Dental imaging in clinical photon-counting CT at a quarter of DVT dose.

OBJECTIVE: To investigate the image quality of a low-dose dental imaging protocol in the first clinical photon-counting computed tomography (PCCT) system in comparison to a normal-dose acquisition in a digital volume tomography (DVT) system. MATERIALS AND METHODS: Clinical PCCT systems offer an increased spatial resolution compared to previous generations of clinical systems. Their spatial resolution is in the order of dental DVT systems. Resolution-matched acquisitions of ten porcine jaws were performed in a PCCT (Naeotom Alpha, Siemens Healthineers) and in a DVT (Orthophos XL, Dentsply Sirona). PCCT images were acquired with 90 kV at a dose of 1 mGy CTDI16 cm. DVT used 85 kV at 4 mGy. Image reconstruction was performed using the standard algorithms of each system to a voxel size of 160 × 160 × 200 µm. The dose-normalized contrast-to-noise ratio (CNRD) was measured between dentine and enamel and dentine and bone. Two readers evaluated overall diagnostic quality of images and quality of relevant structures such as root channels and dentine. RESULTS: CNRD is higher in all PCCT acquisitions. CNRD is 37 % higher for the contrast dentine-enamel and 31 % higher for the dentine-bone contrast (p < 0.05). Overall diagnostic image quality was higher for PCCT over DVT (p < 0.02 and p < 0.04 for readers 1 and 2). Quality scores for anatomical structures were higher in PCCT compared to DVT (all p < 0.05). Inter- and intrareader reproducibility were acceptable (all ICC>0.64). CONCLUSIONS: PCCT provides an increased image quality over DVT even at a lower dose level and might enable complex dental imaging protocols in the future. CLINICAL SIGNIFICANCE: The evolution of photon-counting technology and it's optimization will increasingly move dental imaging towards standardized 3D visualizations providing both minimal radiation exposure and high diagnostic accuracy.

Reducing windmill artifacts in clinical spiral CT using a deep learning-based projection raw data upsampling: Method and robustness evaluation.

BACKGROUND: Multislice spiral computed tomography (MSCT) requires an interpolation between adjacent detector rows during backprojection. Not satisfying the Nyquist sampling condition along the z-axis results in aliasing effects, also known as windmill artifacts. These image distortions are characterized by bright streaks diverging from high contrast structures. PURPOSE: The z-flying focal spot (zFFS) is a well-established hardware-based solution that aims to double the sampling rate in longitudinal direction and therefore reduce aliasing artifacts. However, given the technical complexity of the zFFS, this work proposes a deep learning-based approach as an alternative solution. METHODS: We propose a supervised learning approach to perform a mapping between input projections and the corresponding rows required for double sampling in the z-direction. We present a comprehensive evaluation using both a clinical dataset obtained using raw data from 40 real patient scans acquired with zFFS and a synthetic dataset consisting of 100 simulated spiral scans using a phantom specifically designed for our problem. For the clinical dataset, we utilized 32 scans as training set and 8 scans as validation set, whereas for the synthetic dataset, we used 80 scans for training and 20 scans for validation purposes. Both qualitative and quantitative assessments are conducted on a test set consisting of nine real patient scans and six phantom measurements to validate the performance of our approach. A simulation study was performed to investigate the robustness against different scan configurations in terms of detector collimation and pitch value. RESULTS: In the quantitative comparison based on clinical patient scans from the test set, all network configurations show an improvement in the root mean square error (RMSE) of approximately 20% compared to neglecting the doubled longitudinal sampling by the zFFS. The results of the qualitative analysis indicate that both clinical and synthetic training data can reduce windmill artifacts through the application of a correspondingly trained network. Together with the qualitative results from the test set phantom measurements it is emphasized that a training of our method with synthetic data resulted in superior performance in windmill artifact reduction. CONCLUSIONS: Deep learning-based raw data interpolation has the potential to enhance the sampling in z-direction and thus minimize aliasing effects, as it is the case with the zFFS. Especially a training with synthetic data showed promising results. While it may not outperform zFFS, our method represents a beneficial solution for CT scanners lacking the necessary hardware components for zFFS.

Raw data consistent deep learning-based field of view extension for dual-source dual-energy CT.

BACKGROUND: Due to technical constraints, dual-source dual-energy CT scans may lack spectral information in the periphery of the patient. PURPOSE: Here, we propose a deep learning-based iterative reconstruction to recover the missing spectral information outside the field of measurement (FOM) of the second source-detector pair. METHODS: In today's Siemens dual-source CT systems, one source-detector pair (referred to as A) typically has a FOM of about 50 cm, while the FOM of the other pair (referred to as B) is limited by technical constraints to a diameter of about 35 cm. As a result, dual-energy applications are currently only available within the small FOM, limiting their use for larger patients. To derive a reconstruction at B's energy for the entire patient cross-section, we propose a deep learning-based iterative reconstruction. Starting with A's reconstruction as initial estimate, it employs a neural network in each iteration to refine the current estimate according to a raw data fidelity measure. Here, the corresponding mapping is trained using simulated chest, abdomen, and pelvis scans based on a data set containing 70 full body CT scans. Finally, the proposed approach is tested on simulated and measured dual-source dual-energy scans and compared against existing reference approaches. RESULTS: For all test cases, the proposed approach was able to provide artifact-free CT reconstructions of B for the entire patient cross-section. Considering simulated data, the remaining error of the reconstructions is between 10 and 17 HU on average, which is about half as low as the reference approaches. A similar performance with an average error of 8 HU could be achieved for real phantom measurements. CONCLUSIONS: The proposed approach is able to recover missing dual-energy information for patients exceeding the small 35 cm FOM of dual-source CT systems. Therefore, it potentially allows to extend dual-energy applications to the entire-patient cross section.

Potential radiation dose reduction in clinical photon-counting CT by the small pixel effect: ultra-high resolution (UHR) acquisitions reconstructed to standard resolution.

OBJECTIVE: To assess the potential dose reduction achievable with clinical photon-counting CT (PCCT) in ultra-high resolution (UHR) mode compared to acquisitions using the standard resolution detector mode (Std). MATERIALS AND METHODS: With smaller detector pixels, PCCT achieves far higher spatial resolution than energy-integrating (EI) CT systems. The reconstruction of UHR acquisitions to the lower spatial resolution of conventional systems results in an image noise and radiation dose reduction. We quantify this small pixel effect in measurements of semi-anthropomorphic abdominal phantoms of different sizes as well as in a porcine knuckle in the first clinical PCCT system by using the UHR mode (0.2 mm pixel size at isocenter) in comparison to the standard resolution mode (0.4 mm). At different slice thicknesses (0.4 up to 4 mm) and dose levels between 4 and 12 mGy, reconstructions using filtered backprojection were performed to the same target spatial resolution, i.e., same modulation transfer function, using both detector modes. Image noise and the resulting potential dose reduction was quantified as a figure of merit. RESULTS: Images acquired using the UHR mode yield lower noise in comparison to acquisitions using standard pixels at the same resolution and noise level. This holds for sharper convolution kernels at the spatial resolution limit of the standard mode, e.g., up to a factor 3.2 in noise reduction and a resulting potential dose reduction of up to almost 90%. CONCLUSION: Using sharper convolution kernels, UHR acquisitions allow for a significant dose reduction compared to acquisitions using the standard detector mode. CLINICAL RELEVANCE: Acquisitions should always be performed using the ultra-high resolution detector mode, if possible, to benefit from the intrinsic noise and dose reduction. KEY POINTS: • Ionizing radiation used in computed tomography examinations is a concern to public health. • The ultra-high resolution of novel photon-counting systems can be invested towards a noise and dose reduction if only a spatial resolution below the resolution limit of the detector is desired. • Acquisitions should always be performed in ultra-high resolution mode, if possible, to benefit from an intrinsic dose reduction.

Towards real-time EPID-based 3D in vivo dosimetry for IMRT with Deep Neural Networks: A feasibility study.

We investigate the potential of the Deep Dose Estimate (DDE) neural network to predict 3D dose distributions inside patients with Monte Carlo (MC) accuracy, based on transmitted EPID signals and patient CTs. The network was trained using as input patient CTs and first-order dose approximations (FOD). Accurate dose distributions (ADD) simulated with MC were given as training targets. 83 pelvic CTs were used to simulate ADDs and respective EPID signals for subfields of prostate IMRT plans (gantry at 0∘). FODs were produced as backprojections from the EPID signals. 581 ADD-FOD sets were produced and divided into training and test sets. An additional dataset simulated with gantry at 90∘ (lateral set) was used for evaluating the performance of the DDE at different beam directions. The quality of the FODs and DDE-predicted dose distributions (DDEP) with respect to ADDs, from the test and lateral sets, was evaluated with gamma analysis (3%,2 mm). The passing rates between FODs and ADDs were as low as 46%, while for DDEPs the passing rates were above 97% for the test set. Meaningful improvements were also observed for the lateral set. The high passing rates for DDEPs indicate that the DDE is able to convert FODs into ADDs. Moreover, the trained DDE predicts the dose inside a patient CT within 0.6 s/subfield (GPU), in contrast to 14 h needed for MC (CPU-cluster). 3D in vivo dose distributions due to clinical patient irradiation can be obtained within seconds, with MC-like accuracy, potentially paving the way towards real-time EPID-based in vivo dosimetry.

Dental imaging using an ultra-high resolution photon-counting CT system.

Clinical photon-counting CT (PCCT) offers a spatial resolution of about 200 µm and might allow for acquisitions close to conventional dental CBCTs. In this study, the capabilities of this new system in comparison to dental CBCTs shall be evaluated. All 8 apical osteolysis identified in CBCT were identified by both readers in all three PCCT scan protocols. Mean visibility scores showed statistical significant differences for root canals(p = 0.0001), periodontal space(p = 0.0090), cortical(p = 0.0003) and spongious bone(p = 0.0293) in favor of high and medium dose PCCT acquisitions. Overall, both devices showed excellent image quality of all structures assessed. Interrater-agreement showed high values for all protocols in all structures. Bland-Altman plots revealed a high concordance of both modalities with the reference measurements. In vitro, ultra-high resolution PCCT can reliably identify different diagnostic entities and structures relevant for dental diagnostics similar to conventional dental CBCT with similar radiation dose. Acquisitions of five cadaveric heads were performed in an experimental CT-system containing an ultra-high resolution PC detector (0.25 mm pixel size in isocenter) as well as in a dental CBCT scanner. Acquisitions were performed using dose levels of 8.5 mGy, 38.0 mGy and 66.5 mGy (CTDI16cm) in case of PCCT and of 8.94 mGy (CTDI16cm) in case of CBCT. The quality of delineation of hard tissues, root-canals, periodontal-space as well as apical osteolysis was assessed by two readers. Mean visibility scores and interrater-agreement (overall agreement (%)) were calculated. Vertical bone loss (bl) and thickness (bt) of the buccal bone lamina of 15 lower incisors were measured and compared to reference measurements by ore microscopy and clinical probing.

Dose-efficient assessment of trabecular microstructure using ultra-high-resolution photon-counting CT.

Photon-counting (PC) detectors for clinical computed tomography (CT) may offer improved imaging capabilities compared to conventional energy-integrating (EI) detectors, e.g. superior spatial resolution and detective efficiency. We here investigate if PCCT can reduce the administered dose in examinations aimed at quantifying trabecular bone microstructure. Five human vertebral bodies were scanned three times in an abdomen phantom (QRM, Germany) using an experimental dual-source CT (Somatom CounT, Siemens Healthineers, Germany) housing an EI detector (0.60 mm pixel size at the iso-center) and a PC detector (0.25 mm pixel size). A tube voltage of 120 kV was used. Tube current-time product for EICT was 355 mAs (23.8 mGy CTDI32 cm). Dose-matched UHR-PCCT (UHRdm, 23.8 mGy) and noise-matched acquisitions (UHRnm, 10.5 mGy) were performed and reconstructed to a voxel size of 0.156 mm using a sharp kernel. Measurements of bone mineral density (BMD) and trabecular separation (Tb.Sp) and Tb.Sp percentiles reflecting the different scales of the trabecular interspacing were performed and compared to a gold-standard measurement using a peripheral CT device (XtremeCT, SCANCO Medical, Switzerland) with an isotropic voxel size of 0.082 mm and 6.6 mGy CTDI10 cm. The image noise was quantified and the relative error with respect to the gold-standard along with the agreement between CT protocols using Lin's concordance correlation coefficient (rCCC) were calculated. The Mean ±â€¯StdDev of the measured image noise levels in EICT was 109.6 ±â€¯3.9 HU. UHRdm acquisitions (same dose as EICT) showed a significantly lower noise level of 78.6 ±â€¯4.6 HU (p = 0.0122). UHRnm (44% dose of EICT) showed a noise level of 115.8 ±â€¯3.7 HU, very similar to EICT at the same spatial resolution. For BMD the overall Mean ±â€¯StdDev for EI, UHRdm and UHRnm were 114.8 ±â€¯28.6 mgHA/cm3, 121.6 ±â€¯28.8 mgHA/cm3 and 121.5 ±â€¯28.6 mgHA/cm3, respectively, compared to 123.1 ±â€¯25.5 mgHA/cm3 for XtremeCT. For Tb.Sp these values were 1.86 ±â€¯0.54 mm, 1.80 ±â€¯0.56 mm and 1.84 ±â€¯0.52 mm, respectively, compared to 1.66 ±â€¯0.48 mm for XtremeCT. The ranking of the vertebrae with regard to Tb.Sp data was maintained throughout all Tb.Sp percentiles and among the CT protocols and the gold-standard. The agreement between protocols was very good for all comparisons: UHRnm vs. EICT (BMD rCCC = 0.97; Tb.Sp rCCC = 0.998), UHRnm vs. UHRdm (BMD rCCC = 0.998; Tb.Sp rCCC = 0.993) and UHRdm vs. EICT (BMD rCCC = 0.97; Tb.Sp rCCC = 0.991). Consequently, the relative RMS-errors from linear regressions against the gold-standard for EICT, UHRdm and UHRnm were very similar for BMD (7.1%, 5.2% and 5.4%) and for Tb.Sp (3.3%, 3.3% and 2.9%), with a much lower radiation dose for UHRnm. Short-term reproducibility for BMD measurements was similar and below 0.2% for all protocols, but for Tb.Sp showed better results for UHR (about 1/3 of the level for EICT). In conclusion, CT with UHR-PC detectors demonstrated lower image noise and better reproducibility for assessments of bone microstructure at similar dose levels. For UHRnm, radiation exposure levels could be reduced by 56% without deterioration of performance levels in the assessment of bone mineral density and bone microstructure.

Empirical scatter correction: CBCT scatter artifact reduction without prior information.

BACKGROUND: The image quality of cone beam CT (CBCT) scans severely suffers from scattered radiation if no countermeasures are taken. Scatter artifacts may induce cupping and streak artifacts and lead to a reduced image contrast and wrong CT values of the reconstructed volumes. Established software-based approaches for a correction of scattered radiation typically rely on prior knowledge of the CT system, scan parameters, the scanned object, or all of the aforementioned. PURPOSE: This study proposes a simple and effective postprocessing software-based correction method of scatter artifacts in CBCT scans without specific prior knowledge. METHODS: We propose the empirical scatter correction (ESC), which generates scatter-like basis images from each projection image by convolution operations. A linear combination of these basis images is subtracted from the original projection image. The logarithm is taken and an FDK reconstruction is performed. The coefficients needed for the linear combination are determined automatically by a downhill simplex algorithm such that the resulting reconstructed images show no scatter artifacts. We demonstrate the potential of ESC by correcting simulated volumes with Monte Carlo scatter artifacts, a head phantom scan performed on our table-top CBCT, and a pelvis scan from a Varian Edge CBCT scanner. RESULTS: ESC is able to improve the image quality of CBCT scans, which is shown on the basis of our simulations and on measured data. For a simulated head CT, the CT value difference to the scatter-free reference image was as low as -6 HU after using ESC, whereas the uncorrected data deviated by more than -200 HU from the reference data. Simulations of thorax and abdomen CT scans show that although scatter artifacts are not fully removed, anatomical features which were hard to discover prior to the correction become clearly visible and better segmentable with ESC. Similar results are obtained in the phantom measurement, where a comparison to a slit scan of our head phantom shows only small differences. The CT values in soft tissue are improved in this measurement, as well. In soft tissue areas with severe scatter artifacts, the CT values agree well with those of the slit scan (difference to slit scan: 35 HU corrected and -289 HU uncorrected). Scatter artifacts in measured patient data can also be reduced using the proposed ESC. The results are comparable to those achieved with designated correction algorithms installed on the Varian Edge CBCT system. CONCLUSIONS: ESC allows to reduce artifacts caused by patient scatter solely based on the projection data.

Patient-specific radiation risk-based tube current modulation for diagnostic CT.

PURPOSE: Modern CT scanners use automatic exposure control (AEC) techniques, such as tube current modulation (TCM), to reduce dose delivered to patients while maintaining image quality. In contrast to conventional approaches that minimize the tube current time product of the CT scan, referred to as mAsTCM in the following, we herein propose a new method referred to as riskTCM, which aims at reducing the radiation risk to the patient by taking into account the specific radiation risk of every dose-sensitive organ. METHODS: For current mAsTCM implementations, the mAs product is used as a surrogate for the patient dose. Thus, they do not take into account the varying dose sensitivity of different organs. Our riskTCM framework assumes that a coarse CT reconstruction, an organ segmentation, and an estimation of the dose distribution can be provided in real time, for example, by applying machine learning techniques. Using this information, riskTCM determines a tube current curve that minimizes a patient risk measure, for example, the effective dose, while keeping the image quality constant. We retrospectively applied riskTCM to 20 patients covering all relevant anatomical regions and tube voltages from 70 to 150 kV. The potential reduction of effective dose at same image noise is evaluated as a figure of merit and compared to mAsTCM and to a situation with a constant tube current referred to as noTCM. RESULTS: Anatomical regions like the neck, thorax, abdomen, and the pelvis benefit from the proposed riskTCM. On average, a reduction of effective dose of about 23% for the thorax, 31% for the abdomen, 24% for the pelvis, and 27% for the neck has been evaluated compared to today's state-of-the-art mAsTCM. For the head, the resulting reduction of effective dose is lower, about 13% on average compared to mAsTCM. CONCLUSIONS: With a risk-minimizing TCM, significant higher reduction of effective dose compared to mAs-minimizing TCM is possible.

Real-time estimation of patient-specific dose distributions for medical CT using the deep dose estimation.

PURPOSE: With the rising number of computed tomography (CT) examinations and the trend toward personalized medicine, patient-specific dose estimates are becoming more and more important in CT imaging. However, current approaches are often too slow or too inaccurate to be applied routinely. Therefore, we propose the so-called deep dose estimation (DDE) to provide highly accurate patient dose distributions in real time METHODS: To combine accuracy and computational performance, the DDE algorithm uses a deep convolutional neural network to predict patient dose distributions. To do so, a U-net like architecture is trained to reproduce Monte Carlo simulations from a two-channel input consisting of a CT reconstruction and a first-order dose estimate. Here, the corresponding training data were generated using CT simulations based on 45 whole-body patient scans. For each patient, simulations were performed for different anatomies (pelvis, abdomen, thorax, head), different tube voltages (80 kV, 100 kV, 120 kV), different scan trajectories (circle, spiral), and with and without bowtie filtration and tube current modulation. Similar simulations were performed using a second set of eight whole-body CT scans from the Visual Concept Extraction Challenge in Radiology (Visceral) project to generate testing data. Finally, the DDE algorithm was evaluated with respect to the generalization to different scan parameters and the accuracy of organ dose and effective dose estimates based on an external organ segmentation. RESULTS: DDE dose distributions were quantified in terms of the mean absolute percentage error (MAPE) and a gamma analysis with respect to the ground truth Monte Carlo simulation. Both measures indicate that DDE generalizes well to different scan parameters and different anatomical regions with a maximum MAPE of 6.3% and a minimum gamma passing rate of 91%. Evaluating the organ dose values for all organs listed in the International Commission on Radiological Protection (ICRP) recommendation, shows an average error of 3.1% and maximum error of 7.2% (bone surface). CONCLUSIONS: The DDE algorithm provides an efficient approach to determine highly accurate dose distributions. Being able to process a whole-body CT scan in about 1.5 s, it provides a valuable alternative to Monte Carlo simulations on a graphics processing unit (GPU). Here, the main advantage of DDE is that it can be used on top of any existing Monte Carlo code such that real-time performance can be achieved without major adjustments. Thus, DDE opens up new options not only for dosimetry but also for scan and protocol optimization.

Motion compensation for aortic valves using partial angle CT reconstructions.

PURPOSE: A motion compensation method that is aimed at correcting motion artifacts of cardiac valves is proposed. The primary focus is the aortic valve. METHODS: The method is based around partial angle reconstructions and a cost function including the image entropy. A motion model is applied to approximate the cardiac motion in the temporal and spatial domain. Based on characteristic values for velocities and strain during cardiac motion, penalties for the velocity and spatial derivatives are introduced to maintain anatomically realistic motion vector fields and avoid distortions. The model addresses global elastic deformation, but not the finer and more complicated motion of the valve leaflets. RESULTS: The method is verified based on clinical data. Image quality was improved for most artifact-impaired reconstructions. An image quality study with Likert scoring of the motion artifact severity on a scale from 1 (highest image quality) to 5 (lowest image quality/extreme artifact presence) was performed. The biggest improvements after applying motion compensation were achieved for strongly artifact-impaired initial images scoring 4 and 5, resulting in an average change of the scores by - 0.59 ± 0.06 $-0.59\pm 0.06$ and - 1.33 ± 0.03 $-1.33\pm 0.03$ , respectively. In the case of artifact-free images, a chance to introduce blurring was observed and their average score was raised by 0.42 ± 0.03. CONCLUSION: Motion artifacts were consistently removed and image quality improved.

Dose reduction potential in diagnostic single energy CT through patient-specific prefilters and a wider range of tube voltages.

PURPOSE: Various studies have demonstrated that additional prefilters and/or reduced tube voltages have the potential to significantly increase the contrast-to-noise ratios at unit dose (CNRDs) and thereby to significantly reduce patient dose in clinical CT. An exhaustive analysis, accounting for a wide range of filter thicknesses and a wide range of tube voltages extending beyond the 70 to 150 kV range of today's CT systems, including their specific choice depending on the patient size, is, however, missing. Therefore, this work analyzes the dose reduction potential for patient-specific selectable prefilters combined with a wider range of tube voltages. We do so for soft tissue and iodine contrast in single energy CT. The findings may be helpful to guide further developments of x-ray tubes and automatic filter changers. METHODS: CT acquisitions were simulated for different patient sizes (semianthropomorphic phantoms for child, adult, and obese patients), tube voltages (35-150 kV), prefilter materials (tin and copper), and prefilter thicknesses (up to 5 mm). For each acquisition soft tissue and iodine CNRDs were determined. Dose was calculated using Monte Carlo simulations of a computed tomography dose index (CTDI) phantom. CNRD values of acquisitions with different parameters were used to evaluate dose reduction. RESULTS: Dose reduction through patient-specific prefilters depends on patient size and available tube current among others. With an available tube current time product of 1000 mAs dose reductions of 17% for the child, 32% for the adult and 29% for the obese phantom were achieved for soft tissue contrast. For iodine contrast dose reductions were 57%, 49%, and 39% for child, adult, and obese phantoms, respectively. Here, a tube voltage range extended to lower kV is important. CONCLUSIONS: Substantial dose reduction can be achieved by utilizing patient-specific prefilters. Tube voltages lower than 70 kV are beneficial for dose reduction with iodine contrast, especially for small patients. The optimal implementation of patient-specific prefilters benefits from higher tube power. Tin prefilters should be available in 0.1 mm steps or lower, copper prefilter in 0.3 mm steps or lower. At least 10 different prefilter thicknesses should be used to cover the dose optima of all investigated patient sizes and contrast mechanisms. In many cases it would be advantageous to adapt the prefilter thickness rather than the tube current to the patient size, that is, to always use the maximum available tube current and to control the exposure by adjusting the thickness of the prefilter.

Deep learning-based reconstruction of interventional tools and devices from four X-ray projections for tomographic interventional guidance.

PURPOSE: Image guidance for minimally invasive interventions is usually performed by acquiring fluoroscopic images using a monoplanar or a biplanar C-arm system. However, the projective data provide only limited information about the spatial structure and position of interventional tools and devices such as stents, guide wires, or coils. In this work, we propose a deep learning-based pipeline for real-time tomographic (four-dimensional [4D]) interventional guidance at conventional dose levels. METHODS: Our pipeline is comprised of two steps. In the first one, interventional tools are extracted from four cone-beam CT projections using a deep convolutional neural network. These projections are then Feldkamp reconstructed and fed into a second network, which is trained to segment the interventional tools and devices in this highly undersampled reconstruction. Both networks are trained using simulated CT data and evaluated on both simulated data and C-arm cone-beam CT measurements of stents, coils, and guide wires. RESULTS: The pipeline is capable of reconstructing interventional tools from only four X-ray projections without the need for a patient prior. At an isotropic voxel size of 100 µ m , our methods achieve a precision/recall within a 100 µ m environment of the ground truth of 93%/98%, 90%/71%, and 93%/76% for guide wires, stents, and coils, respectively. CONCLUSIONS: A deep learning-based approach for 4D interventional guidance is able to overcome the drawbacks of today's interventional guidance by providing full spatiotemporal (4D) information about the interventional tools at dose levels comparable to conventional fluoroscopy.

Deep learning-based forward and cross-scatter correction in dual-source CT.

PURPOSE: Dual-source computed tomography (DSCT) uses two source-detector pairs offset by about 90°. In addition to the well-known forward scatter, a special issue in DSCT is cross-scattered radiation from X-ray tube A detected in the detector of system B and vice versa. This effect can lead to artifacts and reduction of the contrast-to-noise ratio of the images. The purpose of this work is to present and evaluate different deep learning-based methods for scatter correction in DSCT. METHODS: We present different neural network-based methods for forward and cross-scatter correction in DSCT. These deep scatter estimation (DSE) methods mainly differ in the input and output information that is provided for training and inference and in whether they operate on two-dimensional (2D) or on three-dimensional (3D) data. The networks are trained and validated with scatter distributions obtained by our in-house Monte Carlo simulation. The simulated geometry is adapted to a realistic clinical setup. RESULTS: All DSE approaches reduce scatter-induced artifacts and lead to superior results than the measurement-based scatter correction. Forward scatter, under the presence of cross-scatter, is best estimated either by our network that uses the current projection and a couple of neighboring views (fDSE 2D few views) or by our 3D network that processes all projections simultaneously (fDSE 3D). Cross-scatter, under the presence of forward scatter, is best estimated using xSSE XDSE 2D, with xSSE referring to a quick single scatter estimate of cross scatter, or by xDSE 3D that uses all projections simultaneously. By using our proposed networks, the total scatter error in dual could be reduced from about 18 HU to approximately 3 HU. CONCLUSIONS: Deep learning-based scatter correction can reduce scatter artifacts in DSCT. To achieve more accurate cross-scatter estimations, the use of a cross-scatter approximation improves the results. Also, the ability to leverage across different projection angles improves the precision of the algorithm.

Deep learning-based coronary artery motion estimation and compensation for short-scan cardiac CT.

PURPOSE: During a typical cardiac short scan, the heart can move several millimeters. As a result, the corresponding CT reconstructions may be corrupted by motion artifacts. Especially the assessment of small structures, such as the coronary arteries, is potentially impaired by the presence of these artifacts. In order to estimate and compensate for coronary artery motion, this manuscript proposes the deep partial angle-based motion compensation (Deep PAMoCo). METHODS: The basic principle of the Deep PAMoCo relies on the concept of partial angle reconstructions (PARs), that is, it divides the short scan data into several consecutive angular segments and reconstructs them separately. Subsequently, the PARs are deformed according to a motion vector field (MVF) such that they represent the same motion state and summed up to obtain the final motion-compensated reconstruction. However, in contrast to prior work that is based on the same principle, the Deep PAMoCo estimates and applies the MVF via a deep neural network to increase the computational performance as well as the quality of the motion compensated reconstructions. RESULTS: Using simulated data, it could be demonstrated that the Deep PAMoCo is able to remove almost all motion artifacts independent of the contrast, the radius and the motion amplitude of the coronary artery. In any case, the average error of the CT values along the coronary artery is about 25 HU while errors of up to 300 HU can be observed if no correction is applied. Similar results were obtained for clinical cardiac CT scans where the Deep PAMoCo clearly outperforms state-of-the-art coronary artery motion compensation approaches in terms of processing time as well as accuracy. CONCLUSIONS: The Deep PAMoCo provides an efficient approach to increase the diagnostic value of cardiac CT scans even if they are highly corrupted by motion.

Toward molecular imaging using spectral photon-counting computed tomography?

Molecular imaging is a valuable tool in drug discovery and development, early screening and diagnosis of diseases, and therapy assessment among others. Although many different imaging modalities are in use today, molecular imaging with computed tomography (CT) is still challenging owing to its low sensitivity and soft tissue contrast compared with other modalities. Recent technical advances, particularly the introduction of spectral photon-counting detectors, might allow overcoming these challenges. Herein, the fundamentals and recent advances in CT relevant to molecular imaging are reviewed and potential future preclinical and clinical applications are highlighted. The review concludes with a discussion of potential future advancements of CT for molecular imaging.

Potential of contrast agents based on high-Z elements for contrast-enhanced photon-counting computed tomography.

PURPOSE: In clinics, only iodine- and barium-based contrast agents are currently used for contrast-enhanced x-ray computed tomography (CT). Recently, the introduction of new photon-counting (PC) detectors increased the interest in developing new contrast agents based on heavier elements. These elements may provide more contrast and spectral information compared to iodine and barium thanks to their k-edges at higher energies. In this paper, the potential of high-Z elements in contrast-enhanced CT was evaluated for different patient sizes and x-ray spectra using a PC detector. METHODS: An adult liver phantom with five high-Z element solutions (iodine, gadolinium, ytterbium, tungsten, and bismuth) was scanned with a whole-body photon-counting computed tomography (PCCT) prototype. For each element, the contrast-to-noise ratio at unit concentration and at unit dose (CNRCD) was evaluated in low threshold images ( T 0 = 20 keV ) as function of the tube voltage (80, 100, 120, and 140 kV) and in bin images (tube voltage = 120 kV) as function of the higher threshold ( T 0 = 20 keV and T 1 ∈ [ 50 , 90 ] keV ). Simulations were performed for validation with measurements and to investigate more elements (cerium and gold), different patient sizes (infant, adult, and obese), and spectrum filtration (with and without 0.4-mm tin filter). The dose reductions associated with the CNRCD improvements over iodine were quantified as well. RESULTS: CNRCD improvements and dose reductions depend on the investigated scenario. For the infant phantom, dose reductions around 30% were reached using cerium or gadolinium in combination with the tin filter. For the adult and obese phantom, reductions around 50% were provided by gadolinium or ytterbium in combination with the tin filter. Independently of the high-Z element, the CNRCD of two optimally combined bin images was higher than the CNRCD of the low threshold image. Good agreement was found between measurements and simulations. CONCLUSIONS: Between the investigated elements, gadolinium resulted to have the highest potential as novel contrast agent in PCCT, providing significant dose reductions for all patient sizes. Compared to the other elements, the implementation of gadolinium as CT contrast agent may be facilitated since it is already deployed as contrast agents for magnetic resonance imaging.

Coronary micro-computed tomography angiography in mice.

Coronary computed tomography angiography is an established technique in clinical practice and a valuable tool in the diagnosis of coronary artery disease in humans. Imaging of coronaries in preclinical research, i.e. in small animals, is very difficult due to the high demands on spatial and temporal resolution. Mice exhibit heart rates of up to 600 beats per minute motivating the need for highest detector framerates while the coronaries show diameters below 100 µm indicating the requirement for highest spatial resolution. We herein use a custom built micro-CT equipped with dedicated reconstruction algorithms to illustrate that coronary imaging in mice is possible. The scanner provides a spatial and temporal resolution sufficient for imaging of smallest, moving anatomical structures and the dedicated reconstruction algorithms reduced radiation dose to less than 1 Gy but do not yet allow for longitudinal studies. Imaging studies were performed in ten mice administered with a blood-pool contrast agent. Results show that the course of the left coronary artery can be visualized in all mice and all major branches can be identified for the first time using micro-CT. This reduces the gap in cardiac imaging between clinical practice and preclinical research.

Real-time scatter estimation for medical CT using the deep scatter estimation: Method and robustness analysis with respect to different anatomies, dose levels, tube voltages, and data truncation.

PURPOSE: X-ray scattering leads to CT images with a reduced contrast, inaccurate CT values as well as streak and cupping artifacts. Therefore, scatter correction is crucial to maintain the diagnostic value of CT and CBCT examinations. However, existing approaches are not able to combine both high accuracy and high computational performance. Therefore, we propose the deep scatter estimation (DSE): a deep convolutional neural network to derive highly accurate scatter estimates in real time. METHODS: Gold standard scatter estimation approaches rely on dedicated Monte Carlo (MC) photon transport codes. However, being computationally expensive, MC methods cannot be used routinely. To enable real-time scatter correction with similar accuracy, DSE uses a deep convolutional neural network that is trained to predict MC scatter estimates based on the acquired projection data. Here, the potential of DSE is demonstrated using simulations of CBCT head, thorax, and abdomen scans as well as measurements at an experimental table-top CBCT. Two conventional computationally efficient scatter estimation approaches were implemented as reference: a kernel-based scatter estimation (KSE) and the hybrid scatter estimation (HSE). RESULTS: The simulation study demonstrates that DSE generalizes well to varying tube voltages, varying noise levels as well as varying anatomical regions as long as they are appropriately represented within the training data. In any case the deviation of the scatter estimates from the ground truth MC scatter distribution is less than 1.8% while it is between 6.2% and 293.3% for HSE and between 11.2% and 20.5% for KSE. To evaluate the performance for real data, measurements of an anthropomorphic head phantom were performed. Errors were quantified by a comparison to a slit scan reconstruction. Here, the deviation is 278 HU (no correction), 123 HU (KSE), 65 HU (HSE), and 6 HU (DSE), respectively. CONCLUSIONS: The DSE clearly outperforms conventional scatter estimation approaches in terms of accuracy. DSE is nearly as accurate as Monte Carlo simulations but is superior in terms of speed (≈10 ms/projection) by orders of magnitude.

Technical Note: Intrinsic raw data-based CT misalignment correction without redundant data.

PURPOSE: CT image reconstruction requires accurate knowledge of the used geometry or image quality might be degraded by misalignment artifacts. To overcome this issue, an intrinsic method, that is, a method not requiring a dedicated calibration phantom, to perform a raw data-based misalignment correction for CT is proposed herein that does not require redundant data and hence is applicable to measurements with less than 180 ∘ plus fan-angle of data. METHODS: The forward projection of a volume reconstructed from a misaligned geometry resembles the acquired raw data if no redundant data are used, that is, if less than 180 ∘ plus fan-angle are used for image reconstruction. Hence, geometric parameters cannot be deduced from such data by an optimization of the geometry-dependent raw data fidelity. We propose to use a nonlinear transform applied to the reconstructed volume to introduce inconsistencies in the raw data that can be employed to estimate geometric parameters using less than 180 ∘ plus fan-angle of data. The proposed method is evaluated using simulations of the FORBILD head phantom and using actual measurements of a contrast-enhanced scan of a mouse acquired using a micro-CT. RESULTS: Noisy simulations and actual measurements demonstrate that the proposed method is capable of correcting for artifacts arising from a misaligned geometry without redundant data while ensuring raw data fidelity. CONCLUSIONS: The proposed method extends intrinsic raw data-based misalignment correction methods to an angular range of 180 ∘ or less and is thus applicable to systems with a limited scan range.