Test-retest reproducibility analysis of lung CT image features

Promises and challenges for the implementation of computational medical imaging (radiomics) in oncology

Medical image processing and analysis (also known as Radiomics) is a rapidly growing discipline that maps digital medical images into quantitative data, with the end goal of generating imaging biomarkers as decision support tools for clinical practice. The use of imaging data from routine clinical work-up has tremendous potential in improving cancer care by heightening understanding of tumor biology and aiding in the implementation of precision medicine. As a noninvasive method of assessing the tumor and its microenvironment in their entirety, radiomics allows the evaluation and monitoring of tumor characteristics such as temporal and spatial heterogeneity. One can observe a rapid increase in the number of computational medical imaging publications-milestones that have highlighted the utility of imaging biomarkers in oncology. Nevertheless, the use of radiomics as clinical biomarkers still necessitates amelioration and standardization in order to achieve routine clinical adoption. This Review addresses the critical issues to ensure the proper development of radiomics as a biomarker and facilitate its implementation in clinical practice.

Towards precision medicine: from quantitative imaging to radiomics

Radiology (imaging) and imaging-guided interventions, which provide multi-parametric morphologic and functional information, are playing an increasingly significant role in precision medicine. Radiologists are trained to understand the imaging phenotypes, transcribe those observations (phenotypes) to correlate with underlying diseases and to characterize the images. However, in order to understand and characterize the molecular phenotype (to obtain genomic information) of solid heterogeneous tumours, the advanced sequencing of those tissues using biopsy is required. Thus, radiologists image the tissues from various views and angles in order to have the complete image phenotypes, thereby acquiring a huge amount of data. Deriving meaningful details from all these radiological data becomes challenging and raises the big data issues. Therefore, interest in the application of radiomics has been growing in recent years as it has the potential to provide significant interpretive and predictive information for decision support. Radiomics is a combination of conventional computer-aided diagnosis, deep learning methods, and human skills, and thus can be used for quantitative characterization of tumour phenotypes. This paper discusses the overview of radiomics workflow, the results of various radiomics-based studies conducted using various radiological images such as computed tomography (CT), magnetic resonance imaging (MRI), and positron-emission tomography (PET), the challenges we are facing, and the potential contribution of radiomics towards precision medicine.

CT Radiomics in Thoracic Oncology: Technique and Clinical Applications

Precision medicine offers better treatment options and improved survival for cancer patients based on individual variability. As the success of precision medicine depends on robust biomarkers, the requirement for improved imaging biomarkers that reflect tumor biology has grown exponentially. Radiomics, the field of study in which high-throughput data are generated and large amounts of advanced quantitative features are extracted from medical images, has shown great potential as a source of quantitative biomarkers in the field of oncology. Radiomics provides quantitative information about the morphology, texture, and intratumoral heterogeneity of the tumor itself as well as features related to pulmonary function. Hence, radiomics data can be used to build descriptive and predictive clinical models that relate imaging characteristics to tumor biology phenotypes. In this review, we describe the workflow of CT radiomics, types of CT radiomics, and its clinical application in thoracic oncology.

Feature selection methodology for longitudinal cone-beam CT radiomics

BACKGROUND

Cone-beam CT (CBCT) scans are typically acquired daily for positioning verification of non-small cell lung cancer (NSCLC) patients. Quantitative information, derived using radiomics, can potentially contribute to (early) treatment adaptation. The aims of this study were to (1) describe and investigate a methodology for feature selection of a longitudinal radiomics approach (2) investigate which time-point during treatment is potentially useful for early treatment response assessment.

MATERIAL AND METHODS

For 90 NSCLC patients CBCT scans of the first two fractions of treatment (considered as 'test-retest' scans) were analyzed, as well as weekly CBCT images. One hundred and sixteen radiomic features were extracted from the GTV of all scans and subsequently absolute and relative differences were calculated between weekly CBCT images and the CBCT of the first fraction. Test-retest scans were used to determine the smallest detectable change (C = 1.96 * SD) allowing for feature selection by choosing a minimum number of patients for which a feature should change more than 'C' to be considered as relevant. Analysis of which features change at which moment during treatment was used to investigate which time-point is potentially relevant to extract longitudinal radiomics information for early treatment response assessment.

RESULTS

A total of six absolute delta features changed for at least ten patients at week 2 of treatment and increased to 61 at week 3, 79 at week 4 and 85 at week 5. There was 93% overlap between features selected at week 3 and the other weeks.

CONCLUSIONS

This study describes a feature selection methodology for longitudinal radiomics that is able to select reproducible delta radiomics features that are informative due to their change during treatment, which can potentially be used for treatment decisions concerning adaptive radiotherapy. Nonetheless, the prognostic value of the selected delta radiomic features should be investigated in future studies.

Clinical applications of textural analysis in non-small cell lung cancer

Lung cancer is the leading cause of cancer mortality worldwide. Treatment pathways include regular cross-sectional imaging, generating large data sets which present intriguing possibilities for exploitation beyond standard visual interpretation. This additional data mining has been termed "radiomics" and includes semantic and agnostic approaches. Textural analysis (TA) is an example of the latter, and uses a range of mathematically derived features to describe an image or region of an image. Often TA is used to describe a suspected or known tumour. TA is an attractive tool as large existing image sets can be submitted to diverse techniques for data processing, presentation, interpretation and hypothesis testing with annotated clinical outcomes. There is a growing anthology of published data using different TA techniques to differentiate between benign and malignant lung nodules, differentiate tissue subtypes of lung cancer, prognosticate and predict outcome and treatment response, as well as predict treatment side effects and potentially aid radiotherapy planning. The aim of this systematic review is to summarize the current published data and understand the potential future role of TA in managing lung cancer.

Interobserver variability in tumor contouring affects the use of radiomics to predict mutational status

Radiomic features characterize tumor imaging phenotype. Nonsmall cell lung cancer (NSCLC) tumors are known for their complexity in shape and wide range in density. We explored the effects of variable tumor contouring on the prediction of epidermal growth factor receptor (EGFR) mutation status by radiomics in NSCLC patients treated with a targeted therapy (Gefitinib). Forty-six early stage NSCLC patients (EGFR mutant:wildtype = 20:26) were included. Three experienced radiologists independently delineated the tumors using a semiautomated segmentation software on a noncontrast-enhanced baseline and three-week post-therapy CT scan images that were reconstructed using 1.25-mm slice thickness and lung kernel. Eighty-nine radiomic features were computed on both scans and their changes (radiomic delta-features) were calculated. The highest area under the curves (AUCs) were 0.87, 0.85, and 0.80 for the three radiologists and the number of significant features ([Formula: see text]) was 3, 5, and 0, respectively. The AUCs of a single feature significantly varied among radiologists (e.g., 0.88, 0.75, and 0.73 for run-length primitive length uniformity). We conclude that a three-week change in tumor imaging phenotype allows identifying the EGFR mutational status of NSCLC. However, interobserver variability in tumor contouring translates into a significant variability in radiomic metrics accuracy.

Radiomics: the bridge between medical imaging and personalized medicine

Radiomics, the high-throughput mining of quantitative image features from standard-of-care medical imaging that enables data to be extracted and applied within clinical-decision support systems to improve diagnostic, prognostic, and predictive accuracy, is gaining importance in cancer research. Radiomic analysis exploits sophisticated image analysis tools and the rapid development and validation of medical imaging data that uses image-based signatures for precision diagnosis and treatment, providing a powerful tool in modern medicine. Herein, we describe the process of radiomics, its pitfalls, challenges, opportunities, and its capacity to improve clinical decision making, emphasizing the utility for patients with cancer. Currently, the field of radiomics lacks standardized evaluation of both the scientific integrity and the clinical relevance of the numerous published radiomics investigations resulting from the rapid growth of this area. Rigorous evaluation criteria and reporting guidelines need to be established in order for radiomics to mature as a discipline. Herein, we provide guidance for investigations to meet this urgent need in the field of radiomics.

CT imaging features associated with recurrence in non-small cell lung cancer patients after stereotactic body radiotherapy

BACKGROUND

Predicting recurrence after stereotactic body radiotherapy (SBRT) in non-small cell lung cancer (NSCLC) patients is problematic, but critical for the decision of following treatment. This study aims to investigate the association of imaging features derived from the first follow-up computed tomography (CT) on lung cancer patient outcomes following SBRT, and identify patients at high risk of recurrence.

METHODS

Fifty nine biopsy-proven non-small cell lung cancer patients were qualified for this study. The first follow-up CTs were performed about 3 months after SBRT (median time: 91 days). Imaging features included 34 manually scored radiological features (semantics) describing the lesion, lung and thorax and 219 quantitative imaging features (radiomics) extracted automatically after delineation of the lesion. Cox proportional hazard models and Harrel's C-index were used to explore predictors of overall survival (OS), recurrence-free survival (RFS), and loco-regional recurrence-free survival (LR-RFS). Five-fold cross validation was performed on the final prognostic model.

RESULTS

The median follow-up time was 42 months. The model for OS contained Eastern Cooperative Oncology Group (ECOG) performance status (HR = 3.13, 95% CI: 1.17-8.41), vascular involvement (HR = 3.21, 95% CI: 1.29-8.03), lymphadenopathy (HR = 3.59, 95% CI: 1.58-8.16) and the 1st principle component of radiomic features (HR = 1.24, 95% CI: 1.02-1.51). The model for RFS contained vascular involvement (HR = 3.06, 95% CI: 1.40-6.70), vessel attachment (HR = 3.46, 95% CI: 1.65-7.25), pleural retraction (HR = 3.24, 95% CI: 1.41-7.42), lymphadenopathy (HR = 6.41, 95% CI: 2.58-15.90) and relative enhancement (HR = 1.40, 95% CI: 1.00-1.96). The model for LR-RFS contained vascular involvement (HR = 4.96, 95% CI: 2.23-11.03), lymphadenopathy (HR = 2.64, 95% CI: 1.19-5.82), circularity (F13, HR = 1.60, 95% CI: 1.10-2.32) and 3D Laws feature (F92, HR = 1.96, 95% CI: 1.35-2.83). Five-fold cross-validated the areas under the receiver operating characteristic curves (AUC) of these three models were all above 0.8.

CONCLUSIONS

Our analysis reveals disease progression could be prognosticated as early as 3 months after SBRT using CT imaging features, and these features would be helpful in clinical decision-making.

Primary Rectal Cancer: Repeatability of Global and Local-Regional MR Imaging Texture Features

Purpose To assess the day-to-day repeatability of global and local-regional magnetic resonance (MR) imaging texture features derived from primary rectal cancer. Materials and Methods After ethical approval and patient informed consent were obtained, two pretreatment T2-weighted axial MR imaging studies performed prospectively with the same imaging unit on 2 consecutive days in 14 patients with rectal cancer (11 men [mean age, 61.7 years], three women [mean age, 70.0 years]) were analyzed to extract (a) global first-order statistical histogram and model-based fractal features reflecting the whole-tumor voxel intensity histogram distribution and repeating patterns, respectively, without spatial information and (b) local-regional second-order and high-order statistical texture features reflecting the intensity and spatial interrelationships between adjacent in-plane or multiplanar voxels or regions, respectively. Repeatability was assessed for 46 texture features, and mean difference, 95% limits of agreement, within-subject coefficient of variation (wCV), and repeatability coefficient (r) were recorded. Results Repeatability was better for global parameters than for most local-regional parameters. In particular, histogram mean, median, and entropy, fractal dimension mean and standard deviation, and second-order entropy, homogeneity, difference entropy, and inverse difference moment demonstrated good repeatability, with narrow limits of agreement and wCVs of 10% or lower. Repeatability was poorest for the following high-order gray-level run-length (GLRL) gray-level zone size matrix (GLZSM) and neighborhood gray-tone difference matrix (NGTDM) parameters: GLRL intensity variability, GLZSM short-zone emphasis, GLZSM intensity nonuniformity, GLZSM intensity variability, GLZSM size zone variability, and NGTDM complexity, demonstrating wider agreement limits and wCVs of 50% or greater. Conclusion MR imaging repeatability is better for global texture parameters than for local-regional texture parameters, indicating that global texture parameters should be sufficiently robust for clinical practice. Online supplemental material is available for this article.

Radiogenomic Analysis of Oncological Data: A Technical Survey

In the last few years, biomedical research has been boosted by the technological development of analytical instrumentation generating a large volume of data. Such information has increased in complexity from basic (i.e., blood samples) to extensive sets encompassing many aspects of a subject phenotype, and now rapidly extending into genetic and, more recently, radiomic information. Radiogenomics integrates both aspects, investigating the relationship between imaging features and gene expression. From a methodological point of view, radiogenomics takes advantage of non-conventional data analysis techniques that reveal meaningful information for decision-support in cancer diagnosis and treatment. This survey is aimed to review the state-of-the-art techniques employed in radiomics and genomics with special focus on analysis methods based on molecular and multimodal probes. The impact of single and combined techniques will be discussed in light of their suitability in correlation and predictive studies of specific oncologic diseases.

Quality of Radiomic Features in Glioblastoma Multiforme: Impact of Semi-Automated Tumor Segmentation Software

Objective

The purpose of this study was to evaluate the reliability and quality of radiomic features in glioblastoma multiforme (GBM) derived from tumor volumes obtained with semi-automated tumor segmentation software.

Materials and Methods

MR images of 45 GBM patients (29 males, 16 females) were downloaded from The Cancer Imaging Archive, in which post-contrast T1-weighted imaging and fluid-attenuated inversion recovery MR sequences were used. Two raters independently segmented the tumors using two semi-automated segmentation tools (TumorPrism3D and 3D Slicer). Regions of interest corresponding to contrast-enhancing lesion, necrotic portions, and non-enhancing T2 high signal intensity component were segmented for each tumor. A total of 180 imaging features were extracted, and their quality was evaluated in terms of stability, normalized dynamic range (NDR), and redundancy, using intra-class correlation coefficients, cluster consensus, and Rand Statistic.

Results

Our study results showed that most of the radiomic features in GBM were highly stable. Over 90% of 180 features showed good stability (intra-class correlation coefficient [ICC] ≥ 0.8), whereas only 7 features were of poor stability (ICC < 0.5). Most first order statistics and morphometric features showed moderate-to-high NDR (4 > NDR ≥1), while above 35% of the texture features showed poor NDR (< 1). Features were shown to cluster into only 5 groups, indicating that they were highly redundant.

Conclusion

The use of semi-automated software tools provided sufficiently reliable tumor segmentation and feature stability; thus helping to overcome the inherent inter-rater and intra-rater variability of user intervention. However, certain aspects of feature quality, including NDR and redundancy, need to be assessed for determination of representative signature features before further development of radiomics.

Quantitative Clinical Imaging Methods for Monitoring Intratumoral Evolution

Solid tumors are multiscale, open, complex, dynamic systems: complex because they have many interacting components, dynamic because both the components and their interactions can change with time, and open because the tumor freely communicates with surrounding and even distant host tissue. Thus, it is not surprising that striking intratumoral variations are commonly observed in clinical imaging such as MRI and CT and that several recent studies found striking regional variations in the molecular properties of cancer cells from the same tumor. Interestingly, this spatial heterogeneity in molecular properties of tumor cells is typically ascribed to branching clonal evolution due to accumulating mutations while macroscopic variations observed in, for example, clinical MRI scans are usually viewed as functions of blood flow. The clinical significance of spatial heterogeneity has not been fully determined but there is a general consensus that the varying intratumoral landscape along with patient factors such as age, morbidity and lifestyle, contributes significantly to the often unpredictable response of individual patients within a disease cohort treated with the same standard-of-care therapy.Here we investigate the potential link between macroscopic tumor heterogeneity observed by clinical imaging and spatial variations in the observed molecular properties of cancer cells. We build on techniques developed in landscape ecology to link regional variations in the distribution of species with local environmental conditions that define their habitat. That is, we view each region of the tumor as a local ecosystem consisting of environmental conditions such as access to nutrients, oxygen, and means of waste clearance related to blood flow and the local population of tumor cells that both adapt to these conditions and, to some extent, change them through, for example, production of angiogenic factors. Furthermore, interactions among neighboring habitats can produce broader regional dynamics so that the internal diversity of tumors is the net result of complex multiscale somatic Darwinian interactions.Methods in landscape ecology harness Darwinian dynamics to link the environmental properties of a given region to the local populations which are assumed to represent maximally fit phenotypes within those conditions. Consider a common task of a landscape ecologist: defining the spatial distribution of species in a large region, e.g., in a satellite image. Clearly the most accurate approach requires a meter by meter survey of the multiple square kilometers in the region of interest. However, this is both impractical and potentially destructive. Instead, landscape ecology breaks the task into component parts relying on the Darwinian interdependence of environmental properties and fitness of specific species' phenotypic and genotypic properties. First, the satellite map is carefully analyzed to define the number and distribution of habitats. Then the species distribution in a representative sampling of each habitat is empirically determined. Ultimately, this permits sufficient bridging of spatial scales to accurately predict spatial distribution of plant and animal species within large regions.Currently, identifying intratumoral subpopulations requires detailed histological and molecular studies that are expensive and time consuming. Furthermore, this method is subject to sampling bias, is invasive for vital organs such as the brain, and inherently destructive precluding repeated assessments for monitoring post-treatment response and proteogenomic evolution. In contrast, modern cross-sectional imaging can interrogate the entire tumor noninvasively, allowing repeated analysis without disrupting the region of interest. In particular, magnetic resonance imaging (MRI) provides exceptional spatial resolution and generates signals that are unique to the molecular constituents of tissue. Here we propose that MRI scans may be the equivalent of satellite images in landscape ecology and, with appropriate application of Darwinian first principles and sophisticated image analytic methods, can be used to estimate regional variations in the molecular properties of cancer cells.We have initially examined this technique in glioblastoma, a malignant brain neoplasm which is morphologically complex and notorious for a fast progression from diagnosis to recurrence and death, making a suitable subject of noninvasive, rapidly repeated assessment of intratumoral evolution. Quantitative imaging analysis of routine clinical MRIs from glioblastoma has identified macroscopic morphologic characteristics which correlate with proteogenomics and prognosis. The key to the accurate detection and forecasting of intratumoral evolution using quantitative imaging analysis is likely to be in the understanding of the synergistic interactions between observable intratumoral subregions and the resulting tumor behavior.

Assessing Agreement between Radiomic Features Computed for Multiple CT Imaging Settings

OBJECTIVES

Radiomics utilizes quantitative image features (QIFs) to characterize tumor phenotype. In practice, radiological images are obtained from different vendors' equipment using various imaging acquisition settings. Our objective was to assess the inter-setting agreement of QIFs computed from CT images by varying two parameters, slice thickness and reconstruction algorithm.

MATERIALS AND METHODS

CT images from an IRB-approved/HIPAA-compliant study assessing thirty-two lung cancer patients were included for the analysis. Each scan's raw data were reconstructed into six imaging series using combinations of two reconstruction algorithms (Lung[L] and Standard[S]) and three slice thicknesses (1.25mm, 2.5mm and 5mm), i.e., 1.25L, 1.25S, 2.5L, 2.5S, 5L and 5S. For each imaging-setting, 89 well-defined QIFs were computed for each of the 32 tumors (one tumor per patient). The six settings led to 15 inter-setting comparisons (combinatorial pairs). To reduce QIF redundancy, hierarchical clustering was done. Concordance correlation coefficients (CCCs) were used to assess inter-setting agreement of the non-redundant feature groups. The CCC of each group was assessed by averaging CCCs of QIFs in the group.

RESULTS

Twenty-three non-redundant feature groups were created. Across all feature groups, the best inter-setting agreements (CCCs>0.8) were 1.25S vs 2.5S, 1.25L vs 2.5L, and 2.5S vs 5S; the worst (CCCs<0.51) belonged to 1.25L vs 5S and 2.5L vs 5S. Eight of the feature groups related to size, shape, and coarse texture had an average CCC>0.8 across all imaging settings.

CONCLUSIONS

Varying degrees of inter-setting disagreements of QIFs exist when features are computed from CT images reconstructed using different algorithms and slice thicknesses. Our findings highlight the importance of harmonizing imaging acquisition for obtaining consistent QIFs to study tumor imaging phonotype.

Quantitative radiomics studies for tissue characterization: a review of technology and methodological procedures

Quantitative analysis of tumour characteristics based on medical imaging is an emerging field of research. In recent years, quantitative imaging features derived from CT, positron emission tomography and MR scans were shown to be of added value in the prediction of outcome parameters in oncology, in what is called the radiomics field. However, results might be difficult to compare owing to a lack of standardized methodologies to conduct quantitative image analyses. In this review, we aim to present an overview of the current challenges, technical routines and protocols that are involved in quantitative imaging studies. The first issue that should be overcome is the dependency of several features on the scan acquisition and image reconstruction parameters. Adopting consistent methods in the subsequent target segmentation step is evenly crucial. To further establish robust quantitative image analyses, standardization or at least calibration of imaging features based on different feature extraction settings is required, especially for texture- and filter-based features. Several open-source and commercial software packages to perform feature extraction are currently available, all with slightly different functionalities, which makes benchmarking quite challenging. The number of imaging features calculated is typically larger than the number of patients studied, which emphasizes the importance of proper feature selection and prediction model-building routines to prevent overfitting. Even though many of these challenges still need to be addressed before quantitative imaging can be brought into daily clinical practice, radiomics is expected to be a critical component for the integration of image-derived information to personalize treatment in the future.

Test-Retest Data for Radiomics Feature Stability Analysis: Generalizable or Study-Specific?

Radiomics is an objective method for extracting quantitative information from medical images. However, in radiomics, standardization, overfitting, and generalization are major challenges to be overcome. Test–retest experiments can be used to select robust radiomic features that have minimal variation. Currently, it is unknown whether they should be identified for each disease (disease specific) or are only imaging device-specific (computed tomography [CT]-specific). Here, we performed a test–retest analysis on CT scans of 40 patients with rectal cancer in a clinical setting. Correlation between radiomic features was assessed using the concordance correlation coefficient (CCC). In total, only 9/542 features have a CCC > 0.85. Furthermore, results were compared with the test–retest results on CT scans of 27 patients with lung cancer with a 15-minute interval. Results show that 446/542 features have a higher CCC for the test–retest analysis of the data set of patients with lung cancer than for patients with rectal cancer. The importance of controlling factors such as scanners, imaging protocol, reconstruction methods, and time points in a radiomics analysis is shown. Moreover, the results imply that test–retest analyses should be performed before each radiomics study. More research is required to independently evaluate the effect of each factor.

A Rapid Segmentation-Insensitive "Digital Biopsy" Method for Radiomic Feature Extraction: Method and Pilot Study Using CT Images of Non-Small Cell Lung Cancer

Quantitative imaging approaches compute features within images' regions of interest. Segmentation is rarely completely automatic, requiring time-consuming editing by experts. We propose a new paradigm, called “digital biopsy,” that allows for the collection of intensity- and texture-based features from these regions at least 1 order of magnitude faster than the current manual or semiautomated methods. A radiologist reviewed automated segmentations of lung nodules from 100 preoperative volume computed tomography scans of patients with non–small cell lung cancer, and manually adjusted the nodule boundaries in each section, to be used as a reference standard, requiring up to 45 minutes per nodule. We also asked a different expert to generate a digital biopsy for each patient using a paintbrush tool to paint a contiguous region of each tumor over multiple cross-sections, a procedure that required an average of <3 minutes per nodule. We simulated additional digital biopsies using morphological procedures. Finally, we compared the features extracted from these digital biopsies with our reference standard using intraclass correlation coefficient (ICC) to characterize robustness. Comparing the reference standard segmentations to our digital biopsies, we found that 84/94 features had an ICC >0.7; comparing erosions and dilations, using a sphere of 1.5-mm radius, of our digital biopsies to the reference standard segmentations resulted in 41/94 and 53/94 features, respectively, with ICCs >0.7. We conclude that many intensity- and texture-based features remain consistent between the reference standard and our method while substantially reducing the amount of operator time required.

Predicting Malignant Nodules from Screening CT Scans

OBJECTIVES

The aim of this study was to determine whether quantitative analyses ("radiomics") of low-dose computed tomography lung cancer screening images at baseline can predict subsequent emergence of cancer.

METHODS

Public data from the National Lung Screening Trial (ACRIN 6684) were assembled into two cohorts of 104 and 92 patients with screen-detected lung cancer and then matched with cohorts of 208 and 196 screening subjects with benign pulmonary nodules. Image features were extracted from each nodule and used to predict the subsequent emergence of cancer.

RESULTS

The best models used 23 stable features in a random forests classifier and could predict nodules that would become cancerous 1 and 2 years hence with accuracies of 80% (area under the curve 0.83) and 79% (area under the curve 0.75), respectively. Radiomics outperformed the Lung Imaging Reporting and Data System and volume-only approaches. The performance of the McWilliams risk assessment model was commensurate.

CONCLUSIONS

The radiomics of lung cancer screening computed tomography scans at baseline can be used to assess risk for development of cancer.

Biomechanical model for computing deformations for whole-body image registration: A meshless approach

Patient-specific biomechanical models have been advocated as a tool for predicting deformations of soft body organs/tissue for medical image registration (aligning two sets of images) when differences between the images are large. However, complex and irregular geometry of the body organs makes generation of patient-specific biomechanical models very time-consuming. Meshless discretisation has been proposed to solve this challenge. However, applications so far have been limited to 2D models and computing single organ deformations. In this study, 3D comprehensive patient-specific nonlinear biomechanical models implemented using meshless Total Lagrangian explicit dynamics algorithms are applied to predict a 3D deformation field for whole-body image registration. Unlike a conventional approach that requires dividing (segmenting) the image into non-overlapping constituents representing different organs/tissues, the mechanical properties are assigned using the fuzzy c-means algorithm without the image segmentation. Verification indicates that the deformations predicted using the proposed meshless approach are for practical purposes the same as those obtained using the previously validated finite element models. To quantitatively evaluate the accuracy of the predicted deformations, we determined the spatial misalignment between the registered (i.e. source images warped using the predicted deformations) and target images by computing the edge-based Hausdorff distance. The Hausdorff distance-based evaluation determines that our meshless models led to successful registration of the vast majority of the image features. Copyright © 2016 John Wiley & Sons, Ltd.

Association of Radiomics and Metabolic Tumor Volumes in Radiation Treatment of Glioblastoma Multiforme

PURPOSE

To build a framework for investigation of the associations between imaging, clinical target volumes (CTVs), and metabolic tumor volumes (MTVs) features for better understanding of the underlying information in the CTVs and dependencies between these volumes. High-throughput extraction of imaging and metabolomic quantitative features from magnetic resonance imaging (MRI) and magnetic resonance spectroscopic imaging of glioblastoma multiforme (GBM) results in tens of variables per patient. In radiation therapy of GBM the relevant metabolic tumor volumes (MTVs) are related to aberrant levels of N-acetyl aspartate (NAA) and choline (Cho). The corresponding clinical target volumes (CTVs) for radiation therapy are based on contrast-enhanced T1-weighted (CE-T1w) and T2-weighted (T2w)/fluid-attenuated inversion recovery MRI.

METHODS AND MATERIALS

Necrotic portions, enhancing lesion, and edema were manually contoured on CE-T1w/T2w images for 17 GBM patients. Clinical target volumes and MTVs for NAA (MTV_NAA) and Cho (MTV_Cho) were constructed. Imaging and metabolic features related to size, shape, and signal intensities of the volumes were extracted. Tumors were also scored categorically for 10 semantic imaging traits by a neuroradiologist. All features were investigated for redundancy. Two-way correlations between imaging and CTVs/MTVs features were visualized as heatmaps. Associations between MTV_NAA and MTV_Cho and imaging features were studied using Spearman correlation.

RESULTS

Forty-eight imaging features were extracted per patient. Half of the imaging traits were replaced with automatically extracted continuous variables. Twenty features were extracted from CTVs and MTVs. A series of semantic imaging traits were replaced with automatically extracted continuous variables. There were multiple (22) significant correlations of imaging measures with CTVs/MTV_NAA, whereas there were only 6 with CTVs/MTV_Cho.

CONCLUSIONS

A framework for investigation of codependencies between MRI and magnetic resonance spectroscopic imaging radiomic features and CTVs/MTVs has been established. The MTV for NAA was found to be closely associated with MRI volumes, whereas very few imaging features were related to MTV_Cho, indicating that Cho provides additional information to imaging.

Improving malignancy prediction through feature selection informed by nodule size ranges in NLST

Computed tomography (CT) is widely used during diagnosis and treatment of Non-Small Cell Lung Cancer (NSCLC). Current computer-aided diagnosis (CAD) models, designed for the classification of malignant and benign nodules, use image features, selected by feature selectors, for making a decision. In this paper, we investigate automated selection of different image features informed by different nodule size ranges to increase the overall accuracy of the classification. The NLST dataset is one of the largest available datasets on CT screening for NSCLC. We used 261 cases as a training dataset and 237 cases as a test dataset. The nodule size, which may indicate biological variability, can vary substantially. For example, in the training set, there are nodules with a diameter of a couple millimeters up to a couple dozen millimeters. The premise is that benign and malignant nodules have different radiomic quantitative descriptors related to size. After splitting training and testing datasets into three subsets based on the longest nodule diameter (LD) parameter accuracy was improved from 74.68% to 81.01% and the AUC improved from 0.69 to 0.79. We show that if AUC is the main factor in choosing parameters then accuracy improved from 72.57% to 77.5% and AUC improved from 0.78 to 0.82. Additionally, we show the impact of an oversampling technique for the minority cancer class. In some particular cases from 0.82 to 0.87.

Sensitivity of Image Features to Noise in Conventional and Respiratory-Gated PET/CT Images of Lung Cancer: Uncorrelated Noise Effects

The effect of noise on image features has yet to be studied in depth. Our objective was to explore how significantly image features are affected by the addition of uncorrelated noise to an image. The signal-to-noise ratio and noise power spectrum were calculated for a positron emission tomography/computed tomography scanner using a Ge-68 phantom. The conventional and respiratory-gated positron emission tomography/computed tomography images of 31 patients with lung cancer were retrospectively examined. Multiple sets of noise images were created for each original image by adding Gaussian noise of varying standard deviation equal to 2.5%, 4.0%, and 6.0% of the maximum intensity for positron emission tomography images and 10, 20, 50, 80, and 120 Hounsfield units for computed tomography images. Image features were extracted from all images, and percentage differences between the original image and the noise image feature values were calculated. These features were then categorized according to the noise sensitivity. The contour-dependent shape descriptors averaged below 4% difference in positron emission tomography and below 13% difference in computed tomography between noise and original images. Gray level size zone matrix features were the most sensitive to uncorrelated noise exhibiting average differences >200% for conventional and respiratory-gated images in computed tomography and 90% in positron emission tomography. Image feature differences increased as the noise level increased for shape, intensity, and gray-level co-occurrence matrix features in positron emission tomography and for gray-level co-occurrence matrix and gray-level size zone matrix features in conventional computed tomography. Investigators should be aware of the noise effects on image features.

Applications and limitations of radiomics

Radiomics is an emerging field in quantitative imaging that uses advanced imaging features to objectively and quantitatively describe tumour phenotypes. Radiomic features have recently drawn considerable interest due to its potential predictive power for treatment outcomes and cancer genetics, which may have important applications in personalized medicine. In this technical review, we describe applications and challenges of the radiomic field. We will review radiomic application areas and technical issues, as well as proper practices for the designs of radiomic studies.

Reproducibility of radiomics for deciphering tumor phenotype with imaging

Radiomics (radiogenomics) characterizes tumor phenotypes based on quantitative image features derived from routine radiologic imaging to improve cancer diagnosis, prognosis, prediction and response to therapy. Although radiomic features must be reproducible to qualify as biomarkers for clinical care, little is known about how routine imaging acquisition techniques/parameters affect reproducibility. To begin to fill this knowledge gap, we assessed the reproducibility of a comprehensive, commonly-used set of radiomic features using a unique, same-day repeat computed tomography data set from lung cancer patients. Each scan was reconstructed at 6 imaging settings, varying slice thicknesses (1.25 mm, 2.5 mm and 5 mm) and reconstruction algorithms (sharp, smooth). Reproducibility was assessed using the repeat scans reconstructed at identical imaging setting (6 settings in total). In separate analyses, we explored differences in radiomic features due to different imaging parameters by assessing the agreement of these radiomic features extracted from the repeat scans reconstructed at the same slice thickness but different algorithms (3 settings in total). Our data suggest that radiomic features are reproducible over a wide range of imaging settings. However, smooth and sharp reconstruction algorithms should not be used interchangeably. These findings will raise awareness of the importance of properly setting imaging acquisition parameters in radiomics/radiogenomics research.

Potential Application of Radiomics for Differentiating Solitary Pulmonary Nodules

A solitary pulmonary nodule is defined as radiographic lesion with diameters no more than 3 cm and completely surrounded by normal lung tissue. It is commonly encountered in clinical practice and its diagnosis is a big challenge. Medical imaging, as a non-invasive approach, plays a crucial role in the diagnosis of solitary pulmonary nodules since the potential morbidity of surgery and the limits of biopsy. Advanced hardware, image acquisition and analysis technologies have led to the utilization of imaging towards quantitative imaging. With the aim of mining more useful information from image data, radiomics with high-throughput extraction can play a useful role. This article is to introduce the current state of radiomics studies and describe the general procedures. Another objective of this paper is to discover the feasibility and potential of radiomics methods on differentiating solitary pulmonary nodules and to look into the future direction of radiomics in this area.

Radiomic Features Are Associated With EGFR Mutation Status in Lung Adenocarcinomas

BACKGROUND

In this study we retrospectively evaluated the capability of computed tomography (CT)-based radiomic features to predict epidermal growth factor receptor (EGFR) mutation status in surgically-resected peripheral lung adenocarcinomas in an Asian cohort of patients.

PATIENTS AND METHODS

Two hundred ninety-eight patients with surgically resected peripheral lung adenocarcinomas were investigated in this institutional review board-approved retrospective study with requirement waived to obtain informed consent. Two hundred nineteen quantitative 3-D features were extracted from segmented volumes of each tumor, and 59 of these, which were considered independent features, were included in the analysis. Clinical and pathological information was obtained from the institutional database.

RESULTS

Mutant EGFR was significantly associated with female sex (P = .0005); never smoker status (P < .0001), lepidic predominant adenocarcinomas (P = .017), and low or intermediate pathologic grade (P = .0002). Statistically significant differences were found in 11 radiomic features between EGFR mutant and wild type groups in univariate analysis. Mutant EGFR status could be predicted by a set of 5 radiomic features that fell into 3 broad groups: CT attenuation energy, tumor main direction, and texture defined according to wavelets and Laws (area under the curve [AUC], 0.647). A multiple logistic regression model showed that adding radiomic features to a clinical model resulted in a significant improvement of predicting power, because the AUC increased from 0.667 to 0.709 (P < .0001).

CONCLUSION

Computed tomography-based radiomic features of peripheral lung adenocarcinomas can capture useful information regarding tumor phenotype, and the model we built can be useful to predict the presence of EGFR mutations in peripheral lung adenocarcinoma in Asian patients when mutational profiling is not available or possible.

Radiomics: Images Are More than Pictures, They Are Data

In the past decade, the field of medical image analysis has grown exponentially, with an increased number of pattern recognition tools and an increase in data set sizes. These advances have facilitated the development of processes for high-throughput extraction of quantitative features that result in the conversion of images into mineable data and the subsequent analysis of these data for decision support; this practice is termed radiomics. This is in contrast to the traditional practice of treating medical images as pictures intended solely for visual interpretation. Radiomic data contain first-, second-, and higher-order statistics. These data are combined with other patient data and are mined with sophisticated bioinformatics tools to develop models that may potentially improve diagnostic, prognostic, and predictive accuracy. Because radiomics analyses are intended to be conducted with standard of care images, it is conceivable that conversion of digital images to mineable data will eventually become routine practice. This report describes the process of radiomics, its challenges, and its potential power to facilitate better clinical decision making, particularly in the care of patients with cancer.

Clinical application of a novel computer-aided detection system based on three-dimensional CT images on pulmonary nodule

The aim of this study was to investigate the clinical application effects of a novel computer-aided detection (CAD) system based on three-dimensional computed tomography (CT) images on pulmonary nodule. 98 cases with pulmonary nodule (PN) in our hospital from Jun, 2009 to Jun, 2013 were analysed in this study. All cases underwent PN detection both by the simple spiral CT scan and by the computer-aided system based on 3D CT images, respectively. Postoperative pathological results were considered as the "gold standard", for both two checking methods, the diagnostic accuracies for determining benign and malignant PN were calculated. Under simple spiral CT scan method, 63 cases is malignant, including 50 true positive cases and 13 false positive cases from the "gold standard"; 35 cases is benign, 16 true negative case and 19 false negative cases, the Sensitivity 1 (Se1)=0.725, Specificity1 (Sp1)=0.448, Agreement rate1 (Kappa 1)=0.673, J1 (Youden's index 1)=0.173, LR(+)1=1.616, LR(-)1=0.499. Kappa 1=0.673 between the 0.4 and 0.75, has a moderate consistency. Underwent computer-aided detection (CAD) based on 3D CT method, 67cases is malignant, including 62 true positive cases and 7 false positive cases; 31 cases is benign, 24 true negative case and 7 false negative cases, Sensitivity 2 (Se2)=0.899, Specificity2 (Sp2)=0.828, Agreement rate (Kappa 2)=0.877, J2 (Youden's index 2)=0.727, LR(+)2=5.212, LR(-)2=0.123. Kappa 2=0.877 >0.75, has a good consistency. Computer-aided PN detecting system based on 3D CT images has better clinical application value, and can help doctor carry out early diagnosis of lung disease (such as cancer, etc.) through CT images.

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.

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.

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.