Filtered Back Projection Images Research Articles

Effect of Model-Based Iterative Reconstruction on Image Quality of Chest Computed Tomography for COVID-19 Pneumonia.

This study aimed to compare the image quality of chest computed tomography (CT) scans for COVID-19 pneumonia using forward-projected model-based iterative reconstruction solution-LUNG (FIRST-LUNG) with filtered back projection (FBP) and hybrid iterative reconstruction (HIR). The CT images of 44 inpatients diagnosed with COVID-19 pneumonia between December 2022 and June 2023 were retrospectively analyzed. The CT images were reconstructed using FBP, HIR, and FIRST-LUNG-MILD/STANDARD/STRONG. The CT values and noise of the lumen of the main trachea and erector spine muscle were measured for each group. Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were calculated. Subjective evaluations included overall image quality, noise, streak artifact, visualization of normal lung structures, and abnormal CT features. One-way analysis of variance was used to compare the objective and subjective indicators among the five groups. The task-based transfer function was derived for three distinct contrasts representing anatomical structures, lower-contrast lesion, and higher-contrast lesion. The results of the study demonstrated significant differences in image noise, SNR, and CNR among the five groups (P < 0.001). The FBP images exhibited the highest levels of noise and the lowest SNR and CNR among the five groups (P < 0.001). When compared to the FBP and HIR groups, the noise was lower in the FIRST-LUNG-MILD/STANDARD/STRONG group, while the SNR and CNR were higher (P < 0.001). The subjective overall image quality score of FIRST-LUNG-MILD/STANDARD was significantly better than FBP and FIRST-LUNG-STRONG (P < 0.001). FIRST-LUNG-MILD was superior to FBP, HIR, FIRST-LUNG-STANDARD, and FIRST-LUNG-STRONG in visualizing proximal and peripheral bronchovascular and subpleural vessels (P < 0.05). Additionally, FIRST-LUNG-MILD achieved the best scores in evaluating abnormal lung structure (P < 0.001). The overall interobserver agreement was substantial (intraclass correlation coefficient = 0.891). The task-based transfer function 50% values of FIRST reconstructions are consistently higher compared to FBP and HIR. The FIRST-LUNG-MILD/STANDARD algorithm can enhance the image quality of chest CT in patients with COVID-19 pneumonia, while preserving important details of the lesions, better than the FBP and HIR algorithms. After evaluating various COVID-19 pneumonia lesions and considering the improvement in image quality, we recommend using the FIRST-LUNG-MILD reconstruction for diagnosing COVID-19 pneumonia.

Assessment of image quality and impact of deep learning-based software in non-contrast head CT scans

In this retrospective study, we aimed to assess the objective and subjective image quality of different reconstruction techniques and a deep learning-based software on non-contrast head computed tomography (CT) images. In total, 152 adult head CT scans (77 female, 75 male; mean age 69.4 ± 18.3 years) obtained from three different CT scanners using different protocols between March and April 2021 were included. CT images were reconstructed using filtered-back projection (FBP), iterative reconstruction (IR), and post-processed using a deep learning-based algorithm (PS). Post-processing significantly reduced noise in FBP-reconstructed images (up to 15.4% reduction) depending on the protocol, leading to improvements in signal-to-noise ratio of up to 19.7%. However, when deep learning-based post-processing was applied to FBP images compared to IR alone, the differences were inconsistent and partly non-significant, which appeared to be protocol or site specific. Subjective assessments showed no significant overall improvement in image quality for all reconstructions and post-processing. Inter-rater reliability was low and preferences varied. Deep learning-based denoising software improved objective image quality compared to FBP in routine head CT. A significant difference compared to IR was observed for only one protocol. Subjective assessments did not indicate a significant clinical impact in terms of improved subjective image quality, likely due to the low noise levels in full-dose images.

Lifelike PixelPrint phantoms for assessing clinical image quality and dose reduction capabilities of a deep learning CT reconstruction algorithm.

Deep learning CT reconstruction (DLR) has become increasingly popular as a method for improving image quality and reducing radiation exposure. Due to their nonlinear nature, these algorithms result in resolution and noise performance which are object-dependent. Therefore, traditional CT phantoms, which lack realistic tissue morphology, have become inadequate for assessing clinical imaging performance. We propose to utilize 3D-printed PixelPrint phantoms, which exhibit lifelike attenuation profiles, textures, and structures, as a better tool for evaluating DLR performance. In this study, we evaluate a DLR algorithm (Precise Image (PI), Philips Healthcare) using a custom PixelPrint lung phantom and perform head-to-head comparisons between DLR, iterative reconstruction, and filtered back projection (FBP) with scans acquired at a broad range of radiation exposures (CTDIvol: 0.5, 1, 2, 4, 6, 9, 12, 15, 19, and 20 mGy). We compared the performance of each resultant image using noise, peak signal to noise ratio (PSNR), structural similarity index (SSIM), feature-based similarity index (FSIM), information theoretic-based statistic similarity measure (ISSM) and universal image quality index (UIQ). Iterative reconstruction at 9 mGy matches the image quality of FBP at 12 mGy (diagnostic reference level) for all metrics, demonstrating a dose reduction capability of 25%. Meanwhile, DLR matches the image quality of diagnostic reference level FBP images at doses between 4 - 9 mGy, demonstrating dose reduction capabilities between 25% and 67%. This study shows that DLR allows for reduced radiation dose compared to both FBP and iterative reconstruction without compromising image quality. Furthermore, PixelPrint phantoms offer more realistic testing conditions compared to traditional phantoms in the evaluation of novel CT technologies. This, in turn, promotes the translation of new technologies, such as DLR, into clinical practice.

Artificial Intelligence Iterative Reconstruction in Computed Tomography Angiography: An Evaluation on Pulmonary Arteries and Aorta With Routine Dose Settings.

The objective of this study is to investigate whether a newly introduced deep learning-based iterative reconstruction algorithm, namely, the artificial intelligence iterative reconstruction (AIIR), has a clinical value in computed tomography angiography (CTA), especially for visualizing vascular structures and related lesions, with routine dose settings. A total of 63 patients were retrospectively collected from the triple rule-out CTA examinations, where both pulmonary and aortic data were available for each patient and were taken as the example for investigation. The images were reconstructed using the filtered back projection (FBP), hybrid iterative reconstruction (HIR), and the AIIR. The visibility of vasculature and pulmonary emboli and the general image quality were assessed. Artificial intelligence iterative reconstruction resulted in significantly ( P < 0.001) lower noise as well as higher signal-to-noise ratio and contrast-to-noise ratio compared with FBP and HIR. Besides, AIIR achieved the highest subjective scores on general image quality ( P < 0.05). For the vasculature visibility, AIIR offered the best vessel conspicuity, especially for the small vessels ( P < 0.05). Also, >90% of emboli on the AIIR images were graded as sharp (score 5), whereas <15% of emboli on FBP and HIR images were scored 5. As demonstrated for pulmonary and aortic CTAs, AIIR improves the image quality and offers a better depiction for vascular structures compared with FBP and HIR. The visibility of the pulmonary emboli was also increased by AIIR.

Verification of optimal conditions for the scattering correction of 123I-FP-CIT SPECT on a single-photon emission tomography system with a two-detector whole-body cadmium-zinc-telluride semiconductor detector.

To identify the optimal scattering correction for 123I-FP-CIT SPECT (DAT-SPECT) using a two-detector whole-body cadmium-zinc-telluride semiconductor detector (C-SPECT) system with a medium-energy high-resolution sensitivity (MEHRS) collimator. The C-SPECT system with the MEHRS collimator assessed image quality and quantification using a striated phantom. Different reconstruction methods and scattering correction settings were compared, including filtered back projection (FBP) and ordered subset expectation maximization (OSEM). Higher %contrast and %CV values were observed > 10% subwindow (SW) for all conditions, with no significant differences between images without scattering correction and those < 7% SW. The FBP images show a greater increase in %CV > 10% SW than the OSEM images. The specific binding ratio in the radioactivity ratio of 8:1 was higher than the true value under all conditions. The C-SPECT system with an MEHRS collimator provided accurate scattering suppression and enabled high-quality imaging for DAT-SPECT. Careful setting of the scattering correction is essential for total count accuracy.

The impact of deep learning reconstruction in low dose computed tomography on the evaluation of interstitial lung disease.

To evaluate the effect of the deep learning model reconstruction (DLM) method in terms of image quality and diagnostic agreement in low-dose computed tomography (LDCT) for interstitial lung disease (ILD), 193 patients who underwent LDCT for suspected ILD were retrospectively reviewed. Datasets were reconstructed using filtered back projection (FBP), adaptive statistical iterative reconstruction Veo (ASiR-V), and DLM. For image quality analysis, the signal, noise, signal-to-noise ratio (SNR), blind/referenceless image spatial quality evaluator (BRISQUE), and visual scoring were evaluated. Also, CT patterns of usual interstitial pneumonia (UIP) were classified according to the 2022 idiopathic pulmonary fibrosis (IPF) diagnostic criteria. The differences between CT images subjected to FBP, ASiR-V 30%, and DLM were evaluated. The image noise and BRISQUE scores of DLM images was lower and SNR was higher than that of the ASiR-V and FBP images (ASiR-V vs. DLM, p < 0.001 and FBP vs. DLR-M, p < 0.001, respectively). The agreement of the diagnostic categorization of IPF between the three reconstruction methods was almost perfect (κ = 0.992, CI 0.990-0.994). Image quality was improved with DLM compared to ASiR-V and FBP.

Dose Optimization Using a Deep Learning Tool in Various CT Protocols for Urolithiasis: A Physical Human Phantom Study.

Background and Objectives: We attempted to determine the optimal radiation dose to maintain image quality using a deep learning application in a physical human phantom. Materials and Methods: Three 5 × 5 × 5 mm3 uric acid stones were placed in a physical human phantom in various locations. Three tube voltages (120, 100, and 80 kV) and four current-time products (100, 70, 30, and 15 mAs) were implemented in 12 scans. Each scan was reconstructed with filtered back projection (FBP), statistical iterative reconstruction (IR, iDose), and knowledge-based iterative model reconstruction (IMR). By applying deep learning to each image, we took 12 more scans. Objective image assessments were calculated using the standard deviation of the Hounsfield unit (HU). Subjective image assessments were performed by one radiologist and one urologist. Two radiologists assessed the subjective assessment and found the stone under the absence of information. We used this data to calculate the diagnostic accuracy. Results: Objective image noise was decreased after applying a deep learning tool in all images of FBP, iDose, and IMR. There was no statistical difference between iDose and deep learning-applied FBP images (10.1 ± 11.9, 9.5 ± 18.5 HU, p = 0.583, respectively). At a 100 kV-30 mAs setting, deep learning-applied FBP obtained a similar objective noise in approximately one third of the radiation doses compared to FBP. In radiation doses with settings lower than 100 kV-30 mAs, the subject image assessment (image quality, confidence level, and noise) showed deteriorated scores. Diagnostic accuracy was increased when the deep learning setting was lower than 100 kV-30 mAs, except for at 80 kV-15 mAs. Conclusions: At the setting of 100 kV-30 mAs or higher, deep learning-applied FBP did not differ in image quality compared to IR. At the setting of 100 kV-30 mAs, the radiation dose can decrease by about one third while maintaining objective noise.

Newly-designed adaptive non-blind deconvolution with structural similarity index in single-photon emission computed tomography

Single-photon emission computed tomography SPECT image reconstruction methods have a significant influence on image quality, with filtered back projection (FBP) and ordered subset expectation maximization (OSEM) being the most commonly used methods. In this study, we proposed newly-designed adaptive non-blind deconvolution with a structural similarity (SSIM) index that can take advantage of the FBP and OSEM image reconstruction methods. After acquiring brain SPECT images, the proposed image was obtained using an algorithm that applied the SSIM metric, defined by predicting the distribution and amount of blurring. As a result of the contrast to noise ratio (CNR) and coefficient of variation evaluation (COV), the resulting image of the proposed algorithm showed a similar trend in spatial resolution to that of FBP, while obtaining values similar to those of OSEM. In addition, we confirmed that the CNR and COV values of the proposed algorithm improved by approximately 1.69 and 1.59 times, respectively, compared with those of the algorithm involving an inappropriate deblurring process. To summarize, we proposed a new type of algorithm that combines the advantages of SPECT image reconstruction techniques and is expected to be applicable in various fields.

Deep-Learning-Based Image Denoising in Imaging of Urolithiasis: Assessment of Image Quality and Comparison to State-of-the-Art Iterative Reconstructions.

This study aimed to compare the image quality and diagnostic accuracy of deep-learning-based image denoising reconstructions (DLIDs) to established iterative reconstructed algorithms in low-dose computed tomography (LDCT) of patients with suspected urolithiasis. LDCTs (CTDIvol, 2 mGy) of 76 patients (age: 40.3 ± 5.2 years, M/W: 51/25) with suspected urolithiasis were retrospectively included. Filtered-back projection (FBP), hybrid iterative and model-based iterative reconstruction (HIR/MBIR, respectively) were reconstructed. FBP images were processed using a Food and Drug Administration (FDA)-approved DLID. ROIs were placed in renal parenchyma, fat, muscle and urinary bladder. Signal- and contrast-to-noise ratios (SNR/CNR, respectively) were calculated. Two radiologists evaluated image quality on five-point Likert scales and urinary stones. The results showed a progressive decrease in image noise from FBP, HIR and DLID to MBIR with significant differences between each method (p < 0.05). SNR and CNR were comparable between MBIR and DLID, while it was significantly lower in HIR followed by FBP (e.g., SNR: 1.5 ± 0.3; 1.4 ± 0.4; 1.0 ± 0.3; 0.7 ± 0.2, p < 0.05). Subjective analysis confirmed best image quality in MBIR, followed by DLID and HIR, both being superior to FBP (p < 0.05). Diagnostic accuracy for urinary stone detection was best using MBIR (0.94), lowest using FBP (0.84) and comparable between DLID (0.90) and HIR (0.90). Stone size measurements were consistent between all reconstructions and showed excellent correlation (r2 = 0.958-0.975). In conclusion, MBIR yielded the highest image quality and diagnostic accuracy, with DLID producing better results than HIR and FBP in image quality and matching HIR in diagnostic precision.

The influence of image reconstruction methods on the diagnosis of pulmonary emphysema with convolutional neural network.

This study investigated the influence of iterative reconstruction (IR) methods on computed tomography (CT) images when training convolutional neural network (CNN) models to diagnose pulmonary emphysema. To evaluate the influence of the IR algorithm on CNN, the present study comprised two steps: the comparison of noise reduction by IR algorithms using phantom examinations and the change in performance of CNN with IR algorithms using patient data. We retrospectively analyzed 97 patients. Raw CT data were reconstructed using the filtered back-projection (FBP) and adaptive statistical iterative reconstruction V (ASIR-V) algorithms with blending levels of 30%, 50%, and 70%. The models were trained using reconstructed CT images and were named the FBP, ASIR-V30, ASIR-V50, and ASIR-V70 models. The mean and the standard deviation of the CT values were 11.3 ± 21.2 at FBP, 11.0 ± 17.3 at ASIR-V30, 11.0 ± 14.4 at ASIR-V50, and 11.0 ± 11.8 at ASIR-V70. For all the evaluation metrics, the best values were obtained with the FBP model applied to the ASIR-V70 test images. The worst values were obtained with the ASIR-V70 model applied to the FBP test images. The model trained with FBP images exhibited significantly better performance than the models trained using IR images. The reduction in image noise with the IR algorithm on the test images contributed to improving the accuracy of the classification of emphysema subtypes using CNN.

Clinical Feasibility of Deep Learning-Based Image Reconstruction on Coronary Computed Tomography Angiography.

This study evaluated the feasibility of deep-learning-based image reconstruction (DLIR) on coronary computed tomography angiography (CCTA). By using a 20 cm water phantom, the noise reduction ratio and noise power spectrum were evaluated according to the different reconstruction methods. Then 46 patients who underwent CCTA were retrospectively enrolled. CCTA was performed using the 16 cm coverage axial volume scan technique. All CT images were reconstructed using filtered back projection (FBP); three model-based iterative reconstructions (MBIR) of 40%, 60%, and 80%; and three DLIR algorithms: low (L), medium (M), and high (H). Quantitative and qualitative image qualities of CCTA were compared according to the reconstruction methods. In the phantom study, the noise reduction ratios of MBIR-40%, MBIR-60%, MBIR-80%, DLIR-L, DLIR-M, and DLIR-H were 26.7 ± 0.2%, 39.5 ± 0.5%, 51.7 ± 0.4%, 33.1 ± 0.8%, 43.2 ± 0.8%, and 53.5 ± 0.1%, respectively. The pattern of the noise power spectrum of the DLIR images was more similar to FBP images than MBIR images. In a CCTA study, CCTA yielded a significantly lower noise index with DLIR-H reconstruction than with the other reconstruction methods. DLIR-H showed a higher SNR and CNR than MBIR (p < 0.05). The qualitative image quality of CCTA with DLIR-H was significantly higher than that of MBIR-80% or FBP. The DLIR algorithm was feasible and yielded a better image quality than the FBP or MBIR algorithms on CCTA.

Precursors for synthetic aperture radar

In this paper we study waveform design for synthetic-aperture radar (SAR) imaging through dispersive media. Under the assumptions of scalar wave propagation through a causal dielectric medium and single-scattering from an isotropic point scatterer, we use asymptotic analysis to derive the asymptotic approximation to the scattered electric field. From this asymptotic approximation, we define a sensing precursor that we propose for the transmit waveform for SAR imaging through dispersive material. We compare our sensing precursor with previously defined optimal waveforms (Varslot et al 2011 SIAM J. Appl. Math. 71 1780–800) in terms of both propagation and scattering capabilities, as well as imaging performance. With the filtered back-projection imaging algorithm that we use, we find that for high levels of signal-to-noise ratio (SNR), the optimal waveforms contain higher frequencies and thus produce better images. For low levels of SNR, the transmitted optimal waveforms and the sensing precursors are similar, thus giving comparable images.

Accuracy and Precision of Iodine Quantification in Subtracted Micro-Computed Tomography: Effect of Reconstruction and Noise Removal Algorithms

PurposeTo evaluate the effect of reconstruction and noise removal algorithms on the accuracy and precision of iodine concentration (CI) quantified with subtracted micro-computed tomography (micro-CT).ProceduresTwo reconstruction algorithms were evaluated: a filtered backprojection (FBP) algorithm and a simultaneous iterative reconstruction technique (SIRT) algorithm. A 3D bilateral filter (BF) was used for noise removal. A phantom study evaluated and compared the image quality, and the accuracy and precision of CI in four scenarios: filtered FBP, filtered SIRT, non-filtered FBP, and non-filtered SIRT. In vivo experiments were performed in an animal model of chemically-induced mammary cancer.ResultsLinear relationships between the measured and nominal CI values were found for all the scenarios in the phantom study (R2 > 0.95). SIRT significantly improved the accuracy and precision of CI compared to FBP, as given by their lower bias (adj. p-value = 0.0308) and repeatability coefficient (adj. p-value < 0.0001). Noise removal enabled a significant decrease in bias in filtered SIRT images only; non-significant differences were found for the repeatability coefficient. The phantom and in vivo studies showed that CI is a reproducible imaging parameter for all the scenarios (Pearson r > 0.99, p-value < 0.001). The contrast-to-noise ratio showed non-significant differences among the evaluated scenarios in the phantom study, while a significant improvement was found in the in vivo study when SIRT and BF algorithms were used.ConclusionsSIRT and BF algorithms improved the accuracy and precision of CI compared to FBP and non-filtered images, which encourages their use in subtracted micro-CT imaging.

Report on the AAPM deep-learning spectral CT Grand Challenge.

This Special Report summarizes the 2022 AAPM Grand Challenge on Deep-Learning spectral Computed Tomography (DL-spectral CT) imagereconstruction. The purpose of the challenge is to develop the most accurate image reconstruction algorithm possible for solving the inverse problem associated with a fast kilovolt switching dual-energy CT scan using a three tissue-map decomposition. Participants could choose to use a deep-learning (DL), iterative, or a hybridapproach. The challenge is based on a 2D breast CT simulation, where the simulated breast phantom consists of three tissue maps: adipose, fibroglandular, and calcification distributions. The phantom specification is stochastic so that multiple realizations can be generated for DL approaches. A dual-energy scan is simulated where the x-ray source potential of successive views alternates between 50 and 80 kilovolts (kV). A total of 512 views are generated, yielding 256 views for each source voltage. We generate 50 and 80 kV images by use of filtered back-projection (FBP) on negative logarithm processed transmission data. For participants who develop a DL approach, 1000 cases are available. Each case consists of the three 512 × 512 tissue maps, 50 and 80-kV transmission data sets and their corresponding FBP images. The goal of the DL network would then be to predict the material maps from either the transmission data, FBP images, or a combination of the two. For participants developing a physics-based approach, all of the required modeling parameters are made available: geometry, spectra, and tissue attenuation curves. The provided information also allows for hybrid approaches where physics is exploited as well as information about the scanned object derived from the 1000 training cases. Final testing is performed by computation of root-mean-square error (RMSE) for predictions on the tissue maps from 100 newcases. Test phase submission were received from 18 research groups. Of the 18 submissions, 17 were results obtained with algorithms that involved DL. Only the second place finishing team developed a physics-based image reconstruction algorithm. Both the winning and second place teams had highly accurate results where the RMSE was nearly zero to single floating point precision. Results from the top 10 also achieved a high degree of accuracy; and as a result, this special report outlines the methodology developed by each of thesegroups. The DL-spectral CT challenge successfully established a forum for developing image reconstruction algorithms that address an important inverse problem relevant forspectral CT.

Combining physics-based models with deep learning image synthesis and uncertainty in intraoperative cone-beam CT of the brain.

Image-guided neurosurgery requires high localization and registration accuracy to enable effective treatment and avoid complications. However, accurate neuronavigation based on preoperative magnetic resonance (MR) or computed tomography (CT) images is challenged by brain deformation occurring during the surgical intervention. To facilitate intraoperative visualization of brain tissues and deformable registration with preoperative images, a 3D deep learning (DL) reconstruction framework (termed DL-Recon) was proposed for improved intraoperative cone-beam CT (CBCT) image quality. The DL-Recon framework combines physics-based models with deep learning CT synthesis and leverages uncertainty information to promote robustness to unseen features. A 3D generative adversarial network (GAN) with a conditional loss function modulated by aleatoric uncertainty was developed for CBCT-to-CT synthesis. Epistemic uncertainty of the synthesis model was estimated via Monte Carlo (MC) dropout. Using spatially varying weights derived from epistemic uncertainty, the DL-Recon image combines the synthetic CT with an artifact-corrected filtered back-projection (FBP) reconstruction. In regions of high epistemic uncertainty, DL-Recon includes greater contribution from the FBP image. Twenty paired real CT and simulated CBCT images of the head were used for network training and validation, and experiments evaluated the performance of DL-Recon on CBCT images containing simulated and real brain lesions not present in the training data. Performance among learning- and physics-based methods was quantified in terms of structural similarity (SSIM) of the resulting image to diagnostic CT and Dice similarity metric (DSC) in lesion segmentation compared to ground truth. A pilot study was conducted involving seven subjects with CBCT images acquired during neurosurgery to assess the feasibility of DL-Recon in clinical data. CBCT images reconstructed via FBP with physics-based corrections exhibited the usual challenges to soft-tissue contrast resolution due to image non-uniformity, noise, and residual artifacts. GAN synthesis improved image uniformity and soft-tissue visibility but was subject to error in the shape and contrast of simulated lesions that were unseen in training. Incorporation of aleatoric uncertainty in synthesis loss improved estimation of epistemic uncertainty, with variable brain structures and unseen lesions exhibiting higher epistemic uncertainty. The DL-Recon approach mitigated synthesis errors while maintaining improvement in image quality, yielding 15%-22% increase in SSIM (image appearance compared to diagnostic CT) and up to 25% increase in DSC in lesion segmentation compared to FBP. Clear gains in visual image quality were also observed in real brain lesions and in clinical CBCT images. DL-Recon leveraged uncertainty estimation to combine the strengths of DL and physics-based reconstruction and demonstrated substantial improvements in the accuracy and quality of intraoperative CBCT. The improved soft-tissue contrast resolution could facilitate visualization of brain structures and support deformable registration with preoperative images, further extending the utility of intraoperative CBCT in image-guided neurosurgery.

Radiation dose reduction using deep learning-based image reconstruction for a low-dose chest computed tomography protocol: a phantom study.

The aim of this study was to compare the dose reduction potential and image quality of deep learning-based image reconstruction (DLIR) with those of filtered back-projection (FBP) and iterative reconstruction (IR) and to determine the clinically usable dose of DLIR for low-dose chest computed tomography (LDCT) scans. Multi-slice computed tomography (CT) scans of a chest phantom were performed with various tube voltages and tube currents, and the images were reconstructed using seven methods to control the amount of noise reduction: FBP, three stages of IR, and three stages of DLIR. For subjective image analysis, four radiologists compared 48 image data sets with reference images and rated on a 5-point scale. For quantitative image analysis, the signal to noise ratio (SNR), contrast to noise ratio (CNR), nodule volume, and nodule diameter were measured. In the subjective analysis, DLIR-Low (0.46 mGy), DLIR-Medium (0.31 mGy), and DLIR-High (0.18 mGy) images showed similar quality to the FBP (2.47 mGy) image. Under the same dose conditions, the SNR and CNR were higher with DLIR-High than with FBP and all the IR methods (all P<0.05). The nodule volume and size with DLIR-High were significantly closer to the real volume than with FBP and all the IR methods (all P<0.001). DLIR can improve the image quality of LDCT compared to FBP and IR. In addition, the appropriate effective dose for LDCT would be 0.24 mGy with DLIR-High.

Effect of Tube Voltage and Radiation Dose on Image Quality in Pediatric Abdominal CT Using Deep Learning Reconstruction: A Phantom Study

Background: Children have a potential risk from radiation exposure because they are more sensitive to radiation than adults. Objective: The purpose of this work is to estimate image quality according to tube voltage (kV) and radiation dose in pediatric computed tomography (CT) using deep learning reconstruction (DLR). Methods: Phantom images of children and adults were obtained for kV, radiation dose, and image reconstruction methods. The CT emits a fan beam to the opposite detector, and the geometry of the detector was symmetrical. Phantom images of children and adults were acquired at a volume CT dose index (CTDIvol) from 0.5 to 10.0 mGy for tube voltages at 80, 100, and 120 kV. A DLR was used to reconstruct the phantom image, and filtered back projection (FBP) and iterative reconstruction (IR) were also performed for comparison with the DLR. Image quality was evaluated by measuring the contrast-to-noise ratio (CNR) and noise. Results: Under the same imaging conditions, the DLR images of pediatric and adult phantoms generally provided improved CNR and noise compared with the FBP and IR images. At a similar CNR and noise, the FBP, IR, and DLR of the pediatric images showed a dose reduction compared with the FBP, IR, and DLR of the adult images, respectively. In terms of the effect of tube voltage, the CNR of the 100 kV DLR images was higher than that of the 120 kV DLR images. Conclusion: According to the results, since pediatric CT images maintain the same image quality at lower doses compared with adult CT images, DLR can improve image quality while reducing the radiation dose in children’s abdominal CT scans.

Physical and visual evaluations of CT image quality of large low-contrast objects with visual model-based iterative reconstruction technique: a phantom study.

We aimed to verify whether the image quality of large low-contrast objects can be improved using visual model-based iterative reconstruction (VMR) while maintaining the visibility of conventional filtered back projection (FBP) and reducing radiation dose through physical and visual evaluation.A 64-row multi-slice CT system with SCENARIA View (FUJIFILM healthcare Corp. Tokyo, Japan) was used. The noise power spectrum (NPS), task-based transfer function (TTF), and signal-to-noise ratio (SNR) were physically evaluated. A low contrast object as a substitute for a liver mass was visually evaluated.In the noise measurement, STD1 showed an 18% lower noise compared to FBP. STR4 was able to reduce noise by 58% compared to FBP. The NPS of VMR was similar to those of FBP from low to high spatial frequency. The NPS of VMR reconstructions showed a similar variation with frequency as FBP reconstructions. STD1 showed the highest 10% TTF, and higher 10% TTF was observed with lower VMR level. The SNR of VMR was close to that of FBP, and higher SNR was observed with higher VMR level. In the results of the visual evaluation, there was no significant difference in visual evaluation between STD1 and FBP (p = 0.99) and between STD2 and FBP (p = 0.56).We found that the NPS of VMR images was similar to that of FBP images, and it can reduce noise and radiation dose by 25% and 50%, respectively, without decreasing the visual image quality compared to FBP.

Dedicated convolutional neural network for noise reduction in ultra-high-resolution photon-counting detector computed tomography

Objective. To develop a convolutional neural network (CNN) noise reduction technique for ultra-high-resolution photon-counting detector computed tomography (UHR-PCD-CT) that can be efficiently implemented using only clinically available reconstructed images. The developed technique was demonstrated for skeletal survey, lung screening, and head angiography (CTA). Approach. There were 39 participants enrolled in this study, each received a UHR-PCD and an energy integrating detector (EID) CT scan. The developed CNN noise reduction technique uses image-based noise insertion and UHR-PCD-CT images to train a U-Net via supervised learning. For each application, 13 patient scans were reconstructed using filtered back projection (FBP) and iterative reconstruction (IR) and allocated into training, validation, and testing datasets (9:1:3). The subtraction of FBP and IR images resulted in approximately noise-only images. The 5-slice average of IR produced a thick reference image. The CNN training input consisted of thick reference images with reinsertion of spatially decoupled noise-only images. The training target consisted of the corresponding thick reference images without noise insertion. Performance was evaluated based on difference images, line profiles, noise measurements, nonlinear perturbation assessment, and radiologist visual assessment. UHR-PCD-CT images were compared with EID images (clinical standard). Main results. Up to 89% noise reduction was achieved using the proposed CNN. Nonlinear perturbation assessment indicated reasonable retention of 1 mm radius and 1000 HU contrast signals (>80% for skeletal survey and head CTA, >50% for lung screening). A contour plot indicated reduced retention for small-radius and low contrast perturbations. Radiologists preferred CNN over IR for UHR-PCD-CT noise reduction. Additionally, UHR-PCD-CT with CNN was preferred over standard resolution EID-CT images. Significance. CT images reconstructed with very sharp kernels and/or thin sections suffer from increased image noise. Deep learning noise reduction can be used to offset noise level and increase utility of UHR-PCD-CT images.

Effects of contrast enhancement boost postprocessing technique in combination with different reconstruction algorithms on the image quality of abdominal CT angiography

ObjectivesTo investigate whether contrast-enhancement-boost (CE-boost) in combination with hybrid iterative reconstruction (Hybrid IR, also named HIR [AIDR 3D, adaptive iterative dose reduction three dimensional]) and model-based iterative reconstruction (MBIR [FIRST, forward projected model-based IR solution]) algorithms can improve the image quality of abdominal CT angiography (CTA). MethodsThis retrospective study included 50 patients who underwent abdominal CTA. Both arterial and portal phases were reconstructed using three different algorithms [filtered-back projection (FBP), AIDR 3D, and FIRST] separately. CE-boost was performed additionally to generate AIDR 3D-boost and FIRST-boost images. Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of the arteries and portal system were compared among the five datasets (FBP, AIDR 3D, FIRST, AIDR 3D-boost, FIRST-boost). In subjective analyses, two radiologists independently ordered images (5, best; 1, worst) based on the visual image quality of distal arterial or portal venous branches. The Friedman and the Dunn-Bonferroni post-hoc tests were used for statistical analysis. ResultsFIRST-boost arterial and portal images had the lowest noise compared with FBP, AIDR 3D, FIRST, and AIDR 3D-boost images (all P < 0.05), and significantly higher SNR and CNR than FBP, AIDR 3D, and FIRST images (all P < 0.05). AIDR 3D-boost images showed lower noise, and higher SNR and CNR than FBP and AIDR 3D images (all P < 0.05). FIRST-boost images had higher subjective grading scores than FBP, AIDR 3D, and AIDR 3D-boost images (all P < 0.05). ConclusionThe postprocessing technique CE-boost can improve the image quality of abdominal CTA images. MBIR in combination with CE-boost (FIRST-boost) images had the best image quality compared with the other four image datasets.