Radiomics: the process and the challenges

Uncertainty analysis of quantitative imaging features extracted from contrast-enhanced CT in lung tumors

PURPOSE

To assess the uncertainty of quantitative imaging features extracted from contrast-enhanced computed tomography (CT) scans of lung cancer patients in terms of the dependency on the time after contrast injection and the feature reproducibility between scans.

METHODS

Eight patients underwent contrast-enhanced CT scans of lung tumors on two sessions 2-7 days apart. Each session included 6 CT scans of the same anatomy taken every 15s, starting 50s after contrast injection. Image features based on intensity histogram, co-occurrence matrix, neighborhood gray-tone difference matrix, run-length matrix, and geometric shape were extracted from the tumor for each scan. Spearman's correlation was used to examine the dependency of features on the time after contrast injection, with values over 0.50 considered time-dependent. Concordance correlation coefficients were calculated to examine the reproducibility of each feature between times of scans after contrast injection and between scanning sessions, with values greater than 0.90 considered reproducible.

RESULTS

The features were found to have little dependency on the time between the contrast injection and the CT scan. Most features were reproducible between times of scans after contrast injection and between scanning sessions. Some features were more reproducible when they were extracted from a CT scan performed at a longer time after contrast injection.

CONCLUSION

The quantitative imaging features tested here are mostly reproducible and show little dependency on the time after contrast injection.

A novel metric for quantification of homogeneous and heterogeneous tumors in PET for enhanced clinical outcome prediction

Oncologic PET images provide valuable information that can enable enhanced prognosis of disease. Nonetheless, such information is simplified significantly in routine clinical assessment to meet workflow constraints. Examples of typical FDG PET metrics include: (i) SUVmax, (2) total lesion glycolysis (TLG), and (3) metabolic tumor volume (MTV). We have derived and implemented a novel metric for tumor quantification, inspired in essence by a model of generalized equivalent uniform dose as used in radiation therapy. The proposed metric, denoted generalized effective total uptake (gETU), is attractive as it encompasses the abovementioned commonly invoked metrics, and generalizes them, for both homogeneous and heterogeneous tumors, using a single parameter a. We evaluated this new metric for improved overall survival (OS) prediction on two different baseline FDG PET/CT datasets: (a) 113 patients with squamous cell cancer of the oropharynx, and (b) 72 patients with locally advanced pancreatic adenocarcinoma. Kaplan-Meier survival analysis was performed, where the subjects were subdivided into two groups using the median threshold, from which the hazard ratios (HR) were computed in Cox proportional hazards regression. For the oropharyngeal cancer dataset, MTV, TLG, SUVmax, SUVmean and SUVpeak produced HR values of 1.86, 3.02, 1.34, 1.36 and 1.62, while the proposed gETU metric for a  = 0.25 (greater emphasis on volume information) enabled significantly enhanced OS prediction with HR  =  3.94. For the pancreatic cancer dataset, MTV, TLG, SUVmax, SUVmean and SUVpeak resulted in HR values of 1.05, 1.25, 1.42, 1.45 and 1.52, while gETU at a  = 3.2 (greater emphasis on SUV information) arrived at an improved HR value of 1.61. Overall, the proposed methodology allows placement of differing degrees of emphasis on tumor volume versus uptake for different types of tumors to enable enhanced clinical outcome prediction.

Radiomic Machine-Learning Classifiers for Prognostic Biomarkers of Head and Neck Cancer

INTRODUCTION

"Radiomics" extracts and mines a large number of medical imaging features in a non-invasive and cost-effective way. The underlying assumption of radiomics is that these imaging features quantify phenotypic characteristics of an entire tumor. In order to enhance applicability of radiomics in clinical oncology, highly accurate and reliable machine-learning approaches are required. In this radiomic study, 13 feature selection methods and 11 machine-learning classification methods were evaluated in terms of their performance and stability for predicting overall survival in head and neck cancer patients.

METHODS

Two independent head and neck cancer cohorts were investigated. Training cohort HN1 consisted of 101 head and neck cancer patients. Cohort HN2 (n = 95) was used for validation. A total of 440 radiomic features were extracted from the segmented tumor regions in CT images. Feature selection and classification methods were compared using an unbiased evaluation framework.

RESULTS

We observed that the three feature selection methods minimum redundancy maximum relevance (AUC = 0.69, Stability = 0.66), mutual information feature selection (AUC = 0.66, Stability = 0.69), and conditional infomax feature extraction (AUC = 0.68, Stability = 0.7) had high prognostic performance and stability. The three classifiers BY (AUC = 0.67, RSD = 11.28), RF (AUC = 0.61, RSD = 7.36), and NN (AUC = 0.62, RSD = 10.52) also showed high prognostic performance and stability. Analysis investigating performance variability indicated that the choice of classification method is the major factor driving the performance variation (29.02% of total variance).

CONCLUSION

Our study identified prognostic and reliable machine-learning methods for the prediction of overall survival of head and neck cancer patients. Identification of optimal machine-learning methods for radiomics-based prognostic analyses could broaden the scope of radiomics in precision oncology and cancer care.

Core samples for radiomics features that are insensitive to tumor segmentation: method and pilot study using CT images of hepatocellular carcinoma

The purpose of this study is to investigate the utility of obtaining "core samples" of regions in CT volume scans for extraction of radiomic features. We asked four readers to outline tumors in three representative slices from each phase of multiphasic liver CT images taken from 29 patients (1128 segmentations) with hepatocellular carcinoma. Core samples were obtained by automatically tracing the maximal circle inscribed in the outlines. Image features describing the intensity, texture, shape, and margin were used to describe the segmented lesion. We calculated the intraclass correlation between the features extracted from the readers' segmentations and their core samples to characterize robustness to segmentation between readers, and between human-based segmentation and core sampling. We conclude that despite the high interreader variability in manually delineating the tumor (average overlap of 43% across all readers), certain features such as intensity and texture features are robust to segmentation. More importantly, this same subset of features can be obtained from the core samples, providing as much information as detailed segmentation while being simpler and faster to obtain.

Fully automatic GBM segmentation in the TCGA-GBM dataset: Prognosis and correlation with VASARI features

Reproducible definition and quantification of imaging biomarkers is essential. We evaluated a fully automatic MR-based segmentation method by comparing it to manually defined sub-volumes by experienced radiologists in the TCGA-GBM dataset, in terms of sub-volume prognosis and association with VASARI features. MRI sets of 109 GBM patients were downloaded from the Cancer Imaging archive. GBM sub-compartments were defined manually and automatically using the Brain Tumor Image Analysis (BraTumIA). Spearman's correlation was used to evaluate the agreement with VASARI features. Prognostic significance was assessed using the C-index. Auto-segmented sub-volumes showed moderate to high agreement with manually delineated volumes (range (r): 0.4 - 0.86). Also, the auto and manual volumes showed similar correlation with VASARI features (auto r = 0.35, 0.43 and 0.36; manual r = 0.17, 0.67, 0.41, for contrast-enhancing, necrosis and edema, respectively). The auto-segmented contrast-enhancing volume and post-contrast abnormal volume showed the highest AUC (0.66, CI: 0.55-0.77 and 0.65, CI: 0.54-0.76), comparable to manually defined volumes (0.64, CI: 0.53-0.75 and 0.63, CI: 0.52-0.74, respectively). BraTumIA and manual tumor sub-compartments showed comparable performance in terms of prognosis and correlation with VASARI features. This method can enable more reproducible definition and quantification of imaging based biomarkers and has potential in high-throughput medical imaging research.

Imaging texture analysis for automated prediction of lung cancer recurrence after stereotactic radiotherapy

Benign radiation-induced lung injury (RILI) is not uncommon following stereotactic ablative radiotherapy (SABR) for lung cancer and can be difficult to differentiate from tumor recurrence on follow-up imaging. We previously showed the ability of computed tomography (CT) texture analysis to predict recurrence. The aim of this study was to evaluate and compare the accuracy of recurrence prediction using manual region-of-interest segmentation to that of a semiautomatic approach. We analyzed 22 patients treated for 24 lesions (11 recurrences, 13 RILI). Consolidative and ground-glass opacity (GGO) regions were manually delineated. The longest axial diameter of the consolidative region on each post-SABR CT image was measured. This line segment is routinely obtained as part of the clinical imaging workflow and was used as input to automatically delineate the consolidative region and subsequently derive a periconsolidative region to sample GGO tissue. Texture features were calculated, and at two to five months post-SABR, the entropy texture measure within the semiautomatic segmentations showed prediction accuracies [areas under the receiver operating characteristic curve (AUC): 0.70 to 0.73] similar to those of manual GGO segmentations (AUC: 0.64). After integration into the clinical workflow, this decision support system has the potential to support earlier salvage for patients with recurrence and fewer investigations of benign RILI.

Quantitative Imaging in Radiation Oncology: An Emerging Science and Clinical Service

Radiation oncology has long required quantitative imaging approaches for the safe and effective delivery of radiation therapy. The past 10 years has seen a remarkable expansion in the variety of novel imaging signals and analyses that are starting to contribute to the prescription and design of the radiation treatment plan. These include a rapid increase in the use of magnetic resonance imaging, development of contrast-enhanced imaging techniques, integration of fluorinated deoxyglucose-positron emission tomography, evaluation of hypoxia imaging techniques, and numerous others. These are reviewed with an effort to highlight challenges related to quantification and reproducibility. In addition, several of the emerging applications of these imaging approaches are also highlighted. Finally, the growing community of support for establishing quantitative imaging approaches as we move toward clinical evaluation is summarized and the need for a clinical service in support of the clinical science and delivery of care is proposed.

Decoding Tumor Phenotypes for ALK, ROS1, and RET Fusions in Lung Adenocarcinoma Using a Radiomics Approach

Quantitative imaging using radiomics can capture distinct phenotypic differences between tumors and may have predictive power for certain phenotypes according to specific genetic mutations. We aimed to identify the clinicoradiologic predictors of tumors with ALK (anaplastic lymphoma kinase), ROS1 (c-ros oncogene 1), or RET (rearranged during transfection) fusions in patients with lung adenocarcinoma.A total of 539 pathologically confirmed lung adenocarcinomas were included in this retrospective study. The baseline clinicopathologic characteristics were retrieved from the patients' medical records and the ALK/ROS1/RET fusion status was reviewed. Quantitative computed tomography (CT) and positron emission tomography imaging characteristics were evaluated using a radiomics approach. Significant features for the fusion-positive tumor prediction model were extracted from all of the clinicoradiologic features, and were used to calculate diagnostic performance for predicting 3 fusions' positivity. The clinicoradiologic features were compared between ALK versus ROS1/RET fusion-positive tumors to identify the clinicoradiologic similarity between the 2 groups.The fusion-positive tumor prediction model was a combination of younger age, advanced tumor stage, solid tumor on CT, higher values for SUV(max) and tumor mass, lower values for kurtosis and inverse variance on 3-voxel distance than those of fusion-negative tumors (sensitivity and specificity, 0.73 and 0.70, respectively). ALK fusion-positive tumors were significantly different in tumor stage, central location, SUV(max), homogeneity on 1-, 2-, and 3-voxel distances, and sum mean on 2-voxel distance compared with ROS1/RET fusion-positive tumors.ALK/ROS1/RET fusion-positive lung adenocarcinomas possess certain clinical and imaging features that enable good discrimination of fusion-positive from fusion-negative lung adenocarcinomas.

[Radiomics: Definition and clinical development]

The ultimate goal in radiation oncology is to offer a personalized treatment to all patients indicated for radiotherapy. Radiomics is a tool that reinforces a deep analysis of tumors at the molecular aspect taking into account intrinsic susceptibility in a long-term follow-up. Radiomics allow qualitative and quantitative performance analyses with high throughput extraction of numeric radiologic data to obtain predictive or prognostic information from patients treated for cancer. A second approach is to define biological or constitutional that could change the practice. This technique included normal tissue individual susceptibility but also potential response of tumors under ionizing radiation treatment. These "omics" are biological and technical techniques leading to simultaneous novel identification and exploration a set of genes, lipids, proteins.

Imaging Tumor Response and Tumoral Heterogeneity in Non-Small Cell Lung Cancer Treated With Antiangiogenic Therapy: Comparison of the Prognostic Ability of RECIST 1.1, an Alternate Method (Crabb), and Image Heterogeneity Analysis

PURPOSE

We aimed to assess computed tomography (CT) intratumoral heterogeneity changes, and compared the prognostic ability of the Response Evaluation Criteria in Solid Tumors (RECIST) 1.1, an alternate response method (Crabb), and CT heterogeneity in non-small cell lung cancer treated with chemotherapy with and without bevacizumab.

MATERIALS AND METHODS

Forty patients treated with chemotherapy (group C) or chemotherapy and bevacizumab (group BC) underwent contrast-enhanced CT at baseline and after 1, 3, and 6 cycles of chemotherapy. Radiologic response was assessed using RECIST 1.1 and an alternate method. CT heterogeneity analysis generating global and locoregional parameters depicting tumor image spatial intensity characteristics was performed. Heterogeneity parameters between the 2 groups were compared using the Mann-Whitney U test. Associations between heterogeneity parameters and radiologic response with overall survival were assessed using Cox regression.

RESULTS

Global and locoregional heterogeneity parameters changed with treatment, with increased tumor heterogeneity in group BC. Entropy [group C: median -0.2% (interquartile range -2.2, 1.7) vs. group BC: 0.7% (-0.7, 3.5), P=0.10] and busyness [-27.7% (-62.2, -5.0) vs. -11.5% (-29.1, 92.4), P=0.10] showed a greater reduction in group C, whereas uniformity [1.9% (-8.0, 9.8) vs. -5.0% (-13.9, 5.6), P=0.10] showed a relative increase after 1 cycle but did not reach statistical significance. Two (9%) and 1 (6%) additional responders were identified using the alternate method compared with RECIST in group C and group BC, respectively. Heterogeneity parameters were not significant prognostic factors.

CONCLUSIONS

The alternate response method described by Crabb identified more responders compared with RECIST. However, both criteria and baseline imaging heterogeneity parameters were not prognostic of survival.

Associating spatial diversity features of radiologically defined tumor habitats with epidermal growth factor receptor driver status and 12-month survival in glioblastoma: methods and preliminary investigation

We analyzed the spatial diversity of tumor habitats, regions with distinctly different intensity characteristics of a tumor, using various measurements of habitat diversity within tumor regions. These features were then used for investigating the association with a 12-month survival status in glioblastoma (GBM) patients and for the identification of epidermal growth factor receptor (EGFR)-driven tumors. T1 postcontrast and T2 fluid attenuated inversion recovery images from 65 GBM patients were analyzed in this study. A total of 36 spatial diversity features were obtained based on pixel abundances within regions of interest. Performance in both the classification tasks was assessed using receiver operating characteristic (ROC) analysis. For association with 12-month overall survival, area under the ROC curve was 0.74 with confidence intervals [0.630 to 0.858]. The sensitivity and specificity at the optimal operating point ([Formula: see text]) on the ROC were 0.59 and 0.75, respectively. For the identification of EGFR-driven tumors, the area under the ROC curve (AUC) was 0.85 with confidence intervals [0.750 to 0.945]. The sensitivity and specificity at the optimal operating point ([Formula: see text]) on the ROC were 0.76 and 0.83, respectively. Our findings suggest that these spatial habitat diversity features are associated with these clinical characteristics and could be a useful prognostic tool for magnetic resonance imaging studies of patients with GBM.

External validation of a prognostic CT-based radiomic signature in oropharyngeal squamous cell carcinoma

BACKGROUND

Oropharyngeal squamous cell carcinoma (OPSCC) is one of the fastest growing disease sites of head and neck cancers. A recently described radiomic signature, based exclusively on pre-treatment computed tomography (CT) imaging of the primary tumor volume, was found to be prognostic in independent cohorts of lung and head and neck cancer patients treated in the Netherlands. Here, we further validate this signature in a large and independent North American cohort of OPSCC patients, also considering CT artifacts.

METHODS

A total of 542 OPSCC patients were included for which we determined the prognostic index (PI) of the radiomic signature. We tested the signature model fit in a Cox regression and assessed model discrimination with Harrell's c-index. Kaplan-Meier survival curves between high and low signature predictions were compared with a log-rank test. Validation was performed in the complete cohort (PMH1) and in the subset of patients without (PMH2) and with (PMH3) visible CT artifacts within the delineated tumor region.

RESULTS

We identified 267 (49%) patients without and 275 (51%) with visible CT artifacts. The calibration slope (β) on the PI in a Cox proportional hazards model was 1.27 (H0: β = 1, p = 0.152) in the PMH1 (n = 542), 0.855 (H0: β = 1, p = 0.524) in the PMH2 (n = 267) and 1.99 (H0: β = 1, p = 0.002) in the PMH3 (n = 275) cohort. Harrell's c-index was 0.628 (p = 2.72e-9), 0.634 (p = 2.7e-6) and 0.647 (p = 5.35e-6) for the PMH1, PMH2 and PMH3 cohort, respectively. Kaplan-Meier survival curves were significantly different (p < 0.05) between high and low radiomic signature model predictions for all cohorts.

CONCLUSION

Overall, the signature validated well using all CT images as-is, demonstrating a good model fit and preservation of discrimination. Even though CT artifacts were shown to be of influence, the signature had significant prognostic power regardless if patients with CT artifacts were included.

A radiomics model from joint FDG-PET and MRI texture features for the prediction of lung metastases in soft-tissue sarcomas of the extremities

This study aims at developing a joint FDG-PET and MRI texture-based model for the early evaluation of lung metastasis risk in soft-tissue sarcomas (STSs). We investigate if the creation of new composite textures from the combination of FDG-PET and MR imaging information could better identify aggressive tumours. Towards this goal, a cohort of 51 patients with histologically proven STSs of the extremities was retrospectively evaluated. All patients had pre-treatment FDG-PET and MRI scans comprised of T1-weighted and T2-weighted fat-suppression sequences (T2FS). Nine non-texture features (SUV metrics and shape features) and forty-one texture features were extracted from the tumour region of separate (FDG-PET, T1 and T2FS) and fused (FDG-PET/T1 and FDG-PET/T2FS) scans. Volume fusion of the FDG-PET and MRI scans was implemented using the wavelet transform. The influence of six different extraction parameters on the predictive value of textures was investigated. The incorporation of features into multivariable models was performed using logistic regression. The multivariable modeling strategy involved imbalance-adjusted bootstrap resampling in the following four steps leading to final prediction model construction: (1) feature set reduction; (2) feature selection; (3) prediction performance estimation; and (4) computation of model coefficients. Univariate analysis showed that the isotropic voxel size at which texture features were extracted had the most impact on predictive value. In multivariable analysis, texture features extracted from fused scans significantly outperformed those from separate scans in terms of lung metastases prediction estimates. The best performance was obtained using a combination of four texture features extracted from FDG-PET/T1 and FDG-PET/T2FS scans. This model reached an area under the receiver-operating characteristic curve of 0.984 ± 0.002, a sensitivity of 0.955 ± 0.006, and a specificity of 0.926 ± 0.004 in bootstrapping evaluations. Ultimately, lung metastasis risk assessment at diagnosis of STSs could improve patient outcomes by allowing better treatment adaptation.

From big data analysis to personalized medicine for all: challenges and opportunities

Recent advances in high-throughput technologies have led to the emergence of systems biology as a holistic science to achieve more precise modeling of complex diseases. Many predict the emergence of personalized medicine in the near future. We are, however, moving from two-tiered health systems to a two-tiered personalized medicine. Omics facilities are restricted to affluent regions, and personalized medicine is likely to widen the growing gap in health systems between high and low-income countries. This is mirrored by an increasing lag between our ability to generate and analyze big data. Several bottlenecks slow-down the transition from conventional to personalized medicine: generation of cost-effective high-throughput data; hybrid education and multidisciplinary teams; data storage and processing; data integration and interpretation; and individual and global economic relevance. This review provides an update of important developments in the analysis of big data and forward strategies to accelerate the global transition to personalized medicine.

Radiomic feature clusters and prognostic signatures specific for Lung and Head & Neck cancer

Radiomics provides a comprehensive quantification of tumor phenotypes by extracting and mining large number of quantitative image features. To reduce the redundancy and compare the prognostic characteristics of radiomic features across cancer types, we investigated cancer-specific radiomic feature clusters in four independent Lung and Head & Neck (H∓N) cancer cohorts (in total 878 patients). Radiomic features were extracted from the pre-treatment computed tomography (CT) images. Consensus clustering resulted in eleven and thirteen stable radiomic feature clusters for Lung and H & N cancer, respectively. These clusters were validated in independent external validation cohorts using rand statistic (Lung RS = 0.92, p < 0.001, H & N RS = 0.92, p < 0.001). Our analysis indicated both common as well as cancer-specific clustering and clinical associations of radiomic features. Strongest associations with clinical parameters: Prognosis Lung CI = 0.60 ± 0.01, Prognosis H & N CI = 0.68 ± 0.01; Lung histology AUC = 0.56 ± 0.03, Lung stage AUC = 0.61 ± 0.01, H & N HPV AUC = 0.58 ± 0.03, H & N stage AUC = 0.77 ± 0.02. Full utilization of these cancer-specific characteristics of image features may further improve radiomic biomarkers, providing a non-invasive way of quantifying and monitoring tumor phenotypic characteristics in clinical practice.

Semiquantitative Computed Tomography Characteristics for Lung Adenocarcinoma and Their Association With Lung Cancer Survival

In this study we developed 25 computed tomography descriptors among 117 patients with lung adenocarcinoma to semiquantitatively assess their association with overall survival. Pleural attachment was significantly associated with an increased risk of death and texture was most important for distinguishing histological subtypes. This approach has the potential to support automated analyses and develop decision-support clinical tools.

BACKGROUND

Computed tomography (CT) characteristics derived from noninvasive images that represent the entire tumor might have diagnostic and prognostic value. The purpose of this study was to assess the association of a standardized set of semiquantitative CT characteristics of lung adenocarcinoma with overall survival.

PATIENTS AND METHODS

An initial set of CT descriptors was developed to semiquantitatively assess lung adenocarcinoma in patients (n = 117) who underwent resection. Survival analyses were used to determine the association between each characteristic and overall survival. Principle component analysis (PCA) was used to determine characteristics that might differentiate histological subtypes.

RESULTS

Characteristics significantly associated with overall survival included pleural attachment (P < .001), air bronchogram (P = .03), and lymphadenopathy (P = .02). Multivariate analyses revealed pleural attachment was significantly associated with an increased risk of death overall (hazard ratio [HR], 3.21; 95% confidence interval [CI], 1.53-6.70) and among patients with lepidic predominant adenocarcinomas (HR, 5.85; 95% CI, 1.75-19.59), and lymphadenopathy was significantly associated with an increased risk of death among patients with adenocarcinomas without a predominant lepidic component (HR, 3.07; 95% CI, 1.09-8.70). A PCA model showed that texture (ground-glass opacity component) was most important for separating the 2 subtypes.

CONCLUSION

A subset of the semiquantitative characteristics described herein has prognostic importance and provides the ability to distinguish between different histological subtypes of lung adenocarcinoma.

Personalized radiotherapy: concepts, biomarkers and trial design

In the past decade, and pointing onwards to the immediate future, clinical radiotherapy has undergone considerable developments, essentially including technological advances to sculpt radiation delivery, the demonstration of the benefit of adding concomitant cytotoxic agents to radiotherapy for a range of tumour types and, intriguingly, the increasing integration of targeted therapeutics for biological optimization of radiation effects. Recent molecular and imaging insights into radiobiology will provide a unique opportunity for rational patient treatment, enabling the parallel design of next-generation trials that formally examine the therapeutic outcome of adding targeted drugs to radiation, together with the critically important assessment of radiation volume and dose-limiting treatment toxicities. In considering the use of systemic agents with presumed radiosensitizing activity, this may also include the identification of molecular, metabolic and imaging markers of treatment response and tolerability, and will need particular attention on patient eligibility. In addition to providing an overview of clinical biomarker studies relevant for personalized radiotherapy, this communication will highlight principles in addressing clinical evaluation of combined-modality-targeted therapeutics and radiation. The increasing number of translational studies that bridge large-scale omics sciences with quality-assured phenomics end points-given the imperative development of open-source data repositories to allow investigators the access to the complex data sets-will enable radiation oncology to continue to position itself with the highest level of evidence within existing clinical practice.

Staging of lung cancer

Primary lung cancer is the leading cause of cancer mortality in the world. Thorough clinical staging of patients with lung cancer is important, because therapeutic options and management are to a considerable degree dependent on stage at presentation. Radiologic imaging is an essential component of clinical staging, including chest radiography in some cases, computed tomography, MRI, and PET. Multiplanar imaging modalities allow assessment of features that are important for surgical, oncologic, and radiation therapy planning, including size of the primary tumor, location and relationship to normal anatomic structures in the thorax, and existence of nodal and/or metastatic disease.

Neuroimaging and neuromodulation approaches to study eating behavior and prevent and treat eating disorders and obesity

Functional, molecular and genetic neuroimaging has highlighted the existence of brain anomalies and neural vulnerability factors related to obesity and eating disorders such as binge eating or anorexia nervosa. In particular, decreased basal metabolism in the prefrontal cortex and striatum as well as dopaminergic alterations have been described in obese subjects, in parallel with increased activation of reward brain areas in response to palatable food cues. Elevated reward region responsivity may trigger food craving and predict future weight gain. This opens the way to prevention studies using functional and molecular neuroimaging to perform early diagnostics and to phenotype subjects at risk by exploring different neurobehavioral dimensions of the food choices and motivation processes. In the first part of this review, advantages and limitations of neuroimaging techniques, such as functional magnetic resonance imaging (fMRI), positron emission tomography (PET), single photon emission computed tomography (SPECT), pharmacogenetic fMRI and functional near-infrared spectroscopy (fNIRS) will be discussed in the context of recent work dealing with eating behavior, with a particular focus on obesity. In the second part of the review, non-invasive strategies to modulate food-related brain processes and functions will be presented. At the leading edge of non-invasive brain-based technologies is real-time fMRI (rtfMRI) neurofeedback, which is a powerful tool to better understand the complexity of human brain-behavior relationships. rtfMRI, alone or when combined with other techniques and tools such as EEG and cognitive therapy, could be used to alter neural plasticity and learned behavior to optimize and/or restore healthy cognition and eating behavior. Other promising non-invasive neuromodulation approaches being explored are repetitive transcranial magnetic stimulation (rTMS) and transcranial direct-current stimulation (tDCS). Converging evidence points at the value of these non-invasive neuromodulation strategies to study basic mechanisms underlying eating behavior and to treat its disorders. Both of these approaches will be compared in light of recent work in this field, while addressing technical and practical questions. The third part of this review will be dedicated to invasive neuromodulation strategies, such as vagus nerve stimulation (VNS) and deep brain stimulation (DBS). In combination with neuroimaging approaches, these techniques are promising experimental tools to unravel the intricate relationships between homeostatic and hedonic brain circuits. Their potential as additional therapeutic tools to combat pharmacorefractory morbid obesity or acute eating disorders will be discussed, in terms of technical challenges, applicability and ethics. In a general discussion, we will put the brain at the core of fundamental research, prevention and therapy in the context of obesity and eating disorders. First, we will discuss the possibility to identify new biological markers of brain functions. Second, we will highlight the potential of neuroimaging and neuromodulation in individualized medicine. Third, we will introduce the ethical questions that are concomitant to the emergence of new neuromodulation therapies.

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.

Lung texture in serial thoracic computed tomography scans: correlation of radiomics-based features with radiation therapy dose and radiation pneumonitis development

PURPOSE

To assess the relationship between radiation dose and change in a set of mathematical intensity- and texture-based features and to determine the ability of texture analysis to identify patients who develop radiation pneumonitis (RP).

METHODS AND MATERIALS

A total of 106 patients who received radiation therapy (RT) for esophageal cancer were retrospectively identified under institutional review board approval. For each patient, diagnostic computed tomography (CT) scans were acquired before (0-168 days) and after (5-120 days) RT, and a treatment planning CT scan with an associated dose map was obtained. 32- × 32-pixel regions of interest (ROIs) were randomly identified in the lungs of each pre-RT scan. ROIs were subsequently mapped to the post-RT scan and the planning scan dose map by using deformable image registration. The changes in 20 feature values (ΔFV) between pre- and post-RT scan ROIs were calculated. Regression modeling and analysis of variance were used to test the relationships between ΔFV, mean ROI dose, and development of grade ≥2 RP. Area under the receiver operating characteristic curve (AUC) was calculated to determine each feature's ability to distinguish between patients with and those without RP. A classifier was constructed to determine whether 2- or 3-feature combinations could improve RP distinction.

RESULTS

For all 20 features, a significant ΔFV was observed with increasing radiation dose. Twelve features changed significantly for patients with RP. Individual texture features could discriminate between patients with and those without RP with moderate performance (AUCs from 0.49 to 0.78). Using multiple features in a classifier, AUC increased significantly (0.59-0.84).

CONCLUSIONS

A relationship between dose and change in a set of image-based features was observed. For 12 features, ΔFV was significantly related to RP development. This study demonstrated the ability of radiomics to provide a quantitative, individualized measurement of patient lung tissue reaction to RT and assess RP development.

Clinical utility of quantitative imaging

Quantitative imaging (QI) is increasingly applied in modern radiology practice, assisting in the clinical assessment of many patients and providing a source of biomarkers for a spectrum of diseases. QI is commonly used to inform patient diagnosis or prognosis, determine the choice of therapy, or monitor therapy response. Because most radiologists will likely implement some QI tools to meet the patient care needs of their referring clinicians, it is important for all radiologists to become familiar with the strengths and limitations of QI. The Association of University Radiologists Radiology Research Alliance Quantitative Imaging Task Force has explored the clinical application of QI and summarizes its work in this review. We provide an overview of the clinical use of QI by discussing QI tools that are currently used in clinical practice, clinical applications of these tools, approaches to reporting of QI, and challenges to implementing QI. It is hoped that these insights will help radiologists recognize the tangible benefits of QI to their patients, their referring clinicians, and their own radiology practice.

Entropy, complexity, and Markov diagrams for random walk cancer models

The notion of entropy is used to compare the complexity associated with 12 common cancers based on metastatic tumor distribution autopsy data. We characterize power-law distributions, entropy, and Kullback-Liebler divergence associated with each primary cancer as compared with data for all cancer types aggregated. We then correlate entropy values with other measures of complexity associated with Markov chain dynamical systems models of progression. The Markov transition matrix associated with each cancer is associated with a directed graph model where nodes are anatomical locations where a metastatic tumor could develop, and edge weightings are transition probabilities of progression from site to site. The steady-state distribution corresponds to the autopsy data distribution. Entropy correlates well with the overall complexity of the reduced directed graph structure for each cancer and with a measure of systemic interconnectedness of the graph, called graph conductance. The models suggest that grouping cancers according to their entropy values, with skin, breast, kidney, and lung cancers being prototypical high entropy cancers, stomach, uterine, pancreatic and ovarian being mid-level entropy cancers, and colorectal, cervical, bladder, and prostate cancers being prototypical low entropy cancers, provides a potentially useful framework for viewing metastatic cancer in terms of predictability, complexity, and metastatic potential.

An update on novel quantitative techniques in the context of evolving whole-body PET imaging

Since its foundation PET has established itself as one of the standard imaging modalities enabling the quantitative assessment of molecular targets in vivo. In the past two decades, quantitative PET has become a necessity in clinical oncology. Despite introduction of various measures for quantification and correction of PET parameters, there is debate on the selection of the appropriate methodology in specific diseases and conditions. In this review, we have focused on these techniques with special attention to topics such as static and dynamic whole body PET imaging, tracer kinetic modeling, global disease burden, texture analysis and radiomics, dual time point imaging and partial volume correction.

VATE: VAlidation of high TEchnology based on large database analysis by learning machine

SUMMARY 

The interaction between implementation of new technologies and different outcomes can allow a broad range of researches to be expanded. The purpose of this paper is to introduce the VAlidation of high TEchnology based on large database analysis by learning machine (VATE) project that aims to combine new technologies with outcomes related to rectal cancer in terms of tumor control and normal tissue sparing. Using automated computer bots and the knowledge for screening data it is possible to identify the factors that can mostly influence those outcomes. Population-based observational studies resulting from the linkage of different datasets will be conducted in order to develop predictive models that allow physicians to share decision with patients into a wider concept of tailored treatment.

High quality machine-robust image features: identification in nonsmall cell lung cancer computed tomography images

PURPOSE

For nonsmall cell lung cancer (NSCLC) patients, quantitative image features extracted from computed tomography (CT) images can be used to improve tumor diagnosis, staging, and response assessment. For these findings to be clinically applied, image features need to have high intra and intermachine reproducibility. The objective of this study is to identify CT image features that are reproducible, nonredundant, and informative across multiple machines.

METHODS

Noncontrast-enhanced, test-retest CT image pairs were obtained from 56 NSCLC patients imaged on three CT machines from two institutions. Two machines ("M1" and "M2") used cine 4D-CT and one machine ("M3") used breath-hold helical 3D-CT. Gross tumor volumes (GTVs) were semiautonomously segmented then pruned by removing voxels with CT numbers less than a prescribed Hounsfield unit (HU) cutoff. Three hundred and twenty eight quantitative image features were extracted from each pruned GTV based on its geometry, intensity histogram, absolute gradient image, co-occurrence matrix, and run-length matrix. For each machine, features with concordance correlation coefficient values greater than 0.90 were considered reproducible. The Dice similarity coefficient (DSC) and the Jaccard index (JI) were used to quantify reproducible feature set agreement between machines. Multimachine reproducible feature sets were created by taking the intersection of individual machine reproducible feature sets. Redundant features were removed through hierarchical clustering based on the average correlation between features across multiple machines.

RESULTS

For all image types, GTV pruning was found to negatively affect reproducibility (reported results use no HU cutoff). The reproducible feature percentage was highest for average images (M1 = 90.5%, M2 = 94.5%, M1∩M2 = 86.3%), intermediate for end-exhale images (M1 = 75.0%, M2 = 71.0%, M1∩M2 = 52.1%), and lowest for breath-hold images (M3 = 61.0%). Between M1 and M2, the reproducible feature sets generated from end-exhale images were relatively machine-sensitive (DSC = 0.71, JI = 0.55), and the reproducible feature sets generated from average images were relatively machine-insensitive (DSC = 0.90, JI = 0.87). Histograms of feature pair correlation distances indicated that feature redundancy was machine-sensitive and image type sensitive. After hierarchical clustering, 38 features, 28 features, and 33 features were found to be reproducible and nonredundant for M1∩M2 (average images), M1∩M2 (end-exhale images), and M3, respectively. When blinded to the presence of test-retest images, hierarchical clustering showed that the selected features were informative by correctly pairing 55 out of 56 test-retest images using only their reproducible, nonredundant feature set values.

CONCLUSIONS

Image feature reproducibility and redundancy depended on both the CT machine and the CT image type. For each image type, the authors found a set of cross-machine reproducible, nonredundant, and informative image features that would be useful for future image-based models. Compared to end-exhale 4D-CT and breath-hold 3D-CT, average 4D-CT derived image features showed superior multimachine reproducibility and are the best candidates for clinical correlation.

The role of texture analysis in imaging as an outcome predictor and potential tool in radiotherapy treatment planning

Predicting a tumour's response to radiotherapy prior to the start of treatment could enhance clinical care management by enabling the personalization of treatment plans based on predicted outcome. In recent years, there has been accumulating evidence relating tumour texture to patient survival and response to treatment. Tumour texture could be measured from medical images that provide a non-invasive method of capturing intratumoural heterogeneity and hence could potentially enable a prior assessment of a patient's predicted response to treatment. In this article, work presented in the literature regarding texture analysis in radiotherapy in relation to survival and outcome is discussed. Challenges facing integrating texture analysis in radiotherapy planning are highlighted and recommendations for future directions in research are suggested.

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.

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.

An individual tumour is often heterogeneous and its various features can be visualised noninvasively using medical imaging. Here, the authors analyse large computed tomography data sets using radiomic algorithms to identify heterogeneity, and find that some of these tumour features have prognostic value across cancer types.

Principles and methods of integrative genomic analyses in cancer

Combined analyses of molecular data, such as DNA copy-number alteration, mRNA and protein expression, point to biological functions and molecular pathways being deregulated in multiple cancers. Genomic, metabolomic and clinical data from various solid cancers and model systems are emerging and can be used to identify novel patient subgroups for tailored therapy and monitoring. The integrative genomics methodologies that are used to interpret these data require expertise in different disciplines, such as biology, medicine, mathematics, statistics and bioinformatics, and they can seem daunting. The objectives, methods and computational tools of integrative genomics that are available to date are reviewed here, as is their implementation in cancer research.

Development and evaluation of an open-source software package "CGITA" for quantifying tumor heterogeneity with molecular images

BACKGROUND

The quantification of tumor heterogeneity with molecular images, by analyzing the local or global variation in the spatial arrangements of pixel intensity with texture analysis, possesses a great clinical potential for treatment planning and prognosis. To address the lack of available software for computing the tumor heterogeneity on the public domain, we develop a software package, namely, Chang-Gung Image Texture Analysis (CGITA) toolbox, and provide it to the research community as a free, open-source project.

METHODS

With a user-friendly graphical interface, CGITA provides users with an easy way to compute more than seventy heterogeneity indices. To test and demonstrate the usefulness of CGITA, we used a small cohort of eighteen locally advanced oral cavity (ORC) cancer patients treated with definitive radiotherapies.

RESULTS

In our case study of ORC data, we found that more than ten of the current implemented heterogeneity indices outperformed SUVmean for outcome prediction in the ROC analysis with a higher area under curve (AUC). Heterogeneity indices provide a better area under the curve up to 0.9 than the SUVmean and TLG (0.6 and 0.52, resp.).

CONCLUSIONS

CGITA is a free and open-source software package to quantify tumor heterogeneity from molecular images. CGITA is available for free for academic use at http://code.google.com/p/cgita.

Systematic analysis of 18F-FDG PET and metabolism, proliferation and hypoxia markers for classification of head and neck tumors

Background

Quantification of molecular cell processes is important for prognostication and treatment individualization of head and neck cancer (HNC). However, individual tumor comparison can show discord in upregulation similarities when analyzing multiple biological mechanisms. Elaborate tumor characterization, integrating multiple pathways reflecting intrinsic and microenvironmental properties, may be beneficial to group most uniform tumors for treatment modification schemes. The goal of this study was to systematically analyze if immunohistochemical (IHC) assessment of molecular markers, involved in treatment resistance, and ¹⁸F-FDG PET parameters could accurately distinguish separate HNC tumors.

Methods

Several imaging parameters and texture features for ¹⁸F-FDG small-animal PET and immunohistochemical markers related to metabolism, hypoxia, proliferation and tumor blood perfusion were assessed within groups of BALB/c nu/nu mice xenografted with 14 human HNC models. Classification methods were used to predict tumor line based on sets of parameters.

Results

We found that ¹⁸F-FDG PET could not differentiate between the tumor lines. On the contrary, combined IHC parameters could accurately allocate individual tumors to the correct model. From 9 analyzed IHC parameters, a cluster of 6 random parameters already classified 70.3% correctly. Combining all PET/IHC characteristics resulted in the highest tumor line classification accuracy (81.0%; cross validation 82.0%), which was just 2.2% higher (p = 5.2×10^-32) than the performance of the IHC parameter/feature based model.

Conclusions

With a select set of IHC markers representing cellular processes of metabolism, proliferation, hypoxia and perfusion, one can reliably distinguish between HNC tumor lines. Addition of ¹⁸F-FDG PET improves classification accuracy of IHC to a significant yet minor degree. These results may form a basis for development of tumor characterization models for treatment allocation purposes.

Quantitative tumor segmentation for evaluation of extent of glioblastoma resection to facilitate multisite clinical trials

Standard-of-care therapy for glioblastomas, the most common and aggressive primary adult brain neoplasm, is maximal safe resection, followed by radiation and chemotherapy. Because maximizing resection may be beneficial for these patients, improving tumor extent of resection (EOR) with methods such as intraoperative 5-aminolevulinic acid fluorescence-guided surgery (FGS) is currently under evaluation. However, it is difficult to reproducibly judge EOR in these studies due to the lack of reliable tumor segmentation methods, especially for postoperative magnetic resonance imaging (MRI) scans. Therefore, a reliable, easily distributable segmentation method is needed to permit valid comparison, especially across multiple sites. We report a segmentation method that combines versatile region-of-interest blob generation with automated clustering methods. We applied this to glioblastoma cases undergoing FGS and matched controls to illustrate the method's reliability and accuracy. Agreement and interrater variability between segmentations were assessed using the concordance correlation coefficient, and spatial accuracy was determined using the Dice similarity index and mean Euclidean distance. Fuzzy C-means clustering with three classes was the best performing method, generating volumes with high agreement with manual contouring and high interrater agreement preoperatively and postoperatively. The proposed segmentation method allows tumor volume measurements of contrast-enhanced T 1-weighted images in the unbiased, reproducible fashion necessary for quantifying EOR in multicenter trials.

Volumetric CT-based segmentation of NSCLC using 3D-Slicer

Accurate volumetric assessment in non-small cell lung cancer (NSCLC) is critical for adequately informing treatments. In this study we assessed the clinical relevance of a semiautomatic computed tomography (CT)-based segmentation method using the competitive region-growing based algorithm, implemented in the free and public available 3D-Slicer software platform. We compared the 3D-Slicer segmented volumes by three independent observers, who segmented the primary tumour of 20 NSCLC patients twice, to manual slice-by-slice delineations of five physicians. Furthermore, we compared all tumour contours to the macroscopic diameter of the tumour in pathology, considered as the "gold standard". The 3D-Slicer segmented volumes demonstrated high agreement (overlap fractions > 0.90), lower volume variability (p = 0.0003) and smaller uncertainty areas (p = 0.0002), compared to manual slice-by-slice delineations. Furthermore, 3D-Slicer segmentations showed a strong correlation to pathology (r = 0.89, 95%CI, 0.81-0.94). Our results show that semiautomatic 3D-Slicer segmentations can be used for accurate contouring and are more stable than manual delineations. Therefore, 3D-Slicer can be employed as a starting point for treatment decisions or for high-throughput data mining research, such as Radiomics, where manual delineating often represent a time-consuming bottleneck.

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

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 Spearman's 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.

Integrative cancer epidemiology--the next generation

We outline an integrative approach to extend the boundaries of molecular cancer epidemiology by integrating modern and rapidly evolving "omics" technologies into state-of-the-art molecular epidemiology. In this way, one can comprehensively explore the mechanistic underpinnings of epidemiologic observations in cancer risk and outcome. We highlight the exciting opportunities to collaborate across large observational studies and to forge new interdisciplinary collaborative ventures.