Technical Note: Development and validation of an open data format for CT projection data

Self-adaption and texture generation: A hybrid loss function for low-dose CT denoising

BACKGROUND

Deep learning has been successfully applied to low-dose CT (LDCT) denoising. But the training of the model is very dependent on an appropriate loss function. Existing denoising models often use per-pixel loss, including mean abs error (MAE) and mean square error (MSE). This ignores the difference in denoising difficulty between different regions of the CT images and leads to the loss of large texture information in the generated image.

PURPOSE

In this paper, we propose a new hybrid loss function that adapts to the noise in different regions of CT images to balance the denoising difficulty and preserve texture details, thus acquiring CT images with high-quality diagnostic value using LDCT images, providing strong support for condition diagnosis.

METHODS

We propose a hybrid loss function consisting of weighted patch loss (WPLoss) and high-frequency information loss (HFLoss). To enhance the model's denoising ability of the local areas which are difficult to denoise, we improve the MAE to obtain WPLoss. After the generated image and the target image are divided into several patches, the loss weight of each patch is adaptively and dynamically adjusted according to its loss ratio. In addition, considering that texture details are contained in the high-frequency information of the image, we use HFLoss to calculate the difference between CT images in the high-frequency information part.

RESULTS

Our hybrid loss function improves the denoising performance of several models in the experiment, and obtains a higher peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM). Moreover, through visual inspection of the generated results of the comparison experiment, the proposed hybrid function can effectively suppress noise and retain image details.

CONCLUSIONS

We propose a hybrid loss function for LDCT image denoising, which has good interpretation properties and can improve the denoising performance of existing models. And the validation results of multiple models using different datasets show that it has good generalization ability. By using this loss function, high-quality CT images with low radiation are achieved, which can avoid the hazards caused by radiation and ensure the disease diagnosis for patients.

Image Noise Reduction Based on a Fixed Wavelet Frame and CNNs Applied to CT

Radiation exposure in CT imaging leads to increased patient risk. This motivates the pursuit of reduced-dose scanning protocols, in which noise reduction processing is indispensable to warrant clinically acceptable image quality. Convolutional Neural Networks (CNNs) have received significant attention as an alternative for conventional noise reduction and are able to achieve state-of-the art results. However, the internal signal processing in such networks is often unknown, leading to sub-optimal network architectures. The need for better signal preservation and more transparency motivates the use of Wavelet Shrinkage Networks (WSNs), in which the Encoding-Decoding (ED) path is the fixed wavelet frame known as Overcomplete Haar Wavelet Transform (OHWT) and the noise reduction stage is data-driven. In this work, we considerably extend the WSN framework by focusing on three main improvements. First, we simplify the computation of the OHWT that can be easily reproduced. Second, we update the architecture of the shrinkage stage by further incorporating knowledge of conventional wavelet shrinkage methods. Finally, we extensively test its performance and generalization, by comparing it with the RED and FBPConvNet CNNs. Our results show that the proposed architecture achieves similar performance to the reference in terms of MSSIM (0.667, 0.662 and 0.657 for DHSN2, FBPConvNet and RED, respectively) and achieves excellent quality when visualizing patches of clinically important structures. Furthermore, we demonstrate the enhanced generalization and further advantages of the signal flow, by showing two additional potential applications, in which the new DHSN2 is used as regularizer: (1) iterative reconstruction and (2) ground-truth free training of the proposed noise reduction architecture. The presented results prove that the tight integration of signal processing and deep learning leads to simpler models with improved generalization.

Upstream Machine Learning in Radiology

Machine learning (ML) and Artificial intelligence (AI) has the potential to dramatically improve radiology practice at multiple stages of the imaging pipeline. Most of the attention has been garnered by applications focused on improving the end of the pipeline: image interpretation. However, this article reviews how AI/ML can be applied to improve upstream components of the imaging pipeline, including exam modality selection, hardware design, exam protocol selection, data acquisition, image reconstruction, and image processing. A breadth of applications and their potential for impact is shown across multiple imaging modalities, including ultrasound, computed tomography, and MRI.

Deep Interactive Denoiser (DID) for X-Ray Computed Tomography

Low-dose computed tomography (LDCT) is desirable for both diagnostic imaging and image-guided interventions. Denoisers are widely used to improve the quality of LDCT. Deep learning (DL)-based denoisers have shown state-of-the-art performance and are becoming mainstream methods. However, there are two challenges to using DL-based denoisers: 1) a trained model typically does not generate different image candidates with different noise-resolution tradeoffs, which are sometimes needed for different clinical tasks; and 2) the model's generalizability might be an issue when the noise level in the testing images differs from that in the training dataset. To address these two challenges, in this work, we introduce a lightweight optimization process that can run on top of any existing DL-based denoiser during the testing phase to generate multiple image candidates with different noise-resolution tradeoffs suitable for different clinical tasks in real time. Consequently, our method allows users to interact with the denoiser to efficiently review various image candidates and quickly pick the desired one; thus, we termed this method deep interactive denoiser (DID). Experimental results demonstrated that DID can deliver multiple image candidates with different noise-resolution tradeoffs and shows great generalizability across various network architectures, as well as training and testing datasets with various noise levels.

Probabilistic self-learning framework for low-dose CT denoising

PURPOSE

Despite the indispensable role of x-ray computed tomography (CT) in diagnostic medicine, the associated harmful ionizing radiation dose is a major concern, as it may cause genetic diseases and cancer. Decreasing patients' exposure can reduce the radiation dose and hence the related risks, but it would inevitably induce higher quantum noise. Supervised deep learning techniques have been used to train deep neural networks for denoising low-dose CT (LDCT) images, but the success of such strategies requires massive sets of pixel-level paired LDCT and normal-dose CT (NDCT) images, which are rarely available in real clinical practice. Our purpose is to mitigate the data scarcity problem for deep learning-based LDCT denoising.

METHODS

To solve this problem, we devised a shift-invariant property-based neural network that uses only the LDCT images to characterize both the inherent pixel correlations and the noise distribution, shaping into our probabilistic self-learning (PSL) framework. The AAPM Low-dose CT Challenge dataset was used to train the network. Both simulated datasets and real dataset were employed to test the denoising performance as well as the model generalizability. The performance was compared to a conventional method (total variation (TV)-based), a popular self-learning method (noise2void (N2V)), and a well-known unsupervised learning method (CycleGAN) by using both qualitative visual inspection and quantitative metrics including peak signal-noise-ratio (PSNR), structural similarity index (SSIM) and contrast-to-noise-ratio (CNR). The standard deviations (STD) of selected flat regions were also calculated for comparison.

RESULTS

The PSL method can improve the averaged PSNR/SSIM values from 27.61/0.5939 (LDCT) to 30.50/0.6797. By contrast, the averaged PSNR/SSIM values were 31.49/0.7284 (TV), 29.43/0.6699 (N2V), and 29.79/0.6992 (CycleGAN). The averaged STDs of selected flat regions were calculated to be 132.3 HU (LDCT), 25.77 HU (TV), 19.95 HU (N2V), 75.06 HU (CycleGAN), 60.62 HU (PSL) and 57.28 HU (NDCT). As for the low-contrast lesion detectability quantification, the CNR were calculated to be 0.202 (LDCT), 0.356 (TV), 0.372 (N2V), 0.383 (CycleGAN), 0.399 (PSL), and 0.359 (NDCT). By visual inspection, we observed that the proposed PSL method can deliver a noise-suppressed and detail-preserved image, while the TV-based method would lead to the blocky artifact, the N2V method would produce over-smoothed structures and CT value biased effect, and the CycleGAN method would generate slightly noisy results with inaccurate CT values. We also verified the generalizability of the PSL method, which exhibited superior denoising performance among various testing datasets with different data distribution shifts.

CONCLUSIONS

A deep learning-based convolutional neural network can be trained without paired datasets. Qualitatively visual inspection showed the proposed PSL method can achieve superior denoising performance than all the competitors, despite that the employed quantitative metrics in terms of PSNR, SSIM and CNR did not always show consistently better values.

Low-dose CT image and projection dataset

PURPOSE

To describe a large, publicly available dataset comprising computed tomography (CT) projection data from patient exams, both at routine clinical doses and simulated lower doses.

ACQUISITION AND VALIDATION METHODS

The library was developed under local ethics committee approval. Projection and image data from 299 clinically performed patient CT exams were archived for three types of clinical exams: noncontrast head CT scans acquired for acute cognitive or motor deficit, low-dose noncontrast chest scans acquired to screen high-risk patients for pulmonary nodules, and contrast-enhanced CT scans of the abdomen acquired to look for metastatic liver lesions. Scans were performed on CT systems from two different CT manufacturers using routine clinical protocols. Projection data were validated by reconstructing the data using several different reconstruction algorithms and through use of the data in the 2016 Low Dose CT Grand Challenge. Reduced dose projection data were simulated for each scan using a validated noise-insertion method. Radiologists marked location and diagnosis for detected pathologies. Reference truth was obtained from the patient medical record, either from histology or subsequent imaging.

DATA FORMAT AND USAGE NOTES

Projection datasets were converted into the previously developed DICOM-CT-PD format, which is an extended DICOM format created to store CT projections and acquisition geometry in a nonproprietary format. Image data are stored in the standard DICOM image format and clinical data in a spreadsheet. Materials are provided to help investigators use the DICOM-CT-PD files, including a dictionary file, data reader, and user manual. The library is publicly available from The Cancer Imaging Archive (https://doi.org/10.7937/9npb-2637).

POTENTIAL APPLICATIONS

This CT data library will facilitate the development and validation of new CT reconstruction and/or denoising algorithms, including those associated with machine learning or artificial intelligence. The provided clinical information allows evaluation of task-based diagnostic performance.

Accelerating iterative coordinate descent using a stored system matrix

PURPOSE

The computational burden associated with model-based iterative reconstruction (MBIR) is still a practical limitation. Iterative coordinate descent (ICD) is an optimization approach for MBIR that has sometimes been thought to be incompatible with modern computing architectures, especially graphics processing units (GPUs). The purpose of this work is to accelerate the previously released open-source FreeCT_ICD to include GPU acceleration and to demonstrate computational performance with ICD that is comparable with simultaneous update approaches.

METHODS

FreeCT_ICD uses a stored system matrix (SSM), which precalculates the forward projector in the form of a sparse matrix and then reconstructs on a rotating coordinate grid to exploit helical symmetry. In our GPU ICD implementation, we shuffle the sinogram memory ordering such that data access in the sinogram coalesce into fewer transactions. We also update N_S voxels in the xy-plane simultaneously to improve occupancy. Conventional ICD updates voxels sequentially (N_S  = 1). Using N_S  > 1 eliminates existing convergence guarantees. Convergence behavior in a clinical dataset was therefore studied empirically.

RESULTS

On a pediatric dataset with sinogram size of 736 × 16 × 13860 reconstructed to a matrix size of 512 × 512 × 128, our code requires about 20 s per iteration on a single GPU compared to 2300 s per iteration for a 6-core CPU using FreeCT_ICD. After 400 iterations, the proposed and reference codes converge within 2 HU RMS difference (RMSD). Using a wFBP initialization, convergence within 10 HU RMSD is achieved within 4 min. Convergence is similar with N_S values between 1 and 256, and N_S  = 16 was sufficient to achieve maximum performance. Divergence was not observed until N_S  > 1024.

CONCLUSIONS

With appropriate modifications, ICD may be able to achieve computational performance competitive with simultaneous update algorithms currently used for MBIR.

Technical Note: Design and implementation of a high-throughput pipeline for reconstruction and quantitative analysis of CT image data

PURPOSE

With recent substantial improvements in modern computing, interest in quantitative imaging with CT has seen a dramatic increase. As a result, the need to both create and analyze large, high-quality datasets of clinical studies has increased as well. At present, no efficient, widely available method exists to accomplish this. The purpose of this technical note is to describe an open-source high-throughput computational pipeline framework for the reconstruction and analysis of diagnostic CT imaging data to conduct large-scale quantitative imaging studies and to accelerate and improve quantitative imaging research.

METHODS

The pipeline consists of two, primary "blocks": reconstruction and analysis. Reconstruction is carried out via a graphics processing unit (GPU) queuing framework developed specifically for the pipeline that allows a dataset to be reconstructed using a variety of different parameter configurations such as slice thickness, reconstruction kernel, and simulated acquisition dose. The analysis portion then automatically analyzes the output of the reconstruction using "modules" that can be combined in various ways to conduct different experiments. Acceleration of analysis is achieved using cluster processing. Efficiency and performance of the pipeline are demonstrated using an example 142 subject lung screening cohort reconstructed 36 different ways and analyzed using quantitative emphysema scoring techniques.

RESULTS

The pipeline reconstructed and analyzed the 5112 reconstructed datasets in approximately 10 days, a roughly 72× speedup over previous efforts using the scanner for reconstructions. Tightly coupled pipeline quality assurance software ensured proper performance of analysis modules with regard to segmentation and emphysema scoring.

CONCLUSIONS

The pipeline greatly reduced the time from experiment conception to quantitative results. The modular design of the pipeline allows the high-throughput framework to be utilized for other future experiments into different quantitative imaging techniques. Future applications of the pipeline being explored are robustness testing of quantitative imaging metrics, data generation for deep learning, and use as a test platform for image-processing techniques to improve clinical quantitative imaging.

Technical Note: FreeCT_ICD: An open-source implementation of a model-based iterative reconstruction method using coordinate descent optimization for CT imaging investigations

PURPOSE

To facilitate investigations into the impacts of acquisition and reconstruction parameters on quantitative imaging, radiomics and CAD using CT imaging, we previously released an open-source implementation of a conventional weighted filtered backprojection reconstruction called FreeCT_wFBP. Our purpose was to extend that work by providing an open-source implementation of a model-based iterative reconstruction method using coordinate descent optimization, called FreeCT_ICD.

METHODS

Model-based iterative reconstruction offers the potential for substantial radiation dose reduction, but can impose substantial computational processing and storage requirements. FreeCT_ICD is an open-source implementation of a model-based iterative reconstruction method that provides a reasonable tradeoff between these requirements. This was accomplished by adapting a previously proposed method that allows the system matrix to be stored with a reasonable memory requirement. The method amounts to describing the attenuation coefficient using rotating slices that follow the helical geometry. In the initially proposed version, the rotating slices are themselves described using blobs. We have replaced this description by a unique model that relies on trilinear interpolation together with the principles of Joseph's method. This model offers an improvement in memory requirement while still allowing highly accurate reconstruction for conventional CT geometries. The system matrix is stored column-wise and combined with an iterative coordinate descent (ICD) optimization. The result is FreeCT_ICD, which is a reconstruction program developed on the Linux platform using C++ libraries and released under the open-source GNU GPL v2.0 license. The software is capable of reconstructing raw projection data of helical CT scans. In this work, the software has been described and evaluated by reconstructing datasets exported from a clinical scanner which consisted of an ACR accreditation phantom dataset and a clinical pediatric thoracic scan.

RESULTS

For the ACR phantom, image quality was comparable to clinical reconstructions as well as reconstructions using open-source FreeCT_wFBP software. The pediatric thoracic scan also yielded acceptable results. In addition, we did not observe any deleterious impact in image quality associated with the utilization of rotating slices. These evaluations also demonstrated reasonable tradeoffs in storage requirements and computational demands.

CONCLUSION

FreeCT_ICD is an open-source implementation of a model-based iterative reconstruction method that extends the capabilities of previously released open-source reconstruction software and provides the ability to perform vendor-independent reconstructions of clinically acquired raw projection data. This implementation represents a reasonable tradeoff between storage and computational requirements and has demonstrated acceptable image quality in both simulated and clinical image datasets.

Low-dose CT for the detection and classification of metastatic liver lesions: Results of the 2016 Low Dose CT Grand Challenge

PURPOSE

Using common datasets, to estimate and compare the diagnostic performance of image-based denoising techniques or iterative reconstruction algorithms for the task of detecting hepatic metastases.

METHODS

Datasets from contrast-enhanced CT scans of the liver were provided to participants in an NIH-, AAPM- and Mayo Clinic-sponsored Low Dose CT Grand Challenge. Training data included full-dose and quarter-dose scans of the ACR CT accreditation phantom and 10 patient examinations; both images and projections were provided in the training data. Projection data were supplied in a vendor-neutral standardized format (DICOM-CT-PD). Twenty quarter-dose patient datasets were provided to each participant for testing the performance of their technique. Images were provided to sites intending to perform denoising in the image domain. Fully preprocessed projection data and statistical noise maps were provided to sites intending to perform iterative reconstruction. Upon return of the denoised or iteratively reconstructed quarter-dose images, randomized, blinded evaluation of the cases was performed using a Latin Square study design by 11 senior radiology residents or fellows, who marked the locations of identified hepatic metastases. Markings were scored against reference locations of clinically or pathologically demonstrated metastases to determine a per-lesion normalized score and a per-case normalized score (a faculty abdominal radiologist established the reference location using clinical and pathological information). Scores increased for correct detections; scores decreased for missed or incorrect detections. The winner for the competition was the entry that produced the highest total score (mean of the per-lesion and per-case normalized score). Reader confidence was used to compute a Jackknife alternative free-response receiver operating characteristic (JAFROC) figure of merit, which was used for breaking ties.

RESULTS

103 participants from 90 sites and 26 countries registered to participate. Training data were shared with 77 sites that completed the data sharing agreements. Subsequently, 41 sites downloaded the 20 test cases, which included only the 25% dose data (CTDIvol = 3.0 ± 1.8 mGy, SSDE = 3.5 ± 1.3 mGy). 22 sites submitted results for evaluation. One site provided binary images and one site provided images with severe artifacts; cases from these sites were excluded from review and the participants removed from the challenge. The mean (range) per-lesion and per-case normalized scores were -24.2% (-75.8%, 3%) and 47% (10%, 70%), respectively. Compared to reader results for commercially reconstructed quarter-dose images with no noise reduction, 11 of the 20 sites showed a numeric improvement in the mean JAFROC figure of merit. Notably two sites performed comparably to the reader results for full-dose commercial images. The study was not designed for these comparisons, so wide confidence intervals surrounded these figures of merit and the results should be used only to motivate future testing.

CONCLUSION

Infrastructure and methodology were developed to rapidly estimate observer performance for liver metastasis detection in low-dose CT examinations of the liver after either image-based denoising or iterative reconstruction. The results demonstrated large differences in detection and classification performance between noise reduction methods, although the majority of methods provided some improvement in performance relative to the commercial quarter-dose images with no noise reduction applied.

Technical Note: Insertion of digital lesions in the projection domain for dual-source, dual-energy CT

PURPOSE

To compare algorithms performing material decomposition and classification in dual-energy CT, it is desirable to know the ground truth of the lesion to be analyzed in real patient data. In this work, we developed and validated a framework to insert digital lesions of arbitrary chemical composition into patient projection data acquired on a dual-source, dual-energy CT system.

METHODS

A model that takes into account beam-hardening effects was developed to predict the CT number of objects with known chemical composition. The model utilizes information about the x-ray energy spectra, the patient/phantom attenuation, and the x-ray detector energy response. The beam-hardening model was validated on samples of iodine (I) and calcium (Ca) for a second-generation dual-source, dual-energy CT scanner for all tube potentials available and a wide range of patient sizes. The seven most prevalent mineral components of renal stones were modeled and digital stones were created with CT numbers computed for each patient/phantom size and x-ray energy spectra using the developed beam-hardening model. Each digital stone was inserted in the dual-energy projection data of a water phantom scanned on a dual-source scanner and reconstructed with the routine algorithms in use in our practice. The geometry of the forward projection for dual-energy data was validated by comparing CT number accuracy and high-contrast resolution of simulated dual-energy CT data of the ACR phantom with experimentally acquired data.

RESULTS

The beam-hardening model and forward projection method accurately predicted the CT number of I and Ca over a wide range of tube potentials and phantom sizes. The images reconstructed after the insertion of digital kidney stones were consistent with the images reconstructed from the scanner, and the CT number ratios for different kidney stone types were consistent with data in the literature. A sample application of the proposed tool was also demonstrated.

CONCLUSION

A framework was developed and validated for the creation of digital objects of known mineral composition, and for inserting the digital objects into projection data from a commercial dual-source, dual-energy CT scanner. Among other applications, it will allow a systematic investigation of the impact of scan and reconstruction parameters on kidney stone dual-energy properties under rigorously controlled conditions.

Lesion insertion in the projection domain: Methods and initial results

PURPOSE

To perform task-based image quality assessment in CT, it is desirable to have a large number of realistic patient images with known diagnostic truth. One effective way of achieving this objective is to create hybrid images that combine patient images with inserted lesions. Because conventional hybrid images generated in the image domain fails to reflect the impact of scan and reconstruction parameters on lesion appearance, this study explored a projection-domain approach.

METHODS

Lesions were segmented from patient images and forward projected to acquire lesion projections. The forward-projection geometry was designed according to a commercial CT scanner and accommodated both axial and helical modes with various focal spot movement patterns. The energy employed by the commercial CT scanner for beam hardening correction was measured and used for the forward projection. The lesion projections were inserted into patient projections decoded from commercial CT projection data. The combined projections were formatted to match those of commercial CT raw data, loaded onto a commercial CT scanner, and reconstructed to create the hybrid images. Two validations were performed. First, to validate the accuracy of the forward-projection geometry, images were reconstructed from the forward projections of a virtual ACR phantom and compared to physically acquired ACR phantom images in terms of CT number accuracy and high-contrast resolution. Second, to validate the realism of the lesion in hybrid images, liver lesions were segmented from patient images and inserted back into the same patients, each at a new location specified by a radiologist. The inserted lesions were compared to the original lesions and visually assessed for realism by two experienced radiologists in a blinded fashion.

RESULTS

For the validation of the forward-projection geometry, the images reconstructed from the forward projections of the virtual ACR phantom were consistent with the images physically acquired for the ACR phantom in terms of Hounsfield unit and high-contrast resolution. For the validation of the lesion realism, lesions of various types were successfully inserted, including well circumscribed and invasive lesions, homogeneous and heterogeneous lesions, high-contrast and low-contrast lesions, isolated and vessel-attached lesions, and small and large lesions. The two experienced radiologists who reviewed the original and inserted lesions could not identify the lesions that were inserted. The same lesion, when inserted into the projection domain and reconstructed with different parameters, demonstrated a parameter-dependent appearance.

CONCLUSIONS

A framework has been developed for projection-domain insertion of lesions into commercial CT images, which can be potentially expanded to all geometries of CT scanners. Compared to conventional image-domain methods, the authors' method reflected the impact of scan and reconstruction parameters on lesion appearance. Compared to prior projection-domain methods, the authors' method has the potential to achieve higher anatomical complexity by employing clinical patient projections and real patient lesions.

An Open Library of CT Patient Projection Data

Lack of access to projection data from patient CT scans is a major limitation for development and validation of new reconstruction algorithms. To meet this critical need, we are building a library of CT patient projection data in an open and vendor-neutral format, DICOM-CT-PD, which is an extended DICOM format that contains sinogram data, acquisition geometry, patient information, and pathology identification. The library consists of scans of various types, including head scans, chest scans, abdomen scans, electrocardiogram (ECG)-gated scans, and dual-energy scans. For each scan, three types of data are provided, including DICOM-CT-PD projection data at various dose levels, reconstructed CT images, and a free-form text file. Several instructional documents are provided to help the users extract information from DICOM-CT-PD files, including a dictionary file for the DICOM-CT-PD format, a DICOM-CT-PD reader, and a user manual. Radiologist detection performance based on the reconstructed CT images is also provided. So far 328 head cases, 228 chest cases, and 228 abdomen cases have been collected for potential inclusion. The final library will include a selection of 50 head, chest, and abdomen scans each from at least two different manufacturers, and a few ECG-gated scans and dual-source, dual-energy scans. It will be freely available to academic researchers, and is expected to greatly facilitate the development and validation of CT reconstruction algorithms.

Lesion Insertion in Projection Domain for Computed Tomography Image Quality Assessment

To perform task-based image quality assessment in CT, it is desirable to have a large number of realistic patient images with known diagnostic truth. One effective way to achieve this objective is to create hybrid images that combine patient images with simulated lesions. Because conventional hybrid images generated in the image-domain fails to reflect the impact of scan and reconstruction parameters on lesion appearance, this study explored a projection-domain approach. Liver lesion models were forward projected according to the geometry of a commercial CT scanner to acquire lesion projections. The lesion projections were then inserted into patient projections (decoded from commercial CT raw data with the assistance of the vendor) and reconstructed to acquire hybrid images. To validate the accuracy of the forward projection geometry, simulated images reconstructed from the forward projections of a digital ACR phantom were compared to physically acquired ACR phantom images. To validate the hybrid images, lesion models were inserted into patient images and visually assessed. Results showed that the simulated phantom images and the physically acquired phantom images had great similarity in terms of HU accuracy and high-contrast resolution. The lesions in the hybrid image had a realistic appearance and merged naturally into the liver background. In addition, the inserted lesion demonstrated reconstruction-parameter-dependent appearance. Compared to conventional image-domain approach, our method enables more realistic hybrid images for image quality assessment.