Single-energy CT Images Research Articles

Image quality of virtual monochromatic and material density iodine images for evaluation of head and neck neoplasms using deep learning-based CT image reconstruction – A retrospective observational study

PurposeTo compare the quality of deep learning image reconstructed (DLIR) virtual monochromatic images (VMI) and material density (MD) iodine images from dual-energy computed tomography (DECT) for the evaluation of head and neck neoplasms with CT scans from a conventional single-energy protocol. MethodA total of 294 head and neck CT scans (98 VMIs operated at 60 keV, 102 MD iodine images, and 94 images from a 120 kVp single-energy CT (SECT) protocol) were retrospectively evaluated. VMIs and MD iodine images were generated using the Gemstone Spectral Imaging (GSI) mode using DLIR and metal artifact reduction (MAR) algorithms. SECT images were generated using adaptive statistical iterative reconstruction (ASIR-V). Images were scored by two independent readers on a 6-point Likert-type scale for overall image quality, vessel contrast, soft tissue contrast, noise texture, noise intensity, artifact reduction, and sharpness. ResultsSubjective overall image quality was rated as superior or excellent in 98 % of DLIR-based MD iodine images and VMIs, but only in 55 % of ASIR-V-based SECT images. For each individual quality criterion, image quality of VMIs and MD iodine images was rated as better than that of SECT images (p < 0.001 in each case). Noise texture and intensity were rated better in MD iodine images than in VMIs. ConclusionDECT using both DLIR and MAR for the generation of VMIs and MD iodine images resulted in higher subjective quality of oncologic head and neck images than ASIR-V-based SECT. Noise reduction and noise texture were best achieved with DLIR-based MD iodine images.

Dual-energy CT applications on liver imaging: what radiologists and radiographers should know? A systematic review.

This review aims to provide a comprehensive summary of DECT techniques, acquisition workflows, and post-processing methods. By doing so, we aim to elucidate the advantages and disadvantages of DECT compared to conventional single-energy CT imaging. A systematic search was conducted on MEDLINE/EMBASE for DECT studies in liver imaging published between 1980 and 2024. Information regarding study design and endpoints, patient characteristics, DECT technical parameters, radiation dose, iodinated contrast agent (ICA) administration and postprocessing methods were extracted. Technical parameters, including DECT phase, field of view, pitch, collimation, rotation time, arterial phase timing (from injection), and venous timing (from injection) from the included studies were reported, along with formal narrative synthesis of main DECT applications for liver imaging. Out of the initially identified 234 articles, 153 met the inclusion criteria. Extensive variability in acquisition parameters was observed, except for tube voltage (80/140 kVp combination reported in 50% of articles) and ICA administration (1.5mL/kg at 3-4mL/s, reported in 91% of articles). Radiation dose information was provided in only 40% of articles (range: 6-80mGy), and virtual non-contrast imaging (VNC) emerged as a common strategy to reduce the radiation dose. The primary application of DECT post-processed images was in detecting focal liver lesions (47% of articles), with predominance of study focusing on hepatocellular carcinoma (HCC) (27%). Furthermore, a significant proportion of the articles (16%) focused on enhancing DECT protocols, while 15% explored metastasis detection. Our review recommends using 80/140 kVp tube voltage with 1.5mL/kg ICA at 3-4mL/s flow rate. Post-processing should include low keV-VMI for enhanced lesion detection, IMs for tumor iodine content evaluation, and VNC for dose reduction. However, heterogeneous literature hinders protocol standardization.

Variation in Hounsfield unit calculated using dual-energy computed tomography: comparison of dual-layer, dual-source, and fast kilovoltage switching technique.

The purpose of the study is to investigate the variation in Hounsfield unit (HU) values calculated using dual-energy computed tomography (DECT) scanners. A tissue characterization phantom inserting 16 reference materials were scanned three times using DECT scanners [dual-layer CT (DLCT), dual-source CT (DSCT), and fast kilovoltage switching CT (FKSCT)] changing scanning conditions. The single-energy CT images (120 or 140 kVp), and virtual monochromatic images at 70keV (VMI70) and 140keV (VMI140) were reconstructed, and the HU values of each reference material were measured. The difference in HU values was larger when the phantom was scanned using the half dose with wrapping with rubber (strong beam-hardening effect) compared with the full dose without the rubber (reference condition), and the difference was larger as the electron density increased. For SECT, the difference in HU values against the reference condition measured by the DSCT (3.2 ± 5.0 HU) was significantly smaller (p < 0.05) than that using DLCT with 120 kVp (22.4 ± 23.8 HU), DLCT with 140 kVp (11.4 ± 12.8 HU), and FKSCT (13.4 ± 14.3 HU). The respective difference in HU values in the VMI70 and VMI140 measured using the DSCT (10.8 ± 17.1 and 3.5 ± 4.1 HU) and FKSCT (11.5 ± 21.8 and 5.5 ± 10.4 HU) were significantly smaller than those measured using the DLCT120 (23.1 ± 27.5 and 12.4 ± 9.4 HU) and DLCT140 (22.3 ± 28.6 and 13.1 ± 11.4 HU). The HU values and the susceptibility to beam-hardening effects varied widely depending on the DECT scanners.

Synthetic Low-Energy Monochromatic Image Generation in Single-Energy Computed Tomography System Using a Transformer-Based Deep Learning Model.

While dual-energy computed tomography (DECT) technology introduces energy-specific information in clinical practice, single-energy CT (SECT) is predominantly used, limiting the number of people who can benefit from DECT. This study proposed a novel method to generate synthetic low-energy virtual monochromatic images at 50keV (sVMI50keV) from SECT images using a transformer-based deep learning model, SwinUNETR. Data were obtained from 85 patients who underwent head and neck radiotherapy. Among these, the model was built using data from 70 patients for whom only DECT images were available. The remaining 15 patients, for whom both DECT and SECT images were available, were used to predict from the actual SECT images. We used the SwinUNETR model to generate sVMI50keV. The image quality was evaluated, and the results were compared with those of the convolutional neural network-based model, Unet. The mean absolute errors from the true VMI50keV were 36.5 ± 4.9 and 33.0 ± 4.4 Hounsfield units for Unet and SwinUNETR, respectively. SwinUNETR yielded smaller errors in tissue attenuation values compared with those of Unet. The contrast changes in sVMI50keV generated by SwinUNETR from SECT were closer to those of DECT-derived VMI50keV than the contrast changes in Unet-generated sVMI50keV. This study demonstrated the potential of transformer-based models for generating synthetic low-energy VMIs from SECT images, thereby improving the image quality of head and neck cancer imaging. It provides a practical and feasible solution to obtain low-energy VMIs from SECT data that can benefit a large number of facilities and patients without access to DECT technology.

Conversion of single-energy CT to parametric maps of dual-energy CT using convolutional neural network.

We propose a deep learning (DL) multitask learning framework using convolutional neural network for a direct conversion of single-energy CT (SECT) to 3 different parametric maps of dual-energy CT (DECT): virtual-monochromatic image (VMI), effective atomic number (EAN), and relative electron density (RED). We propose VMI-Net for conversion of SECT to 70, 120, and 200 keV VMIs. In addition, EAN-Net and RED-Net were also developed to convert SECT to EAN and RED. We trained and validated our model using 67 patients collected between 2019 and 2020. Single-layer CT images with 120 kVp acquired by the DECT (IQon spectral CT; Philips Healthcare, Amsterdam, Netherlands) were used as input, while the VMIs, EAN, and RED acquired by the same device were used as target. The performance of the DL framework was evaluated by absolute difference (AD) and relative difference (RD). The VMI-Net converted 120 kVp SECT to the VMIs with AD of 9.02 Hounsfield Unit, and RD of 0.41% compared to the ground truth VMIs. The ADs of the converted EAN and RED were 0.29 and 0.96, respectively, while the RDs were 1.99% and 0.50% for the converted EAN and RED, respectively. SECT images were directly converted to the 3 parametric maps of DECT (ie, VMIs, EAN, and RED). By using this model, one can generate the parametric information from SECT images without DECT device. Our model can help investigate the parametric information from SECT retrospectively. DL framework enables converting SECT to various high-quality parametric maps of DECT.

Artificial intelligence-based image-domain material decomposition in single-energy computed tomography for head and neck cancer.

While dual-energy computed tomography (DECT) images provide clinically useful information than single-energy CT (SECT), SECT remains the most widely used CT system globally, and only a few institutions can use DECT. This study aimed to establish an artificial intelligence (AI)-based image-domain material decomposition technique using multiple keV-output learning of virtual monochromatic images (VMIs) to create DECT-equivalent images from SECT images. This study involved 82 patients with head and neck cancer. Of these, the AI model was built with data from the 67 patients with only DECT scans, while 15 patients with both SECT and DECT scans were used for SECT testing. Our AI model generated VMI50keV and VMI100keV from VMI70keV equivalent to 120-kVp SECT images. We introduced a loss function for material density images (MDIs) in addition to the loss for VMIs. For comparison, we trained the same model with the loss for VMIs only. DECT-equivalent images were generated from SECT images and compared with the true DECT images. The prediction time was 5.4s per patient. The proposed method with the MDI loss function quantitatively provided more accurate DECT-equivalent images than the model trained with the loss for VMIs only. Using real 120-kVp SECT images, the trained model produced precise DECT images of excellent quality. In this study, we developed an AI-based material decomposition approach for head and neck cancer patients by introducing the loss function for MDIs via multiple keV-output learning. Our results suggest the feasibility of AI-based image-domain material decomposition in a conventional SECT system without a DECT scanner.

Deep-learned generation of renal dual-energy CT from a single-energy scan

To investigate the role of the deep-learning (DL) method in the generation of dual-energy computed tomography (DECT) images from single-energy images for precise diagnosis of kidney stone type. DECT of 23 patients was acquired, and the stone types were investigated based on the DECT software suggestions. The data were divided into two paired groups:120 kVp input and 80 kVp target and 120 kVp input and 135 kVp targets, p2p-UNet-GAN was exploited to generate the different energy images based on the common CT protocols. The images generated of the generative adversarial network (GAN) network were evaluated based on the SSIM, PSNR, and MSE metrics, and the values were estimated as 0.85-0.95, 28-32, and 0.85-0.89 respectively. The attenuation ratio of test patient images were estimated and compared with real patient reports. The network achieved high accuracy in stone region localisation and resulted in accurate stone type predictions. This study presents a useful method based on the DL technique to reduce patient radiation dose and facilitate the prediction of urinary stone types using single-energy CT imaging.

A Study on the Comparison of VNCa and VMI+ Image Quality and Optimized Method according to kV Modulation of DECT: A Porcine Ankle Ligament Model

This study conducted a quantitative and qualitative assessment of the effectiveness of Single-Energy and Dual-Energy Virtual non-calcium imaging, as well as Virtual Monoenergetic Imaging at 55, 65, and 75 keV, for diagnosing ligament conditions with regard to tube voltage modulation. A porcine hindlimb ankle ligament model was utilized for this evaluation. The two widest regions within the ligament model were designated as regions of interest, and measurements of Hounsfield Units, Signal-to-Noise Ratios, and Contrast-to-Noise Ratios were obtained. Quantitative evaluation was then conducted based on the average values. Furthermore, qualitative assessments of ligament diagnosis were carried out by five musculoskeletal radiologists and five radiological technologists, each with over five years of experience in Computed Tomography laboratory work. Following both quantitative and qualitative evaluations, it was observed that the Dual-Energy Virtual non-calcium image obtained at 70/Sn150 kVp and the Virtual Monoenergetic Imaging Plus 65 keV image exhibited superior image quality compared to the Single-Energy CT image. These differences were statistically significant (p&lt;0.05). Moreover, the highest image quality was noted at 65 keV within the Virtual Monoenergetic Imaging Plus energy range. The Dual-Energy Virtual non-calcium image was found to be more suitable for imaging ligaments than the Virtual Monoenergetic Imaging Plus 65 keV image.(p&lt;0.05) Notably, lower tube voltages were associated with improved image quality across all images. Consequently, it was determined that 70/Sn150 kVp Dual-Energy Virtual non-calcium images are more optimized than Single-Energy CT and Virtual Monoenergetic Imaging Plus 65 keV images for diagnosing ligament diseases in patients who present challenges for Magnetic Resonance Imaging and in emergency cases. Additionally, employing Virtual non-calcium Color Coding images for accurately describing ligament thickness or length may enhance the diagnostic value of the images.

Pelvis Treatment Plan Dose Comparison for Proton Therapy Using Single Energy and Dual Energy Computed Tomography Simulation Methods

In proton therapy, plan robustness is ameliorated by expanding the irradiation volume beyond the target, in order to mitigate setup and proton range uncertainties (RU). A byproduct of this expansion is elevated doses to surrounding organs at risk (OARs) which reduce some of the benefits associated with proton therapy. Dual-energy CT (DECT) has been shown in multiple phantom and animal tissue studies to reduce RU without compromising plan robustness. This study quantifies dosimetric differences between single-energy CT (SECT) and DECT for pelvis patients treated with intensity modulated proton therapy (IMPT). Under IRB approval, SECT and DECT scans from 25 IMPT pelvis patients were acquired using a CT scanner. Clinical plans were generated on the SECT images using robust optimization settings of 3.5% RU and 5 mm setup uncertainty in a treatment planning system. Subsequently, the clinical plans were recomputed on the corresponding DECT generated SPR-map images. For each patient, target coverage, mean and maximum OAR doses were compared for both image sets. Comparison of two plans showed systematic differences in target minimum dose (D99%) and V100%. Variations as high as 3.1% with DECT were observed in D99% indicating target under-dosage. On average, use of SECT overestimated V100% by 2.4% when compared to DECT. Since all clinical plans were optimized robustly to meet V95% coverage, higher agreement (<1%) was achieved for V95% (99.9±0.2%), and D95% (99.6±0.3%). DECT relative to SECT indicated slightly higher OAR maximum doses for femoral heads (2.3±2.78%), penile bulb/external genital (1.33±4.00%) and large bowel (0.5±1.25%). Similarly, higher mean dose was observed to rectum (2.08±4.88%), bladder (1.41±0.25%), femoral heads (1.18±6.61%) and penile bulb/external genital (1.78±5.74%) for DECT relative to SECT. Our results show a disparity between evaluated SECT and DECT target and OAR dosimetric parameters. Given the higher accuracies in proton range estimation associated with the use of DECT, its use can imply a potential for more conformal proton plans as well as higher TPS computed target coverage and OAR dose accuracy, both of which enhance overall treatment quality.

Synthetic dual-energy CT reconstruction from single-energy CT Using artificial intelligence.

To develop and assess the utility of synthetic dual-energy CT (sDECT) images generated from single-energy CT (SECT) using two state-of-the-art generative adversarial network (GAN) architectures for artificial intelligence-based image translation. In this retrospective study, 734 patients (389F; 62.8 years ± 14.9) who underwent enhanced DECT of the chest, abdomen, and pelvis between January 2018 and June 2019 were included. Using 70-keV as the input images (n = 141,009) and 50-keV, iodine, and virtual unenhanced (VUE) images as outputs, separate models were trained using Pix2PixHD and CycleGAN. Model performance on the test set (n = 17,839) was evaluated using mean squared error, structural similarity index, and peak signal-to-noise ratio. To objectively test the utility of these models, synthetic iodine material density and 50-keV images were generated from SECT images of 16 patients with gastrointestinal bleeding performed at another institution. The conspicuity of gastrointestinal bleeding using sDECT was compared to portal venous phase SECT. Synthetic VUE images were generated from 37 patients who underwent a CT urogram at another institution and model performance was compared to true unenhanced images. sDECT from both Pix2PixHD and CycleGAN were qualitatively indistinguishable from true DECT by a board-certified radiologist (avg accuracy 64.5%). Pix2PixHD had better quantitative performance compared to CycleGAN (e.g., structural similarity index for iodine: 87% vs. 46%, p-value < 0.001). sDECT using Pix2PixHD showed increased bleeding conspicuity for gastrointestinal bleeding and better removal of iodine on synthetic VUE compared to CycleGAN. sDECT from SECT using Pix2PixHD may afford some of the advantages of DECT.

A Study Toward Automatic Identification of Renal Stone Composition in Single-energy or Ultra-low-dose CT Scan Using Deep Neural Networks

Background: Dual-energy computed tomography (DECT) scan is a non-invasive method for the in vivo identification of renal stone composition. However, DECT scanners have several demerits, including high cost, low accessibility, and high radiation dose to patients. Objectives: The present study aimed to investigate the efficacy of deep neural networks in the classification of renal stone types using single-energy CT imaging. The Taguchi method was used for the optimization of hyperparameters. Patients and Methods: A total of 146 pure renal stone samples were first surgically collected from the patients. The stones were then inserted into a Rando phantom and scanned using a DECT scanner. An ultra-low-dose CT scan was acquired to determine the stone position prior to the DECT scan. The result of chemical analysis was used as the gold standard for determining the stone composition throughout the study. Several neural networks, including ResNet-50, ResNet-18, GoogLeNet, and VGG-19, were used to classify the stone images into three composition groups, including uric acid, calcium oxalate, and cystine. Moreover, the Taguchi method was employed to optimize the network hyperparameters. The signal-to-noise ratio (SNR) was also analyzed to determine the optimal arrangement. Results: In this study, CT scans of 53 uric acid, 55 calcium oxalate, and 38 cystine stones, with diameters of 1 - 3 mm, were acquired. The deep learning findings showed that the ResNet-18 network had the highest accuracy for 120-kVp and 135-kVp CT scanning, while ResNet-50 performed better in 80-kVp CT scanning. The ResNet-50 network showed the best performance of all networks in predicting stone types in 80-kVp scanning, as indicated by its high sensitivity, specificity, and precision. Conclusion: The present results indicated that our deep learning approach could be used for the in vivo determination of renal stone types. Moreover, low-dose or ultra-low-dose single-energy CT scanning is more widely accessible and safer in terms of radiation exposure.

Evaluation of Image Quality and Detectability of Deep Learning Image Reconstruction (DLIR) Algorithm in Single- and Dual-energy CT.

This study is aimed to evaluate effects of deep learning image reconstruction (DLIR) on image quality in single-energy CT (SECT) and dual-energy CT (DECT), in reference to adaptive statistical iterative reconstruction-V (ASIR-V). The Gammex 464 phantom was scanned in SECT and DECT modes at three dose levels (5, 10, and 20mGy). Raw data were reconstructed using six algorithms: filtered back-projection (FBP), ASIR-V at 40% (AV-40) and 100% (AV-100) strength, and DLIR at low (DLIR-L), medium (DLIR-M), and high strength (DLIR-H), to generate SECT 120kVp images and DECT 120kVp-like images. Objective image quality metrics were computed, including noise power spectrum (NPS), task transfer function (TTF), and detectability index (d'). Subjective image quality evaluation, including image noise, texture, sharpness, overall quality, and low- and high-contrast detectability, was performed by six readers. DLIR-H reduced overall noise magnitudes from FBP by 55.2% in a more balanced way of low and high frequency ranges comparing to AV-40, and improved the TTF values at 50% for acrylic inserts by average percentages of 18.32%. Comparing to SECT 20mGy AV-40 images, the DECT 10mGy DLIR-H images showed 20.90% and 7.75% improvement in d' for the small-object high-contrast and large-object low-contrast tasks, respectively. Subjective evaluation showed higher image quality and better detectability. At 50% of the radiation dose level, DECT with DLIR-H yields a gain in objective detectability index compared to full-dose AV-40 SECT images used in daily practice.

Impact of the automatic tube current modulation (ATCM) system on virtual monoenergetic image quality for dual-source CT: A phantom study

PurposeTo assess the impact of the automatic tube current modulation (ATCM) on virtual monoenergetic images (VMIs) quality in dual-source CT(DSCT). Materials and methodsAcquisitions were performed on DSCT using the Mercury phantom. The acquisition parameters for an abdomen-pelvic examination with single-energy CT(SECT) and dual-energy CT(DECT) imaging were used. Acquisitions were performed for each imaging mode using fixed mAs and ATCM. The mAs value was set to obtain a volume CT dose index of 11 mGy in fixed mAs acquisitions. This value was used as the reference mAs in ATCM acquisitions. The noise power spectrum and task-based transfer function at 40,50,60 and 70 keV levels were computed on VMIs and SECT images. The detectability index (d′) was calculated for a lesion with an iodine concentration of 10 mg/mL. ResultsThe noise magnitude on VMIs was higher with the ATCM system than with fixed mAs for all energy levels and section diameters of 21,26 and 31 cm. The noise texture and spatial resolution were similar between the fixed mAs and ATCM acquisitions for both imaging modes. The d’ values were lower for all energy levels with ATCM than with fixed mAs acquisitions for 21 and 26 cm diameters by −39.82 ± 9.32%, similar at 31 cm diameter −4.13 ± 0.24% and higher at 36 cm diameter 10.40 ± 6.69%. It was higher on VMIs at all energy levels compared to SECT images. ConclusionsThe ATCM system could be used with DECT imaging to optimize patient exposure without changing the noise texture and spatial resolution of VMIs compared to fixed mAs and SECT.

Hepatic lesion detectability in abdomen computed tomography: Investigation in low kVp single energy and low keV virtual monochromatic images generated from dual energy computed tomography using task-based image quality assessment in phantom

Background: Low tube potential single-energy (SE) and virtual monochromatic image (VMI) dual energy (DE) abdomen CT images both improve the hepatic lesion detection by increasing the liver lesion contrast on images. Objectives: To study the performance of low kVp single energy and low keV virtual monochromatic images (VMI) generated from dual energy acquisition to detect the hepatic lesion on abdominal CT imaging in phantom. Materials and methods: The anthropomorphic liver with nodule inserted phantom with extension rings simulating the small, medium, and large patient was scanned under the SECT acquisition by varying the kVp from 70-120 kVp and for DECT acquisitions, three kVp combinations (80/-,90/-, and 100/Sn150-kVp). The series of 40-,50-,60-, and 70-keV VMI were generated from DECT data set. All images were used to assess the task-based image quality; task transfer function (TTF), noise power spectrum (NPS), and detectability index (d’) with the diagnostic task to detect 15 mm diameter hyperattenuating hepatic lesion. Results: The result showed that the TTF was higher in low kVp SECT while the lesion contrast was higher at low keV VMI -DECT. The noise magnitude remained constant for all kVp values in SECT, but it was dramatically increased as decreased the energy level from 70- to 40-keV in VMI-DECT. The fav of NPS shifted to higher frequency when increasing the kVp and when increasing the energy level of VMI. The obtained d’ was highest in low kVp SECT at 70-or 80-kVp. Conclusion: The low kVp SECT provided the highest d’ than that in low keV VM image from DECT in all phantom sizes where the highest d’ was found at 70 kVp-SECT for small and medium phantom and at 80 kVp for large phantom. For SECT, reduced the kVp to 70- or 80-kVp improved the detectability index. The kVp combination in DECT impacts to the d’ of VMI; at small phantom, the highest d’ for each keV VMI was found at 80/Sn150 kVp acquisition and at larger phantom size, higher kVp on tube “A” is more favored.

Characteristics of the deep learning-based virtual monochromatic image with fast kilovolt-switching CT: a phantom study.

We assessed the physical properties of virtual monochromatic images (VMIs) obtained with different energy levels in various contrast settings and radiation doses using deep learning-based spectral computed tomography (DL-Spectral CT) and compared the results with those from single-energy CT (SECT) imaging. A Catphan® 600 phantom was scanned by DL-Spectral CT at various radiation doses. We reconstructed the VMIs obtained at 50, 70, and 100keV. SECT (120kVp) images were acquired at the same radiation doses. The standard deviations of the CT number and noise power spectrum (NPS) were calculated for noise characterization. We evaluated the spatial resolution by determining the 10% task-based transfer function (TTF) level, and we assessed the task-based detectability index (d'). Regardless of the radiation dose, the noise was the lowest at 70keV VMI. The NPS showed that the noise amplitude at all spatial frequencies was the lowest among other VMI and 120kVp images. The spatial resolution was higher for 70keV VMI compared to the other VMIs, except for high-contrast objects. The d' of 70keV VMI was the highest among the VMI and 120kVp images at all radiation doses and contrast settings. The d' of the 70keV VMIs at the minimum dose was higher than that at the maximum dose in any other image. The physical properties of the DL-Spectral CT VMIs varied with the energy level. The 70keV VMI had the highest detectability by far among the VMI and 120-kVp images. DL-Spectral CT may be useful to reduce radiation doses.

Image synthesis of effective atomic number images using a deep convolutional neural network-based generative adversarial network.

The effective atomic numbers obtained from dual-energy computed tomography (DECT) can aid in characterization of materials. In this study, an effective atomic number image reconstructed from a DECT image was synthesized using an equivalent single-energy CT image with a deep convolutional neural network (CNN)-based generative adversarial network (GAN). The image synthesis framework to obtain the effective atomic number images from a single-energy CT image at 120 kVp using a CNN-based GAN was developed. The evaluation metrics were the mean absolute error (MAE), relative root mean square error (RMSE), relative mean square error (MSE), structural similarity index (SSIM), peak signal-to-noise ratio (PSNR), and mutual information (MI). The difference between the reference and synthetic effective atomic numbers was within 9.7% in all regions of interest. The averages of MAE, RMSE, MSE, SSIM, PSNR, and MI of the reference and synthesized images in the test data were 0.09, 0.045, 0.0, 0.89, 54.97, and 1.03, respectively. In this study, an image synthesis framework using single-energy CT images was constructed to obtain atomic number images scanned by DECT. This image synthesis framework can aid in material decomposition without extra scans in DECT.

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.

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.

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.

Dual-energy CT angiography in imaging surveillance of endovascular aneurysm repair – Preliminary study results

PurposeTo investigate the value of dual-energy CT imaging to discriminate low- from high- risk type II endoleaks (T2EL) after endovascular aneurysm repair (EVAR). MethodStudy participants were consecutive patients referred for CT at 1-month post-EVAR. CT imaging acquisition included a dual-energy CT angiography (DECTA) and a delayed single-energy CT (SECT) imaging. Patients diagnosed with T2EL were re-examined at 6-months post-EVAR to assess the aneurysm sac growth (ASG). Upon ASG recorded, patients were categorized as having low- (group A) or high- risk (group B) T2EL. DECTA image data were employed to calculate the normalized effective atomic number (NZeff), the normalized iodine concentration, the slope of HUendoleak/HUaorta against monochromatic energy, the dual-energy index and an improvised endoleak index (EI) for each T2EL. Statistical analysis was employed to compare all above parameters regarding their ability to differentiate low- from high- risk T2EL. ResultsAmong 40 patients examined at 1-month post-EVAR, 14 patients were diagnosed with T2EL. NZeff and EI were found to be significantly lower in group A. NZeff was found to have the highest power to discriminate high-risk T2EL with an area-under-curve of 86.7%, showing100% specificity and 60% sensitivity. The optimal contrast-to-noise ratio for T2EL demonstrated a median peak conspicuity level at 54-keV. The mean effective dose from DECTA and SECT scans was 27.8% lower compared to the sum of three SECT acquisitions. ConclusionsNZeff and EI were found to have a significant power in predicting the aggressiveness of T2EL lesions. Virtual monochromatic images at 54-keV may enhance T2EL detection efficiency.