Automatic chest computed tomography image noise quantification using deep learning.

PURPOSE: This study aimed to develop a deep learning (DL) method for noise quantification for clinical chest computed tomography (CT) images without the need for repeated scanning or homogeneous tissue regions. METHODS: A comprehensive phantom CT dataset (three dose levels, six reconstruction methods, amounting to 9240 slices) was acquired and used to train a convolutional neural network (CNN) to output an estimate of local image noise standard deviations (SD) from a single CT scan input. The CNN model consisting of seven convolutional layers was trained on the phantom image dataset representing a range of scan parameters and was tested with phantom images acquired in a variety of different scan conditions, as well as publicly available chest CT images to produce clinical noise SD maps. RESULTS: Noise SD maps predicted by the CNN agreed well with the ground truth both visually and numerically in the phantom dataset (errors of < 5 HU for most scan parameter combinations). In addition, the noise SD estimates obtained from clinical chest CT images were similar to running-average based reference estimates in areas without prominent tissue interfaces. CONCLUSIONS: Predicting local noise magnitudes without the need for repeated scans is feasible using DL. Our implementation trained with phantom data was successfully applied to open-source clinical data with heterogeneous tissue borders and textures. We suggest that automatic DL noise mapping from clinical patient images could be used as a tool for objective CT image quality estimation and protocol optimization.

Assessing post-traumatic changes in cartilage using T1ρ dispersion parameters.

Degeneration of cartilage can be studied non-invasively with quantitative MRI. A promising parameter for detecting early osteoarthritis in articular cartilage is T1ρ, which can be tuned via the amplitude of the spin-lock pulse. By measuring T1ρ at several spin-lock amplitudes, the dispersion of T1ρ is obtained. The aim of this study is to find out if the dispersion contains diagnostically relevant information complementary to a T1ρ measurement at a single spin-lock amplitude. To this end, five differently acquired dispersion parameters are utilized; A, B, τc, T1ρ/T2, and R2 - R1ρ. An open dataset of an equine model of post-traumatic cartilage was utilized to assess the T1ρ dispersion parameters for the evaluation of cartilage degeneration. Firstly, the parameters were compared for their sensitivity in detecting degenerative changes. Secondly, the relationship of the dispersion parameters to histological and biomechanical reference parameters was studied. Parameters A, T1ρ/T2, and R2 - R1ρ were found to be sensitive to lesion-induced changes in the cartilage within sample. Strong correlations of several dispersion parameters with optical density, as well as with collagen fibril angle were found. Most of the dispersion parameters correlated strongly with individual T1ρ values. The results suggest that dispersion parameters can in some cases provide a more accurate description of the biochemical composition of cartilage as compared to conventional MRI parameters. However, in most cases the information given by the dispersion parameters is more of a refinement than complementary to conventional quantitative MRI.

Machine Learning Prediction of Collagen Fiber Orientation and Proteoglycan Content From Multiparametric Quantitative MRI in Articular Cartilage.

BACKGROUND: Machine learning models trained with multiparametric quantitative MRIs (qMRIs) have the potential to provide valuable information about the structural composition of articular cartilage. PURPOSE: To study the performance and feasibility of machine learning models combined with qMRIs for noninvasive assessment of collagen fiber orientation and proteoglycan content. STUDY TYPE: Retrospective, animal model. ANIMAL MODEL: An open-source single slice MRI dataset obtained from 20 samples of 10 Shetland ponies (seven with surgically induced cartilage lesions followed by treatment and three healthy controls) yielded to 1600 data points, including 10% for test and 90% for train validation. FIELD STRENGTH/SEQUENCE: A 9.4 T MRI scanner/qMRI sequences: T1 , T2 , adiabatic T1ρ and T2ρ , continuous-wave T1ρ and relaxation along a fictitious field (TRAFF ) maps. ASSESSMENT: Five machine learning regression models were developed: random forest (RF), support vector regression (SVR), gradient boosting (GB), multilayer perceptron (MLP), and Gaussian process regression (GPR). A nested cross-validation was used for performance evaluation. For reference, proteoglycan content and collagen fiber orientation were determined by quantitative histology from digital densitometry (DD) and polarized light microscopy (PLM), respectively. STATISTICAL TESTS: Normality was tested using Shapiro-Wilk test, and association between predicted and measured values was evaluated using Spearman's Rho test. A P-value of 0.05 was considered as the limit of statistical significance. RESULTS: Four out of the five models (RF, GB, MLP, and GPR) yielded high accuracy (R2  = 0.68-0.75 for PLM and 0.62-0.66 for DD), and strong significant correlations between the reference measurements and predicted cartilage matrix properties (Spearman's Rho = 0.72-0.88 for PLM and 0.61-0.83 for DD). GPR algorithm had the highest accuracy (R2  = 0.75 and 0.66) and lowest prediction-error (root mean squared [RMSE] = 1.34 and 2.55) for PLM and DD, respectively. DATA CONCLUSION: Multiparametric qMRIs in combination with regression models can determine cartilage compositional and structural features, with higher accuracy for collagen fiber orientation than proteoglycan content. EVIDENCE LEVEL: 2 TECHNICAL EFFICACY: Stage 2.

Virtual monochromatic imaging reduces beam hardening artefacts in cardiac interior photon counting computed tomography: a phantom study with cadaveric specimens.

In interior cardiac computed tomography (CT) imaging, the x-ray beam is collimated to a limited field-of-view covering the heart volume, which decreases the radiation exposure to surrounding tissues. Spectral CT enables the creation of virtual monochromatic images (VMIs) through a computational material decomposition process. This study investigates the utility of VMIs for beam hardening (BH) reduction in interior cardiac CT, and further, the suitability of VMIs for coronary artery calcium (CAC) scoring and volume assessment is studied using spectral photon counting detector CT (PCD-CT).Ex vivocoronary artery samples (N = 18) were inserted in an epoxy rod phantom. The rod was scanned in the conventional CT geometry, and subsequently, the rod was positioned in a torso phantom and re-measured in the interior PCD-CT geometry. The total energy (TE) 10-100 keV reconstructions from PCD-CT were used as a reference. The low energy 10-60 keV and high energy 60-100 keV data were used to perform projection domain material decomposition to polymethyl methacrylate and calcium hydroxylapatite basis. The truncated basis-material sinograms were extended using the adaptive detruncation method. VMIs from 30-180 keV range were computed from the detruncated virtual monochromatic sinograms using filtered back projection. Detrending was applied as a post-processing method prior to CAC scoring. The results showed that BH artefacts from the exterior structures can be suppressed with high (≥100 keV) VMIs. With appropriate selection of the monoenergy (46 keV), the underestimation trend of CAC scores and volumes shown in Bland-Altman (BA) plots for TE interior PCD-CT was mitigated, as the BA slope values were -0.02 for the 46 keV VMI compared to -0.21 the conventional TE image. To conclude, spectral PCD-CT imaging using VMIs could be applied to reduce BH artefacts interior CT geometry, and further, optimal selection of VMI may improve the accuracy of CAC scoring assessment in interior PCD-CT.

Generative adversarial networks improve interior computed tomography angiography reconstruction.

In interior computed tomography (CT), the x-ray beam is collimated to a limited field-of-view (FOV) (e.g. the volume of the heart) to decrease exposure to adjacent organs, but the resulting image has a severe truncation artifact when reconstructed with traditional filtered back-projection (FBP) type algorithms. In some examinations, such as cardiac or dentomaxillofacial imaging, interior CT could be used to achieve further dose reductions. In this work, we describe a deep learning (DL) method to obtain artifact-free images from interior CT angiography. Our method employs the Pix2Pix generative adversarial network (GAN) in a two-stage process: (1) An extended sinogram is computed from a truncated sinogram with one GAN model, and (2) the FBP reconstruction obtained from that extended sinogram is used as an input to another GAN model that improves the quality of the interior reconstruction. Our double GAN (DGAN) model was trained with 10 000 truncated sinograms simulated from real computed tomography angiography slice images. Truncated sinograms (input) were used with original slice images (target) in training to yield an improved reconstruction (output). DGAN performance was compared with the adaptive de-truncation method, total variation regularization, and two reference DL methods: FBPConvNet, and U-Net-based sinogram extension (ES-UNet). Our DGAN method and ES-UNet yielded the best root-mean-squared error (RMSE) (0.03 ± 0.01), and structural similarity index (SSIM) (0.92 ± 0.02) values, and reference DL methods also yielded good results. Furthermore, we performed an extended FOV analysis by increasing the reconstruction area by 10% and 20%. In both cases, the DGAN approach yielded best results at RMSE (0.03 ± 0.01 and 0.04 ± 0.01 for the 10% and 20% cases, respectively), peak signal-to-noise ratio (PSNR) (30.5 ± 2.6 dB and 28.6 ± 2.6 dB), and SSIM (0.90 ± 0.02 and 0.87 ± 0.02). In conclusion, our method was able to not only reconstruct the interior region with improved image quality, but also extend the reconstructed FOV by 20%.

T2 -weighted magnetic resonance imaging texture as predictor of low back pain: A texture analysis-based classification pipeline to symptomatic and asymptomatic cases.

Low back pain is a very common symptom and the leading cause of disability throughout the world. Several degenerative imaging findings seen on magnetic resonance imaging are associated with low back pain but none of them is specific for the presence of low back pain as abnormal findings are prevalent among asymptomatic subjects as well. The purpose of this population-based study was to investigate if more specific magnetic resonance imaging predictors of low back pain could be found via texture analysis and machine learning. We used this methodology to classify T2 -weighted magnetic resonance images from the Northern Finland Birth Cohort 1966 data to symptomatic and asymptomatic groups. Lumbar spine magnetic resonance imaging was performed using a fast spin-echo sequence at 1.5 T. Texture analysis pipeline consisting of textural feature extraction, principal component analysis, and logistic regression classifier was applied to the data to classify them into symptomatic (clinically relevant pain with frequency ≥30 days and intensity ≥6/10) and asymptomatic (frequency ≤7 days, intensity ≤3/10, and no previous pain episodes in the follow-up period) groups. Best classification results were observed applying texture analysis to the two lowest intervertebral discs (L4-L5 and L5-S1), with accuracy of 83%, specificity of 83%, sensitivity of 82%, negative predictive value of 94%, precision of 56%, and receiver operating characteristic area-under-curve of 0.91. To conclude, textural features from T2 -weighted magnetic resonance images can be applied in low back pain classification.

Evaluation of articular cartilage with quantitative MRI in an equine model of post-traumatic osteoarthritis.

Chondral lesions lead to degenerative changes in the surrounding cartilage tissue, increasing the risk of developing post-traumatic osteoarthritis (PTOA). This study aimed to investigate the feasibility of quantitative magnetic resonance imaging (qMRI) for evaluation of articular cartilage in PTOA. Articular explants containing surgically induced and repaired chondral lesions were obtained from the stifle joints of seven Shetland ponies (14 samples). Three age-matched nonoperated ponies served as controls (six samples). The samples were imaged at 9.4 T. The measured qMRI parameters included T1 , T2 , continuous-wave T1ρ (CWT1ρ ), adiabatic T1ρ (AdT1ρ ), and T2ρ (AdT2ρ ) and relaxation along a fictitious field (TRAFF ). For reference, cartilage equilibrium and dynamic moduli, proteoglycan content and collagen fiber orientation were determined. Mean values and profiles from full-thickness cartilage regions of interest, at increasing distances from the lesions, were used to compare experimental against control and to correlate qMRI with the references. Significant alterations were detected by qMRI parameters, including prolonged T1 , CWT1ρ , and AdT1ρ in the regions adjacent to the lesions. The changes were confirmed by the reference methods. CWT1ρ was more strongly associated with the reference measurements and prolonged in the affected regions at lower spin-locking amplitudes. Moderate to strong correlations were found between all qMRI parameters and the reference parameters (ρ = -0.531 to -0.757). T1 , low spin-lock amplitude CWT1ρ , and AdT1ρ were most responsive to changes in visually intact cartilage adjacent to the lesions. In the context of PTOA, these findings highlight the potential of T1 , CWT1ρ , and AdT1ρ in evaluation of compositional and structural changes in cartilage.

Interior photon counting computed tomography for quantification of coronary artery calcium: pre-clinical phantom study.

Computed tomography (CT) is the reference method for cardiac imaging, but concerns have been raised regarding the radiation dose of CT examinations. Recently, photon counting detectors (PCDs) and interior tomography, in which the radiation beam is limited to the organ-of-interest, have been suggested for patient dose reduction. In this study, we investigated interior PCD-CT (iPCD-CT) for non-enhanced quantification of coronary artery calcium (CAC) using an anthropomorphic torso phantom and ex vivo coronary artery samples. We reconstructed the iPCD-CT measurements with filtered back projection (FBP), iterative total variation (TV) regularization, padded FBP, and adaptively detruncated FBP and adaptively detruncated TV. We compared the organ doses between conventional CT and iPCD-CT geometries, assessed the truncation and cupping artifacts with iPCD-CT, and evaluated the CAC quantification performance of iPCD-CT. With approximately the same effective dose between conventional CT geometry (0.30 mSv) and interior PCD-CT with 10.2 cm field-of-view (0.27 mSv), the organ dose of the heart was increased by 52.3% with interior PCD-CT when compared to CT. Conversely, the organ doses to peripheral and radiosensitive organs, such as the stomach (55.0% reduction), were often reduced with interior PCD-CT. FBP and TV did not sufficiently reduce the truncation artifact, whereas padded FBP and adaptively detruncated FBP and TV yielded satisfactory truncation artifact reduction. Notably, the adaptive detruncation algorithm reduced truncation artifacts effectively when it was combined with reconstruction detrending. With this approach, the CAC quantification accuracy was good, and the coronary artery disease grade reclassification rate was particularly low (5.6%). Thus, our results confirm that CAC quantification can be performed with the interior CT geometry, that the artifacts are effectively reduced with suitable interior reconstruction methods, and that interior tomography provides efficient patient dose reduction.

Framework for Photon Counting Quantitative Material Decomposition.

In this paper, the accuracy of material decomposition (MD) using an energy discriminating photon counting detector was studied. An MD framework was established and validated using calcium hydroxyapatite (CaHA) inserts of known densities (50 mg/cm3, 100 mg/cm3, 250 mg/cm3, 400 mg/cm3), and diameters (1.2, 3.0, and 5.0 mm). These inserts were placed in a cardiac rod phantom that mimics a tissue equivalent heart and measured using an experimental photon counting detector cone beam computed tomography (PCD-CBCT) setup. The quantitative coronary calcium scores (density, mass, and volume) obtained from the MD framework were compared with the nominal values. In addition, three different calibration techniques, signal-to-equivalent thickness calibration (STC), polynomial correction (PC), and projected equivalent thickness calibration (PETC) were compared to investigate the effect of the calibration method on the quantitative values. The obtained MD estimates agreed well with the nominal values for density (mass) with mean absolute percent errors (MAPEs) 8 ± 11% (9 ± 15%) and 4 ± 6% (9 ± 14%) for STC and PETC calibration methods, respectively. PC displayed large MAPEs for density (27 ± 9%), and mass (25 ± 12%). Volume estimation resulted in large deviations between true and measured values with notable MAPEs for STC (40 ± 90%), PC (40 ± 80%), and PETC (40 ± 90%). The framework demonstrated the feasibility of quantitative CaHA mass and density scoring using PCD-CBCT.

An Automatic Regularization Method: An Application for 3-D X-Ray Micro-CT Reconstruction Using Sparse Data.

X-ray tomography is a reliable tool for determining the inner structure of 3-D object with penetrating X-rays. However, traditional reconstruction methods, such as Feldkamp-Davis-Kress (FDK), require dense angular sampling in the data acquisition phase leading to long measurement times, especially in X-ray micro-tomography to obtain high-resolution scans. Acquiring less data using greater angular steps is an obvious way for speeding up the process and avoiding the need to save huge data sets. However, computing 3-D reconstruction from such a sparsely sampled data set is difficult because the measurement data are usually contaminated by errors, and linear measurement models do not contain sufficient information to solve the problem in practice. An automatic regularization method is proposed for robust reconstruction, based on enforcing sparsity in the 3-D shearlet transform domain. The inputs of the algorithm are the projection data and a priori known expected degree of sparsity, denoted as . The number Cpr can be calibrated from a few dense-angle reconstructions and fixed. Human subchondral bone samples were tested, and morphometric parameters of the bone reconstructions were then analyzed using standard metrics. The proposed method is shown to outperform the baseline algorithm (FDK) in the case of sparsely collected data. The number of X-ray projections can be reduced up to 10% of the total amount 300 projections over 180° with uniform angular step while retaining the quality of the reconstruction images and of the morphometric parameters.

Iterative and discrete reconstruction in the evaluation of the rabbit model of osteoarthritis.

Micro-computed tomography (µCT) is a standard method for bone morphometric evaluation. However, the scan time can be long and the radiation dose during the scan may have adverse effects on test subjects, therefore both of them should be minimized. This could be achieved by applying iterative reconstruction (IR) on sparse projection data, as IR is capable of producing reconstructions of sufficient image quality with less projection data than the traditional algorithm requires. In this work, the performance of three IR algorithms was assessed for quantitative bone imaging from low-resolution data in the evaluation of the rabbit model of osteoarthritis. Subchondral bone images were reconstructed with a conjugate gradient least squares algorithm, a total variation regularization scheme, and a discrete algebraic reconstruction technique to obtain quantitative bone morphometry, and the results obtained in this manner were compared with those obtained from the reference reconstruction. Our approaches were sufficient to identify changes in bone structure in early osteoarthritis, and these changes were preserved even when minimal data were provided for the reconstruction. Thus, our results suggest that IR algorithms give reliable performance with sparse projection data, thereby recommending them for use in µCT studies where time and radiation exposure are preferably minimized.