Search

Purpose: Whole-body positron emission tomography/computed tomography (PET/CT) has become a standard method of imaging patients with various disease conditions, especially cancer. Body-wide accurate quantification of disease burden in PET/CT images is important for characterizing lesions, staging disease, prognosticating patient outcome, planning treatment, and evaluating disease response to therapeutic interventions. However, body-wide anatomy recognition in PET/CT is a critical first step for accurately and automatically quantifying disease body-wide, body-region-wise, and organwise. This latter process, however, has remained a challenge due to the lower quality of the anatomic information portrayed in the CT component of this imaging modality and the paucity of anatomic details in the PET component. In this paper, the authors demonstrate the adaptation of a recently developed automatic anatomy recognition (AAR) methodology [Udupa et al., "Body-wide hierarchical fuzzy modeling, recognition, and delineation of anatomy in medical images," Med. Image Anal. 18, 752-771 (2014)] to PET/CT images. Their goal was to test what level of object localization accuracy can be achieved on PET/CT compared to that achieved on diagnostic CT images. Methods: The authors advance the AAR approach in this work in three fronts: (i) from body-regionwise treatment in the work of Udupa et al. to whole body; (ii) from the use of image intensity in optimal object recognition in the work of Udupa et al. to intensity plus object-specific texture properties, and (iii) from the intramodality model-building-recognition strategy to the intermodality approach. The whole-body approach allows consideration of relationships among objects in different body regions, which was previously not possible. Consideration of object texture allows generalizing the previous optimal threshold-based fuzzy model recognition method from intensity images to any derived fuzzy membership image, and in the process, to bring performance to the level achieved on diagnostic CT and MR images in body-region-wise approaches. The intermodality approach fosters the use of already existing fuzzy models, previously created from diagnostic CT images, on PET/CT and other derived images, thus truly separating the modality-independent object assembly anatomy from modality-specific tissue property portrayal in the image. Results: Key ways of combining the above three basic ideas lead them to 15 different strategies for recognizing objects in PET/CT images. Utilizing 50 diagnostic CT image data sets from the thoracic and abdominal body regions and 16 whole-body PET/CT image data sets, the authors compare the recognition performance among these 15 strategies on 18 objects from the thorax, abdomen, and pelvis in object localization error and size estimation error. Particularly on texture membership images, object localization is within three voxels on whole-body low-dose CT images and 2 voxels on body-region-wise low-dose images of known true locations. Surprisingly, even on direct body-region-wise PET images, localization error within 3 voxels seems possible. Conclusions: The previous body-region-wise approach can be extended to whole-body torso with similar object localization performance. Combined use of image texture and intensity property yields the best object localization accuracy. In both body-region-wise and whole-body approaches, recognition performance on low-dose CT images reaches levels previously achieved on diagnostic CT images. The best object recognition strategy varies among objects; the proposed framework however allows employing a strategy that is optimal for each object. [ABSTRACT FROM AUTHOR]

Purpose: Mammographic percent density (PD%) is known to be a strong risk factor for breast cancer. Recent studies also suggest that parenchymal texture features, which are more granular descriptors of the parenchymal pattern, can provide additional information about breast cancer risk. To date, most studies have measured mammographic texture within selected regions of interest (ROIs) in the breast, which cannot adequately capture the complexity of the parenchymal pattern throughout the whole breast. To better characterize patterns of the parenchymal tissue, the authors have developed a fully automated software pipeline based on a novel lattice-based strategy to extract a range of parenchymal texture features from the entire breast region. Methods: Digital mammograms from 106 cases with 318 age-matched controls were retrospectively analyzed. The lattice-based approach is based on a regular grid virtually overlaid on each mammographic image. Texture features are computed from the intersection (i.e., lattice) points of the grid lines within the breast, using a local window centered at each lattice point. Using this strategy, a range of statistical (gray-level histogram, co-occurrence, and run-length) and structural (edge-enhancing, local binary pattern, and fractal dimension) features are extracted. To cover the entire breast, the size of the local window for feature extraction is set equal to the lattice grid spacing and optimized experimentally by evaluating different windows sizes. The association between their lattice-based texture features and breast cancer was evaluated using logistic regression with leave-one-out cross validation and further compared to that of breast PD% and commonly used single-ROI texture features extracted from the retroareolar or the central breast region. Classification performance was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC). DeLong's test was used to compare the different ROCs in terms of AUC performance. Results: The average univariate performance of the lattice-based features is higher when extracted from smaller than larger window sizes. While not every individual texture feature is superior to breast PD% (AUC: 0.59, STD: 0.03), their combination in multivariate analysis has significantly better performance (AUC: 0.85, STD: 0.02, p < 0.001). The lattice-based texture features also outperform the single-ROI texture features when extracted from the retroareolar or the central breast region (AUC: 0.60-0.74, STD: 0.03). Adding breast PD% does not make a significant performance improvement to the lattice-based texture features or the single-ROI features (p > 0.05). Conclusions: The proposed lattice-based strategy for mammographic texture analysis enables to characterize the parenchymal pattern over the entire breast. As such, these features provide richer information compared to currently used descriptors and may ultimately improve breast cancer risk assessment. Larger studies are warranted to validate these findings and also compare to standard demographic and reproductive risk factors. [ABSTRACT FROM AUTHOR]

Purpose: Benign computed tomography (CT) changes due to radiation induced lung injury (RILI) are common following stereotactic ablative radiotherapy (SABR) and can be difficult to differentiate from tumor recurrence. The authors measured the ability of CT image texture analysis, compared to more traditional measures of response, to predict eventual cancer recurrence based on CT images acquired within 5 months of treatment. Methods: A total of 24 lesions from 22 patients treated with SABR were selected for this study: 13 with moderate to severe benign RILI, and 11 with recurrence. Three-dimensional (3D) consolidative and ground-glass opacity (GGO) changes were manually delineated on all follow-up CT scans. Two size measures of the consolidation regions (longest axial diameter and 3D volume) and nine appearance features of the GGO were calculated: 2 first-order features [mean density and standard deviation of density (first-order texture)], and 7 second-order texture features [energy, entropy, correlation, inverse difference moment (IDM), inertia, cluster shade, and cluster prominence]. For comparison, the corresponding response evaluation criteria in solid tumors measures were also taken for the consolidation regions. Prediction accuracy was determined using the area under the receiver operating characteristic curve (AUC) and two-fold cross validation (CV). Results: For this analysis, 46 diagnostic CT scans scheduled for approximately 3 and 6 months posttreatment were binned based on their recorded scan dates into 2-5 month and 5-8 month follow-up time ranges. At 2-5 months post-treatment, first-order texture, energy, and entropy provided AUCs of 0.79-0.81 using a linear classifier. On two-fold CV, first-order texture yielded 73% accuracy versus 76%-77% with the second-order features. The size measures of the consolidative region, longest axial diameter and 3D volume, gave two-fold CV accuracies of 60% and 57%, and AUCs of 0.72 and 0.65, respectively. Conclusions: Texture measures of the GGO appearance following SABR demonstrated the ability to predict recurrence in individual patients within 5 months of SABR treatment. Appearance changes were also shown to be more accurately predictive of recurrence, as compared to size measures within the same time period. With further validation, these results could form the substrate for a clinically useful computer-aided diagnosis tool which could provide earlier salvage of patients with recurrence. [ABSTRACT FROM AUTHOR]

Purpose: Develop a computer-aided detection (CAD) system for masses in digital breast tomosynthesis (DBT) volume using a deep convolutional neural network (DCNN) with transfer learning from mammograms. Methods: A data set containing 2282 digitized film and digital mammograms and 324 DBT volumes were collected with IRB approval. The mass of interest on the images was marked by an experienced breast radiologist as reference standard. The data set was partitioned into a training set (2282 mammograms with 2461 masses and 230 DBT views with 228 masses) and an independent test set (94 DBT views with 89 masses). For DCNN training, the region of interest (ROI) containing the mass (true positive) was extracted from each image. False positive (FP) ROIs were identified at prescreening by their previously developed CAD systems. After data augmentation, a total of 45 072 mammographic ROIs and 37 450 DBT ROIs were obtained. Data normalization and reduction of non-uniformity in the ROIs across heterogeneous data was achieved using a background correction method applied to each ROI. A DCNN with four convolutional layers and three fully connected (FC) layers was first trained on the mammography data. Jittering and dropout techniques were used to reduce overfitting. After training with the mammographic ROIs, all weights in the first three convolutional layers were frozen, and only the last convolution layer and the FC layers were randomly initialized again and trained using the DBT training ROIs. The authors compared the performances of two CAD systems for mass detection in DBT: one used the DCNN-based approach and the other used their previously developed feature-based approach for FP reduction. The prescreening stage was identical in both systems, passing the same set of mass candidates to the FP reduction stage. For the feature-based CAD system, 3D clustering and active contour method was used for segmentation; morphological, gray level, and texture features were extracted and merged with a linear discriminant classifier to score the detected masses. For the DCNN-based CAD system, ROIs from five consecutive slices centered at each candidate were passed through the trained DCNN and a mass likelihood score was generated. The performances of the CAD systems were evaluated using free-response ROC curves and the performance difference was analyzed using a non-parametric method. Results: Before transfer learning, the DCNN trained only on mammograms with an AUC of 0.99 classified DBT masses with an AUC of 0.81 in the DBT training set. After transfer learning with DBT, the AUC improved to 0.90. For breast-based CAD detection in the test set, the sensitivity for the feature-based and the DCNN-based CAD systems was 83% and 91%, respectively, at 1 FP/DBT volume. The difference between the performances for the two systems was statistically significant (p-value < 0.05). Conclusions: The image patterns learned from the mammograms were transferred to the mass detection on DBT slices through the DCNN. This study demonstrated that large data sets collected from mammography are useful for developing new CAD systems for DBT, alleviating the problem and effort of collecting entirely new large data sets for the new modality. [ABSTRACT FROM AUTHOR]

Purpose: To use novel voxel-based 3D printed textured phantoms in order to compare low-contrast detectability between two reconstruction algorithms, FBP (filtered-backprojection) and SAFIRE (sinogram affirmed iterative reconstruction) and determine what impact background texture (i.e., anatomical noise) has on estimating the dose reduction potential of SAFIRE. Methods: Liver volumes were segmented from 23 abdominal CT cases. The volumes were characterized in terms of texture features from gray-level co-occurrence and run-length matrices. Using a 3D clustered lumpy background (CLB) model, a fitting technique based on a genetic optimization algorithm was used to find CLB textures that were reflective of the liver textures, accounting for CT system factors of spatial blurring and noise. With the modeled background texture as a guide, four cylindrical phantoms (Textures A-C and uniform, 165 mm in diameter, and 30 mm height) were designed, each containing 20 low-contrast spherical signals (6 mm diameter at nominal contrast levels of ~3.2, 5.2, 7.2, 10, and 14 HU with four repeats per signal). The phantoms were voxelized and input into a commercial multimaterial 3D printer (Object Connex 350), with custom software for voxel-based printing (using principles of digital dithering). Images of the textured phantoms and a corresponding uniform phantom were acquired at six radiation dose levels (SOMATOM Flash, Siemens Healthcare) and observer model detection performance (detectability index of a multislice channelized Hotelling observer) was estimated for each condition (5 contrasts × 6 doses × 2 reconstructions × 4 backgrounds = 240 total conditions). A multivariate generalized regression analysis was performed (linear terms, no interactions, random error term, log link function) to assess whether dose, reconstruction algorithm, signal contrast, and background type have statistically significant effects on detectability. Also, fitted curves of detectability (averaged across contrast levels) as a function of dose were constructed for each reconstruction algorithm and background texture. FBP and SAFIRE were compared for each background type to determine the improvement in detectability at a given dose, and the reduced dose at which SAFIRE had equivalent performance compared to FBP at 100% dose. Results: Detectability increased with increasing radiation dose (P = 2.7×10-59) and contrast level (P = 2.2×10-86) and was higher in the uniform phantom compared to the textured phantoms (P = 6.9×10-51). Overall, SAFIRE had higher d' compared to FBP (P = 0.02). The estimated dose reduction potential of SAFIRE was found to be 8%, 10%, 27%, and 8% for Texture-A, Texture-B, Texture-C and uniform phantoms. Conclusions: In all background types, detectability was higher with SAFIRE compared to FBP. However, the relative improvement observed from SAFIRE was highly dependent on the complexity of the background texture. Iterative algorithms such as SAFIRE should be assessed in the most realistic context possible. [ABSTRACT FROM AUTHOR]

Purpose: To develop a new algorithm to measure the similarity between the query lung mass and reference lung mass data set for content-based medical image retrieval (CBMIR). Methods: A lung mass data set including 746 mass regions of interest (ROIs) was assembled. Among them, 375 ROIs depicted malignant lesions and 371 depicted benign lesions. Each mass ROI is represented by a vector of 26 texture features. A kernel function was employed to map the original data in input space to a feature space. In this space, a semisupervised distance metric was learned, which used differential scatter discriminant criterion to represent the semantic relevance, and the regularization term to represent the visual similarity. The learned distance metric can measure the similarity of the query mass and reference mass data set. The clustering accuracy is used to configure the parameters. The retrieval accuracy and classification accuracy are used as the performance assessment index. Results: After configuring the parameters, a mean clustering accuracy of 0.87 can be achieved. For retrieval accuracy, our algorithm achieves better performance than other state-of-the-art retrieval algorithms when applying a leave-one-out validation method to the testing data set. For classification accuracy, the area under the ROC curve of our algorithm can be achieved as 0.941±0.006. The running times of 346 query images with the proposed algorithm are 5.399 and 6.0 s, respectively. Conclusions: The study results demonstrated the proposed algorithm outperforms the compared algorithms, when taking the semantic relevant and visual similarity into account in kernel space. The algorithm can be used in a CBMIR system for a query mass to retrieve similarity masses, which can help doctors make better decisions. [ABSTRACT FROM AUTHOR]

Purpose:With raw digital mammograms (DMs), which retain the relationship with x-ray attenuation of the breast tissue, not being routinely available, processed DMs are often the only viable means to acquire imaging measures. The authors investigate differences in quantitative measures of breast density and parenchymal texture, shown to have value in breast cancer risk assessment, between the two DM representations. Methods: The authors report data from 8458 pairs of bilateral raw ("FOR PROCESSING") and processed ("FOR PRESENTATION") DMs acquired from 4278 women undergoing routine screening evaluation, collected with DM units from two different vendors. Breast dense tissue area and percent density (PD), as well as a range of quantitative descriptors of breast parenchymal texture (statistical, co-occurrence, run-length, and structural descriptors), were measured using previously validated, fully automated software. Feature measurements were compared using matched-pairs Wilcoxon signed-ranks test, correlation (r), and linear-mixed-effects (LME) models, where potential interactions with woman- and system-specific factors were also assessed. The authors also compared texture feature correlations with the established risk factors of the Gail lifetime risk score (rG) and breast PD (rPD), and evaluated the within woman intraclass feature correlation (ICC), a measure of bilateral breast-tissue symmetry, in raw versus processed images. Results: All density measures and most of the texture features were strongly (r = 0.6) or moderately (0.4 ≤ r < 0.6) correlated between raw and processed images. However, measurements were significantly different between the two imaging formats (Wilcoxon signed-ranks test, pw < 0.05). The association between measurements varied across features and vendors, and was substantially modified by woman- and system-specific image acquisition factors, such as age, BMI, and mAs/kVp, respectively. The strongest correlation, combined with minimal LME-model interactions, was observed for structural texture features. Overall, texture measures from either image representation were weakly associated with Gail lifetime risk (-0.2 ≤ rG ≤ 0.2), weakly to moderately associated with breast PD (-0.6 ≤ rPD ≤ 0.6), and had overall strong bilateral symmetry (ICC ≥ 0.6). Conclusions: Differences in measures from processed versus raw DM depend highly on the feature, the DM vendor, and image acquisition settings, where structural features appear to be more robust across the different DM settings. The reported findings may serve as a reference in the design of future large-scale studies on mammographic features and breast cancer risk assessment involving multiple DM representations. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this study is to provide an overview of primary modulation based scatter estimation techniques and evaluate their performance as well as to propose improvements. There have been published two distinct approaches to estimate scatter with primary modulators; however they have not been compared, so far. This work seeks to quantify their performance (focusing on how accurately they can estimate a smooth scatter from primary modulated images with real textures and signal to noise ratios) along with that of proposed improved variants. The influence of the parameters of the described algorithms on the estimation error is also investigated. Methods: Simulations were carried out using primary components derived from real chest DTS projections. After modulation, artificial scatter distributions were added to these projections, and the difference between the estimated and the artificial scatter distributions was quantified. Two existing and four proposed methods were assessed. The performance of the scatter estimators was examined under noisy and noiseless circumstances and with scatter distributions of different bandwidths. The proposed methods (SSE, SSENP, ADASE) solve the problem of varying effective transmission factors in the case of cell-image based methods, and they include an improved gradient based method (LSGSE) as well, which estimates scatter distribution more accurately. Results: It was found that the gradient based algorithms outperformed the cell-image based algorithms under noiseless conditions, while the cell-image based solutions proved to be insensitive to noise. The proposed improved methods reached considerably lower scatter estimation errors than the existing ones. Modulator cell sampling windows of different sizes and shapes were examined. Although much lower effective transmission factors (higher contrast between the attenuated and unattenuated cells) can be achieved using narrow windows, in our case the best estimation results are provided by windows that cover about half of the pixels of a modulator cell. The effect of detector backscatter on scatter estimation was also studied, and a solution was proposed to incorporate this type of scatter into the primary modulation framework. Conclusions: Considering all the above results, the authors suggest the use of LSGE for scatter estimation with primary modulation. [ABSTRACT FROM AUTHOR]

Purpose: Statistical modeling of an ultrasound backscattered echo envelope is used for tissue characterization. However, in the presence of complex structures within the analyzed area, estimation of parameters is disturbed and unreliable, e.g., in the case of breast tumor classification. In order to improve the differentiation of breast lesions, the authors proposed a method based on the segmentation of homodyned K distribution parameter maps. Regions within lesions of different scattering properties were extracted and analyzed. In order to improve the classification, the best-performing features were selected from various regions and then combined. Methods: A radio-frequency data set consisting of 103 breast lesions was used in the authors' analysis. Maps of homodyned K distribution parameters were created using an algorithm based on signal-to-noise ratio, kurtosis, and skewness of fractional-order envelope moments. A Markov random field model was used to segment parametric maps. Features of different segments were extracted and evaluated based on bootstrapping and the receiver operating characteristic curve. To determine the best-performing feature subset, the authors applied the joint mutual information criterion. Results: It was found that there were individual features which performed better than the ones commonly used for lesion characterization, like the parameter obtained through averaging of values over the whole lesion. The authors selected and discussed the best-performing features. Properties of different extracted regions were important and improved the distinction between benign and malignant tumors. The best performance was obtained by combining four features with the area under the receiver operating curve of 0.84. Conclusions: The study showed that the analysis of internal changes in lesion parametric maps leads to a better classification of breast tumors. The authors recommend combining multiple features for characterization, instead of using only one parameter, especially in the case of heterogeneous lesions. [ABSTRACT FROM AUTHOR]

Purpose: To investigate the effects of dose level and reconstruction method on density and texture based features computed from CT lung nodules. Methods: This study had two major components. In the first component, a uniform water phantom was scanned at three dose levels and images were reconstructed using four conventional filtered backprojection (FBP) and four iterative reconstruction (IR) methods for a total of 24 different combinations of acquisition and reconstruction conditions. In the second component, raw projection (sinogram) data were obtained for 33 lung nodules from patients scanned as a part of their clinical practice, where low dose acquisitions were simulated by adding noise to sinograms acquired at clinical dose levels (a total of four dose levels) and reconstructed using one FBP kernel and two IR kernels for a total of 12 conditions. For the water phantom, spherical regions of interest (ROIs) were created at multiple locations within the water phantom on one reference image obtained at a reference condition. For the lung nodule cases, the ROI of each nodule was contoured semiautomatically (with manual editing) from images obtained at a reference condition. All ROIs were applied to their corresponding images reconstructed at different conditions. For 17 of the nodule cases, repeat contours were performed to assess repeatability. Histogram (eight features) and gray level co-occurrence matrix (GLCM) based texture features (34 features) were computed for all ROIs. For the lung nodule cases, the reference condition was selected to be 100% of clinical dose with FBP reconstruction using the B45f kernel; feature values calculated from other conditions were compared to this reference condition. A measure was introduced, which the authors refer to as Q, to assess the stability of features across different conditions, which is defined as the ratio of reproducibility (across conditions) to repeatability (across repeat contours) of each feature. Results: The water phantom results demonstrated substantial variability among feature values calculated across conditions, with the exception of histogram mean. Features calculated from lung nodules demonstrated similar results with histogram mean as the most robust feature (Q = 1), having a mean and standard deviation Q of 0.37 and 0.22, respectively. Surprisingly, histogram standard deviation and variance features were also quite robust. Some GLCM features were also quite robust across conditions, namely, diff. variance, sum variance, sum average, variance, and mean. Except for histogram mean, all features have a Q of larger than one in at least one of the 3% dose level conditions. Conclusions: As expected, the histogram mean is the most robust feature in their study. The effects of acquisition and reconstruction conditions on GLCM features vary widely, though trending toward features involving summation of product between intensities and probabilities being more robust, barring a few exceptions. Overall, care should be taken into account for variation in density and texture features if a variety of dose and reconstruction conditions are used for the quantification of lung nodules in CT, otherwise changes in quantification results may be more reflective of changes due to acquisition and reconstruction conditions than in the nodule itself. [ABSTRACT FROM AUTHOR]

Purpose: Although a number of studies have focused on finding anatomical regions in which iron concentrations are high, no study has been conducted to examine the overall variations in susceptibility maps of Alzheimer's disease (AD). The objective of this study, therefore, was to differentiate AD from cognitive normal (CN) and mild cognitive impairment (MCI) using a texture analysis of quantitative susceptibility maps (QSMs). Methods: The study was approved by the local institutional review board, and informed consent was obtained from all subjects. In each participant group--CN, MCI, and AD--18 elderly subjects were enrolled. A fully first-order flow-compensated 3D gradient-echo sequence was run to obtain axial magnitudes and phase images and to produce QSM data. Sagittal structural 3D T1-weighted (3DT1W) images were also obtained with the magnetization-prepared rapid acquisition of gradientecho sequence to obtain brain tissue images. The first- and second-order texture parameters of the QSMs and 3DT1W images were obtained to evaluate group differences using a one-way analysis of covariance. Results: For the first-order QSM analysis, mean, standard deviation, and covariance of signal intensity separated the subject groups (F = 5.191, p = 0.009). For the second-order analysis, angular second moment, contrast, and correlation separated the subject groups (F = 6.896, p = 0.002). Finally, a receiver operating characteristic curve analysis differentiated MCI from CN in white matter on the QSMs (z = 3.092, p = 0.0020). Conclusions: This was the first study to evaluate the textures of QSM in AD, which overcame the limitations of voxel-based analyses. The QSM texture analysis successfully distinguished both AD and MCI from CN and outperformed the voxel-based analysis using 3DT1-weighed images in separating MCI from CN. The first-order textures were more efficient in differentiating MCI from CN than did the second-order. [ABSTRACT FROM AUTHOR]

Purpose: Although positron emission tomography (PET) images have shown potential to improve the accuracy of targeting in radiation therapy planning and assessment of response to treatment, the boundaries of tumors are not easily distinguishable from surrounding normal tissue owing to the low spatial resolution and inherent noisy characteristics of PET images. The objective of this study is to develop a generic and robust method for automatic delineation of tumor volumes using an active contour model and to evaluate its performance using phantom and clinical studies. Methods: MASAC, a method for automatic segmentation using an active contour model, incorporates the histogram fuzzy C-means clustering, and localized and textural information to constrain the active contour to detect boundaries in an accurate and robust manner. Moreover, the lattice Boltzmann method is used as an alternative approach for solving the level set equation to make it faster and suitable for parallel programming. Twenty simulated phantom studies and 16 clinical studies, including six cases of pharyngolaryngeal squamous cell carcinoma and ten cases of nonsmall cell lung cancer, were included to evaluate its performance. Besides, the proposed method was also compared with the contourlet-based active contour algorithm (CAC) and Schaefer's thresholding method (ST). The relative volume error (RE), Dice similarity coefficient (DSC), and classification error (CE) metrics were used to analyze the results quantitatively. Results: For the simulated phantom studies (PSs), MASAC and CAC provide similar segmentations of the different lesions, while ST fails to achieve reliable results. For the clinical datasets (2 cases with connected high-uptake regions excluded) (CSs), CAC provides for the lowest mean RE (-8.38%±27.49%), while MASAC achieves the best mean DSC (0.71±0.09) and mean CE (53.92%±12.65%), respectively. MASAC could reliably quantify different types of lesions assessed in this work with good accuracy, resulting in a mean RE of -13.35%±11.87% and -11.15%±23.66%, a mean DSC of 0.89±0.05 and 0.71±0.09, and a mean CE of 19.19%±7.89% and 53.92%±12.65%, for PSs and CSs, respectively. Conclusions: The authors' results demonstrate that the developed novel PET segmentation algorithm is applicable to various types of lesions in the authors' study and is capable of producing accurate and consistent target volume delineations, potentially resulting in reduced intraobserver and interobserver variabilities observed when using manual delineation and improved accuracy in treatment planning and outcome evaluation. [ABSTRACT FROM AUTHOR]

Purpose: The aims of this study were to noninvasively and automatically estimate both the radius of the ablated liver tissue and the radius encircling the treated zone, which also defines where the tissue is definitely untreated during a microwave (MW) thermal ablation procedure. Methods: Fourteen ex vivo bovine fresh liver specimens were ablated at 40 W using a 14 G microwave antenna, for durations of 3, 6, 8, and 10 min. The tissues were scanned every 5 s during the ablation using an x-ray CT scanner. In order to estimate the radius of the ablation zone, the acquired images were transformed into a polar presentation by displaying the Hounsfield units (HU) as a function of angle and radius. From this polar presentation, the average HU radial profile was analyzed at each time point and the ablation zone radius was estimated. In addition, textural analysis was applied to the original CT images. The proposed algorithm identified high entropy regions and estimated the treated zone radius per time. The estimated ablated zone radii as a function of treatment durations were compared, by means of correlation coefficient and root mean square error (RMSE) to gross pathology measurements taken immediately post-treatment from similarly ablated tissue. Results: Both the estimated ablation radii and the treated zone radii demonstrated strong correlation with the measured gross pathology values (R² ≥ 0.89 and R² ≥ 0.86, respectively). The automated ablation radii estimation had an average discrepancy of less than 1 mm (RMSE = 0.65 mm) from the gross pathology measured values, while the treated zone radii showed a slight overestimation of approximately 1.5 mm (RMSE = 1.6 mm). Conclusions: Noninvasive monitoring ofMWablation using x-ray CT and image analysis is feasible. Automatic estimations of the ablation zone radius and the radius encompassing the treated zone that highly correlate with actual ablation measured values can be obtained. This technique can therefore potentially be used to obtain real time monitoring and improve the clinical outcome. [ABSTRACT FROM AUTHOR]

Purpose: To develop an automated system for mediastinal lymph node detection and station mapping for chest CT. Methods: The contextual organs, trachea, lungs, and spine are first automatically identified to locate the region of interest (ROI) (mediastinum). The authors employ shape features derived from Hessian analysis, local object scale, and circular transformation that are computed per voxel in the ROI. Eight more anatomical structures are simultaneously segmented by multiatlas label fusion. Spatial priors are defined as the relative multidimensional distance vectors corresponding to each structure. Intensity, shape, and spatial prior features are integrated and parsed by a random forest classifier for lymph node detection. The detected candidates are then segmented by the following curve evolution process. Texture features are computed on the segmented lymph nodes and a support vector machine committee is used for final classification. For lymph node station labeling, based on the segmentation results of the above anatomical structures, the textual definitions of mediastinal lymph node map according to the International Association for the Study of Lung Cancer are converted into patient-specific color-coded CT image, where the lymph node station can be automatically assigned for each detected node. Results: The chest CT volumes from 70 patients with 316 enlarged mediastinal lymph nodes are used for validation. For lymph node detection, their system achieves 88% sensitivity at eight false positives per patient. For lymph node station labeling, 84.5% of lymph nodes are correctly assigned to their stations. Conclusions: Multiple-channel shape, intensity, and spatial prior features aggregated by a random forest classifier improve mediastinal lymph node detection on chest CT. Using the location information of segmented anatomic structures from the multiatlas formulation enables accurate identification of lymph node stations. [ABSTRACT FROM AUTHOR]

Purpose: This paper presents a statistical approach for the prediction of trabecular bone parameters from low-resolution multisequence magnetic resonance imaging (MRI) in children, thus addressing the limitations of high-resolution modalities such as HR-pQCT, including the significant exposure of young patients to radiation and the limited applicability of such modalities to peripheral bones in vivo. Methods: A statistical predictive model is constructed from a database of MRI and HR-pQCT datasets, to relate the low-resolution MRI appearance in the cancellous bone to the trabecular parameters extracted from the high-resolution images. The description of the MRI appearance is achieved between subjects by using a collection of feature descriptors, which describe the texture properties inside the cancellous bone, and which are invariant to the geometry and size of the trabecular areas. The predictive model is built by fitting to the training data a nonlinear partial least square regression between the input MRI features and the output trabecular parameters. Results: Detailed validation based on a sample of 96 datasets shows correlations >0.7 between the trabecular parameters predicted from low-resolution multisequence MRI based on the proposed statistical model and the values extracted from high-resolution HRp-QCT. Conclusions: The obtained results indicate the promise of the proposed predictive technique for the estimation of trabecular parameters in children from multisequence MRI, thus reducing the need for high-resolution radiation-based scans for a fragile population that is under development and growth. [ABSTRACT FROM AUTHOR]

Purpose: Precisely and efficiently locating a tumor with less manual intervention in ultrasound-guided high-intensity focused ultrasound (HIFU) therapy is one of the keys to guaranteeing the therapeutic result and improving the efficiency of the treatment. The segmentation of ultrasound images has always been difficult due to the influences of speckle, acoustic shadows, and signal attenuation as well as the variety of tumor appearance. The quality of HIFU guidance images is even poorer than that of conventional diagnostic ultrasound images because the ultrasonic probe used for HIFU guidance usually obtains images without making contact with the patient’s body. Therefore, the segmentation becomes more difficult. To solve the segmentation problem of ultrasound guidance image in the treatment planning procedure for HIFU therapy, a novel region-based segmentation method for uterine fibroids in HIFU guidance images is proposed. Methods: Tumor partitioning in HIFU guidance image without manual intervention is achieved by a region-based split-and-merge framework. A new iterative multiple region growing algorithm is proposed to first split the image into homogenous regions (superpixels). The features extracted within these homogenous regions will be more stable than those extracted within the conventional neighborhood of a pixel. The split regions are then merged by a superpixel-based adaptive spectral clustering algorithm. To ensure the superpixels that belong to the same tumor can be clustered together in the merging process, a particular construction strategy for the similarity matrix is adopted for the spectral clustering, and the similarity matrix is constructed by taking advantage of a combination of specifically selected first-order and second-order texture features computed from the gray levels and the gray level co-occurrence matrixes, respectively. The tumor region is picked out automatically from the background regions by an algorithm according to a priori information about the tumor position, shape, and size. Additionally, an appropriate cluster number for spectral clustering can be determined by the same algorithm, thus the automatic segmentation of the tumor region is achieved. Results: To evaluate the performance of the proposed method, 50 uterine fibroid ultrasound images from different patients receiving HIFU therapy were segmented, and the obtained tumor contours were compared with those delineated by an experienced radiologist. For area-based evaluation results, the mean values of the true positive ratio, the false positive ratio, and the similarity were 94.42%, 4.71%, and 90.21%, respectively, and the corresponding standard deviations were 2.54%, 3.12%, and 3.50%, respectively. For distance-based evaluation results, the mean values of the normalized Hausdorff distance and the normalized mean absolute distance were 4.93% and 0.90%, respectively, and the corresponding standard deviations were 2.22% and 0.34%, respectively. The running time of the segmentation process was 12.9 s for a 318×333 (pixels) image. Conclusions: Experiments show that the proposed method can segment the tumor region accurately and efficiently with less manual intervention, which provides for the possibility of automatic segmentation and real-time guidance in HIFU therapy. [ABSTRACT FROM AUTHOR]

Purpose: Imaging biomarker research focuses on discovering relationships between radiological features and histological findings. In glioblastoma patients, methylation of the O6-methylguanine methyltransferase (MGMT) gene promoter is positively correlated with an increased effectiveness of current standard of care. In this paper, the authors investigate texture features as potential imaging biomarkers for capturing the MGMT methylation status of glioblastoma multiforme (GBM) tumors when combined with supervised classification schemes. Methods: A retrospective study of 155 GBM patients with known MGMT methylation status was conducted. Co-occurrence and run length texture features were calculated, and both support vector machines (SVMs) and random forest classifiers were used to predict MGMT methylation status. Results: The best classification system (an SVM-based classifier) had a maximum area under the receiver-operating characteristic (ROC) curve of 0.85 (95% CI: 0.78–0.91) using four texture features (correlation, energy, entropy, and local intensity) originating from the T2-weighted images, yielding at the optimal threshold of the ROC curve, a sensitivity of 0.803 and a specificity of 0.813. Conclusions: Results show that supervised machine learning of MRI texture features can predict MGMT methylation status in preoperative GBM tumors, thus providing a new noninvasive imaging biomarker. [ABSTRACT FROM AUTHOR]

Surgical guidance with fluorescence has been demonstrated in individual clinical trials for decades, but the scientific and commercial conditions exist today for a dramatic increase in clinical value. In the past decade, increased use of indocyanine green based visualization of vascular flow, biliary function, and tissue perfusion has spawned a robust growth in commercial systems that have near-infrared emission imaging and video display capabilities. This recent history combined with major preclinical innovations in fluorescent-labeled molecular probes, has the potential for a shift in surgical practice toward resection guidance based upon molecular information in addition to conventional visual and palpable cues. Most surgical subspecialties already have treatment management decisions partially based upon the immunohistochemical phenotype of the cancer, as assessed from molecular pathology of the biopsy tissue. This phenotyping can inform the surgical resection process by spatial mapping of these features. Further integration of the diagnostic and therapeutic value of tumor metabolism sensing molecules or immune binding agents directly into the surgical process can help this field mature. Maximal value to the patient would come from identifying the spatial patterns of molecular expression in vivo that are well known to exist. However, as each molecular agent is advanced into trials, the performance of the imaging system can have a critical impact on the success. For example, use of pre-existing commercial imaging systems are not well suited to image receptor targeted fluorophores because of the lower concentrations expected, requiring orders of magnitude more sensitivity. Additionally the imaging system needs the appropriate dynamic range and image processing features to view molecular probes or therapeutics that may have nonspecific uptake or pharmacokinetic issues which lead to limitations in contrast. Imaging systems need to be chosen based upon objective performance criteria, and issues around calibration, validation, and interpretation need to be established before a clinical trial starts. Finally, as early phase trials become more established, the costs associated with failures can be crippling to the field, and so judicious use of phase 0 trials with microdose levels of agents is one viable paradigm to help the field advance, but this places high sensitivity requirements on the imaging systems used. Molecular-guided surgery has truly transformative potential, and several key challenges are outlined here with the goal of seeing efficient advancement with ideal choices. The focus of this vision 20/20 paper is on the technological aspects that are needed to be paired with these agents. [ABSTRACT FROM AUTHOR]

Purpose: The FDA approved the use of digital breast tomosynthesis (DBT) in 2011 as an adjunct to 2D full field digital mammography (FFDM) with the constraint that all DBT acquisitions must be paired with a 2D image to assure adequate interpretative information is provided. Recently manufacturers have developed methods to provide a synthesized 2D image generated from the DBT data with the hope of sparing patients the radiation exposure from the FFDM acquisition. While this much needed alternative effectively reduces the total radiation burden, differences in image quality must also be considered. The goal of this study was to compare the intrinsic image quality of synthesized 2D C-VIEW and 2D FFDM images in terms of resolution, contrast, and noise. Methods: Two phantoms were utilized in this study: the American College of Radiology mammography accreditation phantom (ACR phantom) and a novel 3D printed anthropomorphic breast phantom. Both phantoms were imaged using a Hologic Selenia Dimensions 3D system. Analysis of the ACR phantom includes both visual inspection and objective automated analysis using in-house software. Analysis of the 3D anthropomorphic phantom includes visual assessment of resolution and Fourier analysis of the noise. Results: Using ACR-defined scoring criteria for the ACR phantom, the FFDM images scored statistically higher than C-VIEW according to both the average observer and automated scores. In addition, between 50% and 70% of C-VIEW images failed to meet the nominal minimum ACR accreditation requirements--primarily due to fiber breaks. Software analysis demonstrated that C-VIEW provided enhanced visualization of medium and large microcalcification objects; however, the benefits diminished for smaller high contrast objects and all low contrast objects. Visual analysis of the anthropomorphic phantom showed a measureable loss of resolution in the C-VIEW image (11 lp/mm FFDM, 5 lp/mm C-VIEW ) and loss in detection of small microcalcification objects. Spectral analysis of the anthropomorphic phantom showed higher total noise magnitude in the FFDM image compared with C-VIEW . Whereas the FFDM image contained approximately white noise texture, the C-VIEW image exhibited marked noise reduction at midfrequency and high frequency with far less noise suppression at low frequencies resulting in a mottled noise appearance. Conclusions: Their analysis demonstrates many instances where the C-VIEW image quality differs from FFDM. Compared to FFDM, C-VIEW offers a better depiction of objects of certain size and contrast, but provides poorer overall resolution and noise properties. Based on these findings, the utilization of C-VIEW images in the clinical setting requires careful consideration, especially if considering the discontinuation of FFDM imaging. Not explicitly explored in this study is how the combination of DBT + C-VIEW performs relative to DBT + FFDM or FFDM alone. [ABSTRACT FROM AUTHOR]

Purpose: In the past decades, computer-aided detection(CADe)systems have been developed to aid screening radiologists in the detection of malignant microcalcifications. These systems are useful to avoid perceptual oversights and can increase the radiologists' detection rate. However, due to the high number of false positives marked by these CADesystems, they are not yet suitable as an independent reader. Breast arterial calcifications (BACs) are one of the most frequent false positives marked by CADesystems. In this study, a method is proposed for the elimination of BACs as positive findings. Removal of these false positives will increase the performance of the CADesystem in finding malignant microcalcifications. Methods: A multistage method is proposed for the removal of BAC findings. The first stage consists of a microcalcification candidate selection, segmentation and grouping of the microcalcifications, and classification to remove obvious false positives. In the second stage, a case-based selection is applied where cases are selected which contain BACs. In the final stage, BACs are removed from the selected cases. The BACs removal stage consists of a GentleBoost classifier trained on microcalcification features describing their shape, topology, and texture. Additionally, novel features are introduced to discriminate BACs from other positive findings. Results: The CADesystem was evaluated with and without BACs removal. Here, both systems were applied on a validation set containing 1088 cases of which 95 cases contained malignant microcalcifications. After bootstrapping, free-response receiver operating characteristics and receiver operating characteristics analyses were carried out. Performance between the two systems was compared at 0.98 and 0.95 specificity. At a specificity of 0.98, the sensitivity increased from 37% to 52% and the sensitivity increased from 62% up to 76% at a specificity of 0.95. Partial areas under the curve in the specificity range of 0.8-1.0 were significantly different between the system without BACs removal and the system with BACs removal, 0.129 ± 0.009 versus 0.144 ± 0.008 (p<0.05), respectively. Additionally, the sensitivity at one false positive per 50 cases and one false positive per 25 cases increased as well, 37% versus 51% (p<0.05) and 58% versus 67% (p<0.05) sensitivity, respectively. Additionally, the CADesystem with BACs removal reduces the number of false positives per case by 29% on average. The same sensitivity at one false positive per 50 cases in the CADesystem without BACs removal can be achieved at one false positive per 80 cases in the CADesystem with BACs removal. Conclusions: By using dedicated algorithms to detect and remove breast arterial calcifications, the performance of CADesystems can be improved, in particular, at false positive rates representative for operating points used in screening. [ABSTRACT FROM AUTHOR]

Purpose: Classify chronic liver disease (CLD) from ultrasound shear-wave elastography (SWE) imaging by means of a computer aided diagnosis (CAD) system. Methods: The proposed algorithm employs an inverse mapping technique (red-green-blue to stiffness) to quantify 85 SWE images (54 healthy and 31 with CLD). Texture analysis is then applied involving the automatic calculation of 330 first and second order textural features from every transformed stiffness value map to determine functional features that characterize liver elasticity and describe liver condition for all available stages. Consequently, a stepwise regression analysis feature selection procedure is utilized toward a reduced feature subset that is fed into the support vector machines (SVMs) classification algorithm in the design of the CAD system. Results: With regard to the mapping procedure accuracy, the stiffness map values had an average difference of 0.01±}0.001 kPa compared to the quantification results derived from the color-box provided by the built-in software of the ultrasound system. Highest classification accuracy from the SVM model was 87.0% with sensitivity and specificity values of 83.3% and 89.1%, respectively. Receiver operating characteristic curves analysis gave an area under the curve value of 0.85 with [0.77-0.89] confidence interval. Conclusions: The proposed CAD system employing color to stiffness mapping and classification algorithms offered superior results, comparing the already published clinical studies. It could prove to be of value to physicians improving the diagnostic accuracy of CLD and can be employed as a second opinion tool for avoiding unnecessary invasive procedures. [ABSTRACT FROM AUTHOR]

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 the center-slice measurements were considered reproducible. Conclusions: Some radiomics features are robust to the noise and poor image quality of CBCT images when the imaging protocol is consistent, relative changes in the features are used, and patients are limited to those with less than 1 cm of motion. [ABSTRACT FROM AUTHOR]

Purpose: Glioblastoma multiforme (GBM) is the most common and aggressive primary brain cancer. Four molecular subtypes of GBM have been described but can only be determined by an invasive brain biopsy. The goal of this study is to evaluate the utility of texture features extracted from magnetic resonance imaging (MRI) scans as a potential noninvasive method to characterize molecular subtypes of GBM and to predict 12-month overall survival status for GBM patients. Methods: The authors manually segmented the tumor regions from postcontrast T1 weighted and T2 fluid-attenuated inversion recovery (FLAIR) MRI scans of 82 patients with de novo GBM. For each patient, the authors extracted five sets of computer-extracted texture features, namely, 48 segmentation-based fractal texture analysis (SFTA) features, 576 histogram of oriented gradients (HOGs) features, 44 run-length matrix (RLM) features, 256 local binary patterns features, and 52 Haralick features, from the tumor slice corresponding to the maximum tumor area in axial, sagittal, and coronal planes, respectively. The authors used an ensemble classifier called random forest on each feature family to predict GBM molecular subtypes and 12-month survival status (a dichotomized version of overall survival at the 12-month time point indicating if the patient was alive or not at 12 months). The performance of the prediction was quantified and compared using receiver operating characteristic (ROC) curves. Results: With the appropriate combination of texture feature set, image plane (axial, coronal, or sagittal), and MRI sequence, the area under ROC curve values for predicting different molecular subtypes and 12-month survival status are 0.72 for classical (with Haralick features on T1 postcontrast axial scan), 0.70 for mesenchymal (with HOG features on T2 FLAIR axial scan), 0.75 for neural (with RLM features on T2 FLAIR axial scan), 0.82 for proneural (with SFTA features on T1 postcontrast coronal scan), and 0.69 for 12-month survival status (with SFTA features on T1 postcontrast coronal scan). Conclusions: The authors evaluated the performance of five types of texture features in predicting GBM molecular subtypes and 12-month survival status. The authors' results show that texture features are predictive of molecular subtypes and survival status in GBM. These results indicate the feasibility of using tumor-derived imaging features to guide genomically informed interventions without the need for invasive biopsies. [ABSTRACT FROM AUTHOR]

Purpose: An accurate quantification of the images in positron emission tomography (PET) requires knowing the actual sensitivity at each voxel, which represents the probability that a positron emitted in that voxel is finally detected as a coincidence of two gamma rays in a pair of detectors in the PET scanner. This sensitivity depends on the characteristics of the acquisition, as it is affected by the attenuation of the annihilation gamma rays in the body, and possible variations of the sensitivity of the scanner detectors. In this work, the authors propose a new approach to handle time-of-flight (TOF) list-mode PET data, which allows performing either or both, a self-attenuation correction, and self-normalization correction based on emission data only. Methods: The authors derive the theory using a fully Bayesian statistical model of complete data. The authors perform an initial evaluation of algorithms derived from that theory and proposed in this work using numerical 2D list-mode simulations with different TOF resolutions and total number of detected coincidences. Effects of randoms and scatter are not simulated. Results: The authors found that proposed algorithms successfully correct for unknown attenuation and scanner normalization for simulated 2D list-mode TOF-PET data. Conclusions: A new method is presented that can be used for corrections for attenuation and normalization (sensitivity) using TOF list-mode data. [ABSTRACT FROM AUTHOR]

Purpose: Aims in this study are to (1) develop a computational model observer which reliably tracks the detectability of human observers in low dose computed tomography (CT) images reconstructed with knowledge-based iterative reconstruction (IMR™, Philips Healthcare) and filtered back projection (FBP) across a range of independent variables, (2) use the model to evaluate detectability trends across reconstructions and make predictions of human observer detectability, and (3) perform human observer studies based on model predictions to demonstrate applications of the model in CT imaging. Methods: Detectability (d') was evaluated in phantom studies across a range of conditions. Images were generated using a numerical CT simulator. Trained observers performed 4-alternative forced choice (4-AFC) experiments across dose (1.3, 2.7, 4.0 mGy), pin size (4, 6, 8 mm), contrast (0.3%, 0.5%, 1.0%), and reconstruction (FBP, IMR), at fixed display window. A five-channel Laguerre-Gauss channelized Hotelling observer (CHO) was developed with internal noise added to the decision variable and/or to channel outputs, creating six different internal noise models. Semianalytic internal noise computation was tested against Monte Carlo and used to accelerate internal noise parameter optimization. Model parameters were estimated from all experiments at once using maximum likelihood on the probability correct, PC. Akaike information criterion (AIC) was used to compare models of different orders. The best model was selected according to AIC and used to predict detectability in blended FBP-IMR images, analyze trends in IMR detectability improvements, and predict dose savings with IMR. Predicted dose savings were compared against 4-AFC study results using physical CT phantom images. Results: Detection in IMR was greater than FBP in all tested conditions. The CHO with internal noise proportional to channel output standard deviations, Model-k4, showed the best trade-off between fit and model complexity according to AICc. With parameters fixed, the model reasonably predicted detectability of human observers in blended FBP-IMR images. Semianalytic internal noise computation gave results equivalent to Monte Carlo, greatly speeding parameter estimation. Using Model-k4, the authors found an average detectability improvement of 2.7±0.4 times that of FBP. IMR showed greater improvements in detectability with larger signals and relatively consistent improvements across signal contrast and x-ray dose. In the phantom tested, Model-k4 predicted an 82% dose reduction compared to FBP, verified with physical CT scans at 80% reduced dose. Conclusions: IMR improves detectability over FBP and may enable significant dose reductions. A channelized Hotelling observer with internal noise proportional to channel output standard deviation agreed well with human observers across a wide range of variables, even across reconstructions with drastically different image characteristics. Utility of the model observer was demonstrated by predicting the effect of image processing (blending), analyzing detectability improvements with IMR across dose, size, and contrast, and in guiding real CT scan dose reduction experiments. Such a model observer can be applied in optimizing parameters in advanced iterative reconstruction algorithms as well as guiding dose reduction protocols in physical CT experiments. [ABSTRACT FROM AUTHOR]

Purpose: In image-guided radio frequency ablation for liver cancer treatment, pre- and post-interventional CT images are typically used to verify the treatment success of the therapy. In current clinical practice, the tumor zone in the diagnostic, preinterventional images is mentally or manually mapped to the ablation zone in the post-interventional images to decide success of the treatment. However, liver deformation and differences in image quality as well as in texture of the ablation zone and the tumor area make the mental or manual registration a challenging task. Purpose of this paper is to develop an automatic framework to register the pre-interventional image to the post-interventional image. Methods: The authors propose a registration approach enabling a nonrigid deformation of the tumor to the ablation zone, while keeping locally rigid deformation of the tumor area. The method was evaluated on CT images of 38 patient datasets from Erasmus MC. The evaluation is based on Dice coefficients of the liver segmentation on both the pre-interventional and post-interventional images, and mean distances between the liver segmentations. Additionally, residual distances after registration between corresponding landmarks and local mean surface distance in the images were computed. Results: The results show that rigid registration gives a Dice coefficient of 87.9%, a mean distance of the liver surfaces of 5.53 mm, and a landmark error of 5.38 mm, while non-rigid registration with local rigid deformation has a Dice coefficient of 92.2%, a mean distance between the liver segmentation boundaries near the tumor area of 3.83 mm, and a landmark error of 2.91 mm, where a part of this error can be attributed to the slice spacing in the authors' CT images. Conclusions: This method is thus a promising tool to assess the success of RFA liver cancer treatment. [ABSTRACT FROM AUTHOR]

Purpose: Breast tissue composition is considered to be associated with breast cancer risk. This study aimed to develop a computer-aided classification (CAC) system to automatically classify echotexture patterns as heterogeneous or homogeneous using automated breast ultrasound (ABUS) images. Methods: A CAC system was proposed that can recognize breast echotexture patterns in ABUS images. For each case, the echotexture pattern was assessed by two expert radiologists and classified as heterogeneous or homogeneous. After neutrosophic image transformation and fuzzy c-mean clusterings, the lower and upper boundaries of the fibroglandular tissues were defined. Then, the number of hypoechoic regions and histogram features were extracted from the fibroglandular tissues, and the support vector machine model with the leave-one-out cross-validation method was utilized as the classifier. The authors' database included a total of 208 ABUS images of the breasts of 104 females. Results: The accuracies of the proposed system for the classification of heterogeneous and homogeneous echotexture patterns were 93.48% (43/46) and 92.59% (150/162), respectively, with an overall Az (area under the receiver operating characteristic curve) of 0.9786. The agreement between the radiologists and the proposed system was almost perfect, with a kappa value of 0.814. Conclusions: The use of ABUS and the proposed method can provide quantitative information on the echotexture patterns of the breast and can be used to evaluate whether breast echotexture patterns are associated with breast cancer risk in the future. [ABSTRACT FROM AUTHOR]

Purpose: Triple-negative breast cancer (TNBC), an aggressive subtype, is frequently misclassified as fibroadenoma due to benign morphologic features on breast ultrasound (US). This study aims to develop a computer-aided diagnosis (CAD) system based on texture features for distinguishing between TNBC and benign fibroadenomas in US images. Methods: US images of 169 pathology-proven tumors (mean size, 1.65 cm; range, 0.7-3.0 cm) composed of 84 benign fibroadenomas and 85 TNBC tumors are used in this study. After a tumor is segmented out using the level-set method, morphological, conventional texture, and multiresolution gray-scale invariant texture feature sets are computed using a best-fitting ellipse, gray-level co-occurrence matrices, and the ranklet transform, respectively. The linear support vector machine with leave-one-out cross-validation schema is used as a classifier, and the diagnostic performance is assessed with receiver operating characteristic curve analysis. Results: The Az values of the morphology, conventional texture, and multiresolution gray-scale invariant texture feature sets are 0.8470 [95% confidence intervals (CIs), 0.7826-0.8973], 0.8542 (95% CI, 0.7911-0.9030), and 0.9695 (95% CI, 0.9376-0.9865), respectively. The Az of the CAD system based on the combined feature sets is 0.9702 (95% CI, 0.9334-0.9882). Conclusions: The CAD system based on texture features extracted via the ranklet transform may be useful for improving the ability to discriminate between TNBC and benign fibroadenomas. [ABSTRACT FROM AUTHOR]

Purpose: To help improve efficacy of screening mammography by eventually establishing a new optimal personalized screening paradigm, the authors investigated the potential of using the quantitative multiscale texture and density feature analysis of digital mammograms to predict near-term breast cancer risk. Methods: The authors' dataset includes digital mammograms acquired from 340 women. Among them, 141 were positive and 199 were negative/benign cases. The negative digital mammograms acquired from the "prior" screening examinations were used in the study. Based on the intensity value distributions, five subregions at different scales were extracted from each mammogram. Five groups of features, including density and texture features, were developed and calculated on every one of the subregions. Sequential forward floating selection was used to search for the effective combinations. Using the selected features, a support vector machine (SVM) was optimized using a tenfold validation method to predict the risk of each woman having image-detectable cancer in the next sequential mammography screening. The area under the receiver operating characteristic curve (AUC) was used as the performance assessment index. Results: From a total number of 765 features computed from multiscale subregions, an optimal feature set of 12 features was selected. Applying this feature set, a SVM classifier yielded performance of AUC= 0.729±0.021. The positive predictive value was 0.657 (92 of 140) and the negative predictive value was 0.755 (151 of 200). Conclusions: The study results demonstrated a moderately high positive association between risk prediction scores generated by the quantitative multiscale mammographic image feature analysis and the actual risk of a woman having an image-detectable breast cancer in the next subsequent examinations. [ABSTRACT FROM AUTHOR]

Purpose: The authors propose a computer-aided diagnosis (CAD) system for prostate cancer to aid in improving the accuracy, reproducibility, and standardization of multiparametric magnetic resonance imaging (MRI). Methods: The proposed system utilizes two MRI sequences [T2-weighted MRI and high-b-value (b = 2000 s/mm2) diffusion-weighted imaging (DWI)] and texture features based on local binary patterns. A three-stage feature selection method is employed to provide the most discriminative features. The authors included a total of 244 patients. Training the CAD system on 108 patients (78 MR-positive prostate cancers and 105 benign MR-positive lesions), two validation studies were retrospectively performed on 136 patients (68 MR-positive prostate cancers, 111 benign MR-positive lesions, and 117 MR-negative benign lesions). Results: In distinguishing cancer from MR-positive benign lesions, an area under receiver operating characteristic curve (AUC) of 0.83 [95% confidence interval (CI): 0.76-0.89] was achieved. For cancer vs MR-positive or MR-negative benign lesions, the authors obtained an AUC of 0.89 AUC (95% CI: 0.84-0.93). The performance of the CAD system was not dependent on the specific regions of the prostate, e.g., a peripheral zone or transition zone. Moreover, the CAD system outperformed other combinations of MRI sequences: T2W MRI, high-b-value DWI, and the standard apparent diffusion coefficient (ADC) map of DWI. Conclusions: The novel CAD system is able to detect the discriminative texture features for cancer detection and localization and is a promising tool for improving the quality and efficiency of prostate cancer diagnosis. [ABSTRACT FROM AUTHOR]

Purpose: To investigate the importance of presurgical computed tomography (CT) intensity and texture information from ground-glass opacities (GGO) and solid nodule components for the prediction of adenocarcinoma recurrence. Methods: For this study, 101 patients with surgically resected stage I adenocarcinoma were selected. During the follow-up period, 17 patients had disease recurrence with six associated cancer-related deaths. GGO and solid tumor components were delineated on presurgical CT scans by a radiologist. Computational texture models of GGO and solid regions were built using linear combinations of steerable Riesz wavelets learned with linear support vector machines (SVMs). Unlike other traditional texture attributes, the proposed texture models are designed to encode local image scales and directions that are specific to GGO and solid tissue. The responses of the locally steered models were used as texture attributes and compared to the responses of unaligned Riesz wavelets. The texture attributes were combined with CT intensities to predict tumor recurrence and patient hazard according to disease-free survival (DFS) time. Two families of predictive models were compared: LASSO and SVMs, and their survival counterparts: Cox-LASSO and survival SVMs. Results: The best-performing predictive model of patient hazard was associated with a concordance index (C-index) of 0.81 ± 0.02 and was based on the combination of the steered models and CT intensities with survival SVMs. The same feature group and the LASSO model yielded the highest area under the receiver operating characteristic curve (AUC) of 0.8 ± 0.01 for predicting tumor recurrence, although no statistically significant difference was found when compared to using intensity features solely. For all models, the performance was found to be significantly higher when image attributes were based on the solid components solely versus using the entire tumors (p < 3.08 × 10-5). Conclusions: This study constitutes a novel perspective on how to interpret imaging information from CT examinations by suggesting that most of the information related to adenocarcinoma aggressiveness is related to the intensity and morphological properties of solid components of the tumor. The prediction of adenocarcinoma relapse was found to have low specificity but very high sensitivity. Our results could be useful in clinical practice to identify patients for which no recurrence is expected with a very high confidence using a presurgical CT scan only. It also provided an accurate estimation of the risk of recurrence after a given duration t from surgical resection (i.e., C-index = 0.81 ± 0.02). [ABSTRACT FROM AUTHOR]

Purpose: Rupture of atherosclerotic plaques in the carotid artery has been implicated in 20% of strokes. 3D ultrasound (US) imaging is emerging as an attractive method to quantify plaque burden and track changes in plaque longitudinally over time. However, plaque segmentation from US images is challenging because of poor boundary contrast and shadowing. The objective of this study is to develop and evaluate a semiautomatic segmentation algorithm with a novel stopping criterion for segmenting outer wall boundary (OWB) and lumen intima boundary (LIB) of common, internal, and external carotid artery from 3D US images for quantifying the vessel wall volume (VWV). Methods: 3D US image volumes were acquired from ten subjects with asymptomatic carotid stenoses. Volumes were acquired using a mechanically scanned linear probe, and the reconstructed volume consisted of 21 slices acquired at an interslice distance of 1 mm. The authors used distance regularized level set method with edge-based energy, region-based energy, smoothness energy, and a novel stopping criterion to segment the LIB and OWB of carotid artery. The algorithm was initialized by six user-selected points on the LIB and OWB in seven 2D cross-sectional slices in each volume. An ellipse fitting and a stopping boundary-based energy is proposed to smooth the OWB contour and to stop leaking of the evolving contour, respectively. The algorithm was compared against ground truth boundaries generated from manual segmentations. The dice similarity coefficient (DSC), Hausdorff distance (HD), and modified HD (MHD) were used as error metrics. Results: The authors' proposed stopping boundary energy-based stopping criterion was compared with percentage change of area and change of the MHD between evolving contours at successive iterations stopping criteria. The performance of the proposed algorithm was better than other two stopping criteria and yielded mean of LIBDSC = 88.78%, OWBDSC = 94.81%, LIBMHD = 0.26 mm, OWBMHD = 0.25 mm, LIBHD = 0.74 mm, and OWBHD = 0.80 mm. The Bland-Altman plot and correlation coefficient (r = 0.99) indicated a high agreement between ground truth and algorithm-generated boundaries. The coefficient of variation (COV) and minimum detectable change of the VWV are 5.2% and 57.2 mm³ (5.18% of mean VWV), calculated from repeated measurements of the VWV by algorithm. The mean absolute distance between corresponding points of the algorithm-generated and the ground truth boundaries was 0.25 mm. Conclusions: The authors have developed a semiautomatic segmentation algorithm for measuring the VWV of the carotid artery using 3D US images with reduced operator interaction and computational time and higher reproducibility using a commercially available 3D US transducer. Their method is a step forward toward routine longitudinal monitoring of 3D plaque progression. [ABSTRACT FROM AUTHOR]

Purpose: Lung dynamic MRI (dMRI) has emerged to be an appealing tool to quantify lung motion for both planning and treatment guidance purposes. However, this modality can result in blurry images due to intrinsically low signal-to-noise ratio in the lung and spatial/temporal interpolation. The image blurring could adversely affect the image processing that depends on the availability of fine landmarks. The purpose of this study is to reduce dMRI blurring using image postprocessing. Methods: To enhance the image quality and exploit the spatiotemporal continuity of dMRI sequences, a low-rank decomposition and dictionary learning (LDDL) method was employed to deblur lung dMRI and enhance the conspicuity of lung blood vessels. Fifty frames of continuous 2D coronal dMRI frames using a steady state free precession sequence were obtained from five subjects including two healthy volunteer and three lung cancer patients. In LDDL, the lung dMRI was decomposed into sparse and low-rank components. Dictionary learning was employed to estimate the blurring kernel based on the whole image, low-rank or sparse component of the first image in the lung MRI sequence. Deblurring was performed on the whole image sequences using deconvolution based on the estimated blur kernel. The deblurring results were quantified using an automated blood vessel extraction method based on the classification of Hessian matrix filtered images. Accuracy of automated extraction was calculated using manual segmentation of the blood vessels as the ground truth. Results: In the pilot study, LDDL based on the blurring kernel estimated from the sparse component led to performance superior to the other ways of kernel estimation. LDDL consistently improved image contrast and fine feature conspicuity of the original MRI without introducing artifacts. The accuracy of automated blood vessel extraction was on average increased by 16% using manual segmentation as the ground truth. Conclusions: Image blurring in dMRI images can be effectively reduced using a low-rank decomposition and dictionary learning method using kernels estimated by the sparse component. [ABSTRACT FROM AUTHOR]

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 IBEX'S 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 IBEX'S 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. © 2015 American Association of Physicists in Medicine. [ABSTRACT FROM AUTHOR]

Purpose: Different computed tomography (CT) reconstruction techniques offer different image quality attributes of resolution and noise, challenging the ability to compare their dose reduction potential against each other. The purpose of this study was to evaluate and compare the task-based imaging performance of CT systems to enable the assessment of the dose performance of a model-based iterative reconstruction (MBIR) to that of an adaptive statistical iterative reconstruction (ASIR) and a filtered back projection (FBP) technique. Methods: The ACR CT phantom (model 464) was imaged across a wide range of mA setting on a 64-slice CT scanner (GE Discovery CT750 HD, Waukesha, WI). Based on previous work, the resolution was evaluated in terms of a task-based modulation transfer function (MTF) using a circular-edge technique and images from the contrast inserts located in the ACR phantom. Noise performance was assessed in terms of the noise-power spectrum (NPS) measured from the uniform section of the phantom. The task-based MTF and NPS were combined with a task function to yield a task-based estimate of imaging performance, the detectability index (d'). The detectability index was computed as a function of dose for two imaging tasks corresponding to the detection of a relatively small and a relatively large feature (1.5 and 25 mm, respectively). The performance of MBIR in terms of the d' was compared with that of ASIR and FBP to assess its dose reduction potential. Results: Results indicated that MBIR exhibits a variability spatial resolution with respect to object contrast and noise while significantly reducing image noise. The NPS measurements for MBIR indicated a noise texture with a low-pass quality compared to the typical midpass noise found in FBP-based CT images. At comparable dose, the d' for MBIR was higher than those of FBP and ASIR by at least 61% and 19% for the small feature and the large feature tasks, respectively. Compared to FBP and ASIR, MBIR indicated a 46%-84% dose reduction potential, depending on task, without compromising the modeled detection performance. Conclusions: The presented methodology based on ACR phantom measurements extends current possibilities for the assessment of CT image quality under the complex resolution and noise characteristics exhibited with statistical and iterative reconstruction algorithms. The findings further suggest that MBIR can potentially make better use of the projections data to reduce CT dose by approximately a factor of 2. Alternatively, if the dose held unchanged, it can improve image quality by different levels for different tasks. [ABSTRACT FROM AUTHOR]

Purpose: To determine the diagnostic performance of three-dimensional (3D) texture analysis (TA) of contrast-enhanced computed tomography (CE-CT) images for treatment response assessment in patients with Hodgkin lymphoma (HL), compared with F-18-fludeoxyglucose (FDG) positron emission tomography/CT. Methods: 3D TA of 48 lymph nodes in 29 patients was performed on venous-phase CE-CT images before and after chemotherapy. All lymph nodes showed pathologically elevated FDG uptake at baseline. A stepwise logistic regression with forward selection was performed to identify classic CT parameters and texture features (TF) that enable the separation of complete response (CR) and persistent disease. Results: The TF fraction of image in runs, calculated for the 45° direction, was able to correctly identify CR with an accuracy of 75%, a sensitivity of 79.3%, and a specificity of 68.4%. Classical CT features achieved an accuracy of 75%, a sensitivity of 86.2%, and a specificity of 57.9%, whereas the combination of TF and CT imaging achieved an accuracy of 83.3%, a sensitivity of 86.2%, and a specificity of 78.9%. Conclusions: 3D TA of CE-CT images is potentially useful to identify nodal residual disease in HL, with a performance comparable to that of classical CT parameters. Best results are achieved when TA and classical CT features are combined. [ABSTRACT FROM AUTHOR]

Purpose: Survival for high-grade gliomas is poor, at least partly explained by intratumoral heterogeneity contributing to treatment resistance. Radiological evaluation of treatment response is in most cases limited to assessment of tumor size months after the initiation of therapy. Diffusion-weighted magnetic resonance imaging (MRI) and its estimate of the apparent diffusion coefficient (ADC) has been widely investigated, as it reflects tumor cellularity and proliferation. The aim of this study was to investigate texture analysis of ADC images in conjunction with multivariate image analysis as a means for identification of pretreatment imaging biomarkers. Methods: Twenty-three consecutive high-grade glioma patients were treated with radiotherapy (2 Gy/60 Gy) with concomitant and adjuvant temozolomide. ADC maps and T1-weighted anatomical images with and without contrast enhancement were collected prior to treatment, and (residual) tumor contrast enhancement was delineated. A gray-level co-occurrence matrix analysis was performed on the ADC maps in a cuboid encapsulating the tumor in coronal, sagittal, and transversal planes, giving a total of 60 textural descriptors for each tumor. In addition, similar examinations and analyses were performed at day 1, week 2, and week 6 into treatment. Principal component analysis (PCA) was applied to reduce dimensionality of the data, and the five largest components (scores) were used in subsequent analyses. MRI assessment three months after completion of radiochemotherapy was used for classifying tumor progression or regression. Results: The score scatter plots revealed that the first, third, and fifth components of the pretreatment examinations exhibited a pattern that strongly correlated to survival. Two groups could be identified: one with a median survival after diagnosis of 1099 days and one with 345 days, p = 0.0001. Conclusions: By combining PCA and texture analysis, ADC texture characteristics were identified, which seems to hold pretreatment prognostic information, independent of known prognostic factors such as age, stage, and surgical procedure. These findings encourage further studies with a larger patient cohort. [ABSTRACT FROM AUTHOR]

Purpose: Quantum noise properties of CT images are generally assessed using simple geometric phantoms with uniform backgrounds. Such phantoms may be inadequate when assessing nonlinear reconstruction or postprocessing algorithms. The purpose of this study was to design anatomically informed textured phantoms and use the phantoms to assess quantum noise properties across two clinically available reconstruction algorithms, filtered back projection (FBP) and sinogram affirmed iterative reconstruction (SAFIRE). Methods: Two phantoms were designed to represent lung and soft-tissue textures. The lung phantom included intricate vessel-like structures along with embedded nodules (spherical, lobulated, and spiculated). The soft tissue phantom was designed based on a three-dimensional clustered lumpy background with included low-contrast lesions (spherical and anthropomorphic). The phantoms were built using rapid prototyping (3D printing) technology and, along with a uniform phantom of similar size, were imaged on a Siemens SOMATOM Definition Flash CT scanner and reconstructed with FBP and SAFIRE. Fifty repeated acquisitions were acquired for each background type and noise was assessed by estimating pixel-value statistics, such as standard deviation (i.e., noise magnitude), autocorrelation, and noise power spectrum. Noise stationarity was also assessed by examining the spatial distribution of noise magnitude. The noise properties were compared across background types and between the two reconstruction algorithms. Results: In FBP and SAFIRE images, noise was globally nonstationary for all phantoms. In FBP images of all phantoms, and in SAFIRE images of the uniform phantom, noise appeared to be locally stationary (within a reasonably small region of interest). Noise was locally nonstationary in SAFIRE images of the textured phantoms with edge pixels showing higher noise magnitude compared to pixels in more homogenous regions. For pixels in uniform regions, noise magnitude was reduced by an average of 60% in SAFIRE images compared to FBP. However, for edge pixels, noise magnitude ranged from 20% higher to 40% lower in SAFIRE images compared to FBP. SAFIRE images of the lung phantom exhibited distinct regions with varying noise texture (i.e., noise autocorrelation/power spectra). Conclusions: Quantum noise properties observed in uniform phantoms may not be representative of those in actual patients for nonlinear reconstruction algorithms. Anatomical texture should be considered when evaluating the performance of CT systems that use such nonlinear algorithms. [ABSTRACT FROM AUTHOR]

Purpose: Iterative reconstruction (IR) reduces noise, thereby allowing dose reduction in computed tomography (CT) while maintaining comparable image quality to filtered back-projection (FBP). This study sought to characterize image quality metrics, delineation, dosimetric assessment, and other aspects necessary to integrate IR into treatment planning. Methods: CT images (Brilliance Big Bore v3.6, Philips Healthcare) were acquired of several phantoms using 120 kVp and 25-800 mAs. IR was applied at levels corresponding to noise reduction of 0.89-0.55 with respect to FBP. Noise power spectrum (NPS) analysis was used to characterize noise magnitude and texture. CT to electron density (CT-ED) curves were generated over all IR levels. Uniformity as well as spatial and low contrast resolution were quantified using a CATPHAN phantom. Task specific modulation transfer functions (MTFtask) were developed to characterize spatial frequency across objects of varied contrast. A prospective dose reduction study was conducted for 14 patients undergoing interfraction CT scans for high-dose rate brachytherapy. Three physicians performed image quality assessment using a six-point grading scale between the normal-dose FBP (reference), low-dose FBP, and low-dose IR scans for the following metrics: image noise, detectability of the vaginal cuff/bladder interface, spatial resolution, texture, segmentation confidence, and overall image quality. Contouring differences between FBP and IR were quantified for the bladder and rectum via overlap indices (OI) and Dice similarity coefficients (DSC). Line profile and region of interest analyses quantified noise and boundary changes. For two subjects, the impact of IR on external beam dose calculation was assessed via gamma analysis and changes in digitally reconstructed radiographs (DRRs) were quantified. Results: NPS showed large reduction in noise magnitude (50%), and a slight spatial frequency shift (~0.1 mm-1) with application of IR at L6. No appreciable changes were observed for CT-ED curves between FBP and IR levels [maximum difference ~13 HU for bone (~1% difference)]. For uniformity, differences were ~1 HU between FBP and IR. Spatial resolution was well conserved; the largest MTFtask decrease between FBP and IR levels was 0.08 A.U. No notable changes in lowcontrast detectability were observed and CNR increased substantially with IR. For the patient study, qualitative image grading showed low-dose IR was equivalent to or slightly worse than normal dose FBP, and is superior to low-dose FBP (p < 0.001 for noise), although these did not translate to differences in CT number, contouring ability, or dose calculation. The largest CT number discrepancy from FBP occurred at a bone/tissue interface using the most aggressive IR level [-1.2 ± 4.9 HU (range: -7.6-12.5 HU)]. No clinically significant contour differences were found between IR and FBP, with OIs and DSCs ranging from 0.85 to 0.95. Negligible changes in dose calculation were observed. DRRs preserved anatomical detail with <2% difference in intensity from FBP combined with aggressive IRL6. Conclusions: These results support integrating IR into treatment planning. While slight degradation in edges and shift in texture were observed in phantom, patient results show qualitative image grading, contouring ability, and dosimetric parameters were not adversely affected. [ABSTRACT FROM AUTHOR]

Purpose: Ultrasound-based solutions for diagnosis and prognosis of prostate cancer are highly desirable. The authors have devised a method for detecting prostate cancer using a vibroelastography (VE) system developed in our group and a tissue classification approach based on texture analysis of VE images. Methods: The VE method applies wide-band mechanical vibrations to the tissue. Here, the authors report on the use of this system for cancer detection and show that the texture of VE images characterized by the first and the second order statistics of the pixel intensities form a promising set of features for tissue typing to detect prostate cancer. The system was used to image patients prior to radical surgery. The removed specimens were sectioned and studied by an experienced histopathologist. The authors registered the whole-mount histology sections to the ultrasound images using an automatic registration algorithm. This enabled the quantitative evaluation of the performance of the authors' imaging method in cancer detection in an unbiased manner. The authors used support vector machine (SVM) classification to measure the cancer detection performance of the VE method. Regions of tissue of size 5 × 5 mm, labeled as cancer and noncancer based on automatic registration to histology slides, were classified using SVM. Results: The authors report an area under ROC of 0.81 ± 0.10 in cancer detection on 1066 tissue regions from 203 images. All cancer tumors in all zones were included in this analysis and were classified versus the noncancer tissue in the peripheral zone. This outcome was obtained in leaveone- patient-out validation. Conclusions: The developed 3D prostate vibroelastography system and the proposed multiparametric approach based on statistical texture parameters from the VE images result in a promising cancer detection method. [ABSTRACT FROM AUTHOR]

Purpose: Efficacy of tuberculosis (TB) treatment is often monitored using chest radiography. Monitoring size of cavities in pulmonary tuberculosis is important as the size predicts severity of the disease and its persistence under therapy predicts relapse. The authors present a method for automatic cavity segmentation in chest radiographs. Methods: A two stage method is proposed to segment the cavity borders, given a user defined seed point close to the center of the cavity. First, a supervised learning approach is employed to train a pixel classifier using texture and radial features to identify the border pixels of the cavity. A likelihood value of belonging to the cavity border is assigned to each pixel by the classifier. The authors experimented with four different classifiers: k-nearest neighbor (kNN), linear discriminant analysis (LDA), GentleBoost (GB), and random forest (RF). Next, the constructed likelihood map was used as an input cost image in the polar transformed image space for dynamic programming to trace the optimal maximum cost path. This constructed path corresponds to the segmented cavity contour in image space. Results: The method was evaluated on 100 chest radiographs (CXRs) containing 126 cavities. The reference segmentation was manually delineated by an experienced chest radiologist. An independent observer (a chest radiologist) also delineated all cavities to estimate interobserver variability. Jaccard overlap measure was computed between the reference segmentation and the automatic segmentation; and between the reference segmentation and the independent observer's segmentation for all cavities. A median overlap of 0.81 (0.76 ± 0.16), and 0.85 (0.82 ± 0.11) was achieved between the reference segmentation and the automatic segmentation, and between the segmentations by the two radiologists, respectively. The best reported mean contour distance and Hausdorff distance between the reference and the automatic segmentation were, respectively, 2.48 ± 2.19 and 8.32 ± 5.66 mm, whereas these distances were 1.66 ± 1.29 and 5.75 ± 4.88 mm between the segmentations by the reference reader and the independent observer, respectively. The automatic segmentations were also visually assessed by two trained CXR readers as "excellent," "adequate," or "insufficient." The readers had good agreement in assessing the cavity outlines and 84% of the segmentations were rated as "excellent" or "adequate" by both readers. Conclusions: The proposed cavity segmentation technique produced results with a good degree of overlap with manual expert segmentations. The evaluation measures demonstrated that the results approached the results of the experienced chest radiologists, in terms of overlap measure and contour distance measures. Automatic cavity segmentation can be employed in TB clinics for treatment monitoring, especially in resource limited settings where radiologists are not available. [ABSTRACT FROM AUTHOR]

Purpose: A method is presented for generating simulated low-dose cone-beam CT (CBCT) preview images from which patient- and task-specific minimum-dose protocols can be confidently selected prospectively in clinical scenarios involving repeat scans. Methods: In clinical scenarios involving a series of CBCT images, the low-dose preview (LDP) method operates upon the first scan to create a projection dataset that accurately simulates the effects of dose reduction in subsequent scans by injecting noise of proper magnitude and correlation, including both quantum and electronic readout noise as important components of image noise in flat-panel detector CBCT. Experiments were conducted to validate the LDP method in both a head phantom and a cadaveric torso by performing CBCT acquisitions spanning a wide dose range (head: 0.8-13.2 mGy, body: 0.8-12.4 mGy) with a prototype mobile C-arm system. After injecting correlated noise to simulate dose reduction, the projections were reconstructed using both conventional filtered backprojection (FBP) and an iterative, model-based image reconstruction method (MBIR). The LDP images were then compared to real CBCT images in terms of noise magnitude, noise-power spectrum (NPS), spatial resolution, contrast, and artifacts. Results: For both FBP and MBIR, the LDP images exhibited accurate levels of spatial resolution and contrast that were unaffected by the correlated noise injection, as expected. Furthermore, the LDP image noise magnitude and NPS were in strong agreement with real CBCT images acquired at the corresponding, reduced dose level across the entire dose range considered. The noise magnitude agreed within 7% for both the head phantom and cadaveric torso, and the NPS showed a similar level of agreement up to the Nyquist frequency. Therefore, the LDP images were highly representative of real image quality across a broad range of dose and reconstruction methods. On the other hand, naïve injection of uncorrelated noise resulted in strong underestimation of the true noise, which would lead to overly optimistic predictions of dose reduction. Conclusions: Correlated noise injection is essential to accurate simulation of CBCT image quality at reduced dose. With the proposed LDP method, the user can prospectively select patient-specific, minimum-dose protocols (viz., acquisition technique and reconstruction method) suitable to a particular imaging task and to the user's own observer preferences for CBCT scans following the first acquisition. The method could provide dose reduction in common clinical scenarios involving multiple CBCT scans, such as image-guided surgery and radiotherapy. [ABSTRACT FROM AUTHOR]

Purpose: Iterative reconstruction (IR) algorithms have the potential to reduce radiation dose in CT diagnostic imaging. As these algorithms become available on the market, a standardizable method of quantifying the dose reduction that a particular IR method can achieve would be valuable. Such a method would assist manufacturers in making promotional claims about dose reduction, buyers in comparing different devices, physicists in independently validating the claims, and the United States Food and Drug Administration in regulating the labeling of CT devices. However, the nonlinear nature of commercially available IR algorithms poses challenges to objectively assessing image quality, a necessary step in establishing the amount of dose reduction that a given IR algorithm can achieve without compromising that image quality. This review paper seeks to consolidate information relevant to objectively assessing the quality of CT IR images, and thereby measuring the level of dose reduction that a given IR algorithm can achieve. Methods: The authors discuss task-based methods for assessing the quality of CT IR images and evaluating dose reduction. Results: The authors explain and review recent literature on signal detection and localization tasks in CT IR image quality assessment, the design of an appropriate phantom for these tasks, possible choices of observers (including human and model observers), and methods of evaluating observer performance. Conclusions: Standardizing the measurement of dose reduction is a problem of broad interest to the CT community and to public health. A necessary step in the process is the objective assessment of CT image quality, for which various task-based methods may be suitable. This paper attempts to consolidate recent literature that is relevant to the development and implementation of task-based methods for the assessment of CT IR image quality. [ABSTRACT FROM AUTHOR]

Purpose: To develop a new spatio-temporal texture (SpTeT) based method for distinguishing vulnerable versus stable atherosclerotic plaques on DCE-MRI using a rabbit model of atherothrombosis. Methods: Aortic atherosclerosis was induced in 20 New Zealand White rabbits by cholesterol diet and endothelial denudation. MRI was performed before (pretrigger) and after (posttrigger) inducing plaque disruption with Russell's-viper-venom and histamine. Of the 30 vascular targets (segments) under histology analysis, 16 contained thrombus (vulnerable) and 14 did not (stable). A total of 352 voxel-wise computerized SpTeT features, including 192 Gabor, 36 Kirsch, 12 Sobel, 52 Haralick, and 60 first-order textural features, were extracted on DCE-MRI to capture subtle texture changes in the plaques over the course of contrast uptake. Different combinations of SpTeT feature sets, in which the features were ranked by a minimum-redundancy-maximum-relevance feature selection technique, were evaluated via a random forest classifier. A 500 iterative 2-fold cross validation was performed for discriminating the vulnerable atherosclerotic plaque and stable atherosclerotic plaque on per voxel basis. Four quantitative metrics were utilized to measure the classification results in separating between vulnerable and stable plaques. Results: The quantitative results show that the combination of five classes of SpTeT features can distinguish between vulnerable (disrupted plaques with an overlying thrombus) and stable plaques with the best AUC values of 0.9631 ± 0.0088, accuracy of 89.98% ± 0.57%, sensitivity of 83.71% ± 1.71%, and specificity of 94.55% ± 0.48%. Conclusions: Vulnerable and stable plaque can be distinguished by SpTeT based features. The SpTeT features, following validation on larger datasets, could be established as effective and reliable imaging biomarkers for noninvasively assessing atherosclerotic risk. [ABSTRACT FROM AUTHOR]

Purpose: In multiphase contrast-enhanced magnetic resonance imaging (CE-MRI), liver segmentation is an important preprocessing step for the computer-aided evaluation of liver disease. However, because of the liver's irregular shape, proximity to surrounding organs, and large intensity variation, and peripheral contrast enhancement in the kidney, liver segmentation has been very challenging. This paper presents a novel hybrid active contour model and overall procedures that are specific to liver segmentation. Methods: The authors introduced an edge-function-scaled (weighted) region-based active contour model (ESRAC) and utilization of registered, multiphase sequences to address leakage-to-kidney and oversegmentation problems. The model incorporated weighted regional information with a compactly supported edge map, computed from a combination of images obtained during arterial and delayed phases, and it was coupled with a geodesic edge term. To cope with signal-inhomogeneity on MRI, all of the axial slices were partitioned into eight sectors with an angular span of 45°, centered on the inferior vena cava, each in the superior and inferior regions and the regional information regarding ESRAC was computed for each partition, henceforth the so-called partitioned ESRAC (p-ESRAC). Initialization of the active contour was performed by thresholding with a range of [200, +8) and simple morphological operation during the delayed phase. At the end, to fill the holes in the segmented images caused by high gradients around the vasculature, noise, or outstanding texture features, iterative morphological operations were performed until convergence. The authors compared the segmentation accuracy of p-ESRAC to that with geodesic active contour, region-based active contour, geodesic active region, and localized region-based active contour using quantitative and visual assessments. Results: In three-dimensional experimental studies conducted on 30 subjects (14 normal or benign cases and 16 malignant cases), compared with other active contours, p-ESRAC achieved the highest dice similarity coefficients of 93.9 ± 1.6% (normal) and 91.6 ± 2.2% (malignant), respectively. In addition, p-ESRAC resulted in the lowest false positive rates of 4.5 ± 3.2% (normal) and 7.9 ± 3.0% (malignant), demonstrating it to be the most effective in reducing oversegmentation. The partition scheme improved segmentation accuracy by 5.4 ± 9.2% (normal) and 22.2 ± 27.6% (malignant) of the true segmentation that was missed by ESRAC. Visual assessment confirmed that p-ESRAC prevented leakage of the segmentation results of the liver into the kidney. Conclusions: A novel active-contour model was developed, allowing for accurate liver segmentation on multiphase CE-MRI, with conditions that include signal inhomogeneity and weak boundary conditions. Such a technique could be useful for applications that involve computeraided diagnosis of liver disease. [ABSTRACT FROM AUTHOR]

Purpose: In this pilot study, the authors examined associations between image-based phenotypes and genomic biomarkers. The potential genetic contribution of UGT2B genes to interindividual variation in breast density and mammographic parenchymal patterns is demonstrated by performing an association study between image-based phenotypes and genomic biomarkers [single-nucleotide polymorphism (SNP) genotypes]. Methods: This candidate-gene approach study included 179 subjects for whom both mammograms and blood DNA samples had been obtained. The full-field digital mammograms were acquired using a GE Senographe 2000D FFDM system (12-bit; 0.1 mm-pixel size). Regions-of-interest, 256 × 256 pixels in size, selected from the central breast region behind the nipple underwent computerized image analysis to yield image-based phenotypes of mammographic density and parenchymal texture patterns. SNP genotyping was performed using a Sequenom MassArray System. One hundred twenty three SNPs with minor allele frequency above 5% were genotyped for the UGT2B gene clusters, and used in the study. The association between the image-based phenotypes and genomic biomarkers was assessed with the Pearson correlation coefficient via the PLINK software, and included permutation and correction for multiple SNP comparisons. Results: From the phenotype-genotype association analysis, a parenchyma texture coarseness feature was found to be correlated with SNP rs451632 after multiple test correction for the multiple SNPs (p = 0.022). The power law ß, which is used to characterize the frequency component of texture patterns, was found to be correlated with SNP rs4148298 (p = 0.035). Conclusions: The authors' results indicate that UGT2B gene variation may contribute to interindividual variation in mammographic parenchymal patterns and breast density. Understanding the relationship between image-based phenotypes and genomic biomarkers may help understand the biologic mechanism for image-based biomarkers and yield a future role in personalized medicine. [ABSTRACT FROM AUTHOR]

Purpose: This paper describes a feasibility study for developing a 35-MHz high-frequency ultrasound computed-tomography (HFUCT) system for imaging rat testicles. Methods: The performances of two kinds of HFUCT-attenuation and sound-speed UCT-based on transmission and pulse-echo modes were investigated in this study. Experiments were carried out using phantoms and actual rat testicles in vitro. HFUCT images were reconstructed using a filtered backprojection algorithm. Results: The phantom experimental results indicated that all types of HFUCT can determine the dimensions of a plastic cylinder with a diameter of 500 μm. Compared to sound-speed HFUCT, attenuation HFUCT exhibited a better performance in recognizing a tiny sclerosed region in a gelatin phantom. Therefore, the in vitro testicular experiments were performed using attenuation HFUCT based on transmission and pulse-echo modes. The experimentally measured attenuation coefficient and sound speed for healthy rat testicles were 2.92 ± 0.25 dB/mm and 1537 ± 25 m/s, respectively. Conclusions: A homogeneous texture was evident for healthy testicles using both modes. An artificial sclerosed tumor could also be clearly observed using two- and three-dimensional attenuation HFUCT in both modes. However, an object artifact was apparent in pulse-echo mode because of ultrasound beam refraction. All of the obtained experimental results indicate the potential of using HFUCT as a novel tool for monitoring the preclinical responses of testicular tumors in small animals. [ABSTRACT FROM AUTHOR]

Purpose: Tumor grading is an important part of breast cancer diagnosis and currently requires biopsy as its standard. Here, the authors investigate quantitative ultrasound parameters in locally advanced breast cancers that can potentially separate tumors from normal breast tissue and differentiate tumor grades. Methods: Ultrasound images and radiofrequency data from 42 locally advanced breast cancer patients were acquired and analyzed. Parameters related to the linear regression of the power spectrum-midband fit, slope, and 0-MHz-intercept-were determined from breast tumors and normal breast tissues. Mean scatterer spacing was estimated from the spectral autocorrelation, and the effective scatterer diameter and effective acoustic concentration were estimated from the Gaussian form factor. Parametric maps of each quantitative ultrasound parameter were constructed from the gated radiofrequency segments in tumor and normal tissue regions of interest. In addition to the mean values of the parametric maps, higher order statistical features, computed from gray-level co-occurrence matrices were also determined and used for characterization. Finally, linear and quadratic discriminant analyses were performed using combinations of quantitative ultrasound parameters to classify breast tissues. Results: Quantitative ultrasound parameters were found to be statistically different between tumor and normal tissue (p < 0.05). The combination of effective acoustic concentration and mean scatterer spacing could separate tumor from normal tissue with 82% accuracy, while the addition of effective scatterer diameter to the combination did not provide significant improvement (83% accuracy). Furthermore, the two advanced parameters, including effective scatterer diameter and mean scatterer spacing, were found to be statistically differentiating among grade I, II, and III tumors (p = 0.014 for scatterer spacing, p = 0.035 for effective scatterer diameter). The separation of the tumor grades further improved when the textural features of the effective scatterer diameter parametric map were combined with the mean value of the map (p = 0.004). Conclusions: Overall, the binary classification results (tumor versus normal tissue) were more promising than tumor grade assessment. Combinations of advanced parameters can further improve the separation of tumors from normal tissue compared to the use of linear regression parameters. While the linear regression parameters were sufficient for characterizing breast tumors and normal breast tissues, advanced parameters and their textural features were required to better characterize tumor subtypes. [ABSTRACT FROM AUTHOR]

Purpose: A novel approach to a computer aided diagnosis system for the Parkinson's disease is proposed. This tool is intended as a supporting tool for physicians, based on fully automated methods that lead to the classification of123I-ioflupane SPECT images. Methods: 123I-ioflupane images from three different databases are used to train the system. The images are intensity and spatially normalized, then subimages are extracted and a 3D gray-level co-occurrence matrix is computed over these subimages, allowing the characterization of the texture using Haralick texture features. Finally, different discrimination estimation methods are used to select a feature vector that can be used to train and test the classifier. Results: Using the leave-one-out cross-validation technique over these three databases, the system achieves results up to a 97.4% of accuracy, and 99.1% of sensitivity, with positive likelihood ratios over 27. Conclusions: The system presents a robust feature extraction method that helps physicians in the diagnosis task by providing objective, operator-independent textural information about123I-ioflupane images, commonly used in the diagnosis of the Parkinson's disease. Textural features computation has been optimized by using a subimage selection algorithm, and the discrimination estimation methods used here makes the system feature-independent, allowing us to extend it to other databases and diseases. [ABSTRACT FROM AUTHOR]

Purpose: To develop and evaluate an image-domain noise reduction method based on a modified nonlocal means (NLM) algorithm that is adaptive to local noise level of CT images and to implement this method in a time frame consistent with clinical workflow. Methods: A computationally efficient technique for local noise estimation directly from CT images was developed. A forward projection, based on a 2D fan-beam approximation, was used to generate the projection data, with a noise model incorporating the effects of the bowtie filter and automatic exposure control. The noise propagation from projection data to images was analytically derived. The analytical noise map was validated using repeated scans of a phantom. A 3D NLM denoising algorithm was modified to adapt its denoising strength locally based on this noise map. The performance of this adaptive NLM filter was evaluated in phantom studies in terms of in-plane and cross-plane high-contrast spatial resolution, noise power spectrum (NPS), subjective low-contrast spatial resolution using the American College of Radiology (ACR) accreditation phantom, and objective low-contrast spatial resolution using a channelized Hotelling model observer (CHO). Graphical processing units (GPU) implementation of this noise map calculation and the adaptive NLM filtering were developed to meet demands of clinical workflow. Adaptive NLM was piloted on lower dose scans in clinical practice. Results: The local noise level estimation matches the noise distribution determined from multiple repetitive scans of a phantom, demonstrated by small variations in the ratio map between the analytical noise map and the one calculated from repeated scans. The phantom studies demonstrated that the adaptive NLM filter can reduce noise substantially without degrading the high-contrast spatial resolution, as illustrated by modulation transfer function and slice sensitivity profile results. The NPS results show that adaptive NLM denoising preserves the shape and peak frequency of the noise power spectrum better than commercial smoothing kernels, and indicate that the spatial resolution at low contrast levels is not significantly degraded. Both the subjective evaluation using the ACR phantom and the objective evaluation on a low-contrast detection task using a CHO model observer demonstrate an improvement on low-contrast performance. The GPU implementation can process and transfer 300 slice images within 5 min. On patient data, the adaptive NLM algorithm provides more effective denoising of CT data throughout a volume than standard NLM, and may allow significant lowering of radiation dose. After a two week pilot study of lower dose CT urography and CT enterography exams, both GI and GU radiology groups elected to proceed with permanent implementation of adaptive NLM in their GI and GU CT practices. Conclusions: This work describes and validates a computationally efficient technique for noise map estimation directly from CT images, and an adaptive NLM filtering based on this noise map, on phantom and patient data. Both the noise map calculation and the adaptive NLM filtering can be performed in times that allow integration with clinical workflow. The adaptive NLM algorithm provides effective denoising of CT data throughout a volume, and may allow significant lowering of radiation dose. [ABSTRACT FROM AUTHOR]