Improved noise reduction in photon-counting detector CT using prior knowledge-aware iterative denoising neural network.

Purpose: We aim to reduce image noise in high-resolution (HR) virtual monoenergetic images (VMIs) from photon-counting detector (PCD) CT scans by developing a prior knowledge-aware iterative denoising neural network (PKAID-Net) that efficiently exploits the unique noise characteristics of VMIs at different energy (keV) levels. Approach: PKAID-Net offers two major features: first, it utilizes a lower-noise VMI (e.g., 70 keV) as a prior input; second, it iteratively constructs a refined training dataset to improve the neural network's denoising performance. In each iteration, the denoised image from the previous module serves as an updated target image, which is included in the dataset for the subsequent training iteration. Our study includes 10 patient coronary CT angiography exams acquired on a clinical dual-source PCD-CT (NAEOTOM Alpha, Siemens Healthineers). The HR VMIs were reconstructed at 50, 70, and 100 keV, using a sharp vascular kernel (Bv68) and thin (0.6 mm) slice thickness (0.3 mm increment). PKAID-Net's performance was evaluated in terms of image noise, spatial detail preservation, and quantitative accuracy. Results: PKAID-Net achieved a noise reduction of 96% compared to filtered back projection and 65% relative to iterative reconstruction, all while preserving spatial and spectral fidelity and maintaining a natural noise texture. The iterative refinement of PCD-CT data during the training process substantially enhanced the robustness of deep learning-based denoising compared to the original method, which resulted in some spatial detail loss. Conclusions: The PKAID-Net provides substantial noise reduction while maintaining spatial and spectral fidelity of the HR VMIs from PCD-CT.

Learned high-resolution cardiac CT imaging from ultra-high-resolution PCD-CT.

Coronary computed tomography angiography (cCTA) is a widely used non-invasive diagnostic exam for patients with coronary artery disease (CAD). However, most clinical CT scanners are limited in spatial resolution from use of energy-integrating detectors (EIDs). Radiological evaluation of CAD is challenging, as coronary arteries are small (3-4 mm diameter) and calcifications within them are highly attenuating, leading to blooming artifacts. As such, this is a task well suited for high spatial resolution. Recently, photon-counting-detector (PCD) CT became commercially available, allowing for ultra-high resolution (UHR) data acquisition. However, PCD-CTs are costly, restricting widespread accessibility. To address this problem, we propose a super resolution convolutional neural network (CNN): ILUMENATE (Improved LUMEN visualization through Artificial super-resoluTion imagEs), creating a high resolution (HR) image simulating UHR PCD-CT. The network was trained and validated using patches extracted from 8 patients with a modified U-Net architecture. Training input and labels consisted of UHR PCD-CT images reconstructed with a smooth kernel degrading resolution (LR input) and sharp kernel (HR label). The network learned the resolution difference and was tested on 5 unseen LR patients. We evaluated network performance quantitatively and qualitatively through visual inspection, line profiles to assess spatial resolution improvements, ROIs for CT number stability and noise assessment, structural similarity index (SSIM), and percent diameter luminal stenosis. Overall, ILUMENATE improved images quantitatively and qualitatively, creating sharper edges more closely resembling reconstructed HR reference images, maintained stable CT numbers with less than 4% difference, reduced noise by 28%, maintained structural similarity (average SSIM = 0.70), and reduced percent diameter stenosis with respect to input images. ILUMENATE demonstrates potential impact for CAD patient management, improving the quality of LR CT images bringing them closer to UHR PCD-CT images.

Improving Stenosis Assessment in Energy Integrating Detector CT via Learned Monoenergetic Imaging Capability.

Coronary CT angiography (cCTA) is a fast non-invasive imaging exam for coronary artery disease (CAD) but struggles with dense calcifications and stents due to blooming artifacts, potentially causing stenosis overestimation. Virtual monoenergetic images (VMIs) at higher keV (e.g., 100 keV) from photon counting detector (PCD) CT have shown promise in reducing blooming artifacts and improving lumen visibility through its simultaneous high-resolution and multi-energy imaging capability. However, most cCTA exams are performed with single-energy CT (SECT) using conventional energy-integrating detectors (EID). Generating VMIs through EID-CT requires advanced multi-energy CT (MECT) scanners and potentially sacrifices temporal resolution. Given these limitations, MECT cCTA exams are not commonly performed on EID-CT and VMIs are not routinely generated. To tackle this, we aim to enhance the multi-energy imaging capability of EID-CT through the utilization of a convolutional neural network to LEarn MONoenergetic imAging from VMIs at Different Energies (LEMONADE). The neural network was trained using ten patient cCTA exams acquired on a clinical PCD-CT (NAEOTOM Alpha, Siemens Healthineers), with 70 keV VMIs as input (which is nominally equivalent to the SECT from EID-CT scanned at 120 kV) and 100 keV VMIs as the target. Subsequently, we evaluated the performance of EID-CT equipped with LEMONADE on both phantom and patient cases (n=10) for stenosis assessment. Results indicated that LEMONADE accurately quantified stenosis in three phantoms, aligning closely with ground truth and demonstrating stenosis percentage area reductions of 13%, 8%, and 9%. In patient cases, it led to a 12.9% reduction in average diameter luminal stenosis when compared to the original SECT without LEMONADE. These outcomes highlight LEMONADE's capacity to enable multi-energy CT imaging, mitigate blooming artifacts, and improve stenosis assessment for the widely available EID-CT. This has a high potential impact as most cCTA exams are performed on EID-CT.

Motion artifact correction in cardiac CT using cross-phase temporospatial information and synergistic attention gate and spatial transformer sub-networks.

Objectives.To improve quality of coronary CT angiography (CCTA) images using a generalizable motion-correction algorithm.Approach. A neural network with attention gate and spatial transformer (ATOM) was developed to correct coronary motion. Phantom and patient CCTA images (39 males, 32 females, age range 19-92, scan date 02/2020 to 10/2021) retrospectively collected from dual-source CT were used to create training, development, and testing sets corresponding to 140- and 75 ms temporal resolution, with 75 ms images as labels. To test generalizability, ATOM was deployed for locally adaptive motion-correction in both 140- and 75 ms patient images. Objective metrics were used to assess motion-corrupted and corrected phantom and patient images, including structural-similarity-index (SSIM), dice-similarity-coefficient (DSC), peak-signal-noise-ratio (PSNR), and normalized root-mean-square-error (NRMSE). In objective quality assessment, ATOM was compared with several baseline networks, including U-net, U-net plus attention gate, U-net plus spatial transformer, VDSR, and ResNet. Two cardiac radiologists independently interpreted motion-corrupted and -corrected images at 75 and 140 ms in a blinded fashion and ranked diagnostic image quality (worst to best: 1-4, no ties).Main results. ATOM improved quality metrics (p< 0.05) before/after correction: in phantom, SSIM 0.87/0.95, DSC 0.85/0.93, PSNR 19.4/22.5, NRMSE 0.38/0.27; in patient images, SSIM 0.82/0.88, DSC 0.88/0.90, PSNR 30.0/32.0, NRMSE 0.16/0.12. ATOM provided more consistent improvement of objective image quality, compared to the presented baseline networks. The motion-corrected images received better ranks than un-corrected at the same temporal resolution (p< 0.05): 140 ms images 1.65/2.25, and 75 ms images 3.1/3.2. The motion-corrected 75 ms images received the best rank in 65% of testing cases. A fair-to-good inter-reader agreement was observed (Kappa score 0.58).Significance. ATOM reduces motion artifacts, improving visualization of coronary arteries. This algorithm can be used to virtually improve temporal resolution in both single- and dual-source CT.

Coronary artery stenosis quantification in patients with dense calcifications using ultra-high-resolution photon-counting-detector computed tomography.

BACKGROUND: To quantify differences in coronary artery stenosis severity in patients with calcified lesions between conventional energy-integrating detector (EID) CT and ultra-high-resolution (UHR) photon-counting-detector (PCD) CT. METHODS: Patients undergoing clinically indicated coronary CT angiography were prospectively recruited and scanned first on an EID-CT (SOMATOM Force, Siemens Healthineers) and then a PCD-CT (NAEOTOM Alpha, Siemens Healthineers) on the same day. EID-CT was performed with standard mode (192 â€‹× â€‹0.6 â€‹mm detector collimation) following our clinical protocol. PCD-CT scans were performed under UHR mode (120 â€‹× â€‹0.2 â€‹mm detector collimation). For each patient, left main, left anterior descending, right coronary artery, and circumflex were reviewed and the most severe stenosis from dense calcification for each coronary was quantified using commercial software. Additionally, each measured stenosis was assigned a severity category based on percent diameter stenosis, and changes in severity category across EID-CT and PCD-CT were assessed. RESULTS: A total of 23 patients were enrolled, with 34 coronary artery stenoses analyzed. Stenosis was significantly reduced in PCD-CT compared to EID-CT (p â€‹< â€‹0.001), resulting in an average of 11% (SD â€‹= â€‹11%) reduction in percent diameter stenosis. Among the 34 lesions, 15 changed in stenosis severity category: 3 went from moderate to minimal, 1 from moderate to mild, 9 from mild to minimal, and 2 from minimal to mild with the use of PCD-CT compared to EID-CT. CONCLUSION: Use of UHR PCD-CT decreased percent diameter stenosis by an average of 11% relative to EID-CT, resulting in 13 of 34 stenoses being downgraded in stenosis severity category, potentially sparing patients from unnecessary intervention.

PKAID-Net: Prior Knowledge Aware Iterative Denoising Neural Network for Photon Counting Detector CT.

An important feature enabled by Photon-Counting Detector (PCD) CT is the simultaneous acquisition of multi-energy data, which can produce virtual monoenergetic images (VMIs) at a high spatial resolution. However, noise levels observed in the high-resolution (HR) VMIs are markedly increased. Recent work involving deep learning methods has shown great potential in CT image denoising. Many CNN applications involve training using spatially co-registered low- and high-dose CT images featuring high and low image noise, respectively. However, this is implausible in routine clinical practice. Further, typical denoising methods treat each VMI energy level independently, without consideration of the valuable information in the spectral domain. To overcome these obstacles, we propose a prior knowledge-aware iterative denoising neural network (PKAID-Net). PKAID-Net offers two major benefits: first, it utilizes spectral information by including a lower-noise VMI as a prior input; and second, it iteratively constructs refined datasets for neural network training to improve the denoising performance. This study includes 10 patient coronary CT angiography (CTA) exams acquired on a clinical HR PCD-CT (NAEOTOM Alpha, Siemens Healthineers). The HR VMIs were reconstructed at 50 and 70 keV, using a sharp kernel (Bv68) and thin (0.6 mm, 0.3 mm increment) slice thickness. Results showed that the PKAID-Net provided a noise reduction of 96% and 70% relative to FBP and iterative reconstruction, respectively while maintaining spatial and spectral fidelity and a natural noise texture. These results demonstrate the noise reduction capacity of PKAID-Net as applied to cutting-edge PCD-CT data to enable HR, multi-energy cardiac CT imaging.

Pie-Net: Prior-information-enabled deep learning noise reduction for coronary CT angiography acquired with a photon counting detector CT.

BACKGROUND: Photon-counting-detector CT (PCD-CT) enables the production of virtual monoenergetic images (VMIs) at a high spatial resolution (HR) via simultaneous acquisition of multi-energy data. However, noise levels in these HR VMIs are markedly increased. PURPOSE: To develop a deep learning technique that utilizes a lower noise VMI as prior information to reduce image noise in HR, PCD-CT coronary CT angiography (CTA). METHODS: Coronary CTA exams of 10 patients were acquired using PCD-CT (NAEOTOM Alpha, Siemens Healthineers). A prior-information-enabled neural network (Pie-Net) was developed, treating one lower-noise VMI (e.g., 70 keV) as a prior input and one noisy VMI (e.g., 50 keV or 100 keV) as another. For data preprocessing, noisy VMIs were reconstructed by filtered back-projection (FBP) and iterative reconstruction (IR), which were then subtracted to generate "noise-only" images. Spatial decoupling was applied to the noise-only images to mitigate overfitting and improve randomization. Thicker slice averaging was used for the IR and prior images. The final training inputs for the convolutional neural network (CNN) inside the Pie-Net consisted of thicker-slice signal images with the reinsertion of spatially decoupled noise-only images and the thicker-slice prior images. The CNN training labels consisted of the corresponding thicker-slice label images without noise insertion. Pie-Net's performance was evaluated in terms of image noise, spatial detail preservation, and quantitative accuracy, and compared to a U-net-based method that did not include prior information. RESULTS: Pie-Net provided strong noise reduction, by 95 ± 1% relative to FBP and by 60 ± 8% relative to IR. For HR VMIs at different keV (e.g., 50 keV or 100 keV), Pie-Net maintained spatial and spectral fidelity. The inclusion of prior information from the PCD-CT data in the spectral domain was able to improve a robust deep learning-based denoising performance compared to the U-net-based method, which caused some loss of spatial detail and introduced some artifacts. CONCLUSION: The proposed Pie-Net achieved substantial noise reduction while preserving HR VMI's spatial and spectral properties.

Quantifying lumen diameter in coronary artery stents with high-resolution photon counting detector CT and convolutional neural network denoising.

BACKGROUND: Small coronary arteries containing stents pose a challenge in CT imaging due to metal-induced blooming artifact. High spatial resolution imaging capability is as the presence of highly attenuating materials limits noninvasive assessment of luminal patency. PURPOSE: The purpose of this study was to quantify the effective lumen diameter within coronary stents using a clinical photon-counting-detector (PCD) CT in concert with a convolutional neural network (CNN) denoising algorithm, compared to an energy-integrating-detector (EID) CT system. METHODS: Seven coronary stents of different materials and inner diameters between 3.43 and 4.72 mm were placed in plastic tubes of diameters 3.96-4.87 mm containing 20 mg/mL of iodine solution, mimicking stented contrast-enhanced coronary arteries. Tubes were placed parallel with or perpendicular to the scanner's z-axis in an anthropomorphic phantom emulating an average-sized patient and scanned with a clinical EID-CT and PCD-CT. EID scans were performed using our standard coronary computed tomography angiography (cCTA) protocol (120 kV, 180 quality reference mAs). PCD scans were performed using the ultra-high-resolution (UHR) mode (120 × 0.2 mm collimation) at 120 kV with tube current adjusted so that CTDIvol was matched to that of EID scans. EID images were reconstructed per our routine clinical protocol (Br40, 0.6 mm thickness), and with the sharpest available kernel (Br69). PCD images were reconstructed at a thickness of 0.6 mm and a dedicated sharp kernel (Br89) which is only possible with the PCD UHR mode. To address increased image noise introduced by the Br89 kernel, an image-based CNN denoising algorithm was applied to the PCD images of stents scanned parallel to the scanner's z-axis. Stents were segmented based on full-width half maximum thresholding and morphological operations, from which effective lumen diameter was calculated and compared to reference sizes measured with a caliper. RESULTS: Substantial blooming artifacts were observed on EID Br40 images, resulting in larger stent struts and reduced lumen diameter (effective diameter underestimated by 41% and 47% for parallel and perpendicular orientations, respectively). Blooming artifacts were observed on EID Br69 images with 19% and 31% underestimation of lumen diameter compared to the caliper for parallel and perpendicular scans, respectively. Overall image quality was substantially improved on PCD, with higher spatial resolution and reduced blooming artifacts, resulting in the clearer delineation of stent struts. Effective lumen diameters were underestimated by 9% and 19% relative to the reference for parallel and perpendicular scans, respectively. CNN reduced image noise by about 50% on PCD images without impacting lumen quantification (<0.3% difference). CONCLUSION: The PCD UHR mode improved in-stent lumen quantification for all seven stents as compared to EID images due to decreased blooming artifacts. Implementation of CNN denoising algorithms to PCD data substantially improved image quality.

Minimizing magnetic resonance image geometric distortion at 7 Tesla for frameless presurgical planning using skin-adhered fiducials.

BACKGROUND: 7T MRI offers significant benefits to spatial and contrast resolution compared to lower field strengths. This superior image quality can help better delineate targets in stereotactic neurosurgical procedures; however, the potential for increased geometric distortions at 7T has impaired its widespread use for these applications. Image geometric distortions can be due to distortions of B0 arising from tissue magnetic susceptibility effects or inherent field inhomogeneities, and nonlinearity of the magnetic field gradients. PURPOSE: The purpose of this study was to investigate the use of 7T MRI for neurosurgical frameless stereotactic navigation procedures. Image geometric distortions at the skin surface in 7T images were minimized and compared to results from clinical 3T frameless imaging protocols. METHODS: A 3D-printed grid phantom filled with oil was designed to perform a fine calibration of the 7T imaging gradients, and an oil-filled head phantom with internal targets was used to determine ground truth (from computed tomography [CT]) positioning errors. Three volunteers and the head phantom were imaged consecutively at 3T and 7T. Ten skin-adhesive fiducial markers were placed on each subject's exposed skin surface at standard clinical placement locations for frameless procedures. Imaging sequences included MPRAGE (three bandwidths at 7T: 400, 690, and 1020 Hz/pixel, and one at 3T: 400 Hz/pixel), T2 SPACE, and T2 SPACE FLAIR acquisitions. An additional GRE field map was acquired on both scanners using a multi-echo GRE sequence. Custom Matlab code was used to perform additional distortion correction of the images using the unwrapped field maps. Fiducial localization was performed with 3D Slicer, with absolute fiducial positioning errors determined in phantom experiments following rigid registration to the CT images. For human experiments, 3T and 7T images were registered and relative differences in fiducial locations were compared using two-tailed paired t-tests. RESULTS: Phantom measurements at 7T yielded gradient distance scaling errors of 1.1%, 2.2%, and 1.0% along the x-, y-, and z-axes, respectively. These system miscalibrations were traced back to phantom manufacturing deviations in the sphericity of the vendor's gradient calibration phantom. Correction factors along each gradient axis were applied, and afterward, geometric distortions of less than 1 mm were obtained in the 7T MR head phantom images for the 1020 Hz/pixel bandwidth MPRAGE sequence. For the human subjects, four fiducial locations were excluded from the analysis due to patient positioning differences. Differences between 3T and 7T MPRAGE with low/medium/high bandwidth were 2.2 /2.6/2.3 mm, respectively, before the correction, reducing to 1.6/1.3/1.0 mm after the correction (p < 0.001). T2 SPACE and T2 SPACE FLAIR yielded a similar pattern when the correction was applied, decreasing from 2.1 to 0.8 mm, and 2.6 to 1.0 mm, respectively. CONCLUSIONS: 7T MRI can be used to perform frameless presurgical planning with skin-adhesive fiducials. Geometric distortions can be reduced to a clinically relevant level (errors < âˆ¼1 mm) with no significant susceptibility-related distortions, by using high receiver bandwidth, ensuring gradients are properly calibrated, and placing skin fiducials in areas where distortions from patient positioning are minimal.