Single-energy CT Research Articles

Improved GAN: Using a transformer module generator approach for material decomposition

Dual-energy computed tomography (CT) can be used for material decomposition, allowing for the precise quantitative mapping of body substances; this has a wide range of clinical applications, including disease diagnosis, treatment response evaluation and prognosis prediction. However, dual-energy CT has not yet become the mainstream technique in most clinical settings due to its limited accessibility. To fully take advantage of material quantification, researchers have attempted to use deep learning to generate material decomposition maps from conventional single-energy CT images, mainly by synthesizing another single-energy CT image from a conventional single-energy CT image to form a dual-energy CT image first and then generate material decomposition maps. This is not a straightforward process, and it potentially introduces many inaccuracies after multiple steps. In this work, we proposed a generative adversarial network (GAN) framework as the base and improved its generator; this approach combines convolutional neural networks (CNNs) and a transformer module to directly generate material decomposition maps from conventional single-energy CT images. Our model pays attention to both local and global information. Then, we compared our method with 6 competitive deep learning methods on water (calcium) and calcium (water) substrate density image datasets. The average PSNR, SSIM, MAE, and RMSE of the generated and ground truth of the water (calcium) substrate density images were 32.7207, 0.9685, 0.0323, and 0.0555, respectively. Furthermore, the average PSNR, SSIM, MAE, and RMSE of the generated and ground truth of the calcium (water) substrate density images were 30.2823, 0.9449, 0.0652, and 0.0715, respectively. Our model achieved better performance and stronger stability than competing approaches.

Metal artifact reduction in cervix brachytherapy with titanium applicators using dual‐energy CT through virtual monoenergetic images and an iterative algorithm: A phantom study

To evaluate an iterative metal-artifact reduction (iMAR) algorithm, dual-energy CT (DECT) through virtual monoenergetic images (VMI), and a combination of iMAR and DECT for reducing metal artifact severity (AS) induced by Fletcher titanium applicators used in cervix brachytherapy, the efficacy of which are hitherto unreported. 120 kVp single-energy CT (SECT) (Siemens) of BEBIG tandem applicators, varying in shape (straight or curved) and diameter (3.5 mm or 5 mm) in a custom-made water-filled phantom, and their DECT images obtained from extrapolation of 80 kVp and 140 kVp, were reconstructed using four methods: DECT through VMI±iMAR, and SECT±iMAR. The DECT images were reconstructed monoenergetically at 70, 150, and 190 keV. AS was evaluated using measured values and statistical analysis. iMAR, DECT, and combined DECT and iMAR reduced AS (p < 0.05). DECT had a lower AS than SECT, even without iMAR (p < 0.025). SECT+iMAR was more effective than DECT-iMAR with VMI at 70 and 190 keV (p < 0.05), whereas showing no statistically significant difference at 150 keV. With DECT and iMAR combined, AS was reduced more effectively compared to the SECT+iMAR or DECT alone. It also reduced the mean interobserver uncertainty by 0.2 mm. These findings indicate that iMAR reduces the AS caused by Fletcher titanium applicators for both SECT and DECT, a combination of iMAR and DECT is superior to either strategy alone, and at low energies, DECT+iMAR also produces similar artifact reduction. These practical strategies promise more accurate source-position and structure definitions in CT-based gynecological brachytherapy treatment planning.

Impact of iodinated contrast media concentration on image quality for dual-energy CT and single-energy CT with low tube voltage settings.

Contrast-induced nephropathy (CIN) is an adverse reaction associated with the use of intravenous contrast media (CM). To investigate the impact of low tube voltage settings on single-energy computed tomography (SECT) and rapid kV switching dual-energy CT (DECT) with reduced concentrations of iodinated CM. A phantom containing four different concentrations of CM (original concentration CM, 20%, 40%, and 60% reductions) was scanned using SECT mode with varying tube voltages (70, 80, 100, and 120 kVp) and DECT mode through reconstructing monoenergetic energy (50 keV and 70 keV) images. ATCM system with different noise index (NI) settings were set, and the images were reconstructed using ASiR-V. Image quality were measured for individual phantom sizes and protocols and compared to a reference protocol for SECT of 120 kVp, NI = 18, threshold contrast enhancement ≥280 HU, and CNR ≥17. Tube voltage settings of 70 kVp together with 40% reduction in the iodinated CM is suitable for small phantom size, those of 80 kVp and 20% reduction is suitable for the medium and large sizes. This allows radiation doses to be reduced by 12%-30%. Values of CNR and contrast for DECT are better than those for SECT with the same NI setting. Diagnostic reference of image quality can be maintained by using SECT with lower tube voltage and DECT with reductions of iodinated CM concentration and radiation dose. Therefore, the NI setting can be increased when DECT is used to achieve a similar image quality.

Virtual computed-tomography system for deep-learning-based material decomposition

Objective. Material decomposition (MD) evaluates the elemental composition of human tissues and organs via computed tomography (CT) and is indispensable in correlating anatomical images with functional ones. A major issue in MD is inaccurate elemental information about the real human body. To overcome this problem, we developed a virtual CT system model, by which various reconstructed images can be generated based on ICRP110 human phantoms with information about six major elements (H, C, N, O, P, and Ca). Approach. We generated CT datasets labelled with accurate elemental information using the proposed generative CT model and trained a deep learning (DL)-based model to estimate the material distribution with the ICRP110 based human phantom as well as the digital Shepp–Logan phantom. The accuracy in quad-, dual-, and single-energy CT cases was investigated. The influence of beam-hardening artefacts, noise, and spectrum variations were analysed with testing datasets including elemental density and anatomical shape variations. Main results. The results indicated that this DL approach can realise precise MD, even with single-energy CT images. Moreover, noise, beam-hardening artefacts, and spectrum variations were shown to have minimal impact on the MD. Significance. Present results suggest that the difficulty to prepare a large CT database can be solved by introducing the virtual CT system and the proposed technique can be applied to clinical radiodiagnosis and radiotherapy.

Impact of beam-hardening corrections on proton relative stopping power estimates from single- and dual-energy CT.

A major contributing factor to proton range uncertainty is the conversion of computed tomography (CT) Hounsfield units (HU) to proton relative stopping power (RSP). This uncertainty is heightened in the presence of X‐ray beam‐hardening artifact (BHA), which has two manifestations: cupping and streaking, especially in and near bone tissue. This uncertainty can affect the accuracy of proton RSP calculation for treatment planning in proton radiotherapy. Dual‐energy CT (DECT) and iterative beam‐hardening correction (iBHC) both show promise in mitigating CT BHA. This present work attempts to analyze the relative robustness of iBHC and DECT techniques on both manifestations of BHA.The stoichiometric method for HU to RSP conversion was used for single‐energy CT (SECT) and DECT‐based monochromatic techniques using a tissue substitute phantom. Cupping BHA was simulated by measuring the HU of a bone substitute plug in wax/3D‐printed phantoms of increasing size. Streaking BHA was simulated by placing a solid water plug between two bone plugs in a wax phantom. Finally, the effect of varying calibration phantom size on RSP was calculated in an anthropomorphic head phantom.The RSP decreased −0.002 cm–1 as phantom size increased for SECT but remained largely constant when iBHC applied or with DECT techniques. The RSP varied a maximum of 2.60% in the presence of streaking BHA in SECT but was reduced to 1.40% with iBHC. For DECT techniques, the maximum difference was 2.40%, reduced to 0.6% with iBHC. Comparing calibration phantoms of 20‐ and 33‐cm diameter, maximum voxel differences of 5 mm in the water‐equivalent thickness were observed in the skull but reduced to 1.3 mm with iBHC. The DECT techniques excelled in mitigating cupping BHA, but streaking BHA still could be observed. The use of iBHC reduced RSP variation with BHA in both SECT and DECT techniques.

Simultaneous vessel segmentation and unenhanced prediction using self-supervised dual-task learning in 3D CTA (SVSUP)

Background and objective: The vessel segmentation in CT angiography (CTA) provides an important basis for automatic diagnosis and hemodynamics analysis. Virtual unenhanced (VU) CT images obtained by dual-energy CT can assist clinical diagnosis and reduce radiation dose by obviating true unenhanced imaging (UECT). However, accurate segmentation of all vessels in the head-neck CTA (HNCTA) remains a challenge, and VU images are currently not available from conventional single-energy CT imaging. Methods:In this paper, we proposed a self-supervised dual-task deep learning strategy to fully automatically segment all vessels and predict unenhanced CT images from single-energy HNCTA based on a developed iterative residual-sharing scheme. The underlying idea was to use the correlation between the two tasks to improve task performance while avoiding manual annotation for model training. Results: The feasibility of the strategy was verified using the data of 24 patients. For vessel segmentation task, the proposed model achieves a significantly higher average Dice coefficient (84.83%, P-values 10−3 in paired t-test) than the state-of-the-art segmentation model, vanilla VNet (78.94%), and several popular 3D vessel segmentation models, including Hessian-matrix based filter (62.59%), optically-oriented flux (66.33%), spherical flux model (66.91%), and deep vessel net (66.47%). For the unenhanced prediction task, the average ROI-based error compared to the UECT in the artery tissue is 6.1±4.5 HU, similar to previously reported 6.4±5.1 HU for VU reconstruction. Conclusions: Results show that the proposed dual-task framework can effectively improve the accuracy of vessel segmentation in HNCTA, and it is feasible to predict the unenhanced image from single-energy CTA, providing a potential new approach for radiation dose saving. Moreover, to our best knowledge, this is the first reported annotation-free deep learning-based full-image vessel segmentation for HNCTA.

Abstract 4139: Dual energy analysis of TKI response in GIST - results of a prospective trial

Abstract Objective: Within in a prospectively conducted trial (‘Unifying Advanced Treatment With Advanced Imaging’, GISTm3, NCT 03404076) we aimed at developing and validating a CT radiomics model to predict to response to tyrosine kinase inhibitors in GIST patients. We used the intratumoral iodine concentration which is less corroborated by tumor sclerosis or intratumoral hemorrhage than classical CT criteria. Materials and Methods: This is a prospective multi-center study of 94 patients (mean age 61 years; age range 28-83 years; 51m, 43f) who underwent a single-energy contrast-enhanced staging CT in a portal venous phase. All patients underwent subsequent preoperative imatinib therapy for at least 6 months (median 12 months, range 4-36 months) and follow-up CT examination. Patients were graded binary as responders and non-responders using their best response throughout the drug treatment course according to the vascular tumor burden to account for pseudo-progression under therapy. Response assessment was performed using RECIST 1.1, modified Choi (mChoi), vascular tumor burden (VTB), DECT vital iodine TB. Two radiologists performed a 3D-segmentation analysis of the GIST lesions on the pre-treatment CT using a dedicated radiomics software (Radiomics Version 1.0.9, Siemens Healthineers, Forchheim, Germany) and a visual evaluation of enhancement and non-enhancement parameters of each GIST lesion. Using a training dataset (n=17), a multivariable logistic regression by least absolute shrinkage and selection operator identified features that predicted therapy response was build. This model was then evaluated in the independent cohort (n=78) for temporal validation. Results: 77 GIST lesions responded to the drug. A total of 53 radiological visual features and radiomic features were rated reproducible (intraclass correlation &amp;gt;0.8). The radiological visual grading and the radiomic features alone resulted in a similar AUC (0.62, 95%CI 0.49-0.76 vs 0.64 95%CI 0.50-0.77). The final model which combined both radiological visual grading (3 features) and also 3 radiomic features had a significantly higher AUC (0.75, 95%CI 0.64-0.86; both p&amp;lt;0.01) when compared to both separate predictive models alone. Using DECT vital iodine TB, median PFS was significantly different between non-responders and responders (18.8 mos vs. 5.6 mos, resp.; p=.02). HR for progression for DECT vital iodine TB non-responders vs. responders was 6.9, 3.3 for VTB, 2.3 for RECIST 1.1, and 2.1 for mChoi. Conclusion: The study presents a predictive model that incorporates radiologist grading and radiomics features. DECT vital iodine TB criteria outperformed RECIST 1.1, VTB and mChoi for response assessment of metastatic GIST under TKI therapy. The technique should be very useful in guiding early management decisions in patients. Citation Format: Peter Hohenberger, Mathias Meyer, Thomas Henzler, Richard F. Riedel, Christina Messiou, Daniele Marin, Stefan Schoenberg. Dual energy analysis of TKI response in GIST - results of a prospective trial [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 4139.

Extracellular Volume Fraction Derived From Dual-Layer Spectral Detector Computed Tomography for Diagnosing Cervical Lymph Nodes Metastasis in Patients With Papillary Thyroid Cancer: A Preliminary Study.

ObjectivesThe current study evaluates the performance of dual-energy computed tomography (DECT) derived extracellular volume (ECV) fraction based on dual-layer spectral detector CT for diagnosing cervical lymph nodes (LNs) metastasis from papillary thyroid cancer (PTC) and compares it with the value of ECV derived from conventional single-energy CT (SECT).MethodsOne hundred and fifty-seven cervical LNs (81 non-metastatic and 76 metastatic) were recruited. Among them, 59 cervical LNs (27 non-metastatic and 32 metastatic) were affected by cervical root artifact on the contrast-enhanced CT images in the arterial phase. Both the SECT-derived ECV fraction (ECVS) and the DECT-derived ECV fraction (ECVD) were calculated. A Pearson correlation coefficient and a Bland–Altman analysis were performed to evaluate the correlations between ECVD and ECVS. Receiver operator characteristic curves analysis and the Delong method were performed to assess and compare the diagnostic performance.ResultsECVD correlated significantly with ECVS (r = 0.925; p <0.001) with a small bias (−0.6). Metastatic LNs showed significantly higher ECVD (42.41% vs 22.53%, p <0.001) and ECVS (39.18% vs 25.45%, p <0.001) than non-metastatic LNs. By setting an ECVD of 36.45% as the cut-off value, optimal diagnostic performance could be achieved (AUC = 0.813), which was comparable with that of ECVS (cut-off value = 34.99%; AUC = 0.793) (p = 0.265). For LNs affected by cervical root artifact, ECVD also showed favorable efficiency (AUC = 0.756), which was also comparable with that of ECVS (AUC = 0.716) (p = 0.244).ConclusionsECVD showed a significant correlation with ECVS. Compared with ECVS, ECVD showed comparable performance in diagnosing metastatic cervical LNs in PTC patients, even though the LNs were affected by cervical root artifacts on arterial phase CT.

Radiation and iodine dose reduced thoraco-abdomino-pelvic dual-energy CT at 40 keV reconstructed with deep learning image reconstruction.

To evaluate the feasibility of a simultaneous reduction of radiation and iodine doses in dual-energy thoraco-abdomino-pelvic CT reconstructed with deep learning image reconstruction (DLIR). Thoraco-abdomino-pelvic CT was prospectively performed in 111 participants; 52 participants underwent a standard-dose single-energy CT with a standard iodine dose (600 mgI/kg; SD group), while 59 underwent a low-dose dual-energy CT with a reduced iodine dose [300 mgI/kg; double low-dose (DLD) group]. CT data were reconstructed with a hybrid iterative reconstruction in the SD group and a high-strength level of DLIR at 40 keV in the DLD group. Two radiologists measured the CT numbers of the descending and abdominal aorta, portal vein, hepatic vein, inferior vena cava, liver, pancreas, spleen, and kidney, and background noise. Two other radiologists assessed diagnostic acceptability using a 5-point scale. The CT dose-index volume (CTDIvol), iodine weight, CT numbers of anatomical structures, background noise, and diagnostic acceptability were compared between the two groups using Mann-Whitney U test. The median CTDIvol [10 mGy; interquartile range (IQR), 9-13 mGy vs 4 mGy; IQR, 4-5 mGy] and median iodine weight (35 g; IQR, 31-38 g vs 16 g; IQR, 14-18 g) were lower in the DLD group than in the SD group (p < 0.001 for each). The CT numbers of all anatomical structures and background noise were higher in the DLD group than in the SD group (p < 0.001 for all). The diagnostic image quality was obtained in 100% (52/52) of participants in the SD group and 95% (56/59) of participants in the DLD group. Virtual monochromatic images at 40 keV reconstructed with DLIR could achieve half doses of radiation and iodine while maintaining diagnostic image quality. Virtual monochromatic images at 40 keV reconstructed with DLIR algorithm allowed to reduce the doses of radiation and iodine while maintaining diagnostic image quality.

Jointly Optimized Deep Neural Networks to Synthesize Monoenergetic Images from Single-Energy CT Angiography for Improving Classification of Pulmonary Embolism.

Detector-based spectral CT offers the possibility of obtaining spectral information from which discrete acquisitions at different energy levels can be derived, yielding so-called virtual monoenergetic images (VMI). In this study, we aimed to develop a jointly optimized deep-learning framework based on dual-energy CT pulmonary angiography (DE-CTPA) data to generate synthetic monoenergetic images (SMI) for improving automatic pulmonary embolism (PE) detection in single-energy CTPA scans. For this purpose, we used two datasets: our institutional DE-CTPA dataset , comprising polyenergetic arterial series and the corresponding VMI at low-energy levels (40 keV) with 7892 image pairs, and a 10% subset of the 2020 RSNA Pulmonary Embolism CT Dataset , which consisted of 161,253 polyenergetic images with dichotomous slice-wise annotations (PE/no PE). We trained a fully convolutional encoder-decoder on to generate SMI from single-energy CTPA scans of , which were then fed into a ResNet50 network for training of the downstream PE classification task. The quantitative results on the reconstruction ability of our framework revealed high-quality visual SMI predictions with reconstruction results of 0.984 ± 0.002 (structural similarity) and 41.706 ± 0.547 dB (peak signal-to-noise ratio). PE classification resulted in an AUC of 0.84 for our model, which achieved improved performance compared to other naïve approaches with AUCs up to 0.81. Our study stresses the role of using joint optimization strategies for deep-learning algorithms to improve automatic PE detection. The proposed pipeline may prove to be beneficial for computer-aided detection systems and could help rescue CTPA studies with suboptimal opacification of the pulmonary arteries from single-energy CT scanners.

Image quality comparison of single-energy and dual-energy computed tomography for head and neck patients: a prospective randomized study

ObjectivesThe aim of this study was to compare the quality of images obtained using single-energy computed tomography (SECT) performed with automated tube voltage adaptation (TVA) with dual-energy CT (DECT) weighted average images.MethodsEighty patients were prospectively randomized to undergo either SECT with TVA (n = 40, ref. mAs 200) or radiation dose–matched DECT (n = 40, 80/Sn150 kV, ref. mAs tube A 91/tube B 61) on a dual-source CT scanner. Objective image quality was evaluated as dose-normalized contrast-to-noise ratio (CNRD) for the jugular veins relative to fatty tissue and muscle tissue and for muscle tissue relative to fatty issue. For subjective image quality, reproduction of anatomical structures, image artifacts, image noise, spatial resolution, and overall diagnostic acceptability were evaluated at sixteen anatomical substructures using Likert-type scales.ResultsEffective radiation dose (ED) was comparable between SECT and DECT study groups (2.9 ± 0.6 mSv/3.1 ± 0.7 mSv, p = 0.5). All examinations were rated as excellent or good for clinical diagnosis. Compared to the CNRD in the SECT group, the CNRD in the DECT group was significantly higher for the jugular veins relative to fatty tissue (7.51/6.08, p < 0.001) and for muscle tissue relative to fatty tissue (4.18/2.90, p < 0.001). The CNRD for the jugular veins relative to muscle tissue (3.33/3.18, p = 0.51) was comparable between groups. Image artifacts were less pronounced and overall diagnostic acceptability was higher in the DECT group (all p = 0.01).ConclusionsDECT weighted average images deliver higher objective and subjective image quality than SECT performed with TVA in head and neck imaging.Key Points• Weighted average images derived from dual-energy CT deliver higher objective and subjective image quality than single-energy CT using automated tube voltage adaptation in head and neck imaging.• If available, dual-energy CT acquisition may be preferred over automated low tube voltage adopted single-energy CT for both malignant and non-malignant conditions.

Potential of a Second-Generation Dual-Layer Spectral CT for Dose Calculation in Particle Therapy Treatment Planning.

In particle therapy treatment planning, dose calculation is conducted using patient-specific maps of tissue ion stopping power ratio (SPR) to predict beam ranges. Improving patient-specific SPR prediction is therefore essential for accurate dose calculation. In this study, we investigated the use of the Spectral CT 7500, a second-generation dual-layer spectral computed tomography (DLCT) system, as an alternative to conventional single-energy CT (SECT) for patient-specific SPR prediction. This dual-energy CT (DECT)-based method allows for the direct prediction of SPR from quantitative measurements of relative electron density and effective atomic number using the Bethe equation, whereas the conventional SECT-based method consists of indirect image data-based prediction through the conversion of calibrated CT numbers to SPR. The performance of the Spectral CT 7500 in particle therapy treatment planning was characterized by conducting a thorough analysis of its SPR prediction accuracy for both tissue-equivalent materials and common non-tissue implant materials. In both instances, DLCT was found to reduce uncertainty in SPR predictions compared to SECT. Mean deviations of 0.7% and 1.6% from measured SPR values were found for DLCT- and SECT-based predictions, respectively, in tissue-equivalent materials. Furthermore, end-to-end analyses of DLCT-based treatment planning were performed for proton, helium, and carbon ion therapies with anthropomorphic head and pelvic phantoms. 3D gamma analysis was performed with ionization chamber array measurements as the reference. DLCT-predicted dose distributions revealed higher passing rates compared to SECT-predicted dose distributions. In the DLCT-based treatment plans, measured distal-edge evaluation layers were within 1 mm of their predicted positions, demonstrating the accuracy of DLCT-based particle range prediction. This study demonstrated that the use of the Spectral CT 7500 in particle therapy treatment planning may lead to better agreement between planned and delivered dose compared to current clinical SECT systems.

Dual-Energy CT and Cinematic Rendering to Improve Assessment of Pelvic Fracture Instability.

Background Grading of pelvic fracture instability is challenging in patients with pelvic binders. Dual-energy CT (DECT) and cinematic rendering can provide ancillary information regarding osteoligamentous integrity, but the utility of these tools remains unknown. Purpose To assess the added diagnostic value of DECT and cinematic rendering, with respect to single-energy CT (SECT), for discriminating any instability and translational instability in patients with pelvic binders. Materials and Methods In this retrospective analysis, consecutive adult patients (age ≥18 years) were stabilized with pelvic binders and scanned in dual-energy mode using a 128-section CT scanner at one level I trauma center between August 2016 and January 2019. Young-Burgess grading by orthopedists served as the reference standard. Two radiologists performed blinded consensus grading with the Young-Burgess system in three reading sessions (session 1, SECT; session 2, SECT plus DECT; session 3, SECT plus DECT and cinematic rendering). Lateral compression (LC) type 1 (LC-1) and anteroposterior compression (APC) type 1 (APC-1) injuries were considered stable; LC type 2 and APC type 2, rotationally unstable; and LC type 3, APC type 3, and vertical shear, translationally unstable. Diagnostic performance for any instability and translational instability was compared between reading sessions using the McNemar and DeLong tests. Radiologist agreement with the orthopedic reference standard was calculated with the weighted κ statistic. Results Fifty-four patients (mean age, 41 years ± 16 [SD]; 41 men) were analyzed. Diagnostic performance was greater with SECT plus DECT and cinematic rendering compared with SECT alone for any instability, with an area under the receiver operating characteristic curve (AUC) of 0.67 for SECT alone and 0.82 for SECT plus DECT and cinematic rendering (P = .04); for translational instability, the AUCs were 0.80 for SECT alone and 0.95 for SECT plus DECT and cinematic rendering (P = .01). For any instability, corresponding sensitivities were 61% (22 of 36 patients) for SECT alone and 86% (31 of 36 patients) for SECT plus DECT and cinematic rendering (P < .001). The corresponding specificities were 72% (13 of 18 patients) and 78% (14 of 18 patients), respectively (P > .99). Agreement (κ value) between radiologists and orthopedist reference standard improved from 0.44 to 0.76 for SECT versus the combination of SECT, DECT, and cinematic rendering. Conclusion Combined use of single-energy CT, dual-energy CT, and cinematic rendering improved instability assessment over that with single-energy CT alone. © RSNA, 2022 Online supplemental material is available for this article.

A generalized simultaneous algebraic reconstruction technique (GSART) for dual-energy X-ray computed tomography.

Dual-energy computed tomography (DECT) is a widely used and actively researched imaging modality that can estimate the physical properties of an object more accurately than single-energy CT (SECT). Recently, iterative reconstruction methods called one-step methods have received attention among various approaches since they can resolve the intermingled limitations of the conventional methods. However, the one-step methods typically have expensive computational costs, and their material decomposition performance is largely affected by the accuracy in the spectral coefficients estimation. In this study, we aim to develop an efficient one-step algorithm that can effectively decompose into the basis material maps and is less sensitive to the accuracy of the spectral coefficients. By use of a new loss function that employs the non-linear forward model and the weighted squared errors, we propose a one-step reconstruction algorithm named generalized simultaneous algebraic reconstruction technique (GSART). The proposed algorithm was compared with the image-domain material decomposition and other existing one-step reconstruction algorithm. In both simulation and experimental studies, we demonstrated that the proposed algorithm effectively reduced the beam-hardening artifacts thereby increasing the accuracy in the material decomposition. The proposed one-step reconstruction for material decomposition in dual-energy CT outperformed the image-domain approach and the existing one-step algorithm. We believe that the proposed method is a practically very useful addition to the material-selective image reconstruction field.

Pseudo low-energy monochromatic imaging of head and neck cancers: Deep learning image reconstruction with dual-energy CT.

Low-energy virtual monochromatic images (VMIs) derived from dual-energy computed tomography (DECT) systems improve lesion conspicuity of head and neck cancer over single-energy CT (SECT). However, DECT systems are installed in a limited number of facilities; thus, only a few facilities benefit from VMIs. In this work, we present a deep learning (DL) architecture suitable for generating pseudo low-energy VMIs of head and neck cancers for facilities that employ SECT imaging. We retrospectively analyzed 115 patients with head and neck cancers who underwent contrast enhanced DECT. VMIs at 70 and 50keV were used as the input and ground truth (GT), respectively. We divided them into two datasets: for DL (104 patients) and for inference with SECT (11 patients). We compared four DL architectures: U-Net, DenseNet-based, and two ResNet-based models. Pseudo VMIs at 50keV (pVMI50keV) were compared with the GT in terms of the mean absolute error (MAE) of Hounsfield unit (HU) values, peak signal-to-noise ratio (PSNR), and structural similarity (SSIM). The HU values for tumors, vessels, parotid glands, muscle, fat, and bone were evaluated. pVMI50keV were generated from actual SECT images and the HU values were evaluated. U-Net produced the lowest MAE (13.32 ± 2.20 HU) and highest PSNR (47.03 ± 2.33dB) and SSIM (0.9965 ± 0.0009), with statistically significant differences (P < 0.001). The HU evaluation showed good agreement between the GT and U-Net. U-Net produced the smallest absolute HU difference for the tumor, at < 5.0 HU. Quantitative comparisons of physical parameters demonstrated that the proposed U-Net could generate high accuracy pVMI50keV in a shorter time compared with the established DL architectures. Although further evaluation on diagnostic accuracy is required, our method can help obtain low-energy VMI from SECT images without DECT systems.

Effective Spatial Resolution of Photon Counting CT for Imaging of Trabecular Structures is Superior to Conventional Clinical CT and Similar to High Resolution Peripheral CT.

Photon counting computed tomography (PCCT) might offer an effective spatial resolution that is significantly improved compared with conventional state-of-the-art computed tomography (CT) and even provide a microstructural level of detail similar to high-resolution peripheral CT (HR-pQCT). The aim of this study was to evaluate the volumetric effective spatial resolution of clinically approved PCCT as an alternative to HR-pQCT for ex vivo or preclinical high-resolution imaging of bone microstructure. The experiment contained 5 human vertebrae embedded in epoxy resin, which were scanned 3 times each, and on 3 different clinical CT scanners: a PCCT (Naeotom Alpha), a dual-energy CT (Somatom Force [SF]), and a single-energy CT (Somatom Sensation 40 [S40]), all manufactured by Siemens Healthineers (Erlangen, Germany). Scans were performed with a tube voltage of 120 kVp and, to provide maximum scan performance and minimum noise deterioration, with exposures of 1500 mAs (SF), 2400 mAs (S40), and 4500 mAs (PCCT) and low slice increments of 0.1 (PCCT) and 0.3 mm (SF, S40). Images were reconstructed with sharp and very sharp bone kernels, Br68 and Br76 (PCCT), Br64 (SF), and B65s and B75h (S40). Ground truth information was obtained from an XtremeCT scanner (Scanco, Brüttisellen, Switzerland). Voxel-wise comparison was performed after registration, calibration, and resampling of the volumes to isotropic voxel size of 0.164 mm. Three-dimensional point spread- and modulation-transfer functions were calculated with Wiener's deconvolution in the anatomical trabecular structure, allowing optimum estimation of device- and kernel-specific smoothing properties as well as specimen-related diffraction effects on the measurement. At high contrast (modulation transfer function [MTF] of 10%), radial effective resolutions of PCCT were 10.5 lp/cm (minimum resolvable object size 476 μm) for kernel Br68 and 16.9 lp/cm (295 μm) for kernel Br76. At low contrast (MTF 5%), radial effective spatial resolutions were 10.8 lp/cm (464 μm) for kernel Br68 and 30.5 lp/cm (164 μm) for kernel Br76. Axial effective resolutions of PCCT for both kernels were between 27.0 (185 μm) and 29.9 lp/cm (167 μm). Spatial resolutions with kernel Br76 might possibly be still higher but were technically limited by the isotropic voxel size of 164 μm. The effective volumetric resolutions of PCCT with kernel Br76 ranged between 61.9 (MTF 10%) and 222.4 (MTF 5%) elements per cubic mm. Photon counting CT improved the effective volumetric resolution by factor 5.5 (MTF 10%) and 18 (MTF 5%) compared with SF and by a factor of 8.7 (MTF 10%) and 20 (MTF 5%) compared with S40. Photon counting CT allowed obtaining similar structural information as HR-pQCT. The effective spatial resolution of PCCT in trabecular bone imaging was comparable with that of HR-pQCT and more than 5 times higher compared with conventional CT. For ex vivo samples and when patient radiation dose can be neglected, PCCT allows imaging bone microstructure at a preclinical level of detail.

Machine learning based oxygen and carbon concentration derivation using dual-energy CT for PET-based dose verification in proton therapy.

Online dose verification based on proton-induced positron emitters requires high accuracy in the assignment of elemental composition (e.g., C and O). We developed a machine learning framework for deriving oxygen and carbon concentration based on dual-energy CT (DECT). Digital phantoms at the head site were constructed based on single-energy CT (SECT) and stoichiometric calibration. DECT images (80 and 140kVp) were synthesized using two methods: (1) theoretical CT numbers with Gaussian noise (method 1) and (2) forward/backward image reconstruction with poly-energetic energy spectrum and Poisson noise modeled (method 2). Two architectures of convolutional neural networks, UNet and ResNet, were investigated to map from DECT images to C/O weights. Four cases (UNet-1: Method 1+UNet, ResNet-1: Method 1+ResNet, UNet-2: Method 2+UNet, and ResNet-2: Method 2 +ResNet) were tested for different tissue types and different noise levels. Monte-Carlo simulation was employed to identify the impact of fluctuation in oxygen and carbon concentration on activity/dose distribution. When no noise is present, all four cases are able to obtain <2% mean absolute errors and <4% root mean square error (RMSE). For the worst image quality (e.g., lowest image SNR), the RMSE for O among all tissue types is 3.02% (UNet-1), 4.46% (ResNet-1), 4.38% (UNet-2), and 6.31% (ResNet-2), respectively. For UNet-1 and ResNet-1, the model performed slightly better in terms of RMSE for skeletal tissue than soft tissues. Such a trend is not observed for UNet-2 and ResNet-2. With regard to the comparison between UNet and ResNet, different accuracy and noise immunity are observed. The activity profiles exhibit 3%-5% difference in terms of mean relative error between the ground truth and machine learning outcome. We explored the feasibility of a machine learning framework to derive elemental concentration of oxygen and carbon based on DECT images. Two machine learning models, UNet and ResNet, are able to utilize spatial correlation and obtain accurate carbon and oxygen concentration. This study lays a foundation for us to apply the proposed approach to clinical DECT images.

Deep Learning and Domain-Specific Knowledge to Segment the Liver from Synthetic Dual Energy CT Iodine Scans.

We map single energy CT (SECT) scans to synthetic dual-energy CT (synth-DECT) material density iodine (MDI) scans using deep learning (DL) and demonstrate their value for liver segmentation. A 2D pix2pix (P2P) network was trained on 100 abdominal DECT scans to infer synth-DECT MDI scans from SECT scans. The source and target domain were paired with DECT monochromatic 70 keV and MDI scans. The trained P2P algorithm then transformed 140 public SECT scans to synth-DECT scans. We split 131 scans into 60% train, 20% tune, and 20% held-out test to train four existing liver segmentation frameworks. The remaining nine low-dose SECT scans tested system generalization. Segmentation accuracy was measured with the dice coefficient (DSC). The DSC per slice was computed to identify sources of error. With synth-DECT (and SECT) scans, an average DSC score of () and () was achieved on the held-out and generalization test sets. Synth-DECT-trained systems required less data to perform as well as SECT-trained systems. Low DSC scores were primarily observed around the scan margin or due to non-liver tissue or distortions within ground-truth annotations. In general, training with synth-DECT scans resulted in improved segmentation performance with less data.

Dual energy CT angiography for lower extremity trauma: comparison with conventional CT.

To determine if rapid switching dual-energy CT (rsDECT) provides improvements in vascular attenuation, subjective diagnostic quality, and detection of vascular injuries compared to conventional CT in trauma patients undergoing lower extremity CT angiography. The IRB approved this HIPAA-compliant retrospective study. Informed consent was waived. Thirty-nine patients with acute lower extremity trauma including gunshot wounds (19 patients), falls (6 patients), motor vehicle accidents (5 patients), stab wounds (4 patients), pedestrian struck (2 patients), and unspecified trauma (3 patients) who underwent IV contrast-enhanced rsDECT angiography of the lower extremities on a rapid-kilovoltage-switching dual-energy CT scanner (Revolution CT, GE Healthcare) from 6/4/2019 to 1/14/2021 were studied. 7 patients were initially positive for vascular injury on conventional CT, while 32 patients were negative. Blended CT reconstructions simulating conventional 120 kVp single-energy CT, and rsDECT reconstructions (50keV monoenergetic and iodine density maps) were reviewed. Region of interest contrast density measurements were recorded on conventional and 50keV reconstructions at multiple levels from the distal aorta to the ankles and compared using Wilcoxon signed-rank tests. Vascular contrast density of 150 HU was used as a minimum cutoff for diagnostically adequate opacification. Images were interpreted by consensus for subjective image quality and presence of injury on both conventional and DECT reconstructions by two fellowship-trained abdominal radiologists blinded to clinical data, and compared using the paired McNemar test. Density measurement differences between conventional and rsDECT at every level of the bilateral lower extremities were statistically significant, with the average difference ranging from 304 Hounsfield units (HU) in the distal aorta to 121 HU at the ankles (p < 0.0001). Using a cutoff of 150 HU, 9.5% (93/976) and 3.1% of vascular segments (30/976) were considered non-diagnostic in the conventional and rsDECT groups, respectively, a reduction of 67.7% (p < 0.0001). Subjective image quality between conventional and rsDECT was not statistically significant, but there were 7 vascular segments out of a total of 976 segments across 3 different patients out of a total of 39 patients in which diagnostic quality was upgraded from non-diagnostic on conventional CT to diagnostic on rsDECT, all of which showed suboptimal bolus quality on conventional CT (unmeasurable in 4/7 and ranging from 56-146 HU in the remaining 3). Similarly, rate of injury detection was identical between conventional CT (15/39 patients) and DECT (15/39 patients). Vascular contrast density is statistically significantly higher with rsDECT compared to conventional CT, and subjective image quality was upgraded from non-diagnostic on conventional CT to diagnostic on rsDECT in 7 vascular segments across 3 patients. rsDECT provides greater vascular contrast density than conventional CT, with potential to salvage suboptimal examinations caused by poor contrast opacification.

Robustness of CT radiomics features: consistency within and between single-energy CT and dual-energy CT

ObjectivesTo evaluate inter- and intra- scan mode and scanner repeatability and reproducibility of radiomics features within and between single-energy CT (SECT) and dual-energy CT (DECT).MethodsA standardized phantom with sixteen rods of clinical-relevant densities was scanned on seven DECT-capable scanners and three SECT-only scanners. The acquisition parameters were selected to present typical abdomen-pelvic examinations with the same voxel size. Images of SECT at 120 kVp and corresponding 120 kVp-like virtual monochromatic images (VMIs) in DECT which were generated according to scanners were analyzed. Regions of interest were drawn with rigid registrations to avoid variations due to segmentation. Radiomics features were extracted via Pyradiomics platform. Test-retest repeatability was evaluated by Bland-Altman analysis for repeated scans. Intra-scanner reproducibility for different scan modes was tested by intraclass correlation coefficient (ICC) and concordance correlation coefficient (CCC). Inter-scanner reproducibility among different scanners for same scan mode was assessed by coefficient of variation (CV) and quartile coefficient of dispersion (QCD).ResultsThe test-retest analysis presented that 92.91% and 87.02% of the 94 assessed features were repeatable for SECT 120kVp and DECT 120 kVp-like VMIs, respectively. The intra-scanner analysis for SECT 120kVp vs DECT 120 kVp-like VMIs demonstrated that 10.76% and 10.28% of features were with ICC > 0.90 and CCC > 0.90, respectively. The inter-scanner analysis showed that 17.09% and 27.73% of features for SECT 120kVp were with CV < 10% and QCD < 10%, and 15.16% and 32.78% for DECT 120 kVp-like VMIs, respectively.ConclusionsThe majority of radiomics features were non-reproducible within and between SECT and DECT.Key Points• Although the test-retest analysis showed high repeatability for radiomics features, the overall reproducibility of radiomics features within and between SECT and DECT was low.• Only about one-tenth of radiomics features extracted from SECT images and corresponding DECT images did match each other, even their average photon energy levels were considered alike, indicating that the scan mode potentially altered the radiomics features.• Less than one-fifth of radiomics features were reproducible among multiple SECT and DECT scanners, regardless of their fixed acquisition and reconstruction parameters, suggesting the necessity of scanning protocol adjustment and post-scan harmonization process.