Jinzhong Yang

Measuring Computed Tomography Scanner Variability of Radiomics Features.

ObjectivesThe purpose of this study was to determine the significance of interscanner variability in CT image radiomics studies. Materials and MethodsWe 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 4 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 interscanner variability, we introduced the metric feature noise. To look for patterns in the scans, we performed hierarchical clustering for each cartridge. ResultsThe 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 phantoms dynamic range includes that of the tumors. The interscanner variability of the feature values depended on both the cartridge material and the feature, and the variability was large relative to the interpatient variability in the NSCLC tumors for some features. The feature interscanner 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. ConclusionsThe 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 interscanner differences should be considered, and their effects should be minimized in future radiomics studies.

A statistical signal processing approach to image fusion for concealed weapon detection

A statistical signal processing approach to multisensor image fusion is presented for concealed weapon detection (CWD). This approach is based on an image formation model in which the sensor images are described as the true scene corrupted by additive non-Gaussian distortion. The expectation-maximization (EM) algorithm is used to estimate the model parameters and the fused image. We demonstrate the efficiency of this approach by applying this method to fusion of visual and non-visual images with emphasis on CWD applications.

Diffusion Tensor Image Registration Using Tensor Geometry and Orientation Features

This paper presents a method for deformable registration of diffusion tensor (DT) images that integrates geometry and orientation features into a hierarchical matching framework. The geometric feature is derived from the structural geometry of diffusion and characterizes the shape of the tensor in terms of prolateness, oblateness, and sphericity of the tensor. Local spatial distributions of the prolate, oblate, and spherical geometry are used to create an attribute vector of geometric feature for matching. The orientation feature improves the matching of the WM fiber tracts by taking into account the statistical information of underlying fiber orientations. These features are incorporated into a hierarchical deformable registration framework to develop a diffusion tensor image registration algorithm. Extensive experiments on simulated and real brain DT data establish the superiority of this algorithm for deformable matching of diffusion tensors, thereby aiding in atlas creation. The robustness of the method makes it potentially useful for group-based analysis of DT images acquired in large studies to identify disease-induced and developmental changes.

ibex: An open infrastructure software platform to facilitate collaborative work in radiomics

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 (IBEX), 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 IBEX software package was developed using the MATLAB and c/c++ 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, IBEX 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, IBEX provides an integrated development environment on top of MATLAB and c/c++, so users are not limited to its built-in functions. In the IBEX developer studio, users can plug in, debug, and test new algorithms, extending IBEXs functionality. IBEX 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 IBEX 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 IBEX software to be intuitive, powerful, and easy to use. IBEX 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 IBEX and IBEXs source code can be downloaded. CONCLUSIONS The authors successfully implemented IBEX, 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.

Dose constraints to prevent radiation-induced brachial plexopathy in patients treated for lung cancer.

PURPOSE As the recommended radiation dose for non-small-cell lung cancer (NSCLC) increases, meeting dose constraints for critical structures like the brachial plexus becomes increasingly challenging, particularly for tumors in the superior sulcus. In this retrospective analysis, we compared dose-volume histogram information with the incidence of plexopathy to establish the maximum dose tolerated by the brachial plexus. METHODS AND MATERIALS We identified 90 patients with NSCLC treated with definitive chemoradiation from March 2007 through September 2010, who had received >55 Gy to the brachial plexus. We used a multiatlas segmentation method combined with deformable image registration to delineate the brachial plexus on the original planning CT scans and scored plexopathy according to Common Terminology Criteria for Adverse Events version 4.03. RESULTS Median radiation dose to the brachial plexus was 70 Gy (range, 56-87.5 Gy; 1.5-2.5 Gy/fraction). At a median follow-up time of 14.0 months, 14 patients (16%) had brachial plexopathy (8 patients [9%] had Grade 1, and 6 patients [7%] had Grade ≥2); median time to symptom onset was 6.5 months (range, 1.4-37.4 months). On multivariate analysis, receipt of a median brachial plexus dose of >69 Gy (odds ratio [OR] 10.091; 95% confidence interval [CI], 1.512-67.331; p = 0.005), a maximum dose of >75 Gy to 2 cm(3) of the brachial plexus (OR, 4.909; 95% CI, 0.966-24.952; p = 0.038), and the presence of plexopathy before irradiation (OR, 4.722; 95% CI, 1.267-17.606; p = 0.021) were independent predictors of brachial plexopathy. CONCLUSIONS For lung cancers near the apical region, brachial plexopathy is a major concern for high-dose radiation therapy. We developed a computer-assisted image segmentation method that allows us to rapidly and consistently contour the brachial plexus and establish the dose limits to minimize the risk of brachial plexopathy. Our results could be used as a guideline in future prospective trials with high-dose radiation therapy for unresectable lung cancer.

The thin plate spline robust point matching (TPS-RPM) algorithm: A revisit

This paper reviews the TPS-RPM algorithm (Chui and Rangarajan, 2003) for robustly registering two sets of points and demonstrates from a theoretical point of view its inherent limited performance when outliers are present in both point sets simultaneously. A double-sided outlier handling approach is proposed to overcome this limitation with a rigorous mathematical proof as the underlying theoretical support. This double-sided outlier handling approach is proved to be equivalent to the original formulation of the point matching problem. For a practical application, we also extend the TPS-RPM algorithms to non-rigid image registration by registering two sets of sparse features extracted from images. The intensity information of the extracted features are incorporated into feature matching in order to reduce the impact from outliers. Our experiments demonstrate the double-sided outlier handling approach and the efficiency of intensity information in assisting outlier detection.

Impact of heart and lung dose on early survival in patients with non-small cell lung cancer treated with chemoradiation

BACKGROUND AND PURPOSE To determine whether the impact of heart dose on early overall survival (OS) reported in RTOG 0617 could be confirmed in an independent cohort. MATERIALS AND METHODS Heart and lung dose-volume histogram data were retrospectively extracted for patients with stage IIIA-IIIB non-small cell lung cancer (NSCLC) who had received radiotherapy using 3D CRT, IMRT or proton therapy delivered with concurrent chemotherapy between 1999 and 2010. Potential associations between clinical and dosimetric factors and OS up to 24months after start of treatment were assessed in univariate and multivariate analyses with log-rank tests or Cox proportional hazards models. RESULTS 468 patients met inclusion criteria. Factors associated with increased risk of early death in univariate analyses were performance status (PS), stage, treatment with 3D conformal radiotherapy, lower tumor dose and larger gross tumor volume (GTV), mean heart dose (MHD), heart V5, mean lung dose (MLD) and lung V5. Factors retaining significance in multivariate analysis were PS, GTV, and MLD. There was a strong correlation between MHD and heart V5 with MLD. However, no evidence was found that heart doses had an independent effect on OS during the first 2years. CONCLUSIONS In a large group of patients treated with chemoradiation for locally advanced NSCLC, heart dose was not found to be associated with early survival outcomes when lung dose was taken into account. Nevertheless, based on the known adverse effects of radiotherapy on vasculature and cardiac function, dose to the heart should be minimized during radiotherapy planning.

Quality assurance assessment of diagnostic and radiation therapy-simulation CT image registration for head and neck radiation therapy: Anatomic region of interest-based comparison of rigid and deformable algorithms

PURPOSE To develop a quality assurance (QA) workflow by using a robust, curated, manually segmented anatomic region-of-interest (ROI) library as a benchmark for quantitative assessment of different image registration techniques used for head and neck radiation therapy-simulation computed tomography (CT) with diagnostic CT coregistration. MATERIALS AND METHODS Radiation therapy-simulation CT images and diagnostic CT images in 20 patients with head and neck squamous cell carcinoma treated with curative-intent intensity-modulated radiation therapy between August 2011 and May 2012 were retrospectively retrieved with institutional review board approval. Sixty-eight reference anatomic ROIs with gross tumor and nodal targets were then manually contoured on images from each examination. Diagnostic CT images were registered with simulation CT images rigidly and by using four deformable image registration (DIR) algorithms: atlas based, B-spline, demons, and optical flow. The resultant deformed ROIs were compared with manually contoured reference ROIs by using similarity coefficient metrics (ie, Dice similarity coefficient) and surface distance metrics (ie, 95% maximum Hausdorff distance). The nonparametric Steel test with control was used to compare different DIR algorithms with rigid image registration (RIR) by using the post hoc Wilcoxon signed-rank test for stratified metric comparison. RESULTS A total of 2720 anatomic and 50 tumor and nodal ROIs were delineated. All DIR algorithms showed improved performance over RIR for anatomic and target ROI conformance, as shown for most comparison metrics (Steel test, P < .008 after Bonferroni correction). The performance of different algorithms varied substantially with stratification by specific anatomic structures or category and simulation CT section thickness. CONCLUSION Development of a formal ROI-based QA workflow for registration assessment demonstrated improved performance with DIR techniques over RIR. After QA, DIR implementation should be the standard for head and neck diagnostic CT and simulation CT allineation, especially for target delineation.

Preliminary investigation into sources of uncertainty in quantitative imaging features

Several recent studies have demonstrated the potential for quantitative imaging features to classify non-small cell lung cancer (NSCLC) patients as high or low risk. However applying the results from one institution to another has been difficult because of the variations in imaging techniques and feature measurement. Our study was designed to determine the effect of some of these sources of uncertainty on image features extracted from computed tomography (CT) images of non-small cell lung cancer (NSCLC) tumors. CT images from 20 NSCLC patients were obtained for investigating the impact of four sources of uncertainty: Two region of interest (ROI) selection conditions (breathing phase and single-slice vs. whole volume) and two imaging protocol parameters (peak tube voltage and current). Texture values did not vary substantially with the choice of breathing phase; however, almost half (12 out of 28) of the measured textures did change significantly when measured from the average images compared to the end-of-exhale phase. Of the 28 features, 8 showed a significant variation when measured from the largest cross sectional slice compared to the entire tumor, but 14 were correlated to the entire tumor value. While simulating a decrease in tube voltage had a negligible impact on texture features, simulating a decrease in mA resulted in significant changes for 13 of the 23 texture values. Our results suggest that substantial variation exists when textures are measured under different conditions, and thus the development of a texture analysis standard would be beneficial for comparing features between patients and institutions.

A Region-Based Image Fusion Method Using the Expectation-Maximization Algorithm

We present a novel region-based image fusion method using a rigorous application of estimation theory. This method takes advantage of the similar intensity or texture in a region for fusion. A statistical image formation model using Gaussian mixture distortion is built for each region and the EM (expectation-maximization) algorithm is used in conjunction with the model to develop the region-level EM fusion algorithm to produce the fused image. Since in most applications of image fusion, objects carry the information of interest and regions can be used to represent objects, the region-based fusion approaches could be more meaningful than pixel-based methods. Our experiments demonstrate the efficiency of the proposed region-base fusion method and the advantages in dealing with region interface artifacts for concealed weapon detection and night vision applications.