Optimal combination of anti-scatter grids and software correction for CBCT imaging

Feasibility of proton dosimetry overriding planning CT with daily CBCT elaborated through generative artificial intelligence tools

Radiotherapy commonly utilizes cone beam computed tomography (CBCT) for patient positioning and treatment monitoring. CBCT is deemed to be secure for patients, making it suitable for the delivery of fractional doses. However, limitations such as a narrow field of view, beam hardening, scattered radiation artifacts, and variability in pixel intensity hinder the direct use of raw CBCT for dose recalculation during treatment. To address this issue, reliable correction techniques are necessary to remove artifacts and remap pixel intensity into Hounsfield Units (HU) values. This study proposes a deep-learning framework for calibrating CBCT images acquired with narrow field of view (FOV) systems and demonstrates its potential use in proton treatment planning updates. Cycle-consistent generative adversarial networks (cGAN) processes raw CBCT to reduce scatter and remap HU. Monte Carlo simulation is used to generate CBCT scans, enabling the possibility to focus solely on the algorithm's ability to reduce artifacts and cupping effects without considering intra-patient longitudinal variability and producing a fair comparison between planning CT (pCT) and calibrated CBCT dosimetry. To showcase the viability of the approach using real-world data, experiments were also conducted using real CBCT. Tests were performed on a publicly available dataset of 40 patients who received ablative radiation therapy for pancreatic cancer. The simulated CBCT calibration led to a difference in proton dosimetry of less than 2%, compared to the planning CT. The potential toxicity effect on the organs at risk decreased from about 50% (uncalibrated) up the 2% (calibrated). The gamma pass rate at 3%/2 mm produced an improvement of about 37% in replicating the prescribed dose before and after calibration (53.78% vs 90.26%). Real data also confirmed this with slightly inferior performances for the same criteria (65.36% vs 87.20%). These results may confirm that generative artificial intelligence brings the use of narrow FOV CBCT scans incrementally closer to clinical translation in proton therapy planning updates.

The impact of X-ray scatter correction software on abdomen radiography in terms of image quality and radiation dose

INTRODUCTION

The conventional anti-scatter grid is widely used in X-ray radiography to reduce scattered X-rays, but it increases patient dose. Scatter-correction software offers a dose-reducing alternative by correcting for scattered X-rays without a physical grid. Grids and software correction are necessary to reduce scatter radiation and improve image quality especially for the large body parts. The scatter correction can be beneficial in situations where the use of grid is challenging. The implementation of grids and advanced software correction techniques is imperative to ensure that radiographic images maintain high levels of clarity, contrast, and resolution, and ultimately facilitating more accurate diagnoses. This study compares image quality and radiation dose for abdomen exams using scatter correction software and physical grids.

METHODS

An anthropomorphic phantom (abdomen) underwent imaging with varying fat and lean tissue layers and body mass index (BMI) configurations. Imaging parameters included 70 kVp tube voltage, 110 cm SID, and Automatic Exposure Control (AEC) both lateral and central chambers. AP abdomen X-ray projections were acquired with and without an anti-scatter grid, and scatter correction software was applied. Image quality was assessed using contrast to noise ratio (CNR) and signal to noise ratio (SNR) metrics. The tube current mAs was considered an exposure factor that affected radiation dose and was used to compare the VG software and physical grid. Radiation dose was measured using Dose Area Products (DAP). The effective dose was estimated using Monte Carlo simulation-PCXMC software. Paired t-tests were used to investigate the image quality difference between the Gridless and VG software, Gridless and PG, and VG software and PG approaches. For the DAP and effective dose, paired t-test was used to investigate the difference between VG software and PG.

RESULTS

Images acquired with a grid had the highest mean CNR (71.3 ± 32) compared to Gridless (50 ± 33.8) and scatter correction software (59.3 ± 37.9). The mean SNR of the grid images was (82.7.3 ± 38.9), which is 18% higher than the scatter correction software images (70.4 ± 36.7) and 29% higher than in the Gridless images (62.9.3 ± 34). The mean DAP value was reduced by 81% when the scatter correction software was used compared to the grid (mean: 65.4 μGy.m2 and 338.2 μGy.m2, respectively) with a significant difference (p = 0.001). Scatter correction software resulted in a lower effective dose compared to physical grid use, (mean difference± SD = -0.3 ± 0.18 mSv) with a significant difference (P = 0.02).

CONCLUSION

Scatter correction software reduced the radiation dose required but images employing a grid yielded higher CNR and SNR. However, the radiation dose reduction might affect the image quality to a level that impacts the diagnostic information available. Thus, further research needs to be conducted to optimise the use of the scatter correction software.

IMPLICATION FOR PRACTICE

Objectively, X-ray scatter correction software might be promising in conditions where a grid cannot be applied.

Energy-guided diffusion model for CBCT-to-CT synthesis

Cone Beam Computed Tomography (CBCT) plays a crucial role in Image-Guided Radiation Therapy (IGRT), providing essential assurance of accuracy in radiation treatment by monitoring changes in anatomical structures during the treatment process. However, CBCT images often face interference from scatter noise and artifacts, posing a significant challenge when relying solely on CBCT for precise dose calculation and accurate tissue localization. There is an urgent need to enhance the quality of CBCT images, enabling a more practical application in IGRT. This study introduces EGDiff, a novel framework based on the diffusion model, designed to address the challenges posed by scatter noise and artifacts in CBCT images. In our approach, we employ a forward diffusion process by adding Gaussian noise to CT images, followed by a reverse denoising process using ResUNet with an attention mechanism to predict noise intensity, ultimately synthesizing CBCT-to-CT images. Additionally, we design an energy-guided function to retain domain-independent features and discard domain-specific features during the denoising process, enhancing the effectiveness of CBCT-CT generation. We conduct numerous experiments on the thorax dataset and pancreas dataset. The results demonstrate that EGDiff performs better on the thoracic tumor dataset with SSIM of 0.850, MAE of 26.87 HU, PSNR of 19.83 dB, and NCC of 0.874. EGDiff outperforms SoTA CBCT-to-CT synthesis methods on the pancreas dataset with SSIM of 0.754, MAE of 32.19 HU, PSNR of 19.35 dB, and NCC of 0.846. By improving the accuracy and reliability of CBCT images, EGDiff can enhance the precision of radiation therapy, minimize radiation exposure to healthy tissues, and ultimately contribute to more effective and personalized cancer treatment strategies.

Impact of cone-beam computed tomography artifacts on dose calculation accuracy for lung cancer

BACKGROUND

To implement image-guided adaptive radiotherapy (IGART), many studies investigated dose calculations on cone-beam computed tomography (CBCT). A high HU accuracy is crucial for a high dose calculation accuracy and many imaging sites showed satisfactory results. It has been shown that the dose calculation accuracy for lung cancer lags behind.

PURPOSE

To examine why the dose calculation accuracy for lung is insufficient, the relative effects of the field-of-view (FOV), breathing motion, and scatter on dose calculation accuracy were studied.

METHODS

A framework was built to simulate CBCT scans for lung cancer patients by forward projecting repeat CT (rCT) scans for two scan geometries: small (SFOV) and medium FOV (MFOV). Breathing motion was modeled by applying a 4D deformation vector field to the mid-position rCT. Scatter was modeled by Monte-Carlo simulations with/without an anti-scatter grid (ASG). Simulated projections were reconstructed using filtered back-projection with/without scatter correction. In case of the SFOV, the CBCT images were patched with the planning CT scan in axial direction. The treatment plan was recalculated on the rCT and simulated CBCT. The mean Hounsfield unit (HU) difference (ΔHUmean ), the structural similarity index measure (SSIM), and γ metrics were calculated for the CBCT datasets of various imaging settings.

RESULTS

The differences in HU, SSIM and dose calculation accuracy for CBCTs with and without breathing motion were negligible (mean ΔHUmean  = 6.4 vs. 13.7, mean SSIM = 0.941 vs. 0.957, mean γ (ref = MFOV) = 0.75). The SFOV resulted in a lower HU (mean ΔHUmean  = -9.2 vs. 13.7) and SSIM (mean SSIM = 0.912 vs. 0.957), and therefore in dose differences compared to the MFOV (mean γ = 1.22). Scatter led to considerable discrepancies in all metrics. Adding only the ASG improved the results more than only applying a scatter correction algorithm. Combining ASG and scatter correction algorithm resulted in an even higher dose calculation accuracy.

CONCLUSIONS

Scatter and FOV are the main contributors to dose inaccuracies and motion has only a minor effect on dose calculation accuracy. Therefore, utilizing an appropriate scatter correction and FOV is important to achieve sufficient dose calculation accuracy to facilitate IGART for lung.

Improving the accuracy of bone mineral density using a multisource CBCT

Multisource cone beam computed tomography CBCT (ms-CBCT) has been shown to overcome some of the inherent limitations of a conventional CBCT. The purpose of this study was to evaluate the accuracy of ms-CBCT for measuring the bone mineral density (BMD) of mandible and maxilla compared to the conventional CBCT. The values measured from a multi-detector CT (MDCT) were used as substitutes for the ground truth. An anthropomorphic adult skull and tissue equivalent head phantom and a homemade calibration phantom containing inserts with varying densities of calcium hydroxyapatite were imaged using the ms-CBCT, the ms-CBCT operating in the conventional single source CBCT mode, and two clinical CBCT scanners at similar imaging doses; and a clinical MDCT. The images of the anthropomorphic head phantom were reconstructed and registered, and the cortical and cancellous bones of the mandible and the maxilla were segmented. The measured CT Hounsfield Unit (HU) and Greyscale Value (GV) at multiple region-of-interests were converted to the BMD using scanner-specific calibration functions. The results from the various CBCT scanners were compared to that from the MDCT. Statistical analysis showed a significant improvement in the agreement between the ms-CBCT and MDCT compared to that between the CBCT and MDCT.

Adaptive scatter kernel deconvolution modeling for cone-beam CT scatter correction via deep reinforcement learning

BACKGROUND

Scattering photons can seriously contaminate cone-beam CT (CBCT) image quality with severe artifacts and substantial degradation of CT value accuracy, which is a major concern limiting the widespread application of CBCT in the medical field. The scatter kernel deconvolution (SKD) method commonly used in clinic requires a Monte Carlo (MC) simulation to determine numerous quality-related kernel parameters, and it cannot realize intelligent scatter kernel parameter optimization, causing limited accuracy of scatter estimation.

PURPOSE

Aiming at improving the scatter estimation accuracy of the SKD algorithm, an intelligent scatter correction framework integrating the SKD with deep reinforcement learning (DRL) scheme is proposed.

METHODS

Our method firstly builds a scatter kernel model to iteratively convolve with raw projections, and then the deep Q-network of the DRL scheme is introduced to intelligently interact with the scatter kernel to achieve a projection adaptive parameter optimization. The potential of the proposed framework is demonstrated on CBCT head and pelvis simulation data and experimental CBCT measurement data. Furthermore, we have implemented the U-net based scatter estimation approach for comparison.

RESULTS

The simulation study demonstrates that the mean absolute percentage error (MAPE) of the proposed method is less than 9.72% and the peak signal-to-noise ratio (PSNR) is higher than 23.90 dB, while for the conventional SKD algorithm, the minimum MAPE is 17.92% and the maximum PSNR is 19.32 dB. In the measurement study, we adopt a hardware-based beam stop array algorithm to obtain the scatter-free projections as a comparison baseline, and our method can achieve superior performance with MAPE < 17.79% and PSNR > 16.34 dB.

CONCLUSIONS

In this paper, we propose an intelligent scatter correction framework that integrates the physical scatter kernel model with DRL algorithm, which has the potential to improve the accuracy of the clinical scatter correction method to obtain better CBCT imaging quality.

Reproducibility and location-stability of radiomic features derived from cone-beam computed tomography: a phantom study

OBJECTIVES

This study aims to determine the reproducibility and location-stability of cone-beam computed tomography (CBCT) radiomic features.

METHODS

Centrifugal tubes with six concentrations of K2HPO4 solutions (50, 100, 200, 400, 600, and 800 mg ml-1) were imaged within a customized phantom. For each concentration, images were captured twice as test and retest sets. Totally, 69 radiomic features were extracted by LIFEx. The reproducibility was assessed between the test and retest sets. We used the concordance correlation coefficient (CCC) to screen qualified features and then compared the differences in the numbers of them under 24 series (four locations groups * six concentrations). The location-stability was assessed using the Kruskal-Wallis test under different concentration sets; likewise, the numbers of qualified features under six test sets were analyzed.

RESULTS

There were 20 and 23 qualified features in the reproducibility and location-stability experiments, respectively. In the reproducibility experiment, the performance of the peripheral groups and high-concentration sets was significantly better than the center groups and low-concentration sets. The effect of concentration on the location-stability of features was not monotonic, and the number of qualified features in the low-concentration sets was greater than that in the high-concentration sets. No features were qualified in both experiments.

CONCLUSIONS

The density and location of the target object can affect the number of reproducible radiomic features, and its density can also affect the number of location-stable radiomic features. The problem of feature reliability should be treated cautiously in radiomic research on CBCT.

A simulation study to evaluate the effect of 2D antiscatter grid primary transmission on flat panel detector based CBCT image quality

Purpose. Two-dimensional antiscatter grids' (2D-ASGs) septal shadows and their impact on primary transmission play a critical role in cone-beam computed tomography (CBCT) image noise and artifact characteristics. Therefore, a numerical simulation platform was developed to evaluate the effect of 2D-ASG's primary transmission on image quality, as a function of grid geometry and CBCT system properties.Methods. To study the effect of 2D-ASG's septal shadows on primary transmission and CBCT image quality, two new methods were introduced; one to simulate projection signal gradients in septal shadows, and the other to simulate septal shadow variations due to gantry flex. Signal gradients in septal shadows were simulated by generating a system point spread function that was directly extracted from projection images of 2D-ASG prototypes in experiments. Variations in septal shadows due to gantry flex were simulated by generating oversampled shadow profiles extracted from experiments. Subsequently, the effect of 2D-ASG's septal shadows on primary transmission and image quality was evaluated.Results.For an apparent septal thickness of 0.15 mm, the primary transmission of 2D-ASG varied between 72%-90% for grid pitches 1-3 mm. In low-contrast phantoms, the effect of 2D-ASG's radiopaque footprint on information loss was subtle. At high spatial frequencies, information loss manifested itself as undersampling artifacts, however, its impact on image quality is subtle when compared to quantum noise. Effects of additive electronic noise and gantry flex induced ring artifacts on image quality varied as a function of grid pitch and septal thickness. Such artifacts were substantially less in lower resolution images.Conclusion. The proposed simulation platform allowed successful evaluation of CBCT image quality variations as a function of 2D-ASG primary transmission properties and CBCT system characteristics. This platform can be potentially used for optimizing 2D-ASG design properties based on the imaging task and properties of the CBCT system.

Monte Carlo model of a prototype flat-panel detector for multi-energy applications in radiotherapy

BACKGROUND

The incorporation of multi-energy capabilities into radiotherapy flat-panel detectors offers advantages including enhanced soft tissue visualization by reduction of signal from overlapping anatomy such as bone in 2D image projections; creation of virtual monoenergetic images for 3D contrast enhancement, metal artefact reduction and direct acquisition of relative electron density. A novel dual-layer on-board imager offering dual energy processing capabilities is being designed. As opposed to other dual-energy implementation techniques which require separate acquisition with two different x-ray spectra, the dual-layer detector design enables simultaneous acquisition of high and low energy images with a single exposure. A computational framework is required to optimize the design parameters and evaluate detector performance for specific clinical applications.

PURPOSE

In this study, we report on the development of a Monte Carlo (MC) model of the imager including model validation.

METHODS

The stack-up of the dual-layer imager (DLI) was implemented in GEANT4 Application for Tomographic Emission (GATE). The DLI model has an active area of 43×43 cm2 , with top and bottom Cesium Iodide (CsI) scintillators of 600 and 800 μm thickness, respectively. Measurement of spatial resolution and imaging of dedicated multi-material dual-energy (DE) phantoms were used to validate the model. The modulation transfer function (MTF) of the detector was calculated for a 120 kVp x-ray spectrum using a 0.5 mm thick tantalum edge rotated by 2.5o . For imaging validation, the DE phantom was imaged using a 140 kVp x-ray spectrum. For both validation simulations, corresponding measurements were done using an initial prototype of the imager. Agreement between simulations and measurement was assessed using normalized root mean square error (NRMSE) and 1D profile difference for the MTF and phantom images respectively. Further comparison between measurement and simulation was made using virtual monoenergetic images (VMIs) generated from basis material images derived using precomputed look-up tables.

RESULTS

The MTF of the bottom layer of the dual-layer model shows values decreasing more quickly with spatial frequency, compared to the top layer, due to the thicker bottom scintillator thickness and scatter from the top layer. A comparison with measurement shows NRMSE of 0.013 and 0.015 as well as identical MTF50 of 0.8 mm1 and 1.0 mm1 for the top and bottom layer respectively. For the DE imaging of the DE-phantom, although a maximum deviation of 3.3% is observed for the 10 mm aluminum and Teflon inserts at the top layer, the agreement for all other inserts is less than 2.2% of the measured value at both layers. Material decomposition of simulated scatter-free DE images gives an average accuracy in PMMA and aluminum composition of 4.9% and 10.3% for 11-30 mm PMMA and 1-10 mm aluminum objects respectively. A comparison of decomposed values using scatter containing measured and simulated DE images shows good agreement within statistical uncertainty.

CONCLUSION

Validation using both MTF and phantom imaging shows good agreement between simulation and measurements. With the present configuration of the digital prototype, the model can generate material decomposed images and virtual monoenergetic images.

Adaptive Radiation Therapy: A Review of CT-based Techniques

Adaptive radiation therapy is a feedback process by which imaging information acquired over the course of treatment, such as changes in patient anatomy, can be used to reoptimize the treatment plan, with the end goal of improving target coverage and reducing treatment toxicity. This review describes different types of adaptive radiation therapy and their clinical implementation with a focus on CT-guided online adaptive radiation therapy. Depending on local anatomic changes and clinical context, different anatomic sites and/or disease stages and presentations benefit from different adaptation strategies. Online adaptive radiation therapy, where images acquired in-room before each fraction are used to adjust the treatment plan while the patient remains on the treatment table, has emerged to address unpredictable anatomic changes between treatment fractions. Online treatment adaptation places unique pressures on the radiation therapy workflow, requiring high-quality daily imaging and rapid recontouring, replanning, plan review, and quality assurance. Generating a new plan with every fraction is resource intensive and time sensitive, emphasizing the need for workflow efficiency and clinical resource allocation. Cone-beam CT is widely used for image-guided radiation therapy, so implementing cone-beam CT-guided online adaptive radiation therapy can be easily integrated into the radiation therapy workflow and potentially allow for rapid imaging and replanning. The major challenge of this approach is the reduced image quality due to poor resolution, scatter, and artifacts. Keywords: Adaptive Radiation Therapy, Cone-Beam CT, Organs at Risk, Oncology © RSNA, 2023.

New technique and application of truncated CBCT processing in adaptive radiotherapy for breast cancer

OBJECTIVE

A generative adversarial network (TCBCTNet) was proposed to generate synthetic computed tomography (sCT) from truncated low-dose cone-beam computed tomography (CBCT) and planning CT (pCT). The sCT was applied to the dose calculation of radiotherapy for patients with breast cancer.

METHODS

The low-dose CBCT and pCT images of 80 female thoracic patients were used for training. The CBCT, pCT, and replanning CT (rCT) images of 20 thoracic patients and 20 patients with breast cancer were used for testing. All patients were fixed in the same posture with a vacuum pad. The CBCT images were scanned under the Fast Chest M20 protocol with a 50% reduction in projection frames compared with the standard Chest M20 protocol. Rigid registration was performed between pCT and CBCT, and deformation registration was performed between rCT and CBCT. In the training stage of the TCBCTNet, truncated CBCT images obtained from complete CBCT images by simulation were used. The input of the CBCT→CT generator was truncated CBCT and pCT, and TCBCTNet was applied to patients with breast cancer after training. The accuracy of the sCT was evaluated by anatomy and dosimetry and compared with the generative adversarial network with UNet and ResNet as the generators (named as UnetGAN, ResGAN).

RESULTS

The three models could improve the image quality of CBCT and reduce the scattering artifacts while preserving the anatomical geometry of CBCT. For the chest test set, TCBCTNet achieved the best mean absolute error (MAE, 21.18±3.76 HU), better than 23.06±3.90 HU in UnetGAN and 22.47±3.57 HU in ResGAN. When applied to patients with breast cancer, TCBCTNet performance decreased, and MAE was 25.34±6.09 HU. Compared with rCT, sCT by TCBCTNet showed consistent dose distribution and subtle absolute dose differences between the target and the organ at risk. The 3D gamma pass rates were 98.98%±0.64% and 99.69%±0.22% at 2 mm/2% and 3 mm/3%, respectively. Ablation experiments confirmed that pCT and content loss played important roles in TCBCTNet.

CONCLUSIONS

High-quality sCT images could be synthesized from truncated low-dose CBCT and pCT by using the proposed TCBCTNet model. In addition, sCT could be used to accurately calculate the dose distribution for patients with breast cancer.

3D-printed large-area focused grid for scatter reduction in cone-beam CT

BACKGROUND

Cone-beam computed tomography (CBCT) systems acquire volumetric data more efficiently than fan-beam or multislice CT, particularly when the anatomy of interest resides within the axial field-of-view of the detector and data can be acquired in one rotation. For such systems, scattered radiation remains a source of image quality degradation leading to increased noise, image artifacts, and CT number inaccuracies.

PURPOSE

Recent advances in metal additive manufacturing allow the production of highly focused antiscatter grids (2D-ASGs) that can be used to reduce scatter intensity, while preserving primary radiation transmission. We present the first implementation of a large-area, 2D-ASG for flat-panel CBCT, including grid-line artifact removal and related improvements in image quality.

METHODS

A 245 × 194 × 10 mm 2D-ASG was manufactured from chrome-cobalt alloy using laser powder-bed fusion (LPBF) (AM-400; Renishaw plc, New Mills Wotton-under-Edge, UK). The 2D-ASG had a square profile with a pitch of 9.09 lines/cm and 10:1 grid-ratio. The nominal 0.1 mm grid septa were focused to a 732 mm x-ray source to optimize primary x-ray transmission and reduce grid-line shadowing at the detector. Powder-bed fusion ensured the structural stability of the ASG with no need for additional interseptal support. The 2D-ASG was coupled to a 0.139-mm element pitch flat-panel detector (DRX 3543, Carestream Health) and proper alignment was confirmed by consistent grid-line shadow thickness across the whole detector array. A 154-mm diameter CBCT image-quality-assurance phantom was imaged using a rotary stage and a ceiling-mounted, x-ray unit (Proteus XR/a, GE Medical Systems, 80kVp, 0.5mAs). Grid-line artifacts were removed using a combination of exposure-dependent gain correction and spatial-frequency, Fourier filtering. Projections were reconstructed using a Parker-weighted, FDK algorithm and voxels were spatially averaged to 357 × 357 × 595 µm to improve the signal-to-noise characteristics of the CBCT reconstruction. Finally, in order to compare image quality with and without scatter, the phantom was scanned again under the same CBCT conditions but with no 2D-ASG. No additional antiscatter (i.e., air-gap, bowtie filtration) strategies were used to evaluate the effects in image quality caused by the 2D-ASG alone.

RESULTS

The large-area, 2D-ASG prototype was successfully designed and manufactured using LPBF. CBCT image-quality improvements using the 2D-ASG included: an overall 14.5% CNR increase across the volume; up to 48.8% CNR increase for low-contrast inserts inside the contrast plate of the QA phantom; and a 65% reduction of cupping artifact in axial profiles of water-filled cross sections of the phantom. Advanced image processing strategies to remove grid line artifacts did not affect the spatial resolution or geometric accuracy of the system.

CONCLUSIONS

LPBF can be used to manufacture highly efficient, 2D-focused ASGs that can be easily coupled to clinical, flat-panel detectors. The implementation of ASGs in CBCT leads to reduced scatter-related artifacts, improved CT number accuracy, and enhanced CNR with no increased equivalent dose to the patient. Further improvements to image quality might be achieved with a combination of scatter-correction algorithms and iterative-reconstruction strategies. Finally, clinical applications where other scatter removal strategies are unfeasible might now achieve superior soft-tissue visualization and quantitative capabilities.

Deep learning for x-ray scatter correction in dedicated breast CT

BACKGROUND

Accurate correction of x-ray scatter in dedicated breast computed tomography (bCT) imaging may result in improved visual interpretation and is crucial to achieve quantitative accuracy during image reconstruction and analysis.

PURPOSE

To develop a deep learning (DL) model to correct for x-ray scatter in bCT projection images.

METHODS

A total of 115 patient scans acquired with a bCT clinical system were segmented into the major breast tissue types (skin, adipose, and fibroglandular tissue). The resulting breast phantoms were divided into training (n = 110) and internal validation cohort (n = 5). Training phantoms were augmented by a factor of four by random translation of the breast in the image field of view. Using a previously validated Monte Carlo (MC) simulation algorithm, 12 primary and scatter bCT projection images with a 30-degree step were generated from each phantom. For each projection, the thickness map and breast location in the field of view were also calculated. A U-Net based DL model was developed to estimate the scatter signal based on the total input simulated image and trained single-projection-wise, with the thickness map and breast location provided as additional inputs. The model was internally validated using MC-simulated projections and tested using an external data set of 10 phantoms derived from images acquired with a different bCT system. For this purpose, the mean relative difference (MRD) and mean absolute error (MAE) were calculated. To test for accuracy in reconstructed images, a full bCT acquisition was mimicked with MC-simulations and then assessed by calculating the MAE and the structural similarity (SSIM). Subsequently, scatter was estimated and subtracted from the bCT scans of three patients to obtain the scatter-corrected image. The scatter-corrected projections were reconstructed and compared with the uncorrected reconstructions by evaluating the correction of the cupping artifact, increase in image contrast, and contrast-to-noise ratio (CNR).

RESULTS

The mean MRD and MAE across all cases (min, max) for the internal validation set were 0.04% (-1.1%, 1.3%) and 2.94% (2.7%, 3.2%), while for the external test set they were -0.64% (-1.6%, 0.2%) and 2.84% (2.3%, 3.5%), respectively. For MC-simulated reconstruction slices, the computed SSIM was 0.99 and the MAE was 0.11% (range: 0%, 0.35%) with a single outlier slice of 2.06%. For the three patient bCT reconstructed images, the correction increased the contrast by a mean of 25% (range: 20%, 30%), and reduced the cupping artifact. The mean CNR increased by 0.32 after scatter correction, which was not found to be significant (95% confidence interval: [-0.01, 0.65], p = 0.059). The time required to correct the scatter in a single bCT projection was 0.2 s on an NVIDIA GeForce GTX 1080 GPU.

CONCLUSION

The developed DL model could accurately estimate scatter in bCT projection images and could enhance contrast and correct for cupping artifact in reconstructed patient images without significantly affecting the CNR. The time required for correction would allow its use in daily clinical practice, and the reported accuracy will potentially allow quantitative reconstructions.

Deep learning-based segmentation in prostate radiation therapy using Monte Carlo simulated cone-beam computed tomography

PURPOSE

Segmenting organs in cone-beam CT (CBCT) images would allow to adapt the radiotherapy based on the organ deformations that may occur between treatment fractions. However, this is a difficult task because of the relative lack of contrast in CBCT images, leading to high inter-observer variability. Deformable image registration (DIR) and deep-learning based automatic segmentation approaches have shown interesting results for this task in the past years. However, they are either sensitive to large organ deformations, or require to train a convolutional neural network (CNN) from a database of delineated CBCT images, which is difficult to do without improvement of image quality. In this work, we propose an alternative approach: to train a CNN (using a deep learning-based segmentation tool called nnU-Net) from a database of artificial CBCT images simulated from planning CT, for which it is easier to obtain the organ contours.

METHODS

Pseudo-CBCT (pCBCT) images were simulated from readily available segmented planning CT images, using the GATE Monte Carlo simulation. CT reference delineations were copied onto the pCBCT, resulting in a database of segmented images used to train the neural network. The studied segmentation contours were: bladder, rectum, and prostate contours. We trained multiple nnU-Net models using different training: (1) segmented real CBCT, (2) pCBCT, (3) segmented real CT and tested on pseudo-CT (pCT) generated from CBCT with cycleGAN, and (4) a combination of (2) and (3). The evaluation was performed on different datasets of segmented CBCT or pCT by comparing predicted segmentations with reference ones thanks to Dice similarity score and Hausdorff distance. A qualitative evaluation was also performed to compare DIR-based and nnU-Net-based segmentations.

RESULTS

Training with pCBCT was found to lead to comparable results to using real CBCT images. When evaluated on CBCT obtained from the same hospital as the CT images used in the simulation of the pCBCT, the model trained with pCBCT scored mean DSCs of 0.92 ± 0.05, 0.87 ± 0.02, and 0.85 ± 0.04 and mean Hausdorff distance 4.67 ± 3.01, 3.91 ± 0.98, and 5.00 ± 1.32 for the bladder, rectum, and prostate contours respectively, while the model trained with real CBCT scored mean DSCs of 0.91 ± 0.06, 0.83 ± 0.07, and 0.81 ± 0.05 and mean Hausdorff distance 5.62 ± 3.24, 6.43 ± 5.11, and 6.19 ± 1.14 for the bladder, rectum, and prostate contours, respectively. It was also found to outperform models using pCT or a combination of both, except for the prostate contour when tested on a dataset from a different hospital. Moreover, the resulting segmentations demonstrated a clinical acceptability, where 78% of bladder segmentations, 98% of rectum segmentations, and 93% of prostate segmentations required minor or no corrections, and for 76% of the patients, all structures of the patient required minor or no corrections.

CONCLUSION

We proposed to use simulated CBCT images to train a nnU-Net segmentation model, avoiding the need to gather complex and time-consuming reference delineations on CBCT images.

Improving cone-beam CT quality using a cycle-residual connection with a dilated convolution-consistent generative adversarial network

Objective.Cone-Beam CT (CBCT) often results in severe image artifacts and inaccurate HU values, meaning poor quality CBCT images cannot be directly applied to dose calculation in radiotherapy. To overcome this, we propose a cycle-residual connection with a dilated convolution-consistent generative adversarial network (Cycle-RCDC-GAN). Approach. The cycle-consistent generative adversarial network (Cycle-GAN) was modified using a dilated convolution with different expansion rates to extract richer semantic features from input images. Thirty pelvic patients were used to investigate the effect of synthetic CT (sCT) from CBCT, and 55 head and neck patients were used to explore the generalizability of the model. Three generalizability experiments were performed and compared: the pelvis trained model was applied to the head and neck; the head and neck trained model was applied to the pelvis, and the two datasets were trained together. Main results. The mean absolute error (MAE), the root mean square error (RMSE), peak signal to noise ratio (PSNR), the structural similarity index (SSIM), and spatial nonuniformity (SNU) assessed the quality of the sCT generated from CBCT. Compared with CBCT images, the MAE improved from 28.81 to 18.48, RMSE from 85.66 to 69.50, SNU from 0.34 to 0.30, and PSNR from 31.61 to 33.07, while SSIM improved from 0.981 to 0.989. The sCT objective indicators of Cycle-RCDC-GAN were better than Cycle-GAN’s. The objective metrics for generalizability were also better than Cycle-GAN’s. Significance. Cycle-RCDC-GAN enhances CBCT image quality and has better generalizability than Cycle-GAN, which further promotes the application of CBCT in radiotherapy.

Synthetic CT generation based on CBCT using respath-cycleGAN

PURPOSE

Cone-beam computed tomography (CBCT) plays an important role in radiotherapy, but the presence of a large number of artifacts limits its application. The purpose of this study was to use respath-cycleGAN to synthesize CT (sCT) similar to planning CT (pCT) from CBCT for future clinical practice.

METHODS

The method integrates the respath concept into the original cycleGAN, called respath-cycleGAN, to map CBCT to pCT. Thirty patients were used for training, and 15 for testing.

RESULTS

The mean absolute error (MAE), root mean square error (RMSE), peak signal to noise ratio (PSNR), structural similarity index (SSIM), and spatial non-uniformity (SNU) were calculated to assess the quality of sCT generated from CBCT. Compared with CBCT images, the MAE improved from 197.72 to 140.7, RMSE from 339.17 to 266.51, and PSNR from 22.07 to 24.44, while SSIM increased from 0.948 to 0.964. Both visually and quantitatively, sCT with respath is superior to sCT without respath. We also performed a generalization test of the head-and-neck (H&N) model on a pelvic dataset. The results again showed that our model was superior.

CONCLUSION

We developed a respath-cycleGAN method to synthesize CT with good quality from CBCT. In future clinical practice, this method may be used to develop radiotherapy plans. This article is protected by copyright. All rights reserved.

Image quality of dual-energy cone-beam CT with total nuclear variation regularization

Despite the improvements in image quality of cone beam computed tomography (CBCT) scans, application remains limited to patient positioning. In this study, we propose to improve image quality by dual energy (DE) imaging and iterative reconstruction using least squares fitting with total variation (TV) regularization. The generalization of TV called total nuclear variation (TNV) was used to generate DE images. We acquired single energy (SE) and DE scans of an image quality phantom (IQP) and of an anthropomorphic human male phantom (HMP). The DE scans were dual arc acquisitions of 70kV and 130kV with a variable dose partitioning between low energy (LE) and high energy (HE) arcs. To investigate potential benefits from a larger spectral separation between LE and HE, DE scans with an additional 2 mm copper beam filtration in the HE arc were acquired for the IQP. The DE TNV scans were compared to SE scans reconstructed with FDK and iterative TV with varying parameters. The contrast-to-noise ratio (CNR), spatial frequency, and structural similarity (SSIM) were used as image quality metrics. Results showed largely improved image quality for DE TNV over FDK for both phantoms. DE TNV with the highest dose allocation in the LE arm yielded the highest CNR. Compared to SE TV, these DE TNV results had a slightly lower CNR with similar spatial resolution for the IQP. A decrease in the dose allocated to the LE arm improved the spatial resolution with a trade-off against CNR. For the HMP, DE TNV displayed a lower CNR and/or lower spatial resolution depending on the reconstruction parameters. Regarding the SSIM, DE TNV was superior to FDK and SE TV for both phantoms. The additional beam filtration for the IQP led to improved image quality in all metrics, surpassing the SE TV results in CNR and spatial resolution.

Scatter-to-primary ratio in dentomaxillofacial cone-beam CT: effect of field of view and beam energy

OBJECTIVE

The aim of this study was to evaluate the effect of field of view (FOV) and beam energy on the scatter-to-primary ratio (SPR) in dental cone-beam CT (CBCT).

METHODS

An anthropomorphic phantom representing an adult male (ATOM Max 711-HN, Norfolk, VA, USA) was scanned using the 3D Accuitomo 170 CBCT (J. Morita, Kyoto, Japan) using 11 FOVs. During each scan, half of the X-ray beam was blocked. Each scan was performed at three exposure settings with varying beam energy and equal radiation dose: 90 kV 5 mA, 77 kV 7.5 mA and 69 kV 10 mA. The SPR was estimated by measuring the grey values in the blocked and non-blocked regions of the RAW data. The effect of FOV on SPR was evaluated using Dunn's multiple comparison test, and the effect of the exposure settings was compared using a Wilcoxon signed rank test.

RESULTS

Larger FOVs showed increased scatter. FOVs with a shorter isocenter-detector distance showed a particularly high SPR. Most intercomparisons between FOVs were statistically significant. The largest difference was found between 17 × 12 cm and 6 × 6 cm (lower jaw), with the former showing a 4.9-fold higher SPR. The effect of beam energy was relatively small and varied between FOV sizes and positions.

CONCLUSION

While the choice of FOV size and position is determined by the diagnostic region of interest, the image quality deterioration for large FOVs due to scatter provides another incentive to limit the FOV size as much as possible.

Generating synthetic CT from low-dose cone-beam CT by using generative adversarial networks for adaptive radiotherapy

OBJECTIVE

To develop high-quality synthetic CT (sCT) generation method from low-dose cone-beam CT (CBCT) images by using attention-guided generative adversarial networks (AGGAN) and apply these images to dose calculations in radiotherapy.

METHODS

The CBCT/planning CT images of 170 patients undergoing thoracic radiotherapy were used for training and testing. The CBCT images were scanned under a fast protocol with 50% less clinical projection frames compared with standard chest M20 protocol. Training with aligned paired images was performed using conditional adversarial networks (so-called pix2pix), and training with unpaired images was carried out with cycle-consistent adversarial networks (cycleGAN) and AGGAN, through which sCT images were generated. The image quality and Hounsfield unit (HU) value of the sCT images generated by the three neural networks were compared. The treatment plan was designed on CT and copied to sCT images to calculated dose distribution.

RESULTS

The image quality of sCT images by all the three methods are significantly improved compared with original CBCT images. The AGGAN achieves the best image quality in the testing patients with the smallest mean absolute error (MAE, 43.5 ± 6.69), largest structural similarity (SSIM, 93.7 ± 3.88) and peak signal-to-noise ratio (PSNR, 29.5 ± 2.36). The sCT images generated by all the three methods showed superior dose calculation accuracy with higher gamma passing rates compared with original CBCT image. The AGGAN offered the highest gamma passing rates (91.4 ± 3.26) under the strictest criteria of 1 mm/1% compared with other methods. In the phantom study, the sCT images generated by AGGAN demonstrated the best image quality and the highest dose calculation accuracy.

CONCLUSIONS

High-quality sCT images were generated from low-dose thoracic CBCT images by using the proposed AGGAN through unpaired CBCT and CT images. The dose distribution could be calculated accurately based on sCT images in radiotherapy.

Comparison of Supervised and Unsupervised Approaches for the Generation of Synthetic CT from Cone-Beam CT

Due to major artifacts and uncalibrated Hounsfield units (HU), cone-beam computed tomography (CBCT) cannot be used readily for diagnostics and therapy planning purposes. This study addresses image-to-image translation by convolutional neural networks (CNNs) to convert CBCT to CT-like scans, comparing supervised to unsupervised training techniques, exploiting a pelvic CT/CBCT publicly available dataset. Interestingly, quantitative results were in favor of supervised against unsupervised approach showing improvements in the HU accuracy (62% vs. 50%), structural similarity index (2.5% vs. 1.1%) and peak signal-to-noise ratio (15% vs. 8%). Qualitative results conversely showcased higher anatomical artifacts in the synthetic CBCT generated by the supervised techniques. This was motivated by the higher sensitivity of the supervised training technique to the pixel-wise correspondence contained in the loss function. The unsupervised technique does not require correspondence and mitigates this drawback as it combines adversarial, cycle consistency, and identity loss functions. Overall, two main impacts qualify the paper: (a) the feasibility of CNN to generate accurate synthetic CT from CBCT images, which is fast and easy to use compared to traditional techniques applied in clinics; (b) the proposal of guidelines to drive the selection of the better training technique, which can be shifted to more general image-to-image translation.

Synthetic CT generation from CBCT images via unsupervised deep learning

Adaptive-radiation-therapy (ART) is applied to account for anatomical variations observed over the treatment course. Daily or weekly cone-beam computed tomography (CBCT) is commonly used in clinic for patient positioning, but CBCT's inaccuracy in Hounsfield units (HU) prevents its application to dose calculation and treatment planning. Adaptive re-planning can be performed by deformably registering planning CT (pCT) to CBCT. However, scattering artifacts and noise in CBCT decrease the accuracy of deformable registration and induce uncertainty in treatment plan. Hence, generating from CBCT a synthetic CT (sCT) that has the same anatomical structure as CBCT but accurate HU values is desirable for ART. We proposed an unsupervised style-transfer-based approach to generate sCT based on CBCT and pCT. Unsupervised learning was desired because exactly matched CBCT and CT are rarely available, even when they are taken a few minutes apart. In the proposed model, CBCT and pCT are two inputs that provide anatomical structure and accurate HU information, respectively. The training objective function is designed to simultaneously minimize (1) contextual loss between sCT and CBCT to maintain the content and structure of CBCT in sCT and (2) style loss between sCT and pCT to achieve pCT-like image quality in sCT. We used CBCT and pCT images of 114 patients to train and validate the designed model, and another 29 independent patient cases to test the model's effectiveness. We quantitatively compared the resulting sCT with the original CBCT using the deformed same-day pCT as reference. Structure-similarity-index, peak-signal-to-noise-ratio, and mean-absolute-error in HU of sCT were 0.9723, 33.68, and 28.52, respectively, while those of CBCT were 0.9182, 29.67, and 49.90, respectively. We have demonstrated the effectiveness of the proposed model in using CBCT and pCT to synthesize CT-quality images. This model may permit using CBCT for advanced applications such as adaptive treatment planning.

MV CBCT-Based Synthetic CT Generation Using a Deep Learning Method for Rectal Cancer Adaptive Radiotherapy

Due to image quality limitations, online Megavoltage cone beam CT (MV CBCT), which represents real online patient anatomy, cannot be used to perform adaptive radiotherapy (ART). In this study, we used a deep learning method, the cycle-consistent adversarial network (CycleGAN), to improve the MV CBCT image quality and Hounsfield-unit (HU) accuracy for rectal cancer patients to make the generated synthetic CT (sCT) eligible for ART. Forty rectal cancer patients treated with the intensity modulated radiotherapy (IMRT) were involved in this study. The CT and MV CBCT images of 30 patients were used for model training, and the images of the remaining 10 patients were used for evaluation. Image quality, autosegmentation capability and dose calculation capability using the autoplanning technique of the generated sCT were evaluated. The mean absolute error (MAE) was reduced from 135.84 ± 41.59 HU for the CT and CBCT comparison to 52.99 ± 12.09 HU for the CT and sCT comparison. The structural similarity (SSIM) index for the CT and sCT comparison was 0.81 ± 0.03, which is a great improvement over the 0.44 ± 0.07 for the CT and CBCT comparison. The autosegmentation model performance on sCT for femoral heads was accurate and required almost no manual modification. For the CTV and bladder, although modification was needed for autocontouring, the Dice similarity coefficient (DSC) indices were high, at 0.93 and 0.94 for the CTV and bladder, respectively. For dose evaluation, the sCT-based plan has a much smaller dose deviation from the CT-based plan than that of the CBCT-based plan. The proposed method solved a key problem for rectal cancer ART realization based on MV CBCT. The generated sCT enables ART based on the actual patient anatomy at the treatment position.

Clinical Enhancement in AI-Based Post-processed Fast-Scan Low-Dose CBCT for Head and Neck Adaptive Radiotherapy

Purpose: To assess image quality and uncertainty in organ-at-risk segmentation on cone beam computed tomography (CBCT) enhanced by deep-learning convolutional neural network (DCNN) for head and neck cancer.

Methods: An in-house DCNN was trained using forty post-operative head and neck cancer patients with their planning CT and first-fraction CBCT images. Additional fifteen patients with repeat simulation CT (rCT) and CBCT scan taken on the same day (oCBCT) were used for validation and clinical utility assessment. Enhanced CBCT (eCBCT) images were generated from the oCBCT using the in-house DCNN. Quantitative imaging quality improvement was evaluated using HU accuracy, signal-to-noise-ratio (SNR), and structural similarity index measure (SSIM). Organs-at-risk (OARs) were delineated on o/eCBCT and compared with manual structures on the same day rCT. Contour accuracy was assessed using dice similarity coefficient (DSC), Hausdorff distance (HD), and center of mass (COM) displacement. Qualitative assessment of users’ confidence in manual segmenting OARs was performed on both eCBCT and oCBCT by visual scoring.

Results: eCBCT organs-at-risk had significant improvement on mean pixel values, SNR (p < 0.05), and SSIM (p < 0.05) compared to oCBCT images. Mean DSC of eCBCT-to-rCT (0.83 ± 0.06) was higher than oCBCT-to-rCT (0.70 ± 0.13). Improvement was observed for mean HD of eCBCT-to-rCT (0.42 ± 0.13 cm) vs. oCBCT-to-rCT (0.72 ± 0.25 cm). Mean COM was less for eCBCT-to-rCT (0.28 ± 0.19 cm) comparing to oCBCT-to-rCT (0.44 ± 0.22 cm). Visual scores showed OAR segmentation was more accessible on eCBCT than oCBCT images.

Conclusion: DCNN improved fast-scan low-dose CBCT in terms of the HU accuracy, image contrast, and OAR delineation accuracy, presenting potential of eCBCT for adaptive radiotherapy.

Improving linac integrated cone beam computed tomography image quality using tube current modulation

PURPOSE

Linac integrated cone beam CT (CBCT) scanners have become widespread tool for image guidance in radiotherapy. The current implementation uses constant imaging fluence across all the projection angles, which leads to anisotropic noise properties and suboptimal image quality for noncircular symmetric objects. Tube current modulation (TCM) is widely used in conventional CT. The purpose of this work was to implement TCM on a linac integrated CBCT scanner and evaluate its impact on image quality under varying scatter conditions and scatter correction strategies.

METHODS

We have implemented TCM on a nonclinical Elekta Versa HD linear accelerator with enhanced x-ray generator functionality including pulse width modulation. The pulse width was modulated using two Arduino programmable microcontrollers: one placed on the kV arm to measure the projection angle and the other connected to the kV generator control board to vary x-ray pulse width as function of gantry angle and precalculated transmission. An in-house developed phantom with a ratio of the left-right to anterior-posterior path length of 1.85:1 was scanned. Image quality was determined using the anisotropicity of the 2D noise power spectra (NPS) in the transverse plane and the contrast-to-noise ratio (CNR). In addition, to determine the impact of scatter on the applicability of the TCM method we have modified the generated scatter using three different collimators in the cranio-caudal direction as well as with and without an antiscatter grid (ASG).

RESULTS

Application of the TCM led to 30-78% reduction of the angular anisotropicity of the NPS in the transverse plane. The amount of reduction depended on the scatter conditions, with lower values corresponding to higher scatter conditions. The same was true for the CNR: when scatter contribution was low (presence of an ASG or very aggressive collimation) the CNR was improved by about 30%, while in high scatter conditions the CNR was improved by about 12%.

CONCLUSIONS

TCM has the potential to improve CBCT image quality, but this depends on the amount of detected x-ray scatter.

Evaluation of scatter rejection and correction performance of 2D antiscatter grids in cone beam computed tomography

PURPOSE

We have been investigating two-dimensional (2D) antiscatter grids (2D ASGs) to reduce scatter fluence and improve image quality in cone beam computed tomography (CBCT). In this work, two different aspects of 2D ASGs, their scatter rejection and correction capability, were investigated in CBCT experiments. To correct residual scatter transmitted through the 2D ASG, it was used as a scatter measurement device with a novel method: grid-based scatter sampling.

METHODS

Three focused 2D ASG prototypes with grid ratios of 8, 12, and 16 were developed for linac-mounted offset detector CBCT geometry. In the first phase, 2D ASGs were used as a scatter rejection device, and the effect of grid ratio on CT number accuracy and contrast-to-noise ratio (CNR) evaluated in CBCT images. In the second phase, a grid-based scatter sampling method which exploits the signal modulation characteristics of the 2D ASG's septal shadows to measure and correct residual scatter transmitted through the grid was implemented. To evaluate CT number accuracy, the percent change in CT numbers was measured by changing the phantom from head to pelvis size and configuration.

RESULTS

When 2D ASG was used as a scatter rejection device, CT number accuracy increased and the CT number variation due to change in phantom dimensions was reduced from 23% to 2-6%. A grid ratio of 16 yielded the lowest CT number variation. All three 2D ASGs yielded improvement in CNR, up to a factor of two in pelvis-sized phantoms. When 2D ASG prototypes were used for both scatter rejection and correction, CT number variations were reduced further, to 1.3-2.6%. In comparisons with a clinical CBCT system and a high-performance radiographic ASG, 2D ASG provided higher CT number accuracy under the same imaging conditions.

CONCLUSIONS

When 2D ASG is used solely as a scatter rejection device, substantial improvement in CT number accuracy can be achieved by increasing the grid ratio. Two-dimensional ASGs also provided significant CNR improvement even at lower grid ratios. Two-dimensional ASGs used in conjunction with the grid-based scatter sampling method provided further improvement in CT number accuracy, irrespective of the grid ratio, while preserving 2D ASGs' capacity to improve CNR. The combined effect of scatter rejection and residual scatter correction by 2D ASG may accelerate implementation of new techniques in CBCT that require high quantitative accuracy, such as radiotherapy dose calculation and dual energy CBCT.

Contextual loss based artifact removal method on CBCT image

Purpose

Cone beam computed tomography (CBCT) offers advantages such as high ray utilization rate, the same spatial resolution within and between slices, and high precision. It is one of the most actively studied topics in international computed tomography (CT) research. However, its application is hindered owing to scatter artifacts. This paper proposes a novel scatter artifact removal algorithm that is based on a convolutional neural network (CNN), where contextual loss is employed as the loss function.

Methods

In the proposed method, contextual loss is added to a simple CNN network to correct the CBCT artifacts in the pelvic region. The algorithm aims to learn the mapping from CBCT images to planning CT images. The 627 CBCT‐CT pairs of 11 patients were used to train the network, and the proposed algorithm was evaluated in terms of the mean absolute error (MAE), average peak signal‐to‐noise ratio (PSNR) and so on. The proposed method was compared with other methods to illustrate its effectiveness.

Results

The proposed method can remove artifacts (including streaking, shadowing, and cupping) in the CBCT image. Furthermore, key details such as the internal contours and texture information of the pelvic region are well preserved. Analysis of the average CT number, average MAE, and average PSNR indicated that the proposed method improved the image quality. The test results obtained with the chest data also indicated that the proposed method could be applied to other anatomies.

Conclusions

Although the CBCT‐CT image pairs are not completely matched at the pixel level, the method proposed in this paper can effectively correct the artifacts in the CBCT slices and improve the image quality. The average CT number of the regions of interest (including bones, skin) also exhibited a significant improvement. Furthermore, the proposed method can be applied to enhance the performance on such applications as dose estimation and segmentation.

Artificial intelligence in radiotherapy: a technological review

Radiation therapy (RT) is widely used to treat cancer. Technological advances in RT have occurred in the past 30 years. These advances, such as three-dimensional image guidance, intensity modulation, and robotics, created challenges and opportunities for the next breakthrough, in which artificial intelligence (AI) will possibly play important roles. AI will replace certain repetitive and labor-intensive tasks and improve the accuracy and consistency of others, particularly those with increased complexity because of technological advances. The improvement in efficiency and consistency is important to manage the increasing cancer patient burden to the society. Furthermore, AI may provide new functionalities that facilitate satisfactory RT. The functionalities include superior images for real-time intervention and adaptive and personalized RT. AI may effectively synthesize and analyze big data for such purposes. This review describes the RT workflow and identifies areas, including imaging, treatment planning, quality assurance, and outcome prediction, that benefit from AI. This review primarily focuses on deep-learning techniques, although conventional machine-learning techniques are also mentioned.

Image guidance in radiation therapy for better cure of cancer

The key goal and main challenge of radiation therapy is the elimination of tumors without any concurring damages of the surrounding healthy tissues and organs. Radiation doses required to achieve sufficient cancer‐cell kill exceed in most clinical situations the dose that can be tolerated by the healthy tissues, especially when large parts of the affected organ are irradiated. High‐precision radiation oncology aims at optimizing tumor coverage, while sparing normal tissues. Medical imaging during the preparation phase, as well as in the treatment room for localization of the tumor and directing the beam, referred to as image‐guided radiotherapy (IGRT), is the cornerstone of precision radiation oncology. Sophisticated high‐resolution real‐time IGRT using X‐rays, computer tomography, magnetic resonance imaging, or ultrasound, enables delivery of high radiation doses to tumors without significant damage of healthy organs. IGRT is the most convincing success story of radiation oncology over the last decades, and it remains a major driving force of innovation, contributing to the development of personalized oncology, for example, through the use of real‐time imaging biomarkers for individualized dose delivery.

Improvement of image quality applying iterative scatter correction for grid-less skeletal radiography in trauma room setting

BACKGROUND

Iterative reconstruction is well established for CT. Plain radiography also takes advantage of iterative algorithms to reduce scatter radiation and improve image quality. First applications have been described for bedside chest X-ray. A recent experimental approach also provided proof of principle for skeletal imaging.

PURPOSE

To examine clinical applicability of iterative scatter correction for skeletal imaging in the trauma setting.

MATERIAL AND METHODS

In this retrospective single-center study, 209 grid-less radiographs were routinely acquired in the trauma room for 12 months, with imaging of the chest (n = 31), knee (n = 111), pelvis (n = 14), shoulder (n = 24), and other regions close to the trunk (n = 29). Radiographs were postprocessed with iterative scatter correction, doubling the number of images. The radiographs were then independently evaluated by three radiologists and three surgeons. A five-step rating scale and visual grading characteristics analysis were used. The area under the VGC curve (AUC_VGC) quantified differences in image quality.

RESULTS

Images with iterative scatter correction were generally rated significantly better (AUC_VGC = 0.59, P < 0.01). This included both radiologists (AUC_VGC = 0.61, P < 0.01) and surgeons (AUC_VGC = 0.56, P < 0.01). The image-improving effect was significant for all body regions; in detail: chest (AUC_VGC = 0.64, P < 0.01), knee (AUC_VGC = 0.61, P < 0.01), pelvis (AUC_VGC = 0.60, P = 0.01), shoulder (AUC_VGC = 0.59, P = 0.02), and others close to the trunk (AUC_VGC = 0.59, P < 0.01).

CONCLUSION

Iterative scatter correction improves the image quality of grid-less skeletal radiography in the clinical setting for a wide range of body regions. Therefore, iterative scatter correction may be the future method of choice for free exposure imaging when an anti-scatter grid is omitted due to high risk of tube-detector misalignment.

Visual enhancement of Cone-beam CT by use of CycleGAN

PURPOSE

Cone-beam computed tomography (CBCT) offers advantages over conventional fan-beam CT in that it requires a shorter time and less exposure to obtain images. However, CBCT images suffer from low soft-tissue contrast, noise, and artifacts compared to conventional fan-beam CT images. Therefore, it is essential to improve the image quality of CBCT.

METHODS

In this paper, we propose a synthetic approach to translate CBCT images with deep neural networks. Our method requires only unpaired and unaligned CBCT images and planning fan-beam CT (PlanCT) images for training. The CBCT images and PlanCT images may be obtained from other patients as long as they are acquired with the same scanner settings. Once trained, three-dimensionally reconstructed CBCT images can be directly translated into high-quality PlanCT-like images.

RESULTS

We demonstrate the effectiveness of our method with images obtained from 20 prostate patients, and provide a statistical and visual comparison. The image quality of the translated images shows substantial improvement in voxel values, spatial uniformity, and artifact suppression compared to those of the original CBCT. The anatomical structures of the original CBCT images were also well preserved in the translated images.

CONCLUSIONS

Our method produces visually PlanCT-like images from CBCT images while preserving anatomical structures.

Effect of grid geometry on the transmission properties of 2D grids for flat detectors in CBCT

To suppress scatter in cone beam computed tomography (CBCT), two-dimensional antiscatter grids (2D grid) have been recently proposed. In this work, we developed several grid prototypes with higher grid ratios and smaller grid pitches than previous designs, and quantified their primary and scatter transmission properties in the context of CBCT for radiation therapy. Three focused 2D grid prototypes were developed with grid ratios at 12 and 16, and grid pitches at 2 and 3 mm. Their scatter transmission properties were measured between 80-140 kVp, and benchmarked against a high performance radiographic grid (1D grid) using a Varian TrueBeam CBCT system. The effect of source-grid misalignment on the primary transmission and the improvement in contrast-to-noise ratio (CNR) were also evaluated. Changing the grid pitch from two to three mm increased the average primary transmission from 84% to 89%. Maximum scatter-to-primary ratio (SPR) with grid ratio of 12 was 0.3, and increasing the grid ratio to 16 reduced SPR by 30%. A 10 mm misalignment in 2D grid position led to a 6%-8% reduction in average primary transmission, and reduction was more pronounced for the higher grid ratio. 2D grids provided up to factor of seven lower SPR and 21% better primary transmission than the 1D grid, and their scatter transmission exhibited lower energy dependence. While 2D grids provided up to factor of 2.3 higher CNR improvement, a significant variation in CNR improvement was not observed among different grid pitch and ratios. In summary, grid ratio of 16 and grid pitch of 2 mm can keep SPRs below 0.2 even in high scatter conditions, while keeping primary transmission fractions above 80%, key benefits of the investigated 2D grids in improving image quality of CBCT. However, such grids require precise alignment in source-grid geometry during CBCT acquisitions. This study also implies that 2D grids can provide substantially better scatter suppression and primary transmission than high-performance 1D grids currently available.

Paired cycle-GAN-based image correction for quantitative cone-beam computed tomography

PURPOSE

The incorporation of cone-beam computed tomography (CBCT) has allowed for enhanced image-guided radiation therapy. While CBCT allows for daily 3D imaging, images suffer from severe artifacts, limiting the clinical potential of CBCT. In this work, a deep learning-based method for generating high quality corrected CBCT (CCBCT) images is proposed.

METHODS

The proposed method integrates a residual block concept into a cycle-consistent adversarial network (cycle-GAN) framework, called res-cycle GAN, to learn a mapping between CBCT images and paired planning CT images. Compared with a GAN, a cycle-GAN includes an inverse transformation from CBCT to CT images, which constrains the model by forcing calculation of both a CCBCT and a synthetic CBCT. A fully convolution neural network with residual blocks is used in the generator to enable end-to-end CBCT-to-CT transformations. The proposed algorithm was evaluated using 24 sets of patient data in the brain and 20 sets of patient data in the pelvis. The mean absolute error (MAE), peak signal-to-noise ratio (PSNR), normalized cross-correlation (NCC) indices, and spatial non-uniformity (SNU) were used to quantify the correction accuracy of the proposed algorithm. The proposed method is compared to both a conventional scatter correction and another machine learning-based CBCT correction method.

RESULTS

Overall, the MAE, PSNR, NCC, and SNU were 13.0 HU, 37.5 dB, 0.99, and 0.05 in the brain, 16.1 HU, 30.7 dB, 0.98, and 0.09 in the pelvis for the proposed method, improvements of 45%, 16%, 1%, and 93% in the brain, and 71%, 38%, 2%, and 65% in the pelvis, over the CBCT image. The proposed method showed superior image quality as compared to the scatter correction method, reducing noise and artifact severity. The proposed method produced images with less noise and artifacts than the comparison machine learning-based method.

CONCLUSIONS

The authors have developed a novel deep learning-based method to generate high-quality corrected CBCT images. The proposed method increases onboard CBCT image quality, making it comparable to that of the planning CT. With further evaluation and clinical implementation, this method could lead to quantitative adaptive radiation therapy.

Evaluating the impact of cone-beam computed tomography scatter mitigation strategies on radiotherapy dose calculation accuracy

BACKGROUND AND PURPOSE

The scatter induced image quality degradation of cone-beam computed tomography (CBCT) prevents more advanced applications in radiotherapy. We evaluated the dose calculation accuracy on CBCT of various disease sites using different scatter mitigation strategies.

MATERIALS AND METHODS

CBCT scans of two patient cohorts (C1, C2) were reconstructed using a uniform (USC) and an iterative scatter correction (ISC) method, combined with an anti-scatter grid (ASG). Head and neck (H&N), lung, pelvic region, and prostate patients were included. To achieve a high accuracy Hounsfield unit and physical density calibrations were performed. The dose distributions of the original treatment plans were analyzed with the γ evaluation method using criteria of 1%/2 mm using the planning CT as the reference. The investigated parameters were the mean γ (γmean), the points in agreement (Pγ≤1) and the 99th percentile (γ1%).

RESULTS

Significant differences between USC and ISC in C1 were found for the lung and prostate, where the latter using the ISC produced the best results with medians of 0.38, 98%, and 1.1 for γmean, Pγ≤1 and γ1%, respectively. For C2 the ISC with ASG showed an improvement for all imaging sites. The lung demonstrated the largest relative increase in accuracy with improvements between 48% and 54% for the medians of γmean, Pγ≤1 and γ1%.

CONCLUSIONS

The introduced method demonstrated high dosimetric accuracy for H&N, prostate and pelvic region if an ASG is applied. A significantly lower accuracy was seen for lung. The ISC yielded a higher robustness against scatter variations than the USC.

Scatter Corrections in X-Ray Computed Tomography: A Physics-Based Analysis

Fundamental limits for the calculation of scattering corrections within X-ray computed tomography (CT) are found within the independent atom approximation from an analysis of the cross sections, CT geometry, and the Nyquist sampling theorem, suggesting large reductions in computational time compared to existing methods. By modifying the scatter by less than 1 %, it is possible to treat some of the elastic scattering in the forward direction as inelastic to achieve a smoother elastic scattering distribution. We present an analysis showing that the number of samples required for the smoother distribution can be greatly reduced. We show that fixed forced detection can be used with many fewer points for inelastic scattering, but that for pure elastic scattering, a standard Monte Carlo calculation is preferred. We use smoothing for both elastic and inelastic scattering because the intrinsic angular resolution is much poorer than can be achieved for projective tomography. Representative numerical examples are given.

Acuros CTS: A fast, linear Boltzmann transport equation solver for computed tomography scatter - Part I: Core algorithms and validation

PURPOSE

To describe Acuros^® CTS, a new software tool for rapidly and accurately estimating scatter in x-ray projection images by deterministically solving the linear Boltzmann transport equation (LBTE).

METHODS

The LBTE describes the behavior of particles as they interact with an object across spatial, energy, and directional (propagation) domains. Acuros CTS deterministically solves the LBTE by modeling photon transport associated with an x-ray projection in three main steps: (a) Ray tracing photons from the x-ray source into the object where they experience their first scattering event and form scattering sources. (b) Propagating photons from their first scattering sources across the object in all directions to form second scattering sources, then repeating this process until all high-order scattering sources are computed using the source iteration method. (c) Ray-tracing photons from scattering sources within the object to the detector, accounting for the detector's energy and anti-scatter grid responses. To make this process computationally tractable, a combination of analytical and discrete methods is applied. The three domains are discretized using the Linear Discontinuous Finite Elements, Multigroup, and Discrete Ordinates methods, respectively, which confer the ability to maintain the accuracy of a continuous solution. Furthermore, through the implementation in CUDA, we sought to exploit the parallel computing capabilities of graphics processing units (GPUs) to achieve the speeds required for clinical utilization. Acuros CTS was validated against Geant4 Monte Carlo simulations using two digital phantoms: (a) a water phantom containing lung, air, and bone inserts (WLAB phantom) and (b) a pelvis phantom derived from a clinical CT dataset. For these studies, we modeled the TrueBeam^® (Varian Medical Systems, Palo Alto, CA) kV imaging system with a source energy of 125 kVp. The imager comprised a 600 μm-thick Cesium Iodide (CsI) scintillator and a 10:1 one-dimensional anti-scatter grid. For the WLAB studies, the full-fan geometry without a bowtie filter was used (with and without the anti-scatter grid). For the pelvis phantom studies, a half-fan geometry with bowtie was used (with the anti-scatter grid). Scattered and primary photon fluences and energies deposited in the detector were recorded.

RESULTS

The Acuros CTS and Monte Carlo results demonstrated excellent agreement. For the WLAB studies, the average percent difference between the Monte Carlo- and Acuros-generated scattered photon fluences at the face of the detector was -0.7%. After including the detector response, the average percent differences between the Monte Carlo- and Acuros-generated scatter fractions (SF) were -0.1% without the grid and 0.6% with the grid. For the digital pelvis simulation, the Monte Carlo- and Acuros-generated SFs agreed to within 0.1% on average, despite the scatter-to-primary ratios (SPRs) being as high as 5.5. The Acuros CTS computation time for each scatter image was ~1 s using a single GPU.

CONCLUSIONS

Acuros CTS enables a fast and accurate calculation of scatter images by deterministically solving the LBTE thus offering a computationally attractive alternative to Monte Carlo methods. Part II describes the application of Acuros CTS to scatter correction of CBCT scans on the TrueBeam system.