Koons, Emily K.

A deep learning–based neural network enabled virtual monoenergetic imaging at energy-integrating detector CT, reduced blooming artifacts, and improved stenosis assessment in heavily calcified coronary plaques, with performance comparable to ultrahigh-resolution photon-counting detector CT.

Abstract Background To utilize high spatial resolution reconstructions for cardiac imaging at energy‐integrating detector CT (EID)‐CT with comparable noise to similar reconstructions at photon‐counting detector (PCD)‐CT, methods to control EID‐CT image noise are needed. Supervised convolutional neural networks (CNN) have shown promise for denoising, but a challenge remains to efficiently create high‐quality and unbiased estimates of noise without access to dedicated software or proprietary information, such that natural noise texture is retained in CNN‐denoised CT images. Purpose This study aims to develop and test image‐based noise estimation methods that can be used to train a CNN model, and to evaluate denoising performance and noise texture preservation for EID‐CT coronary CT angiography (cCTA) images reconstructed with high‐resolution kernels. Methods U‐net CNN models were trained for denoising. To supervise training, noise‐only images were estimated directly from high‐resolution kernel (Bv59) reconstructed EID‐CT (HR EID‐CT) patient images using two different methods: subtraction of low‐ and high‐strength iterative reconstruction (IR); subtraction of adjacent image slices with the same IR strength. The noise estimates from these methods contain differing noise texture and anatomical information. Networks were trained and validated separately for three data sets: the training data from each of the two noise‐estimation methods, and a 50%–50% partition of training data between the two methods. The trained models were applied to two sets of testing data: CT images of a uniform water phantom to measure noise power spectra (NPS), and an independent cohort of seven patient cCTA HR EID‐CT exams. The denoised patient images were compared to standard resolution EID‐CT reconstructions (Bv40). As a low‐noise reference, patient images acquired on the same day with a PCD‐CT and reconstructed using a similar kernel as HR EID‐CT were used for comparison. Results Models trained with each noise‐image estimation method denoised the HR EID‐CT images by 74%–79% to achieve a comparable noise magnitude to the HR PCD‐CT images. The peak, average, and 10% peak frequencies of the NPS of the input images (6.08, 6.24, and 12.0 cm −1 ) were better approximated by the model trained on adjacent slice subtraction (6.56, 5.87, and 11.5 cm −1 ) than by the model trained on subtraction of low‐ and high‐IR images (4.64, 5.44, and 11.3 cm −1 ). In cCTA images, the IR subtraction model images retained anatomic structures from input images but resulted in undesirable salt‐and‐pepper noise texture and CT number bias. The model trained on adjacent slice subtraction images had more natural texture and no significant bias, but the model sometimes removed small anatomic structures. The model trained on the mixed training dataset preserved both noise texture and anatomy from the model inputs and enabled visualization of small structures seen in PCD‐CT images that were previously unresolved by EID‐CT. Conclusions The noise texture and anatomical accuracy in CT images denoised with an image‐based supervised CNN are greatly influenced by the characteristics and partitioning of training data. With higher‐resolution reconstructions and noise texture‐preserving deep learning denoising, the quality of cCTA images from EID‐CT can be enhanced to enable resolvability of subtle anatomy similar to PCD‐CT.

Abstract Background Coronary computed tomography angiography (cCTA) is a widely used noninvasive diagnostic exam to assess patients for coronary artery disease (CAD). However, the spatial resolution of most CT scanners is limited due to the use of energy‐integrating detectors (EIDs). Purpose To develop a convolutional neural network ( I mproved LUMEN visualization through A rtificial super‐resolu T ion imag E s (ILUMENATE)) informed by photon‐counting‐detector (PCD)‐CT to improve EID‐CT image resolution and determine its impact on cCTA. Materials and methods With IRB approval, 30 patients undergoing clinically indicated cCTA were scanned with EID‐CT (SOMATOM Force, Siemens Healthineers, Forchheim, Germany) and subsequently with ultra‐high‐resolution (UHR) PCD‐CT (NAEOTOM Alpha, Siemens Healthineers) on the same day. ILUMENATE was trained on eight patient PCD‐CT datasets (67,890 patch pairs with 90% for training (61,101), 10% reserved for validation (6,789)) and applied to 22 unseen EID‐CT cases. Spatial resolution was evaluated using line profiles and percent diameter stenosis quantified with a severity score assigned. Two experienced radiologists, blinded to image type, selected preferred series and scored images for overall quality, sharpness, and noise comparing original EID‐CT and ILUMENATE output. Results Visual assessment and line profiles showed substantial resolution improvement with ILUMENATE. Percent diameter stenosis was significantly reduced (mean ± standard deviation: 4.42% ± 4.82%) using ILUMENATE ( p < 0.001) with nine lesions shifting down in severity score. Readers preferred ILUMENATE images in 22/22 cases and scored ILUMENATE superiorly for overall quality, sharpness, and noise ( p < 0.05). Conclusions ILUMENATE enhanced image resolution, resulting in improved overall image quality, reduced calcium blooming artifacts, and improved lumen visibility in cCTA exams performed using EID‐CT. This could potentially allow for improved accessibility to UHR image quality, allowing for more accurate assessment of CAD.

Abstract 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.

AbstractBackgroundSmall 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.PurposeThe 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.MethodsSeven 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.ResultsSubstantial 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).ConclusionThe 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.

AbstractBackgroundPhoton‐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.PurposeTo 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).MethodsCoronary 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.ResultsPie‐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.ConclusionThe proposed Pie‐Net achieved substantial noise reduction while preserving HR VMI's spatial and spectral properties.

AbstractBackground7T 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.PurposeThe 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.MethodsA 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.ResultsPhantom 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.Conclusions7T MRI can be used to perform frameless presurgical planning with skin‐adhesive fiducials. Geometric distortions can be reduced to a clinically relevant level (errors < ∼1 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.