Advancements in supervised deep learning for metal artifact reduction in computed tomography: A systematic review.

BACKGROUND: Metallic artefacts caused by metal implants, are a common problem in computed tomography (CT) imaging, degrading image quality and diagnostic accuracy. With advancements in artificial intelligence, novel deep learning (DL)-based metal artefact reduction (MAR) algorithms are entering clinical practice. OBJECTIVE: This systematic review provides an overview of the performance of the current supervised DL-based MAR algorithms for CT, focusing on three different domains: sinogram, image, and dual domain. METHODS: A literature search was conducted in PubMed, EMBASE, Web of Science, and Scopus. Outcomes were assessed using peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) or any other objective measure comparing MAR performance to uncorrected images. RESULTS: After screening, fourteen studies were selected that compared DL-based MAR-algorithms with uncorrected images. MAR-algorithms were categorised into the three domains. Thirteen MAR-algorithms showed a higher PSNR and SSIM value compared to the uncorrected images and to non-DL MAR-algorithms. One study showed statistically significant better MAR performance on clinical data compared to the uncorrected images and non-DL MAR-algorithms based on Hounsfield unit calculations. CONCLUSION: DL MAR-algorithms show promising results in reducing metal artefacts, but standardised methodologies are needed to evaluate DL-based MAR-algorithms on clinical data to improve comparability between algorithms. CLINICAL RELEVANCE STATEMENT: Recent studies highlight the effectiveness of supervised Deep Learning-based MAR-algorithms in improving CT image quality by reducing metal artefacts in the sinogram, image and dual domain. A systematic review is needed to provide an overview of newly developed algorithms.

Computed tomography-based preoperative muscle measurements as prognostic factors for anastomotic leakage following oncological sigmoid and rectal resections.

BACKGROUND: Oncological sigmoid and rectal resections are accompanied with substantial risk of anastomotic leakage. Preoperative risk assessment and patient selection remain difficult, highlighting the importance of finding easy-to-use parameters. This study evaluates the prognostic value of contrast-enhanced (CE) computed tomography (CT)-based muscle measurements for predicting anastomotic leakage. METHODS: Patients that underwent oncological sigmoid and rectal resections in the LUMC between 2016 and 2020 were included. Preoperative CE-CT scans, were analyzed using Vitrea software to measure total abdominal muscle area (TAMA) and total psoas area (TPA). Muscle areas were standardized using patient's height into: psoas muscle index (PMI) and skeletal muscle index (SMI) (cm2 /m2 ). RESULTS: In total 46 patients were included, of which 13 (8.9%) suffered from anastomotic leakage. Patients with anastomotic leakage had a significantly lower PMI (22.1 vs. 25.1, p < 0.01) and SMI (41.8 vs. 46.6, p < 0.01). After adjusting for confounders (age and comorbidity), lower PMI (odds ratio [OR]: 0.85, 95% confidence interval [CI] 0.71-0.99, p = 0.03) and SMI (OR: 0.93, 95%CI 0.86-0.99, p = 0.02) were both associated with anastomotic leakage. CONCLUSION: This study showed that lower PMI and SMI were associated with anastomotic leakage. These results indicate that preoperative CT-based muscle measurements can be used as prognostic factor for risk stratification for anastomotic leakage.

Reinducing Radioiodine-Sensitivity in Radioiodine-Refractory Thyroid Cancer Using Lenvatinib (RESET): Study Protocol for a Single-Center, Open Label Phase II Trial.

Background: Management of patients with radioiodine (RAI)-refractory differentiated thyroid cancer (DTC) is a challenge as I-131 therapy is deemed ineffective while standard-of-care systemic therapy with tyrosine kinase inhibitor (TKI) lenvatinib is associated with frequent toxicities leading to dose reductions and withdrawal. A potential new treatment approach is to use TKIs as redifferentiation agent to restore RAI uptake to an extent that I-131 therapy is warranted. Prior studies show that short-term treatment with other TKIs restores RAI uptake in 50-60% of radioiodine-refractory DTC patients, but this concept has not been investigated for lenvatinib. Furthermore, the optimal duration of treatment with TKIs for maximal redifferentiation has not been explored. Methods and Design: A total of 12 patients with RAI-refractory DTC with an indication for lenvatinib will undergo I-124 PET/CT to quantify RAI uptake. This process is repeated after 6 and 12 weeks post-initiating lenvatinib after which the prospective dose estimate to target lesions and organs at risk will be determined. Patients will subsequently stop lenvatinib and undergo I-131 treatment if it is deemed effective and safe by predefined norms. The I-124 PET/CT measurements after 6 and 12 weeks of the first six patients are compared and the optimal timepoint will be determined for the remaining patients. In all I-131 treated patients post-therapy SPECT/CT dosimetry verification will be performed. During follow-up, clinical response will be evaluated using serum thyroglobulin levels and F-18 FDG PET/CT imaging for 6 months. It is hypothesized that at least 40% of patients will show meaningful renewed RAI uptake after short-term lenvatinib treatment. Discussion: Shorter treatment duration of lenvatinib treatment is preferred because of frequent toxicity-related dose reductions and drug withdrawals in long-term lenvatinib treatment. Short-term treatment with lenvatinib with subsequent I-131 therapy poses a potential new management approach for these patients. Since treatment duration is reduced and I-131 therapy is more tolerable for most patients, this potentially leads to less toxicity and higher quality of life. Identifying RAI-refractory DTC patients who redifferentiate after lenvatinib therapy is therefore crucial. Trial Registration: ClinicalTrials.gov, NTC04858867.

The effect of deep learning reconstruction on abdominal CT densitometry and image quality: a systematic review and meta-analysis.

OBJECTIVE: To determine the difference in CT values and image quality of abdominal CT images reconstructed by filtered back-projection (FBP), hybrid iterative reconstruction (IR), and deep learning reconstruction (DLR). METHODS: PubMed and Embase were systematically searched for articles regarding CT densitometry in the abdomen and the image reconstruction techniques FBP, hybrid IR, and DLR. Mean differences in CT values between reconstruction techniques were analyzed. A comparison between signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of FBP, hybrid IR, and DLR was made. A comparison of diagnostic confidence between hybrid IR and DLR was made. RESULTS: Sixteen articles were included, six being suitable for meta-analysis. In the liver, the mean difference between hybrid IR and DLR was - 0.633 HU (p = 0.483, SD ± 0.902 HU). In the spleen, the mean difference between hybrid IR and DLR was - 0.099 HU (p = 0.925, SD ± 1.061 HU). In the pancreas, the mean difference between hybrid IR and DLR was - 1.372 HU (p = 0.353, SD ± 1.476 HU). In 14 articles, CNR was described. In all cases, DLR showed a significantly higher CNR. In 9 articles, SNR was described. In all cases but one, DLR showed a significantly higher SNR. In all cases, DLR showed a significantly higher diagnostic confidence. CONCLUSIONS: There were no significant differences in CT values reconstructed by FBP, hybrid IR, and DLR in abdominal organs. This shows that these reconstruction techniques are consistent in reconstructing CT values. DLR images showed a significantly higher SNR and CNR, compared to FBP and hybrid IR. KEY POINTS: CT values of abdominal CT images are similar between deep learning reconstruction (DLR), filtered back-projection (FBP), and hybrid iterative reconstruction (IR). DLR results in improved image quality in terms of SNR and CNR compared to FBP and hybrid IR images. DLR can thus be safely implemented in the clinical setting resulting in improved image quality without affecting CT values.

Gamma detector dead time correction using Lambert W function.

BACKGROUND: For therapeutic applications of several isotopes (e.g., 131I, 153Sm, 177Lu) in nuclear medicine, the high activities typically applied require accurate dead time correction in early time point imaging. We present a novel, straightforward dead time correction method using the Lambert W function, which is in principle exact for the paralyzable detector model with a single parameter τ (i.e., dead time). RESULTS: As a proof of concept, the method is validated with a simple model: a commonly used isotope, 99mTc, with a single photopeak. We measured count rates of a gamma camera both intrinsically and extrinsically (i.e., with collimators) with point sources in air and in a scatter phantom (extrinsic only). τ was estimated for both open window (τOW) and a 99mTc photopeak window (τTc), using a "graphical" method for fitting the count rate of decaying sources. These values for τ were subsequently used for dead time correction. τ varied significantly between the different geometries for both energy windows, but τOW was more reproducible than τTc, particularly for the scatter phantom measurements. τOW measured from the phantom measurements was approximately 30% lower than τOW from the intrinsic measurement but corresponded within 15% with the extrinsic point source measurements. Accordingly, using the intrinsic τOW led to an overcorrection of 8% at high count rates; τOW from the extrinsic point source measurements corrected the phantom measurement to within 2%. However, significant differences were observed between τTc values. All measured τTc values underestimated dead time losses in a second independent phantom measurement, with even τTc from the first phantom measurement underestimating activity with 5-10% at the highest count rates. Based on measurements of the effect of energy window settings and geometry, we tentatively attribute the added dead time losses to pulse pile-up. CONCLUSIONS: Analytic dead time correction based on the Lambert W function is accurate for the range in which gamma detectors behave as paralyzable systems. However, further investigation indicated measured τ values to be variable with geometry as well as window fraction. We propose that dead time correction should be based on the open window value, τOW, corrected for window fraction.

Experimental comparison of high-density scintillators for EMCCD-based gamma ray imaging.

Detection of x-rays and gamma rays with high spatial resolution can be achieved with scintillators that are optically coupled to electron-multiplying charge-coupled devices (EMCCDs). These can be operated at typical frame rates of 50 Hz with low noise. In such a set-up, scintillation light within each frame is integrated after which the frame is analyzed for the presence of scintillation events. This method allows for the use of scintillator materials with relatively long decay times of a few milliseconds, not previously considered for use in photon-counting gamma cameras, opening up an unexplored range of dense scintillators. In this paper, we test CdWO4 and transparent polycrystalline ceramics of Lu2O3:Eu and (Gd,Lu)2O3:Eu as alternatives to currently used CsI:Tl in order to improve the performance of EMCCD-based gamma cameras. The tested scintillators were selected for their significantly larger cross-sections at 140 keV ((99m)Tc) compared to CsI:Tl combined with moderate to good light yield. A performance comparison based on gamma camera spatial and energy resolution was done with all tested scintillators having equal (66%) interaction probability at 140 keV. CdWO4, Lu2O3:Eu and (Gd,Lu)2O3:Eu all result in a significantly improved spatial resolution over CsI:Tl, albeit at the cost of reduced energy resolution. Lu2O3:Eu transparent ceramic gives the best spatial resolution: 65 µm full-width-at-half-maximum (FWHM) compared to 147 µm FWHM for CsI:Tl. In conclusion, these 'slow' dense scintillators open up new possibilities for improving the spatial resolution of EMCCD-based scintillation cameras.

Maximum-likelihood scintillation detection for EM-CCD based gamma cameras.

Gamma cameras based on charge-coupled devices (CCDs) coupled to continuous scintillation crystals can combine a good detection efficiency with high spatial resolutions with the aid of advanced scintillation detection algorithms. A previously developed analytical multi-scale algorithm (MSA) models the depth-dependent light distribution but does not take statistics into account. Here we present and validate a novel statistical maximum-likelihood algorithm (MLA) that combines a realistic light distribution model with an experimentally validated statistical model. The MLA was tested for an electron multiplying CCD optically coupled to CsI(Tl) scintillators of different thicknesses. For (99m)Tc imaging, the spatial resolution (for perpendicular and oblique incidence), energy resolution and signal-to-background counts ratio (SBR) obtained with the MLA were compared with those of the MSA. Compared to the MSA, the MLA improves the energy resolution by more than a factor of 1.6 and the SBR is enhanced by more than a factor of 1.3. For oblique incidence (approximately 45°), the depth-of-interaction corrected spatial resolution is improved by a factor of at least 1.1, while for perpendicular incidence the MLA resolution does not consistently differ significantly from the MSA result for all tested scintillator thicknesses. For the thickest scintillator (3 mm, interaction probability 66% at 141 keV) a spatial resolution (perpendicular incidence) of 147 µm full width at half maximum (FWHM) was obtained with an energy resolution of 35.2% FWHM. These results of the MLA were achieved without prior calibration of scintillations as is needed for many statistical scintillation detection algorithms. We conclude that the MLA significantly improves the gamma camera performance compared to the MSA.

A pinhole gamma camera with optical depth-of-interaction elimination.

The performance of pinhole single photon emission computed tomography (SPECT) depends on the spatial resolution of the gamma-ray detectors used. Pinhole cameras suffer from strong resolution loss due to the varying depth-of-interaction (DOI) of gamma quanta that enter the detector material at an angle. We eliminate DOI effects in a scintillation gamma camera via a dedicated optic fiber bundle that acts as a focusing collimator for light generated in a scintillation crystal. A curved crystal is connected to a concavely shaped fiber-optic bundle such that the fibers connect perpendicularly to the crystal's convex surface and point straight at the pinhole opening. Limiting the fiber numerical apertures can be used to suppress resolution losses due to light spread. Here we demonstrate experimentally that this prototype position-sensitive gamma sensor successfully eliminates DOI effects, and has an intrinsic resolution of better than 280 microm full width at half maximum with an interaction probability of 67% for 140 keV photons. Therefore, the detector has great potential for increasing the resolution of pinhole SPECT.

A micro-machined retro-reflector for improving light yield in ultra-high-resolution gamma cameras.

High-resolution imaging of x-ray and gamma-ray distributions can be achieved with cameras that use charge coupled devices (CCDs) for detecting scintillation light flashes. The energy and interaction position of individual gamma photons can be determined by rapid processing of CCD images of individual flashes. Here we investigate the improvement of such a gamma camera when a micro-machined retro-reflector is used to increase the light output of a continuous scintillation crystal. At 122 keV we found that retro-reflectors improve the intrinsic energy resolution (full width at half maximum (FWHM)) by 32% (from 50% to 34%) and the signal-to-noise (SNR) ratio by 18%. The spatial resolution (FWHM) was improved by about 4%, allowing us to obtain a resolution of 159 microm. The full width at tenth maximum (FWTM) improvement was 13%. Therefore, this enhancement is a next step towards realizing compact high-resolution devices for imaging gamma emitters.

Multi-scale algorithm for improved scintillation detection in a CCD-based gamma camera.

Gamma cameras based on charge-coupled devices (CCDs) and micro-columnar CsI scintillators can reach high spatial resolutions. However, the gamma interaction probability of these scintillators is low (typically <30% at 141 keV) due to the limited thickness of presently available micro-columnar scintillators. Continuous scintillators can improve the interaction probability but suffer from increased light spread compared to columnar scintillators. In addition, for both types of scintillators, gamma photons incident at an oblique angle reduce the spatial resolution due to the variable depth of interaction (DOI). To improve the spatial resolution and spectral characteristics of these detectors, we have developed a fast analytic scintillation detection algorithm that makes use of a depth-dependent light spread model and as a result is able to estimate the DOI in the scintillator. This algorithm, performing multi-scale frame analysis, was tested for an electron multiplying CCD (EM-CCD) optically coupled to CsI(Tl) scintillators of different thicknesses. For the thickest scintillator (2.6 mm) a spatial resolution of 148 microm full width half maximum (FWHM) was obtained with an energy resolution of 46% FWHM for perpendicularly incident gamma photons (interaction probability 61% at 141 keV). The multi-scale algorithm improves the spatial resolution up to 11%, the energy resolution up to 36% and the signal-to-background counts ratio up to 46% compared to a previously implemented algorithm that did not model the depth-dependent light spread. In addition, the multi-scale algorithm can accurately estimate DOI. As a result, degradation of the spatial resolution due to the variable DOI for gamma photons incident at a 45 degrees angle was improved from 2.0 10(3) to 448 microm FWHM. We conclude that the multi-scale algorithm significantly improves CCD-based gamma cameras as can be applied in future SPECT systems.

Front-illuminated versus back-illuminated photon-counting CCD-based gamma camera: important consequences for spatial resolution and energy resolution.

Charge-coupled devices (CCDs) coupled to scintillation crystals can be used for high-resolution imaging with x-rays and gamma rays. When the CCD images can be read out fast enough, the energy and interaction position of individual gamma quanta can be estimated by a real-time image analysis of the scintillation light flashes ('photon-counting mode'). The electron-multiplying CCD (EMCCD) is well suited for fast read out, since even at high frame rates it has extremely low read-out noise. Back-illuminated (BI) EMCCDs have much higher quantum efficiency than front-illuminated (FI) EMCCDs. Here we compare the spatial and energy resolution of gamma cameras based on FI and BI EMCCDs. The CCDs are coupled to a 1000 microm thick columnar CsI(Tl) crystal for the purpose of Tc-99m and I-125 imaging. Intrinsic spatial resolutions of 44 microm for I-125 and 49 microm for Tc-99m were obtained when using a BI EMCCD, which is an improvement by a factor of about 1.2-2 over the FI EMCCD. Furthermore, in the energy spectrum of the BI EMCCD, the I-125 signal could be clearly separated from the background noise, which was not the case for the FI EMCCD. The energy resolution of a BI EMCCD for Tc-99m was estimated to be approximately 36 keV, full width at half maximum, at 141 keV. The excellent results for the BI EMCCD encouraged us to investigate the cooling requirements for our setup. We have found that for the BI EMCCD, the spatial and energy resolution, as well as image noise, remained stable over a range of temperatures from -50 degrees C to -15 degrees C. This is a significant advantage over the FI EMCCD, which suffered from loss of spatial and especially energy resolution at temperatures as low as -40 degrees C. We conclude that the use of BI EMCCDs may significantly improve the imaging capabilities and the cost efficiency of CCD-based high-resolution gamma cameras.