Objectives The purpose of this study was to determine the significance of inter-scanner variability in CT image radiomics studies. Materials and Methods We compared the radiomics features calculated for non-small cell lung cancer (NSCLC) tumors from 20 patients with those calculated for 17 scans of a specially designed radiomics phantom. The phantom comprised 10 cartridges, each filled with different materials to produce a wide range of radiomics feature values. The scans were acquired using General Electric, Philips, Siemens, and Toshiba scanners from four medical centers using their routine thoracic imaging protocol. The radiomics feature studied included the mean and standard deviations of the CT numbers as well as textures derived from the neighborhood gray-tone difference matrix. To quantify the significance of the inter-scanner variability, we introduced the metric feature noise. To look for patterns in the scans, we performed hierarchical clustering for each cartridge. Results The mean CT numbers for the 17 CT scans of the phantom cartridges spanned from -864 to 652 Hounsfield units compared with a span of -186 to 35 Hounsfield units for the CT scans of the NSCLC tumors, showing that the phantom’s dynamic range includes that of the tumors. The inter-scanner variability of the feature values depended on both the cartridge material and the feature, and the variability was large relative to the inter-patient variability in the NSCLC tumors for some features. The feature inter-scanner noise was greatest for busyness and least for texture strength. Hierarchical clustering produced different clusters of the phantom scans for each cartridge, although there was some consistent clustering by scanner manufacturer. Conclusions The variability in the values of radiomics features calculated on CT images from different CT scanners can be comparable to the variability in these features found in CT images of NSCLC tumors. These inter-scanner differences should be considered, and their effects should be minimized in future radiomics studies.

Purpose: Radiomics, which is the high-throughput extraction and analysis of quantitative image features, has been shown to have considerable potential to quantify the tumor phenotype. However, at present, a lack of software infrastructure has impeded the development of radiomics and its applications. Therefore, the authors developed the imaging biomarker explorer (), an open infrastructure software platform that flexibly supports common radiomics workflow tasks such as multimodality image data import and review, development of feature extraction algorithms, model validation, and consistent data sharing among multiple institutions. Methods: The  software package was developed using the  and /++ programming languages. The software architecture deploys the modern model-view-controller, unit testing, and function handle programming concepts to isolate each quantitative imaging analysis task, to validate if their relevant data and algorithms are fit for use, and to plug in new modules. On one hand,  is self-contained and ready to use: it has implemented common data importers, common image filters, and common feature extraction algorithms. On the other hand,  provides an integrated development environment on top of  and /++, so users are not limited to its built-in functions. In the  developer studio, users can plug in, debug, and test new algorithms, extending 's functionality.  also supports quality assurance for data and feature algorithms: image data, regions of interest, and feature algorithm-related data can be reviewed, validated, and/or modified. More importantly, two key elements in collaborative workflows, the consistency of data sharing and the reproducibility of calculation result, are embedded in the  workflow: image data, feature algorithms, and model validation including newly developed ones from different users can be easily and consistently shared so that results can be more easily reproduced between institutions. Results: Researchers with a variety of technical skill levels, including radiation oncologists, physicists, and computer scientists, have found the  software to be intuitive, powerful, and easy to use.  can be run at any computer with the windows operating system and 1GB RAM. The authors fully validated the implementation of all importers, preprocessing algorithms, and feature extraction algorithms. Windows version 1.0 beta of stand-alone  and 's source code can be downloaded. Conclusions: The authors successfully implemented , an open infrastructure software platform that streamlines common radiomics workflow tasks. Its transparency, flexibility, and portability can greatly accelerate the pace of radiomics research and pave the way toward successful clinical translation. C 2015 American Association of Physicists in Medicine. [http://dx

Purpose To determine whether pretreatment CT texture features can improve patient risk stratification beyond conventional prognostic factors (CPFs) in stage III non-small cell lung cancer (NSCLC). Methods and Materials We retrospectively reviewed 91 patients with stage III NSCLC treated with definitive chemoradiation. All patients underwent a pretreatment diagnostic contrast enhanced CT (CE-CT) followed by a 4D-CT for treatment simulation. We used the average (average-CT) and expiratory (T50-CT) images from the 4D-CT along with the CE-CT for texture extraction. Histogram, gradient, co-occurrence, gray-tone difference, and filtration-based techniques were used for texture feature extraction. Penalized Cox regression implementing cross-validation was used for covariate selection and modeling. Models incorporating texture features from the 3 image types and CPFs were compared to models incorporating CPFs alone for overall survival (OS), local-regional control (LRC), and freedom from distant metastases (FFDM). Predictive Kaplan-Meier curves were generated using leave-one-out cross-validation. Patients were stratified based on their predicted outcome being above/below the median. Reproducibility of texture features was evaluated using test-retest scans from independent patients and quantified using concordance correlation coefficients (CCC). We compared models incorporating the reproducibility seen on test-retest scans to our original models and determined the classification reproducibility. Results Models incorporating both texture features and CPFs demonstrated a significant improvement in risk stratification compared to models using CPFs alone for OS (p=0.046), LRC (p=0.01), and FFDM (p=0.005). The average CCC was 0.89, 0.91, and 0.67 for texture features extracted from the average-CT, T50-CT, and CE-CT, respectively. Incorporating reproducibility within our models yielded 80.4 (SD=3.7), 78.3 (SD=4.0), and 78.8 (SD=3.9) percent classification reproducibility in terms of OS, LRC, and FFDM, respectively. Conclusions Pretreatment tumor texture may provide prognostic information beyond what is obtained from CPFs. Models incorporating feature reproducibility achieved classification rates of ~80%. External validation would be required to establish texture as a prognostic factor.

Purpose: Increasing evidence suggests radiomics features extracted from computed tomography (CT) images may be useful in prognostic models for patients with nonsmall cell lung cancer (NSCLC). This study was designed to determine whether such features can be reproducibly obtained from cone-beam CT (CBCT) images taken using medical Linac onboard-imaging systems in order to track them through treatment. Methods: Test-retest CBCT images of ten patients previously enrolled in a clinical trial were retrospectively obtained and used to determine the concordance correlation coefficient (CCC) for 68 different texture features. The volume dependence of each feature was also measured using the Spearman rank correlation coefficient. Features with a high reproducibility (CCC > 0.9) that were not due to volume dependence in the patient test-retest set were further examined for their sensitivity to differences in imaging protocol, level of scatter, and amount of motion by using two phantoms. The first phantom was a texture phantom composed of rectangular cartridges to represent different textures. Features were measured from two cartridges, shredded rubber and dense cork, in this study. The texture phantom was scanned with 19 different CBCT imagers to establish the features' interscanner variability. The effect of scatter on these features was studied by surrounding the same texture phantom with scattering material (rice and solid water). The effect of respiratory motion on these features was studied using a dynamic-motion thoracic phantom and a specially designed tumor texture insert of the shredded rubber material. The differences between scans acquired with different Linacs and protocols, varying amounts of scatter, and with different levels of motion were compared to the mean intrapatient difference from the test-retest image set. Results: Of the original 68 features, 37 had a CCC >0.9 that was not due to volume dependence. When the Linac manufacturer and imaging protocol were kept consistent, 4-13 of these 37 features passed our criteria for reproducibility more than 50% of the time, depending on the manufacturerprotocol combination. Almost all of the features changed substantially when scatter material was added around the phantom. For the dense cork, 23 features passed in the thoracic scans and 11 features passed in the head scans when the differences between one and two layers of scatter were compared. Using the same test for the shredded rubber, five features passed the thoracic scans and eight features passed the head scans. Motion substantially impacted the reproducibility of the features. With 4 mm of motion, 12 features from the entire volume and 14 features from the center slice measurements were reproducible. With 6-8 mm of motion, three features (Laplacian of Gaussian filtered kurtosis, gray-level nonuniformity, and entropy), from the entire volume and seven features (coarseness, high gray-level run emphasis, gray-level nonuniformity, sum-average, information measure correlation, scaled mean, and entropy) from ...