Innovations in clinical PET image reconstruction: advances in Bayesian penalized likelihood algorithm and deep learning.

The Bayesian penalized likelihood (BPL) reconstruction algorithm, Q.Clear, can achieve a higher signal-to-noise ratio on images and more accurate quantitation than ordered subset-expectation maximization (OSEM). The reconstruction parameter (β) in BPL requires optimization according to the radiopharmaceutical tracer. The present study aimed to define the optimal β value in BPL required to diagnose Alzheimer disease from brain positron emission tomography (PET) images acquired using 18 F-fluoro-2-deoxy-D-glucose ([18 F]FDG) and 11 C-labeled Pittsburg compound B ([11 C]PiB). Images generated from Hoffman 3D brain and cylindrical phantoms were acquired using a Discovery PET/computed tomography (CT) 710 and reconstructed using OSEM+time-of-flight (TOF) under clinical conditions and BPL+TOF (β=20-1000). Contrast was calculated from images generated by the Hoffman 3D brain phantom, and noise and uniformity were calculated from those generated by the cylindrical phantom. Five cognitively healthy controls and five patients with Alzheimer disease were assessed using [18 F]FDG and [11 C]PiB PET to validate the findings from the phantom study. The β values were restricted by the findings of the phantom study, then one certified nuclear medicine physician and two certified nuclear medicine technologists visually determined optimal β values by scoring the quality parameters of image contrast, image noise, cerebellar stability, and overall image quality of PET images from 1 (poor) to 5 (excellent). The contrast in BPL satisfied the Japanese Society of Nuclear Medicine (JSNM) criterion of ≥55% and exceeded that of OSEM at ranges of β=20-450 and 20-600 for [18 F]FDG and [11 C]PiB, respectively. The image noise in BPL satisfied the JSNM criterion of ≤15% and was below that in OSEM when β=150-1000 and 400-1000 for [18 F]FDG and [11 C]PiB, respectively. The phantom study restricted the ranges of β values to 100-300 and 300-500 for [18 F]FDG and [11 C]PiB, respectively. The BPL scores for gray-white matter contrast and image noise, exceeded those of OSEM in [18 F]FDG and [11 C]PiB images regardless of β values. Visual evaluation confirmed that the optimal β values were 200 and 450 for [18 F]FDG and [11 C]PiB, respectively. The BPL achieved better image contrast and less image noise than OSEM, while maintaining quantitative standardized uptake value ratios (SUVR) due to full convergence, more rigorous noise control, and edge preservation. The optimal β values for [18 F]FDG and [11 C]PiB brain PET were apparently 200 and 450, respectively. The present study provides useful information about how to determine optimal β values in BPL for brain PET imaging.

Introduction: PET/CT and PET/MRI are valuable multimodality imaging techniques for visualizing both functional and anatomical information. The most used PET reconstruction algorithm is Ordered Subset Expectation Maximization (OSEM). In OSEM, the image noise increases with increased number of iterations, and the reconstruction needs to be stopped before complete convergence. The Bayesian penalized likelihood (BPL) algorithm, recently introduced, uses a noise penalty factor (β) to achieve full convergence while controlling noise. This study aims to evaluate how reconstruction algorithms and lesion radioactivity levels affect PET image quality and quantitative accuracy across three different PET systems. Materials and Methods: A NEMA phantom was filled with 18F and scanned by one PET/MRI and two PET/CT systems with sphere-to-background concentration ratio (SBR) of 2:1, 4:1, or 10:1. PET images were reconstructed with OSEM or BPL with TOF. The number of iterations and β-values were varied, while the matrix size, number of subsets, and filter size remained constant. Contrast recovery (CR) and background variability (BV) were measured in images. Results: CR increased with increased sphere size and SBR. CR and BV decreased with increased β for the 10mm sphere. Increased number of iterations in OSEM showed increased BV with limited variation in CR. BPL gave higher CR and lower BV values than OSEM. The optimal reconstruction was BPL with β between 150 and 350, where BPL was available, and OSEM with two iterations and 21 subsets for the PET/CT without BPL. Conclusion: BPL outperforms OSEM, and SBR significantly influences tracer uptake quantification in small lesions. Future studies should explore the clinical implications of these findings on diagnosis, staging, prognosis, and treatment follow-up.

A novel supervised learning method to generate CT images for attenuation correction in delayed pet scans

This work aims to evaluate the impact of lowering PET dose on image quality and diagnostic confidence of PET images reconstructed by filtered back-projection (FBP), standard maximum-likelihood expectation-maximization (MLEM) and advanced MR-assisted methods such as kernel EM (KEM) and maximum a posteriori EM (MAPEM). List-mode FDG PET data from 5 patients were thinned into count levels of 50% down to just 1% of the full data. The impact of post-reconstruction smoothing on clinical rating of standard-dose PET images was also evaluated. An adaptive post-reconstruction smoothing was devised for each reconstruction and dose level. For 50% dose reduction, all methods maintained the same overall image quality as full-dose ones. For dose levels <25%, image quality deteriorated for FBP and MLEM, while KEM and MAPEM permitted this limit to be further reduced down to 5-10% of the standard dose, corresponding to injected activities of 10-20 MBq. Post-reconstruction smoothing levels up to about 8 mm did not notably affect the diagnostic task of assessing broadly varying FDG uptake patterns in the brain, thereby indicating a dose level lower than the standard one could be administered. In conclusion, these preliminary results suggest that current MR-assisted methods may allow notably reduced injected doses for PET-MR, at least down to 10%, for clinical tasks requiring broad pattern recognition, such as used in assessment of dementia.

The effect of a novel Bayesian penalised likelihood PET reconstruction algorithm on the assessment of malignancy risk in solitary pulmonary nodules according to the British Thoracic Society guidelines

BackgroundIterative computed tomography (CT) image reconstruction shows high potential for the preservation of image quality in diagnostic CT while reducing patients’ exposure; it has become available for low-dose CT (LD-CT) in high-end hybrid imaging systems (e.g. single-photon emission computed tomography [SPECT]-CT).PurposeTo examine the effect of an iterative CT reconstruction algorithm on image quality, image noise, detectability, and the reader’s confidence for LD-CT data by a subjective assessment.Material and MethodsThe LD-CT data were validated for 40 patients examined by an abdominal hybrid SPECT-CT (U = 120 kV, I = 40 mA, pitch = 1.375). LD-CT was reconstructed using either filtered back projection (FBP) or an iterative image reconstruction algorithm (Adaptive Statistical Iterative Reconstruction [ASIR]®) with different parameters (ASIR levels 50% and 100%). The data were validated by two independent blinded readers using a scoring system for image quality, image noise, detectability, and reader confidence, for a predefined set of 16 anatomic substructures.ResultsThe image quality was significantly improved by iterative reconstruction of the LD-CT data compared with FBP (P ≤ 0.0001). While detectability increased in only 2/16 structures (P ≤ 0.03), the reader’s confidence increased significantly due to iterative reconstruction (P ≤ 0.002). Meanwhile, at the ASIR level of 100%, the detectability in bone structure was highly reduced (P = 0.003).ConclusionAn ASIR level of 50% represents a good compromise in abdominal LD-CT image reconstruction. The specific ASIR level improved image quality (reduced image noise) and reader confidence, while preserving detectability of bone structure.

BackgroundImage optimization is a key step in clinical nuclear medicine, and phantoms play an essential role in this process. However, most phantoms do not accurately reflect the complexity of human anatomy, and this presents a particular challenge when imaging endocrine glands to detect small (often subcentimeter) tumors. To address this, we developed a novel phantom for optimization of positron emission tomography (PET) imaging of the human pituitary gland. Using radioactive 3D printing, phantoms were created which mimicked the distribution of 11C-methionine in normal pituitary tissue and in a small tumor embedded in the gland (i.e., with no inactive boundary, thereby reproducing the in vivo situation). In addition, an anatomical phantom, replicating key surrounding structures [based on computed tomography (CT) images from an actual patient], was created using material extrusion 3D printing with specialized filaments that approximated the attenuation properties of bone and soft tissue.ResultsThe phantom enabled us to replicate pituitary glands harboring tumors of varying sizes (2, 4 and 6 mm diameters) and differing radioactive concentrations (2 ×, 5 × and 8 × the normal gland). The anatomical phantom successfully approximated the attenuation properties of surrounding bone and soft tissue. Two iterative reconstruction algorithms [ordered subset expectation maximization (OSEM); Bayesian penalized likelihood (BPL)] with a range of reconstruction parameters (e.g., 3, 5, 7 and 9 OSEM iterations with 24 subsets; BPL regularization parameter (β) from 50 to 1000) were tested. Images were analyzed quantitatively and qualitatively by eight expert readers. Quantitatively, signal was the highest using BPL with β = 50; noise was the lowest using BPL with β = 1000; contrast was the highest using BPL with β = 100. The qualitative review found that accuracy and confidence were the highest when using BPL with β = 400.ConclusionsThe development of a bespoke phantom has allowed the identification of optimal parameters for molecular pituitary imaging: BPL reconstruction with TOF, PSF correction and a β value of 400; in addition, for small (< 4 mm) tumors with low contrast (2:1 or 5:1), sensitivity may be improved using a β value of 100. Together, these findings should increase tumor detection and confidence in reporting scans.

For PET/CT systems, PET image reconstruction requires corresponding CT images for anatomical localization and attenuation correction. In the case of PET respiratory gating, multiple gated CT scans can offer phase-matched attenuation and motion correction, at the expense of increased radiation dose. We aim to minimize the dose of the CT scan, while preserving adequate image quality for the purpose of PET attenuation correction by introducing sparse view CT data acquisition.We investigated sparse view CT acquisition protocols resulting in ultra-low dose CT scans designed for PET attenuation correction. We analyzed the tradeoffs between the number of views and the integrated tube current per view for a given dose using CT and PET simulations of a 3D NCAT phantom with lesions inserted into liver and lung. We simulated seven CT acquisition protocols with {984, 328, 123, 41, 24, 12, 8} views per rotation at a gantry speed of 0.35 s. One standard dose and four ultra-low dose levels, namely, 0.35 mAs, 0.175 mAs, 0.0875 mAs, and 0.043 75 mAs, were investigated. Both the analytical Feldkamp, Davis and Kress (FDK) algorithm and the Model Based Iterative Reconstruction (MBIR) algorithm were used for CT image reconstruction. We also evaluated the impact of sinogram interpolation to estimate the missing projection measurements due to sparse view data acquisition. For MBIR, we used a penalized weighted least squares (PWLS) cost function with an approximate total-variation (TV) regularizing penalty function. We compared a tube pulsing mode and a continuous exposure mode for sparse view data acquisition. Global PET ensemble root-mean-squares-error (RMSE) and local ensemble lesion activity error were used as quantitative evaluation metrics for PET image quality.With sparse view sampling, it is possible to greatly reduce the CT scan dose when it is primarily used for PET attenuation correction with little or no measureable effect on the PET image. For the four ultra-low dose levels simulated, sparse view protocols with 41 and 24 views best balanced the tradeoff between electronic noise and aliasing artifacts. In terms of lesion activity error and ensemble RMSE of the PET images, these two protocols, when combined with MBIR, are able to provide results that are comparable to the baseline full dose CT scan. View interpolation significantly improves the performance of FDK reconstruction but was not necessary for MBIR. With the more technically feasible continuous exposure data acquisition, the CT images show an increase in azimuthal blur compared to tube pulsing. However, this blurring generally does not have a measureable impact on PET reconstructed images.Our simulations demonstrated that ultra-low-dose CT-based attenuation correction can be achieved at dose levels on the order of 0.044 mAs with little impact on PET image quality. Highly sparse 41- or 24- view ultra-low dose CT scans are feasible for PET attenuation correction, providing the best tradeoff between electronic noise and view aliasing artifacts. The continuous exposure acquisition mode could potentially be implemented in current commercially available scanners, thus enabling sparse view data acquisition without requiring x-ray tubes capable of operating in a pulsing mode.

BackgroundWe evaluate the Omni Legend 32 cm (OMNI6R), a digital-BGO PET/CT using the deep learning (DL) based algorithm, Precision Deep Learning (PDL), emulating time-of-flight (TOF) enhancement and compare its performance to the TOF-equipped Discovery-MI 25 cm (DMI5R) in terms of detection sensitivity, quantification, and overall image quality.MethodsThirty patients were administered with an average single dose of 2 MBq/kg [18F]-FDG and were scanned consecutively on DMI5R first and on OMNI6R afterwards. Total scan duration on DMI5R and OMNI6R were 10 and 6 min, respectively. OMNI6R data were reconstructed using Bayesian Penalized Likelihood (BPL) algorithm with a beta of 650 and PDL-High setting. A total of 150 inserted synthetic lesions (ISL), ranging in size from 6 to 10 mm and exhibiting contrast levels between 3 and 15 relative to their initial background activity, were distributed across the cohort. Three readers blindly assessed detection sensitivity and quantification of these lesions. We tested a non-inferiority hypothesis based on the ISL true positive rate (TPR) and compared calculated recovery coefficients (RC) using SUVmean and SUVmax metrics of the detected ISL. Additionally, image quality, sharpness, conspicuity, noise characteristics, and diagnostic confidence were assessed as clinical quality indicators with a 5-point Likert scale on clinical images without ISL, using same beta as DMI5R and different PDL settings (None, High, Medium, Low).ResultsTPR were 84.67% (95% CI 80.04–89.29%) and 84.44% (95% CI 77.76–91.13%) respectively for DMI5R and OMNI6R-PDL-High, and demonstrated non-inferiority. OMNI6R-PDL-High yielded higher RC without overestimation for all ISL sizes. Remarkably, these findings were observed despite a 9% activity decay in ISL and a 40% reduction in whole-body acquisition time. All PDL settings led to increased average median scores across clinical quality metrics, surpassing the DMI5R in most cases.ConclusionsOMNI6R using PDL-High demonstrated non-inferior diagnostic performance compared to DMI5R, as evidenced by ISL detection sensitivity and quantitation. Importantly, the use of OMNI-PDL-High did not increase the risk of false-negative findings, despite reductions in activity and acquisition time. OMNI6R using PDL enhances overall image quality while improving clinical workflow and patient comfort. These results support DL-based enhancement algorithms as effective solutions for non-TOF PET imaging.Trial registration number and date of registration: NCT05154877, December 13th 2021.

The objective of this study was to assess the value of an integrated circuit (IC) detector, potentially improving spatial resolution by means of reduced cross talk between detector channels, in coronary computed tomographic (CT) angiography regarding image quality and stenosis quantification compared with conventional detector technology. In the ex vivo part of the study, a coronary phantom including 63 defined stenoses and 7 plaque densities (degree of stenosis, 10%-90%; plaque densities, -100 to 1000 Hounsfield unit [HU]) was loaded with contrast agent diluted to 300 HU and placed in an anthropomorphic chest phantom. The phantom was scanned in 0-, 45-, and 90-degree orientations to the z-axis of the CT scanner table. Images were acquired using 128-section dual-source CT equipped with IC and with conventional detector technology. Data were reconstructed with filtered back projection (FBP) and with sinogram-affirmed iterative reconstruction (IR) at a slice thickness of 0.6 mm (increment, 0.4 mm). Data acquired with the IC detector were additionally reconstructed with a slice thickness of 0.5 mm (increment, 0.3 mm) combined with IR. Two readers rated image quality; image noise and degree of stenosis were assessed. In the in vivo part of the study, phantom observations were validated in 30 consecutive patients (11 women; mean [SD] age, 62 [13] years; mean [SD] heart rate, 81 [17] beats per minute) undergoing coronary CT angiography with IC for clinical indications. Images of the patients were reconstructed with FBP (slice thickness, 0.6 mm) and with IR (slice thickness, 0.5 mm) and were assessed for image quality and degree of stenosis. Interreader agreement for image quality was evaluated using intraclass correlation coefficients. The image quality was compared with the Wilcoxon signed rank test. The image noise and the degree of stenosis were compared with the Student t test for paired samples. The interreader agreement for the assessment of image quality was substantial (intraclass correlation coefficients, 0.79). The image quality was significantly (P < 0.001) higher for the images acquired with the IC detector as compared with the conventional detector. The image noise with IR was significantly (P = 0.020) reduced for the IC detector as compared with the conventional detector. The IC detector yielded significantly more accurate results regarding stenosis grading when compared with the images acquired with the conventional detector regarding both FBP (mean [SD] error FBP, 12.1% [7.6%] vs 13.7% [7.6%]; P = 0.043) and IR (mean [SD] error IR, 10.5% [6.6%] vs 13.0% [6.9%]; P < 0.001). The images with a slice thickness of 0.5 mm reconstructed with IR (mean [SD] error, 8.8% [5.9%]) obtained by the IC detector significantly (P < 0.001) improved measurement accuracy in the phantom as compared with FBP with a slice thickness of 0.6 mm (mean [SD] error, 12.1% [7.6%]). In the patients, we found a significantly (P < 0.001) higher image quality, and stenoses were quantified significantly (P = 0.009) smaller with FBP as compared with IR (mean stenosis, 47.6% vs 42.1%; mean difference, 5.5%). Our ex vivo and patient study indicates significantly reduced image noise and more accurate stenosis quantification in coronary CT angiography when acquiring data using an IC detector and combining IR with high-resolution images as compared with conventional detector technology and FBP reconstructions.

We evaluated the feasibility of sub-millisievert (mSv) coronary CT angiography (CCTA) using low tube voltage, prospective ECG gating, and a knowledge-based iterative model reconstruction algorithm. Twenty-four non-obese healthy subjects (M:F 13:11; mean age 50.2±7.8years) were enrolled. Three sets of CT images were reconstructed using three different reconstruction methods: filtered back projection (FBP), iterative reconstruction (IR), and knowledge-based iterative model reconstruction (IMR). The scanning parameters were as follows: step-and-shoot axial scanning, 80kVp, and 200mAs. On the three sets of CT images, the attenuation and image noise values were measured at the aortic root. The signal-to-noise ratio (SNR) and the contrast-to-noise ratio (CNR) were calculated at the proximal right coronary artery and the left main coronary artery. The qualitative image quality of the CCTA with IMR was assessed using a 4-point grading scale (grade 1, poor; grade 4, excellent). The mean radiation dose of the CCTA was 0.89±0.09mSv. The attenuation values with IMR were not different from those of other reconstruction methods. The image noise with IMR was significantly lower than with IR and FBP. Compared to FBP, the noise reduction rate of IMR was 69%. The SNR and CNR of CCTA with IMR were significantly higher than with FBP or IR. On the qualitative analysis with IMR, all included segments were diagnostic (grades 2, 3, and 4), and the mean image quality score was 3.6±0.6. In conclusion, CCTA with low tube voltage, prospective ECG gating, and an IMR algorithm might be a feasible method that allows for sub-millisievert radiation doses and good image quality when used with non-obese subjects.

Time-of-flight technology (TOF) is at the leading edge of advancements in PET/CT imaging, and is made possible due to the availability of new scanner design, scintillating materials and fast computers. The location of annihilation is estimated according to the time difference between scintillation events produced by two 511KeV gamma photons travelling in opposite directions. The additional information is incorporated into image reconstruction to suppress noise propagation and increase signal-to-noise ratio. As shown in previous studies, these properties can be translated in to clinical usage to obtain improved image quality using the same acquisition time, while also enhancing image quality under shortened acquisition or reduce tracer dosage injected to patients.\n\nSemi-quantification units such as standardized uptake value (SUV) and standard deviation (SD) are measured on static PET images and are widely used clinically to quantify the rate of cell metabolism. Signal-to-noise ratio (SNR) and coefficient of variation (CV) can be calculated to assess image quality. However, these parameters depend on image reconstruction and are therefore expected to change with the use of TOF.\n\nBreath holding (BH) PET/CT imaging protocol has been suggested to help evaluation of lesions affected by respiratory motion. However, the PET image quality is significantly degraded since the acquisition time is shortened (e.g. 30 seconds). Noise on BH PET image may cause inaccuracy in semi-quantitation and difficulties in visual assessment. TOF can be applied to improve the image quality and enhance subtle lesions, thus helping the characterization of small lung nodules (SLN) with potential clinical impact.\n\nThis thesis aims to evaluate the impact of TOF on PET image quality and the quantification of SUV in clinical practice. Firstly, the performance of a TOF PET/CT scanner is tested using a phantom mimicking human body trunk with ‘lesions’. Using the same acquisition time (2 minutes/bed), TOF images outperformed conventional images in terms of lesion detectability and background uniformity, especially for small spheres and under low lesion-to-background ratio. Moreover, TOF images acquired using a shorter scan time (1.5 minutes/bed) also maintained acceptable image quality. In the second study, the influence on SUV measurement and image quality (in terms of CV) are evaluated in twelve normal organ structures on whole-body FDG PET/CT images. TOF significantly decreased SUVmax (9/12) and SUVmean (8/12) among the twelve normal organ structures investigated. It also improved the image quality, particularly in solid organs in the abdomen. The combined utility of TOF and BH PET/CT imaging protocol for the detection of SLN is demonstrated in the third study. Lesions showing PET activity, which were misaligned with anatomical location on CT, had higher SUVmax and comparable SNR on BH images. PET/CT fusion was also markedly improved. The additional use of TOF further enhanced lesion detection and improved SNR.\n\nThe results demonstrate the benefits of using TOF in clinical PET/CT, including its advantage with breath holding PET/CT imaging. This information not only offers a better understanding of this increasingly popular technology in modern PET/CT scanners, but also highlights its potential applications in clinical practice.

Contrast-enhanced computed tomography (CT) is essential for tumor assessment, but the detection of low-contrast liver lesions remains challenging. Reducing the radiation dose increases image noise, compromising image quality and diagnostic accuracy. Iterative reconstruction (IR) algorithms can reduce noise; however, they can also alter image texture and limit lesion detection. Deep-learning image reconstruction (DLIR) represents a promising alternative, but its efficacy in ultra-low-dose (ULD) hepatic CT for detecting small, low-contrast lesions remains underexplored. Thus, this study aimed to evaluate a novel real-time DLIR algorithm in ULD hepatic CT, focusing on image quality and lesion detection. In total, 65 patients with hepatic lesions underwent both standard-dose and ULD abdominal CT scans during the portal venous phase. The standard-dose protocol (group A) used 120 kV with a signal-to-noise ratio (SNR) of 1.0, and the images were reconstructed using 50% IR. The ULD protocol (group B) used 120 kV with an SNR of 0.5, and the images were reconstructed using 50% IR and 50% DLIR (groups B1 and B2, respectively). The quantitative and qualitative image quality parameters were assessed. The lesion detection rates were evaluated by lesion type and size using the metrics of detection rate, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Group B showed a 73.3% reduction in the radiation dose compared to group A (1.5±0.8 vs. 6.9±2.0 mSv, P<0.001). Image noise differed significantly across the protocols: group B1 had the highest noise [10.05±2.94 Hounsfield units (HU)], followed by groups A (8.29±2.82 HU) and B2 (8.04±2.71 HU; all pairwise P<0.05 except group A vs. group B2: P=0.625). The CT values and contrast-to-noise ratios (CNRs) were comparable between groups B2 and A (all P>0.05), while group B2 had a 29.9-42.2% higher CNR than group B1 (all P<0.001). The qualitative assessments confirmed that the image quality and diagnostic acceptability of groups B2 (100%) and A (all P>0.05) were comparable, while the images of group B1 were diagnostically unacceptable (all scores <3). Overall, lesion detection was comparable in groups B2 (90.5%, 133/147) and A (98.0%, 144/147; P>0.05). However, group B2 had a significantly lower detection rate for small lesions (<0.5 cm: 77.8%, 42/54) compared to group A (P<0.05), but outperformed group B1 (57.4%, 31/54; P<0.05). Group B2 also had a significantly improved lesion detection rate and sensitivity for low-contrast lesions (87.2%, 95/109) compared to group B1 (75.2%, 82/109; P<0.05). The novel DLIR algorithm achieved a reconstruction speed of 60 images per second (ips), which was significantly faster than that of other DLIR approaches, while maintaining comparable performance to the IR algorithm. The combination of tube current reduction with a novel real-time DLIR algorithm enabled ULD abdominal CT to achieve a 73.3% reduction in the radiation dose while maintaining image quality and diagnostic performance for detecting hepatic lesions larger than 0.5 cm.

Background: This systematic review evaluates articles investigating the use of iterative reconstruction (IR) algorithms and artificial intelligence (AI)-based noise reduction techniques to improve the quality of oral CBCT images. Materials and Methods: A detailed search was performed across PubMed, Scopus, Web of Science, ScienceDirect, and Embase databases. The inclusion criteria were prospective or retrospective studies with IR and AI for CBCT images, studies in which the image quality was statistically assessed, studies on humans, and studies published in peer-reviewed journals in English. Quality assessment was performed independently by two authors, and the conflicts were resolved by the third expert. For bias assessment, the Quality Assessment of Diagnostic Accuracy Studies (QUADAS)-2 tool was used for bias assessment. Material: A total of eleven studies were included, analyzing a range of IR and AI methods designed to reduce noise and artifacts in CBCT images. Results: A statistically significant improvement in CBCT image quality parameters was achieved by the algorithms used in each of the articles we reviewed. The most commonly used image quality measures were peak signal-to-noise ratio (PSNR) and contrast-to-noise ratio (CNR). The most significant increase in PSNR was demonstrated by Ylisiurua et al. and Vestergaard et al., who reported an increase in this parameter of more than 30% for both deep learning (DL) techniques used. Another subcategory used to improve the quality of CBCT images is the reconstruction of synthetic computed tomography (sCT) images using AI. The use of sCT allowed an increase in PSNR ranging from 17% to 30%. For the more traditional methods, FBP and iterative reconstructions, there was an improvement in the PSNR parameter but not as high, ranging from 3% to 13%. Among the research papers evaluating the CNR parameter, an improvement of 17% to 29% was achieved. Conclusions: The use of AI and IR can significantly improve the quality of oral CBCT images by reducing image noise.

To prospectively compare traditional filtered back projection (FBP) and iterative image reconstruction for the evaluation of heavily calcified arteries with coronary computed tomography (CT) angiography. The study had institutional review board approval and was HIPAA compliant. Written informed consent was obtained from all patients. Fifty-five consecutive patients (35 men, 20 women; mean age, 58 years ± 12 [standard deviation]) with Agatston scores of at least 400 underwent coronary CT angiography and cardiac catheterization. Image data were reconstructed with both FBP and iterative reconstruction techniques with corresponding cardiac algorithms. Image noise and subjective image quality were compared. To objectively assess the effect of FBP and iterative reconstruction on blooming artifacts, volumes of circumscribed calcifications were measured with dedicated volume analysis software. FBP and iterative reconstruction series were independently evaluated for coronary artery stenosis greater than 50%, and their diagnostic accuracy was compared, with cardiac catheterization as the reference standard. Statistical analyses included paired t tests, Kruskal-Wallis analysis of variance, and a modified McNemar test. Image noise measured significantly lower (P = .011-.035) with iterative reconstruction instead of FBP. Image quality was rated significantly higher (P = .031 and .042) with iterative reconstruction series than with FBP. Calcification volumes measured significantly lower (P = .019 and .026) with iterative reconstruction (44.3 mm(3) ± 64.7 and 46.2 mm(3) ± 68.8) than with FBP (54.5 mm(3) ± 69.5 and 56.3 mm(3) ± 72.5). Iterative reconstruction significantly improved some measures of per-segment diagnostic accuracy of coronary CT angiography for the detection of significant stenosis compared with FBP (accuracy: 95.9% vs 91.8%, P = .0001; specificity: 95.8% vs 91.2%, P = .0001; positive predictive value: 76.9% vs 61.1%, P = .0001). Iterative reconstruction reduces image noise and blooming artifacts from calcifications, leading to improved diagnostic accuracy of coronary CT angiography in patients with heavily calcified coronary arteries.