Data driven surrogate signal extraction for dynamic PET using selective PCA: time windows versus the combination of components.

Respiratory motion correction is beneficial in PET, as it can reduce artefacts caused by motion and improve quantitative accuracy. Methods of motion correction are commonly based on a respiratory trace obtained through an external device (like the Real Time Position Management System) or a data driven method, such as those based on dimensionality reduction techniques (for instance PCA). PCA itself being a linear transformation to the axis of greatest variation. Data driven methods have the advantage of being non-invasive, and can be performed post-acquisition. However, their main downside being that they are adversely affected by the tracer kinetics of the dynamic PET acquisition. Therefore, they are mostly limited to static PET acquisitions. This work seeks to extend on existing PCA-based data-driven motion correction methods, to allow for their applicability to dynamic PET imaging. The methods explored in this work include; a moving window approach (similar to the Kinetic Respiratory Gating method from Schleyer et al.), extrapolation of the principal component from later time points to earlier time points, and a method to score, select, and combine multiple respiratory components. The resulting respiratory traces were evaluated on 22 data sets from a dynamic 18FFDG study on patients with Idiopathic Pulmonary Fibrosis. This was achieved by calculating their correlation with a surrogate signal acquired using a Real Time Position Management System. The results indicate that all methods produce better surrogate signals than when applying conventional PCA to dynamic data (for instance, a higher correlation with a gold standard respiratory trace). Extrapolating a late time point principal component produced more promising results than using a moving window. Scoring, selecting, and combining components held benefits over all other methods. This work allows for the extraction of a surrogate signal from dynamic PET data earlier in the acquisition and with a greater accuracy than previous work. This potentially allows for numerous other methods (for instance, respiratory motion correction) to be applied to this data (when they otherwise could not be previously used).

Data-driven gating (DDG)-based motion match for improved CTAC registration.

BACKGROUND: Respiratory motion artefacts are a pitfall in thoracic PET/CT imaging. A source of these motion artefacts within PET images is the CT used for attenuation correction of the images. The arbitrary respiratory phase in which the helical CT ( CT helical ) is acquired often causes misregistration between PET and CT images, leading to inaccurate attenuation correction of the PET image. As a result, errors in tumour delineation or lesion uptake values can occur. To minimise the effect of motion in PET/CT imaging, a data-driven gating (DDG)-based motion match (MM) algorithm has been developed that estimates the phase of the CT helical , and subsequently warps this CT to a given phase of the respiratory cycle, allowing it to be phase-matched to the PET. A set of data was used which had four-dimensional CT (4DCT) acquired alongside PET/CT. The 4DCT allowed ground truth CT phases to be generated and compared to the algorithm-generated motion match CT (MMCT). Measurements of liver and lesion margin positions were taken across CT images to determine any differences and establish how well the algorithm performed concerning warping the CT helical to a given phase (end-of-expiration, EE). RESULTS: Whilst there was a minor significance in the liver measurement between the 4DCT and MMCT ( p = 0.045 ), no significant differences were found between the 4DCT or MMCT for lesion measurements ( p = 1.0 ). In all instances, the CT helical was found to be significantly different from the 4DCT ( p < 0.001 ). Consequently, the 4DCT and MMCT can be considered equivalent with respect to warped CT generation, showing the DDG-based MM algorithm to be successful. CONCLUSION: The MM algorithm successfully enables the phase-matching of a CT helical to the EE of a ground truth 4DCT. This would reduce the motion artefacts caused by PET/CT registration without requiring additional patient dose (required for a 4DCT).

Validation of a discovery MI 4-ring model according to the NEMA NU 2-2018 standards: from Monte Carlo simulations to clinical-like reconstructions.

BACKGROUND: We propose a comprehensive evaluation of a Discovery MI 4-ring (DMI) model, using a Monte Carlo simulator (GATE) and a clinical reconstruction software package (PET toolbox). The following performance characteristics were compared with actual measurements according to NEMA NU 2-2018 guidelines: system sensitivity, count losses and scatter fraction (SF), coincidence time resolution (CTR), spatial resolution (SR), and image quality (IQ). For SR and IQ tests, reconstruction of time-of-flight (TOF) simulated data was performed using the manufacturer's reconstruction software. RESULTS: Simulated prompt, random, true, scatter and noise equivalent count rates closely matched the experimental rates with maximum relative differences of 1.6%, 5.3%, 7.8%, 6.6%, and 16.5%, respectively, in a clinical range of less than 10 kBq/mL. A 3.6% maximum relative difference was found between experimental and simulated sensitivities. The simulated spatial resolution was better than the experimental one. Simulated image quality metrics were relatively close to the experimental results. CONCLUSIONS: The current model is able to reproduce the behaviour of the DMI count rates in the clinical range and generate clinical-like images with a reasonable match in terms of contrast and noise.

Deep learning-based time-of-flight (ToF) image enhancement of non-ToF PET scans.

PURPOSE: To improve the quantitative accuracy and diagnostic confidence of PET images reconstructed without time-of-flight (ToF) using deep learning models trained for ToF image enhancement (DL-ToF). METHODS: A total of 273 [18F]-FDG PET scans were used, including data from 6 centres equipped with GE Discovery MI ToF scanners. PET data were reconstructed using the block-sequential-regularised-expectation-maximisation (BSREM) algorithm with and without ToF. The images were then split into training (n = 208), validation (n = 15), and testing (n = 50) sets. Three DL-ToF models were trained to transform non-ToF BSREM images to their target ToF images with different levels of DL-ToF strength (low, medium, high). The models were objectively evaluated using the testing set based on standardised uptake value (SUV) in 139 identified lesions, and in normal regions of liver and lungs. Three radiologists subjectively rated the models using testing sets based on lesion detectability, diagnostic confidence, and image noise/quality. RESULTS: The non-ToF, DL-ToF low, medium, and high methods resulted in - 28 ± 18, - 28 ± 19, - 8 ± 22, and 1.7 ± 24% differences (mean; SD) in the SUVmax for the lesions in testing set, compared to ToF-BSREM image. In background lung VOIs, the SUVmean differences were 7 ± 15, 0.6 ± 12, 1 ± 13, and 1 ± 11% respectively. In normal liver, SUVmean differences were 4 ± 5, 0.7 ± 4, 0.8 ± 4, and 0.1 ± 4%. Visual inspection showed that our DL-ToF improved feature sharpness and convergence towards ToF reconstruction. Blinded clinical readings of testing sets for diagnostic confidence (scale 0-5) showed that non-ToF, DL-ToF low, medium, and high, and ToF images scored 3.0, 3.0, 4.1, 3.8, and 3.5 respectively. For this set of images, DL-ToF medium therefore scored highest for diagnostic confidence. CONCLUSION: Deep learning-based image enhancement models may provide converged ToF-equivalent image quality without ToF reconstruction. In clinical scoring DL-ToF-enhanced non-ToF images (medium and high) on average scored as high as, or higher than, ToF images. The model is generalisable and hence, could be applied to non-ToF images from BGO-based PET/CT scanners.

Image enhancement of whole-body oncology [18F]-FDG PET scans using deep neural networks to reduce noise.

PURPOSE: To enhance the image quality of oncology [18F]-FDG PET scans acquired in shorter times and reconstructed by faster algorithms using deep neural networks. METHODS: List-mode data from 277 [18F]-FDG PET/CT scans, from six centres using GE Discovery PET/CT scanners, were split into ¾-, ½- and »-duration scans. Full-duration datasets were reconstructed using the convergent block sequential regularised expectation maximisation (BSREM) algorithm. Short-duration datasets were reconstructed with the faster OSEM algorithm. The 277 examinations were divided into training (n = 237), validation (n = 15) and testing (n = 25) sets. Three deep learning enhancement (DLE) models were trained to map full and partial-duration OSEM images into their target full-duration BSREM images. In addition to standardised uptake value (SUV) evaluations in lesions, liver and lungs, two experienced radiologists scored the quality of testing set images and BSREM in a blinded clinical reading (175 series). RESULTS: OSEM reconstructions demonstrated up to 22% difference in lesion SUVmax, for different scan durations, compared to full-duration BSREM. Application of the DLE models reduced this difference significantly for full-, ¾- and ½-duration scans, while simultaneously reducing the noise in the liver. The clinical reading showed that the standard DLE model with full- or ¾-duration scans provided an image quality substantially comparable to full-duration scans with BSREM reconstruction, yet in a shorter reconstruction time. CONCLUSION: Deep learning-based image enhancement models may allow a reduction in scan time (or injected activity) by up to 50%, and can decrease reconstruction time to a third, while maintaining image quality.

mDixon-Based Synthetic CT Generation for PET Attenuation Correction on Abdomen and Pelvis Jointly Using Transfer Fuzzy Clustering and Active Learning-Based Classification.

We propose a new method for generating synthetic CT images from modified Dixon (mDixon) MR data. The synthetic CT is used for attenuation correction (AC) when reconstructing PET data on abdomen and pelvis. While MR does not intrinsically contain any information about photon attenuation, AC is needed in PET/MR systems in order to be quantitatively accurate and to meet qualification standards required for use in many multi-center trials. Existing MR-based synthetic CT generation methods either use advanced MR sequences that have long acquisition time and limited clinical availability or use matching of the MR images from a newly scanned subject to images in a library of MR-CT pairs which has difficulty in accounting for the diversity of human anatomy especially in patients that have pathologies. To address these deficiencies, we present a five-phase interlinked method that uses mDixon MR acquisition and advanced machine learning methods for synthetic CT generation. Both transfer fuzzy clustering and active learning-based classification (TFC-ALC) are used. The significance of our efforts is fourfold: 1) TFC-ALC is capable of better synthetic CT generation than methods currently in use on the challenging abdomen using only common Dixon-based scanning. 2) TFC partitions MR voxels initially into the four groups regarding fat, bone, air, and soft tissue via transfer learning; ALC can learn insightful classifiers, using as few but informative labeled examples as possible to precisely distinguish bone, air, and soft tissue. Combining them, the TFC-ALC method successfully overcomes the inherent imperfection and potential uncertainty regarding the co-registration between CT and MR images. 3) Compared with existing methods, TFC-ALC features not only preferable synthetic CT generation but also improved parameter robustness, which facilitates its clinical practicability. Applying the proposed approach on mDixon-MR data from ten subjects, the average score of the mean absolute prediction deviation (MAPD) was 89.78±8.76 which is significantly better than the 133.17±9.67 obtained using the all-water (AW) method (p=4.11E-9) and the 104.97±10.03 obtained using the four-cluster-partitioning (FCP, i.e., external-air, internal-air, fat, and soft tissue) method (p=0.002). 4) Experiments in the PET SUV errors of these approaches show that TFC-ALC achieves the highest SUV accuracy and can generally reduce the SUV errors to 5% or less. These experimental results distinctively demonstrate the effectiveness of our proposed TFCALC method for the synthetic CT generation on abdomen and pelvis using only the commonly-available Dixon pulse sequence.

UTE-mDixon-based thorax synthetic CT generation.

PURPOSE: Accurate photon attenuation assessment from MR data remains an unmet challenge in the thorax due to tissue heterogeneity and the difficulty of MR lung imaging. As thoracic tissues encompass the whole physiologic range of photon absorption, large errors can occur when using, for example, a uniform, water-equivalent or a soft-tissue-only approximation. The purpose of this study was to introduce a method for voxel-wise thoracic synthetic CT (sCT) generation from MR data attenuation correction (AC) for PET/MR or for MR-only radiation treatment planning (RTP). METHODS: Acquisition: A radial stack-of-stars combining ultra-short-echo time (UTE) and modified Dixon (mDixon) sequence was optimized for thoracic imaging. The UTE-mDixon pulse sequence collects MR signals at three TE times denoted as UTE, Echo1, and Echo2. Three-point mDixon processing was used to reconstruct water and fat images. Bias field correction was applied in order to avoid artifacts caused by inhomogeneity of the MR magnetic field. ANALYSIS: Water fraction and R2* maps were estimated using the UTE-mDixon data to produce a total of seven MR features, that is UTE, Echo1, Echo2, Dixon water, Dixon fat, Water fraction, and R2*. A feature selection process was performed to determine the optimal feature combination for the proposed automatic, 6-tissue classification for sCT generation. Fuzzy c-means was used for the automatic classification which was followed by voxel-wise attenuation coefficient assignment as a weighted sum of those of the component tissues. Performance evaluation: MR data collected using the proposed pulse sequence were compared to those using a traditional two-point Dixon approach. Image quality measures, including image resolution and uniformity, were evaluated using an MR ACR phantom. Data collected from 25 normal volunteers were used to evaluate the accuracy of the proposed method compared to the template-based approach. Notably, the template approach is applicable here, that is normal volunteers, but may not be robust enough for patients with pathologies. RESULTS: The free breathing UTE-mDixon pulse sequence yielded images with quality comparable to those using the traditional breath holding mDixon sequence. Furthermore, by capturing the signal before T2* decay, the UTE-mDixon image provided lung and bone information which the mDixon image did not. The combination of Dixon water, Dixon fat, and the Water fraction was the most robust for tissue clustering and supported the classification of six tissues, that is, air, lung, fat, soft tissue, low-density bone, and dense bone, used to generate the sCT. The thoracic sCT had a mean absolute difference from the template-based (reference) CT of less than 50 HU and which was better agreement with the reference CT than the results produced using the traditional Dixon-based data. CONCLUSION: MR thoracic acquisition and analyses have been established to automatically provide six distinguishable tissue types to generate sCT for MR-based AC of PET/MR and for MR-only RTP.

Improving Bone Mineral Density Assessment Using Spectral Detector CT.

INTRODUCTION: Bone mineral density (BMD) analysis by Dual-Energy x-ray Absorptiometry (DXA) can have some false negatives due to overlapping structures in the projections. Spectral Detector CT (SDCT) can overcome these limitations by providing volumetric information. We investigated its performance for BMD assessment and compared it to DXA and phantomless volumetric bone mineral density (PLvBMD), the latter known to systematically underestimate BMD. DXA is the current standard for BMD assessment, while PLvBMD is an established alternative for opportunistic BMD analysis using CT. Similarly to PLvBMD, spectral data could allow BMD screening opportunistically, without additional phantom calibration. METHODOLOGY: Ten concentrations of dipotassium phosphate (K2HPO4) ranging from 0 to 600 mg/ml, in an acrylic phantom were scanned using SDCT in four different, clinically-relevant scan conditions. Images were processed to estimate the K2HPO4 concentrations. A model representing a human lumbar spine (European Spine Phantom) was scanned and used for calibration via linear regression analysis. After calibration, our method was retrospectively applied to abdominal SDCT scans of 20 patients for BMD assessment, who also had PLvBMD and DXA. Performance of PLvBMD, DXA and our SDCT method were compared by sensitivity, specificity, negative predictive value and positive predictive value for decreased BMD. RESULTS: There was excellent correlation (R2 >0.99, p < 0.01) between true and measured K2HPO4 concentrations for all scan conditions. Overall mean measurement error ranged from -11.5 ± 4.7 mg/ml (-2.8 ± 6.0%) to -12.3 ± 6.3 mg/ml (-4.8 ± 3.0%) depending on scan conditions. Using DXA as a reference standard, sensitivity/specificity for detecting decreased BMD in the scanned patients were 100%/73% using SDCT, 100%/40% using PLvBMD provided T-scores, and 90-100%/40-53% using PLvBMD hydroxyapatite density classifications, respectively. CONCLUSIONS: Our results show excellent sensitivity and high specificity of SDCT for detecting decreased BMD, demonstrating clinical feasibility. Further validation in prospective clinical trials will be required.

Abdominal, multi-organ, auto-contouring method for online adaptive magnetic resonance guided radiotherapy: An intelligent, multi-level fusion approach.

BACKGROUND: Manual contouring remains the most laborious task in radiation therapy planning and is a major barrier to implementing routine Magnetic Resonance Imaging (MRI) Guided Adaptive Radiation Therapy (MR-ART). To address this, we propose a new artificial intelligence-based, auto-contouring method for abdominal MR-ART modeled after human brain cognition for manual contouring. METHODS/MATERIALS: Our algorithm is based on two types of information flow, i.e. top-down and bottom-up. Top-down information is derived from simulation MR images. It grossly delineates the object based on its high-level information class by transferring the initial planning contours onto daily images. Bottom-up information is derived from pixel data by a supervised, self-adaptive, active learning based support vector machine. It uses low-level pixel features, such as intensity and location, to distinguish each target boundary from the background. The final result is obtained by fusing top-down and bottom-up outputs in a unified framework through artificial intelligence fusion. For evaluation, we used a dataset of four patients with locally advanced pancreatic cancer treated with MR-ART using a clinical system (MRIdian, Viewray, Oakwood Village, OH, USA). Each set included the simulation MRI and onboard T1 MRI corresponding to a randomly selected treatment session. Each MRI had 144 axial slices of 266 × 266 pixels. Using the Dice Similarity Index (DSI) and the Hausdorff Distance Index (HDI), we compared the manual and automated contours for the liver, left and right kidneys, and the spinal cord. RESULTS: The average auto-segmentation time was two minutes per set. Visually, the automatic and manual contours were similar. Fused results achieved better accuracy than either the bottom-up or top-down method alone. The DSI values were above 0.86. The spinal canal contours yielded a low HDI value. CONCLUSION: With a DSI significantly higher than the usually reported 0.7, our novel algorithm yields a high segmentation accuracy. To our knowledge, this is the first fully automated contouring approach using T1 MRI images for adaptive radiotherapy.

Machine learning-based dual-energy CT parametric mapping.

The aim is to develop and evaluate machine learning methods for generating quantitative parametric maps of effective atomic number (Zeff), relative electron density (ρ e), mean excitation energy (I x ), and relative stopping power (RSP) from clinical dual-energy CT data. The maps could be used for material identification and radiation dose calculation. Machine learning methods of historical centroid (HC), random forest (RF), and artificial neural networks (ANN) were used to learn the relationship between dual-energy CT input data and ideal output parametric maps calculated for phantoms from the known compositions of 13 tissue substitutes. After training and model selection steps, the machine learning predictors were used to generate parametric maps from independent phantom and patient input data. Precision and accuracy were evaluated using the ideal maps. This process was repeated for a range of exposure doses, and performance was compared to that of the clinically-used dual-energy, physics-based method which served as the reference. The machine learning methods generated more accurate and precise parametric maps than those obtained using the reference method. Their performance advantage was particularly evident when using data from the lowest exposure, one-fifth of a typical clinical abdomen CT acquisition. The RF method achieved the greatest accuracy. In comparison, the ANN method was only 1% less accurate but had much better computational efficiency than RF, being able to produce parametric maps in 15 s. Machine learning methods outperformed the reference method in terms of accuracy and noise tolerance when generating parametric maps, encouraging further exploration of the techniques. Among the methods we evaluated, ANN is the most suitable for clinical use due to its combination of accuracy, excellent low-noise performance, and computational efficiency.

SSC-EKE: Semi-Supervised Classification with Extensive Knowledge Exploitation.

We introduce a new, semi-supervised classification method that extensively exploits knowledge. The method has three steps. First, the manifold regularization mechanism, adapted from the Laplacian support vector machine (LapSVM), is adopted to mine the manifold structure embedded in all training data, especially in numerous label-unknown data. Meanwhile, by converting the labels into pairwise constraints, the pairwise constraint regularization formula (PCRF) is designed to compensate for the few but valuable labelled data. Second, by further combining the PCRF with the manifold regularization, the precise manifold and pairwise constraint jointly regularized formula (MPCJRF) is achieved. Third, by incorporating the MPCJRF into the framework of the conventional SVM, our approach, referred to as semi-supervised classification with extensive knowledge exploitation (SSC-EKE), is developed. The significance of our research is fourfold: 1) The MPCJRF is an underlying adjustment, with respect to the pairwise constraints, to the graph Laplacian enlisted for approximating the potential data manifold. This type of adjustment plays the correction role, as an unbiased estimation of the data manifold is difficult to obtain, whereas the pairwise constraints, converted from the given labels, have an overall high confidence level. 2) By transforming the values of the two terms in the MPCJRF such that they have the same range, with a trade-off factor varying within the invariant interval [0, 1), the appropriate impact of the pairwise constraints to the graph Laplacian can be self-adaptively determined. 3) The implication regarding extensive knowledge exploitation is embodied in SSC-EKE. That is, the labelled examples are used not only to control the empirical risk but also to constitute the MPCJRF. Moreover, all data, both labelled and unlabelled, are recruited for the model smoothness and manifold regularization. 4) The complete framework of SSC-EKE organically incorporates multiple theories, such as joint manifold and pairwise constraint-based regularization, smoothness in the reproducing kernel Hilbert space, empirical risk minimization, and spectral methods, which facilitates the preferable classification accuracy as well as the generalizability of SSC-EKE.

Multi-View Maximum Entropy Clustering by Jointly Leveraging Inter-View Collaborations and Intra-View-Weighted Attributes.

As a dedicated countermeasure for heterogeneous multi-view data, multi-view clustering is currently a hot topic in machine learning. However, many existing methods either neglect the effective collaborations among views during clustering or do not distinguish the respective importance of attributes in views, instead treating them equivalently. Motivated by such challenges, based on maximum entropy clustering (MEC), two specialized criteria-inter-view collaborative learning (IEVCL) and intra-view-weighted attributes (IAVWA)-are first devised as the bases. Then, by organically incorporating IEVCL and IAVWA into the formulation of classic MEC, a novel, collaborative multi-view clustering model and the matching algorithm referred to as the view-collaborative, attribute-weighted MEC (VC-AW-MEC) are proposed. The significance of our efforts is three-fold: 1) both IEVCL and IAVWA are dedicatedly devised based on MEC so that the proposed VC-AW-MEC is qualified to effectively handle as many multi-view data scenes as possible; 2) IEVCL is competent in seeking the consensus across all involved views throughout clustering, whereas IAVWA is capable of adaptively discriminating the individual impact regarding the attributes within each view; and 3) benefiting from jointly leveraging IEVCL and IAVWA, compared with some existing state-of-the-art approaches, the proposed VC-AW-MEC algorithm generally exhibits preferable clustering effectiveness and stability on heterogeneous multi-view data. Our efforts have been verified in many synthetic or real-world multi-view data scenes.

Affinity and Penalty Jointly Constrained Spectral Clustering With All-Compatibility, Flexibility, and Robustness.

The existing, semisupervised, spectral clustering approaches have two major drawbacks, i.e., either they cannot cope with multiple categories of supervision or they sometimes exhibit unstable effectiveness. To address these issues, two normalized affinity and penalty jointly constrained spectral clustering frameworks as well as their corresponding algorithms, referred to as type-I affinity and penalty jointly constrained spectral clustering (TI-APJCSC) and type-II affinity and penalty jointly constrained spectral clustering (TII-APJCSC), respectively, are proposed in this paper. TI refers to type-I and TII to type-II. The significance of this paper is fourfold. First, benefiting from the distinctive affinity and penalty jointly constrained strategies, both TI-APJCSC and TII-APJCSC are substantially more effective than the existing methods. Second, both TI-APJCSC and TII-APJCSC are fully compatible with the three well-known categories of supervision, i.e., class labels, pairwise constraints, and grouping information. Third, owing to the delicate framework normalization, both TI-APJCSC and TII-APJCSC are quite flexible. With a simple tradeoff factor varying in the small fixed interval (0, 1], they can self-adapt to any semisupervised scenario. Finally, both TI-APJCSC and TII-APJCSC demonstrate strong robustness, not only to the number of pairwise constraints but also to the parameter for affinity measurement. As such, the novel TI-APJCSC and TII-APJCSC algorithms are very practical for medium- and small-scale semisupervised data sets. The experimental studies thoroughly evaluated and demonstrated these advantages on both synthetic and real-life semisupervised data sets.

Knowledge-leveraged transfer fuzzy C-Means for texture image segmentation with self-adaptive cluster prototype matching.

We study a novel fuzzy clustering method to improve the segmentation performance on the target texture image by leveraging the knowledge from a prior texture image. Two knowledge transfer mechanisms, i.e. knowledge-leveraged prototype transfer (KL-PT) and knowledge-leveraged prototype matching (KL-PM) are first introduced as the bases. Applying them, the knowledge-leveraged transfer fuzzy C-means (KL-TFCM) method and its three-stage-interlinked framework, including knowledge extraction, knowledge matching, and knowledge utilization, are developed. There are two specific versions: KL-TFCM-c and KL-TFCM-f, i.e. the so-called crisp and flexible forms, which use the strategies of maximum matching degree and weighted sum, respectively. The significance of our work is fourfold: 1) Owing to the adjustability of referable degree between the source and target domains, KL-PT is capable of appropriately learning the insightful knowledge, i.e. the cluster prototypes, from the source domain; 2) KL-PM is able to self-adaptively determine the reasonable pairwise relationships of cluster prototypes between the source and target domains, even if the numbers of clusters differ in the two domains; 3) The joint action of KL-PM and KL-PT can effectively resolve the data inconsistency and heterogeneity between the source and target domains, e.g. the data distribution diversity and cluster number difference. Thus, using the three-stage-based knowledge transfer, the beneficial knowledge from the source domain can be extensively, self-adaptively leveraged in the target domain. As evidence of this, both KL-TFCM-c and KL-TFCM-f surpass many existing clustering methods in texture image segmentation; and 4) In the case of different cluster numbers between the source and target domains, KL-TFCM-f proves higher clustering effectiveness and segmentation performance than does KL-TFCM-c.

Cross-domain, soft-partition clustering with diversity measure and knowledge reference.

Conventional, soft-partition clustering approaches, such as fuzzy c-means (FCM), maximum entropy clustering (MEC) and fuzzy clustering by quadratic regularization (FC-QR), are usually incompetent in those situations where the data are quite insufficient or much polluted by underlying noise or outliers. In order to address this challenge, the quadratic weights and Gini-Simpson diversity based fuzzy clustering model (QWGSD-FC), is first proposed as a basis of our work. Based on QWGSD-FC and inspired by transfer learning, two types of cross-domain, soft-partition clustering frameworks and their corresponding algorithms, referred to as type-I/type-II knowledge-transfer-oriented c-means (TI-KT-CM and TII-KT-CM), are subsequently presented, respectively. The primary contributions of our work are four-fold: (1) The delicate QWGSD-FC model inherits the most merits of FCM, MEC and FC-QR. With the weight factors in the form of quadratic memberships, similar to FCM, it can more effectively calculate the total intra-cluster deviation than the linear form recruited in MEC and FC-QR. Meanwhile, via Gini-Simpson diversity index, like Shannon entropy in MEC, and equivalent to the quadratic regularization in FC-QR, QWGSD-FC is prone to achieving the unbiased probability assignments, (2) owing to the reference knowledge from the source domain, both TI-KT-CM and TII-KT-CM demonstrate high clustering effectiveness as well as strong parameter robustness in the target domain, (3) TI-KT-CM refers merely to the historical cluster centroids, whereas TII-KT-CM simultaneously uses the historical cluster centroids and their associated fuzzy memberships as the reference. This indicates that TII-KT-CM features more comprehensive knowledge learning capability than TI-KT-CM and TII-KT-CM consequently exhibits more perfect cross-domain clustering performance and (4) neither the historical cluster centroids nor the historical cluster centroid based fuzzy memberships involved in TI-KT-CM or TII-KT-CM can be inversely mapped into the raw data. This means that both TI-KT-CM and TII-KT-CM can work without disclosing the original data in the source domain, i.e. they are of good privacy protection for the source domain. In addition, the convergence analyses regarding both TI-KT-CM and TII-KT-CM are conducted in our research. The experimental studies thoroughly evaluated and demonstrated our contributions on both synthetic and real-life data scenarios.

Generation of brain pseudo-CTs using an undersampled, single-acquisition UTE-mDixon pulse sequence and unsupervised clustering.

PURPOSE: MR-based pseudo-CT has an important role in MR-based radiation therapy planning and PET attenuation correction. The purpose of this study is to establish a clinically feasible approach, including image acquisition, correction, and CT formation, for pseudo-CT generation of the brain using a single-acquisition, undersampled ultrashort echo time (UTE)-mDixon pulse sequence. METHODS: Nine patients were recruited for this study. For each patient, a 190-s, undersampled, single acquisition UTE-mDixon sequence of the brain was acquired (TE = 0.1, 1.5, and 2.8 ms). A novel method of retrospective trajectory correction of the free induction decay (FID) signal was performed based on point-spread functions of three external MR markers. Two-point Dixon images were reconstructed using the first and second echo data (TE = 1.5 and 2.8 ms). R2(∗) images (1/T2(∗)) were then estimated and were used to provide bone information. Three image features, i.e., Dixon-fat, Dixon-water, and R2(∗), were used for unsupervised clustering. Five tissue clusters, i.e., air, brain, fat, fluid, and bone, were estimated using the fuzzy c-means (FCM) algorithm. A two-step, automatic tissue-assignment approach was proposed and designed according to the prior information of the given feature space. Pseudo-CTs were generated by a voxelwise linear combination of the membership functions of the FCM. A low-dose CT was acquired for each patient and was used as the gold standard for comparison. RESULTS: The contrast and sharpness of the FID images were improved after trajectory correction was applied. The mean of the estimated trajectory delay was 0.774 µs (max: 1.350 µs; min: 0.180 µs). The FCM-estimated centroids of different tissue types showed a distinguishable pattern for different tissues, and significant differences were found between the centroid locations of different tissue types. Pseudo-CT can provide additional skull detail and has low bias and absolute error of estimated CT numbers of voxels (-22 ± 29 HU and 130 ± 16 HU) when compared to low-dose CT. CONCLUSIONS: The MR features generated by the proposed acquisition, correction, and processing methods may provide representative clustering information and could thus be used for clinical pseudo-CT generation.

Image Quality and Diagnostic Performance of a Digital PET Prototype in Patients with Oncologic Diseases: Initial Experience and Comparison with Analog PET.

UNLABELLED: We report our initial clinical experience for image quality and diagnostic performance of a digital PET prototype scanner with time-of-flight (DigitalTF), compared with an analog PET scanner with time-of-flight (GeminiTF PET/CT). METHODS: Twenty-one oncologic patients, mean age 58 y, first underwent clinical (18)F-FDG PET/CT on the GeminiTF. The scanner table was then withdrawn while the patient remained on the table, and the DigitalTF was inserted between the GeminiTF PET and CT scanner. The patients were scanned for a second time using the same PET field of view with CT from the GeminiTF for attenuation correction. Two interpreters reviewed the 2 sets of PET/CT images for overall image quality, lesion conspicuity, and sharpness. They counted the number of suggestive (18)F-FDG-avid lesions and provided the TNM staging for the 5 patients referred for initial staging. Standardized uptake values (SUVs) and SUV gradients as a measure of lesion sharpness were obtained. RESULTS: The DigitalTF showed better image quality than the GeminiTF. In a side-by-side comparison using a 5-point scale, lesion conspicuity (4.3 ± 0.6), lesion sharpness (4.3 ± 0.6), and diagnostic confidence (3.4 ± 0.7) were better with DigitalTF than with GeminiTF (P < 0.01). In 52 representative lesions, the lesion maximum SUV was 36% higher with DigitalTF than with GeminiTF, lesion-to-blood-pool SUV ratio was 59% higher, and SUV gradient was 51% higher, with good correlation between the 2 scanners. Lesions less than 1.5 cm showed a greater increase in SUV from GeminiTF to DigitalTF than those lesions 1.5 cm or greater. In 5 of 21 patients, DigitalTF showed an additional 8 suggestive lesions that were not seen using GeminiTF. In the 15 restaging patients, the true-negative rate was 100% and true-positive rate was 78% for both scanners. In the 5 patients for initial staging, DigitalTF led to upstaging in 2 patients and showed the same staging in the other 3 patients, compared with GeminiTF. CONCLUSION: DigitalTF provides better image quality, diagnostic confidence, and accuracy than GeminiTF. DigitalTF may be the most beneficial in detecting small tumor lesions and disease staging.

k-space sampling optimization for ultrashort TE imaging of cortical bone: applications in radiation therapy planning and MR-based PET attenuation correction.

PURPOSE: The ultrashort echo-time (UTE) sequence is a promising MR pulse sequence for imaging cortical bone which is otherwise difficult to image using conventional MR sequences and also poses strong attenuation for photons in radiation therapy and PET imaging. The authors report here a systematic characterization of cortical bone signal decay and a scanning time optimization strategy for the UTE sequence through k-space undersampling, which can result in up to a 75% reduction in acquisition time. Using the undersampled UTE imaging sequence, the authors also attempted to quantitatively investigate the MR properties of cortical bone in healthy volunteers, thus demonstrating the feasibility of using such a technique for generating bone-enhanced images which can be used for radiation therapy planning and attenuation correction with PET/MR. METHODS: An angularly undersampled, radially encoded UTE sequence was used for scanning the brains of healthy volunteers. Quantitative MR characterization of tissue properties, including water fraction and R2(∗) = 1/T2(∗), was performed by analyzing the UTE images acquired at multiple echo times. The impact of different sampling rates was evaluated through systematic comparison of the MR image quality, bone-enhanced image quality, image noise, water fraction, and R2(∗) of cortical bone. RESULTS: A reduced angular sampling rate of the UTE trajectory achieves acquisition durations in proportion to the sampling rate and in as short as 25% of the time required for full sampling using a standard Cartesian acquisition, while preserving unique MR contrast within the skull at the cost of a minimal increase in noise level. The R2(∗) of human skull was measured as 0.2-0.3 ms(-1) depending on the specific region, which is more than ten times greater than the R2(∗) of soft tissue. The water fraction in human skull was measured to be 60%-80%, which is significantly less than the >90% water fraction in brain. High-quality, bone-enhanced images can be generated using a reduced sampled UTE sequence with no visible compromise in image quality and they preserved bone-to-air contrast with as low as a 25% sampling rate. CONCLUSIONS: This UTE strategy with angular undersampling preserves the image quality and contrast of cortical bone, while reducing the total scanning time by as much as 75%. The quantitative results of R2(∗) and the water fraction of skull based on Dixon analysis of UTE images acquired at multiple echo times provide guidance for the clinical adoption and further parameter optimization of the UTE sequence when used for radiation therapy and MR-based PET attenuation correction.

Performance evaluation of the Ingenuity TF PET/CT scanner with a focus on high count-rate conditions.

This study evaluated the positron emission tomography (PET) imaging performance of the Ingenuity TF 128 PET/computed tomography (CT) scanner which has a PET component that was designed to support a wider radioactivity range than is possible with those of Gemini TF PET/CT and Ingenuity TF PET/MR. Spatial resolution, sensitivity, count rate characteristics and image quality were evaluated according to the NEMA NU 2-2007 standard and ACR phantom accreditation procedures; these were supplemented by additional measurements intended to characterize the system under conditions that would be encountered during quantitative cardiac imaging with (82)Rb. Image quality was evaluated using a hot spheres phantom, and various contrast recovery and noise measurements were made from replicated images. Timing and energy resolution, dead time, and the linearity of the image activity concentration, were all measured over a wide range of count rates. Spatial resolution (4.8-5.1 mm FWHM), sensitivity (7.3 cps kBq(-1)), peak noise-equivalent count rate (124 kcps), and peak trues rate (365 kcps) were similar to those of the Gemini TF PET/CT. Contrast recovery was higher with a 2 mm, body-detail reconstruction than with a 4 mm, body reconstruction, although the precision was reduced. The noise equivalent count rate peak was broad (within 10% of peak from 241-609 MBq). The activity measured in phantom images was within 10% of the true activity for count rates up to those observed in (82)Rb cardiac PET studies.

Dexamethasone-induced insulin resistance: kinetic modeling using novel PET radiopharmaceutical 6-deoxy-6-[(18)F]fluoro-D-glucose.

PURPOSE: An insulin-resistant rat model, induced by dexamethasone, was used to evaluate a Michaelis-Menten-based kinetic model using 6-deoxy-6-[(18)F]fluoro-D-glucose (6-[(18)F]FDG) to quantify glucose transport with PET. PROCEDURES: Seventeen, male, Sprague-Dawley rats were studied in three groups: control (Ctrl), control + insulin (Ctrl + I), and dexamethasone + insulin (Dex + I). PET scans were acquired for 2 h under euglycemic conditions in the Ctrl group and under hyperinsulinemic-euglycemic conditions in the Ctrl + I and Dex + I groups. RESULTS: Glucose transport, assessed according to the 6-[(18)F]FDG concentration, was highest in skeletal muscle in the Ctrl + I, intermediate in the Dex + I, and lowest in the Ctrl group, while that in the brain was similar among the groups. Modeling analysis applied to the skeletal muscle uptake curves yielded values of parameters related to glucose transport that were greatest in the Ctrl + I group and increased to a lesser degree in the Dex + I group, compared to the Ctrl group. CONCLUSION: 6-[(18)F]FDG and the Michaelis-Menten-based model can be used to measure insulin-stimulated glucose transport under basal and an insulin resistant state in vivo.