scans, more advanced quantitative imaging features (i.e. “Radiomics” features) are increasingly investigated for treatment monitoring, outcome prediction, or as potential biomarkers. With these prospected applications of Radiomics features, it is a requisite that they provide robust and reliable measurements. The aim of our study was therefore to perform an integrated stability analysis of a large number of PET-derived features in non-small cell lung carcinoma (NSCLC), based on both a test-retest and an inter-observer setup. Methods. Eleven NSCLC patients were included in the test-retest cohort. Patients underwent repeated PET imaging within a one day interval, before any treatment was delivered. Lesions were delineated by applying a threshold of 50% of the maximum uptake value within the tumor. Twenty-three NSCLC patients were included in the inter-observer cohort. Patients underwent a diagnostic whole body PET-computed tomography (CT). Lesions were manually delineated based on fused PET-CT, using a standardized clinical delineation protocol. Delineation was performed independently by five observers, blinded to each other. Fifteen first order statistics, 39 descriptors of intensity volume histograms, eight geometric features and 44 textural features were extracted. For every feature, test-retest and inter-observer stability was assessed with the intra-class correlation coefficient (ICC) and the coefficient of variability, normalized to mean and range. Similarity between test-retest and inter-observer stability rankings of features was assessed with Spearmans rank correlation coefficient. Results. Results showed that the majority of assessed features had both a high test-retest (71%) and inter-observer (91%) stability in terms of their ICC. Overall, features more stable in repeated PET imaging were also found to be more robust against inter-observer variability. Conclusion. Results suggest that further research of quantitative imaging features is warranted with respect to more advanced applications of PET imaging as being used for treatment monitoring, outcome prediction or imaging biomarkers.

Machine Learning methods for Quantitative Radiomic Biomarkers

Radiomics extracts and mines large number of medical imaging features quantifying tumor phenotypic characteristics. Highly accurate and reliable machine-learning approaches can drive the success of radiomic applications in clinical care. In this radiomic study, fourteen feature selection methods and twelve classification methods were examined in terms of their performance and stability for predicting overall survival. A total of 440 radiomic features were extracted from pre-treatment computed tomography (CT) images of 464 lung cancer patients. To ensure the unbiased evaluation of different machine-learning methods, publicly available implementations along with reported parameter configurations were used. Furthermore, we used two independent radiomic cohorts for training (n = 310 patients) and validation (n = 154 patients). We identified that Wilcoxon test based feature selection method WLCX (stability = 0.84 ± 0.05, AUC = 0.65 ± 0.02) and a classification method random forest RF (RSD = 3.52%, AUC = 0.66 ± 0.03) had highest prognostic performance with high stability against data perturbation. Our variability analysis indicated that the choice of classification method is the most dominant source of performance variation (34.21% of total variance). Identification of optimal machine-learning methods for radiomic applications is a crucial step towards stable and clinically relevant radiomic biomarkers, providing a non-invasive way of quantifying and monitoring tumor-phenotypic characteristics in clinical practice.

Robust Radiomics Feature Quantification Using Semiautomatic Volumetric Segmentation

Due to advances in the acquisition and analysis of medical imaging, it is currently possible to quantify the tumor phenotype. The emerging field of Radiomics addresses this issue by converting medical images into minable data by extracting a large number of quantitative imaging features. One of the main challenges of Radiomics is tumor segmentation. Where manual delineation is time consuming and prone to inter-observer variability, it has been shown that semi-automated approaches are fast and reduce inter-observer variability. In this study, a semiautomatic region growing volumetric segmentation algorithm, implemented in the free and publicly available 3D-Slicer platform, was investigated in terms of its robustness for quantitative imaging feature extraction. Fifty-six 3D-radiomic features, quantifying phenotypic differences based on tumor intensity, shape and texture, were extracted from the computed tomography images of twenty lung cancer patients. These radiomic features were derived from the 3D-tumor volumes defined by three independent observers twice using 3D-Slicer, and compared to manual slice-by-slice delineations of five independent physicians in terms of intra-class correlation coefficient (ICC) and feature range. Radiomic features extracted from 3D-Slicer segmentations had significantly higher reproducibility (ICC = 0.85±0.15, p = 0.0009) compared to the features extracted from the manual segmentations (ICC = 0.77±0.17). Furthermore, we found that features extracted from 3D-Slicer segmentations were more robust, as the range was significantly smaller across observers (p = 3.819e-07), and overlapping with the feature ranges extracted from manual contouring (boundary lower: p = 0.007, higher: p = 5.863e-06). Our results show that 3D-Slicer segmented tumor volumes provide a better alternative to the manual delineation for feature quantification, as they yield more reproducible imaging descriptors. Therefore, 3D-Slicer can be employed for quantitative image feature extraction and image data mining research in large patient cohorts.