A qualitative study of improving megavoltage computed tomography image quality and maintaining dose accuracy using cycleGAN-based image synthesis

BACKGROUND

Due to inconsistent positioning, tumor shrinking, and weight loss during fractionated treatment, the initial plan was no longer appropriate after a few fractional treatments, and the patient will require adaptive helical tomotherapy (HT) to overcome the issue. Patients are scanned with megavoltage computed tomography (MVCT) before each fractional treatment, which is utilized for patient setup and provides information for dose reconstruction. However, the low contrast and high noise of MVCT make it challenging to delineate treatment targets and organs at risk (OAR).

PURPOSE

This study developed a deep-learning-based approach to generate high-quality synthetic kilovoltage computed tomography (skVCT) from MVCT and meet clinical dose requirements.

METHODS

Data from 41 head and neck cancer patients were collected; 25 (2995 slices) were used for training, and 16 (1898 slices) for testing. A cycle generative adversarial network (cycleGAN) based on attention gate and residual blocks was used to generate MVCT-based skVCT. For the 16 patients, kVCT-based plans were transferred to skVCT images and electron density profile-corrected MVCT images to recalculate the dose. The quantitative indices and clinically relevant dosimetric metrics, including the mean absolute error (MAE), structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR), gamma passing rates, and dose-volume-histogram (DVH) parameters (Dmax , Dmean , Dmin ), were used to assess the skVCT images.

RESULTS

The MAE, PSNR, and SSIM of MVCT were 109.6 ± 12.3 HU, 27.5 ± 1.1 dB, and 91.9% ± 1.7%, respectively, while those of skVCT were 60.6 ± 9.0 HU, 34.0 ± 1.9 dB, and 96.5% ± 1.1%. The image quality and contrast were enhanced, and the noise was reduced. The gamma passing rates improved from 98.31% ± 1.11% to 99.71% ± 0.20% (2 mm/2%) and 99.77% ± 0.18% to 99.98% ± 0.02% (3 mm/3%). No significant differences (p > 0.05) were observed in DVH parameters between kVCT and skVCT.

CONCLUSION

With training on a small data set (2995 slices), the model successfully generated skVCT with improved image quality, and the dose calculation accuracy was similar to that of MVCT. MVCT-based skVCT can increase treatment accuracy and offer the possibility of implementing adaptive radiotherapy.

Metal artifacts reduction in kV-CT images with polymetallic dentures and complex metals based on MV-CBCT images in radiotherapy

This paper proposes a metal artifact reduction method of using MV-CBCT images to correct metal artifacts in kV-CT images, especially for the complex metal artifacts caused by multi-metal interaction of patients with head and neck tumors. The different tissue regions are segmented in the MV-CBCT images to obtain template images and the metal region is segmented in the kV-CT images. Forward projection is performed to get sinogram of the template images, kV-CT images and metal region images. Artifact images can be reconstructed through those sonograms. Corrected images is generated by subtracting the artifact images from the original kV-CT images. After the first correction, the template images are generated again and brought into the previous step for iteration to get better correction result. CT data set of 7 patients are used in this study, compared with linear interpolation metal artifact (LIMAR) and normalized metal artifact reduction method, mean relative error of CT value is reduced by 50.5% and 63.3%, noise is reduced by 56.2% and 58.9%. The Identifiability Score of the tooth, upper/lower jaw, tongue, lips, masseter muscle and cavity in the corrected images by the proposed method have significantly improved (P < 0.05) than original images. The artifacts correction method proposed in this paper can effectively remove the metal artifacts in the images and greatly improve the CT value accuracy, especially in the case of multi-metal and complex metal implantation.

A deep-learning method for generating synthetic kV-CT and improving tumor segmentation for helical tomotherapy of nasopharyngeal carcinoma

Objective:Megavoltage computed tomography (MV-CT) is used for setup verification and adaptive radiotherapy in tomotherapy. However, its low contrast and high noise lead to poor image quality. This study aimed to develop a deep-learning-based method to generate synthetic kilovoltage CT (skV-CT) and then evaluate its ability to improve image quality and tumor segmentation.Approach:The planning kV-CT and MV-CT images of 270 patients with nasopharyngeal carcinoma (NPC) treated on an Accuray TomoHD system were used. An improved cycle-consistent adversarial network which used residual blocks as its generator was adopted to learn the mapping between MV-CT and kV-CT and then generate skV-CT from MV-CT. A Catphan 700 phantom and 30 patients with NPC were used to evaluate image quality. The quantitative indices included contrast-to-noise ratio (CNR), uniformity and signal-to-noise ratio (SNR) for the phantom and the structural similarity index measure (SSIM), mean absolute error (MAE), and peak signal-to-noise ratio (PSNR) for patients. Next, we trained three models for segmentation of the clinical target volume (CTV): MV-CT, skV-CT, and MV-CT combined with skV-CT. The segmentation accuracy was compared with indices of the dice similarity coefficient (DSC) and mean distance agreement (MDA).Mainresults:Compared with MV-CT, skV-CT showed significant improvement in CNR (184.0%), image uniformity (34.7%), and SNR (199.0%) in the phantom study and improved SSIM (1.7%), MAE (24.7%), and PSNR (7.5%) in the patient study. For CTV segmentation with only MV-CT, only skV-CT, and MV-CT combined with skV-CT, the DSCs were 0.75 ± 0.04, 0.78 ± 0.04, and 0.79 ± 0.03, respectively, and the MDAs (in mm) were 3.69 ± 0.81, 3.14 ± 0.80, and 2.90 ± 0.62, respectively.Significance:The proposed method improved the image quality of MV-CT and thus tumor segmentation in helical tomotherapy. The method potentially can benefit adaptive radiotherapy.

Improved contrast and noise of megavoltage computed tomography (MVCT) through cycle-consistent generative machine learning

PURPOSE

Megavoltage computed tomography (MVCT) has been implemented on many radiation therapy treatment machines as a tomographic imaging modality that allows for three-dimensional visualization and localization of patient anatomy. Yet MVCT images exhibit lower contrast and greater noise than its kilovoltage CT (kVCT) counterpart. In this work, we sought to improve these disadvantages of MVCT images through an image-to-image-based machine learning transformation of MVCT and kVCT images. We demonstrated that by learning the style of kVCT images, MVCT images can be converted into high-quality synthetic kVCT (skVCT) images with higher contrast and lower noise, when compared to the original MVCT.

METHODS

Kilovoltage CT and MVCT images of 120 head and neck (H&N) cancer patients treated on an Accuray TomoHD system were retrospectively analyzed in this study. A cycle-consistent generative adversarial network (CycleGAN) machine learning, a variant of the generative adversarial network (GAN), was used to learn Hounsfield Unit (HU) transformations from MVCT to kVCT images, creating skVCT images. A formal mathematical proof is given describing the interplay between function sensitivity and input noise and how it applies to the error variance of a high-capacity function trained with noisy input data. Finally, we show how skVCT shares distributional similarity to kVCT for various macro-structures found in the body.

RESULTS

Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were improved in skVCT images relative to the original MVCT images and were consistent with kVCT images. Specifically, skVCT CNR for muscle-fat, bone-fat, and bone-muscle improved to 14.8 ± 0.4, 122.7 ± 22.6, and 107.9 ± 22.4 compared with 1.6 ± 0.3, 7.6 ± 1.9, and 6.0 ± 1.7, respectively, in the original MVCT images and was more consistent with kVCT CNR values of 15.2 ± 0.8, 124.9 ± 27.0, and 109.7 ± 26.5, respectively. Noise was significantly reduced in skVCT images with SNR values improving by roughly an order of magnitude and consistent with kVCT SNR values. Axial slice mean (S-ME) and mean absolute error (S-MAE) agreement between kVCT and MVCT/skVCT improved, on average, from -16.0 and 109.1 HU to 8.4 and 76.9 HU, respectively.

CONCLUSIONS

A kVCT-like qualitative aid was generated from input MVCT data through a CycleGAN instance. This qualitative aid, skVCT, was robust toward embedded metallic material, dramatically improves HU alignment from MVCT, and appears perceptually similar to kVCT with SNR and CNR values equivalent to that of kVCT images.

Evaluating the effects of metal artifacts on dose distribution of the pelvic region

Aim of the Study

Some cancerous patients have hip prosthesis of metal elements when they undergo radiation therapy. Metal implants are a cause of metal artifacts in computed tomography (CT) images due to their higher density compared to normal tissues. The aim of this study is to evaluate the quantitative effects of metal artifacts on dose distribution of the pelvic region.

Materials and Methods

Seven patients with metal implants in the pelvic region were scanned and CT images were exported to the Monaco treatment planning system. Based on the diagnosis of each patient, three-dimensional plans were implemented on CT images and dose distributions were extracted. At the next step, metal artifacts were contoured and electron densities of these new structures were modified to the extent of soft tissue. Finally, dose distributions and the differences were investigated by VeriSoft software.

Results

The results of this study showed that if the electron density to metal artifacts is not assigned properly, it will increase the calculated monitor units (MUs) by almost 3.78 MUs/fraction which will significantly affect total dose distribution of treatment.

Conclusion

For the precise implementation of the treatment and in order to minimize the systematic errors related to the calculated MUs, necessary corrections on the electron density of metal artifacts should be considered before the treatment planning. The issue will be more critical in advanced treatment modalities where dose escalation is needed.

Clinical commissioning of intensity-modulated proton therapy systems: Report of AAPM Task Group 185

Proton therapy is an expanding radiotherapy modality in the United States and worldwide. With the number of proton therapy centers treating patients increasing, so does the need for consistent, high-quality clinical commissioning practices. Clinical commissioning encompasses the entire proton therapy system's multiple components, including the treatment delivery system, the patient positioning system, and the image-guided radiotherapy components. Also included in the commissioning process are the x-ray computed tomography scanner calibration for proton stopping power, the radiotherapy treatment planning system, and corresponding portions of the treatment management system. This commissioning report focuses exclusively on intensity-modulated scanning systems, presenting details of how to perform the commissioning of the proton therapy and ancillary systems, including the required proton beam measurements, treatment planning system dose modeling, and the equipment needed.

Effects of 16-bit CT imaging scanning conditions for metal implants on radiotherapy dose distribution

Dose distribution was calculated and analyzed on the basis of 16-bit computed tomography (CT) images in order to investigate the effect of scanning conditions on CT for metal implants. Stainless steel and titanium rods were inserted into a phantom, and CT images were obtained by scanning the phantom under various scanning conditions: i) Fixed tube current of 230 mA and tube voltages of 100, 120, and 140 kV; and ii) fixed tube voltage of 120 kV and tube currents of 180, 230, and 280 mA. The CT value of the metal rod was examined and corrected. In a Varian treatment planning system, a treatment plan was designed on the basis of the CT images obtained under the set scanning conditions. The dose distributions in the phantom were then calculated and compared. The CT value of the metal area slightly changed upon tube current alteration. The dose distribution in the phantom was also similar. The maximum CT values of the stainless steel rod were 14,568, 14,127 and 13,295 HU when the tube voltages were modified to 100, 120, and 140 kV, respectively. The corresponding CT values of the titanium rod were 9,420, 8,140 and 7,310 HU. The dose distribution of the radiotherapy plan changed significantly as the tube voltage varied. Compared with the reference dose, the respective maximum dose differences of the stainless steel and titanium rods in the phantom were 5.70, and 6.62% when the tube voltage varied. The changes in tube currents resulted in a maximum dose error of <1% for stainless steel and titanium. In CT imaging, changes in tube voltages can significantly alter the CT values of metal implants. Thus, this can lead to large errors in radiotherapy dose distributions.

Quantitative CT assessment of a novel direction-modulated brachytherapy tandem applicator

PURPOSE

The purpose of this study was to quantitatively assess the CT metal-induced artifacts from a novel direction-modulated brachytherapy (DMBT) tandem applicator prototype, recently designed for cervical cancer treatments.

METHODS AND MATERIALS

A water-based pelvic phantom was constructed for CT scanning. The DMBT applicator was imaged using our institutional protocol, one with higher kVp and mAs settings, and repetition of these protocols using 3-mm slices. A conventional stainless steel applicator was also scanned. In addition to the standard reconstructed images, applicator images were reconstructed using a commercial metal artifact-reduction (MAR) algorithm and an in-house-developed research algorithm. Subsequently, image quality and artifact severity were evaluated.

RESULTS

Artifact severity, measured in terms of SDs in CT numbers, decreased asymptotically to background water levels with the distance away from the applicator. Artifact-reduction algorithms lead to significant and visible improvements in image quality, with >50% and >20% decrease in artifact severity achieved at a 10-mm distance for the DMBT and stainless steel applicators, respectively. Differences in artifact severity were minimal between the four imaging protocols. DMBT dimensions were the same on images with and without the commercial MAR algorithm, within <1 mm of the theoretical value. Both the commercial and in-house algorithms restored the CT numbers outside the applicator, albeit a better performance was achieved by the in-house algorithm.

CONCLUSIONS

The artifacts produced by both applicators were minimized with the use of MAR algorithms. Adoption of the DMBT and stainless steel applicators for CT-guided brachytherapy is anticipated as MAR algorithms are widely available on CT scanners.

Polyenergetic known-component CT reconstruction with unknown material compositions and unknown x-ray spectra

Metal artifacts can cause substantial image quality issues in computed tomography. This is particularly true in interventional imaging where surgical tools or metal implants are in the field-of-view. Moreover, the region-of-interest is often near such devices which is exactly where image quality degradations are largest. Previous work on known-component reconstruction (KCR) has shown the incorporation of a physical model (e.g. shape, material composition, etc) of the metal component into the reconstruction algorithm can significantly reduce artifacts even near the edge of a metal component. However, for such approaches to be effective, they must have an accurate model of the component that include energy-dependent properties of both the metal device and the CT scanner, placing a burden on system characterization and component material knowledge. In this work, we propose a modified KCR approach that adopts a mixed forward model with a polyenergetic model for the component and a monoenergetic model for the background anatomy. This new approach called Poly-KCR jointly estimates a spectral transfer function associated with known components in addition to the background attenuation values. Thus, this approach eliminates both the need to know component material composition a prior as well as the requirement for an energy-dependent characterization of the CT scanner. We demonstrate the efficacy of this novel approach and illustrate its improved performance over traditional and model-based iterative reconstruction methods in both simulation studies and in physical data including an implanted cadaver sample.

Metal artifact reduction through MVCBCT and kVCT in radiotherapy

This study proposes a new method for removal of metal artifacts from megavoltage cone beam computed tomography (MVCBCT) and kilovoltage CT (kVCT) images. Both images were combined to obtain prior image, which was forward projected to obtain surrogate data and replace metal trace in the uncorrected kVCT image. The corrected image was then reconstructed through filtered back projection. A similar radiotherapy plan was designed using the theoretical CT image, the uncorrected kVCT image, and the corrected image. The corrected images removed most metal artifacts, and the CT values were accurate. The corrected image also distinguished the hollow circular hole at the center of the metal. The uncorrected kVCT image did not display the internal structure of the metal, and the hole was misclassified as metal portion. Dose distribution calculated based on the corrected image was similar to that based on the theoretical CT image. The calculated dose distribution also evidently differed between the uncorrected kVCT image and the theoretical CT image. The use of the combined kVCT and MVCBCT to obtain the prior image can distinctly improve the quality of CT images containing large metal implants.

[Consequences of prosthesis on quality of the radiation therapy]

Dose prescription, delineation and dose calculation are clearly complicated when a patient have been operated on with insertion of prosthesis. Knowledge of the physical and material characteristics is needed to decrease incertitude of calculations. Recommendations for each step of treatments are proposed in this article allowing to optimization of the treatment safety.

Application of Metal Implant 16-Bit Imaging: New Technique in Radiotherapy

OBJECTIVE

This study aimed to evaluate the computed tomography number and the variation of dose distribution based on 12-bit, 16-bit, and revised 16-bit images while the metal bars were inserted.

METHODS

The phantoms containing stainless steel, titanium alloy, and aluminum bar were scanned with computed tomography. These images were reconstructed with 12-bit and 16-bit imaging technologies. The "cupping artifacts" computed tomography value of the metal object revised by Matlab software was called the revised 16-bit image. The computed tomography values of these metal materials were analyzed. Two radiotherapy treatment plans were designed using the treatment plan system: (1) gantry was of 0° irradiation field and (2) gantry was of 90° and 270° for 2 opposed irradiation fields. The dose profile and dose-volume histogram of a structure of interest were analyzed in various images. The analysis was based on the radiotherapy plan differences between 3 different imaging techniques (12-bit imaging, 16-bit imaging, and revised 16-bit imaging technologies).

RESULTS

For low-density metal object (computed tomography value <3071 Hounsfield unit, HU), the radiotherapy plan results were consistent based on 3 different imaging techniques. For high-density metal object (computed tomography value >3071 HU), the difference in radiotherapy plan results was obvious. The dose of 12-bit was 15.9% higher than revised 16-bit on average for the downstream of titanium rod. For stainless steel, this number reached up to 42.7%.

CONCLUSION

A 16-bit imaging technology of metal implants can distinguish the computed tomography value of different metal materials. Furthermore, the revised 16-bit imaging technology can improve the dose computational accuracy of radiotherapy plan with high-density metal implants.

Generation of hybrid sinograms for the recovery of kV-CT images with metal artifacts for helical tomotherapy

PURPOSE

The overall goal of this study is to restore kilovoltage computed tomography (kV-CT) images which are disfigured by patients' metal prostheses. By generating a hybrid sinogram that is a combination of kV and megavoltage (MV) projection data, the authors suggest a novel metal artifact-reduction (MAR) method that retains the image quality to match that of kV-CT and simultaneously restores the information of metal prostheses lost due to photon starvation.

METHODS

CT projection data contain information about attenuation coefficients and the total length of the attenuation. By normalizing raw kV projections with their own total lengths of attenuation, mean attenuation projections were obtained. In the same manner, mean density projections of MV-CT were obtained by the normalization of MV projections resulting from the forward projection of density-calibrated MV-CT images with the geometric parameters of the kV-CT device. To generate the hybrid sinogram, metal-affected signals of the kV sinogram were identified and replaced by the corresponding signals of the MV sinogram following a density calibration step with kV data. Filtered backprojection was implemented to reconstruct the hybrid CT image. To validate the authors' approach, they simulated four different scenarios for three heads and one pelvis using metallic rod inserts within a cylindrical phantom. Five inserts describing human body elements were also included in the phantom. The authors compared the image qualities among the kV, MV, and hybrid CT images by measuring the contrast-to-noise ratio (CNR), the signal-to-noise ratio (SNR), the densities of all inserts, and the spatial resolution. In addition, the MAR performance was compared among three existing MAR methods and the authors' hybrid method. Finally, for clinical trials, the authors produced hybrid images of three patients having dental metal prostheses to compare their MAR performances with those of the kV, MV, and three existing MAR methods.

RESULTS

The authors compared the image quality and MAR performance of the hybrid method with those of other imaging modalities and the three MAR methods, respectively. The total measured mean of the CNR (SNR) values for the nonmetal inserts was determined to be 14.3 (35.3), 15.3 (37.8), and 25.5 (64.3) for the kV, MV, and hybrid images, respectively, and the spatial resolutions of the hybrid images were similar to those of the kV images. The measured densities of the metal and nonmetal inserts in the hybrid images were in good agreement with their true densities, except in cases of extremely low densities, such as air and lung. Using the hybrid method, major streak artifacts were suitably removed and no secondary artifacts were introduced in the resultant image. In clinical trials, the authors verified that kV and MV projections were successfully combined and turned into the resultant hybrid image with high image contrast, accurate metal information, and few metal artifacts. The hybrid method also outperformed the three existing MAR methods with regard to metal information restoration and secondary artifact prevention.

CONCLUSIONS

The authors have shown that the hybrid method can restore the overall image quality of kV-CT disfigured by severe metal artifacts and restore the information of metal prostheses lost due to photon starvation. The hybrid images may allow for the improved delineation of structures of interest and accurate dose calculations for radiation treatment planning for patients with metal prostheses.

Computed tomography imaging parameters for inhomogeneity correction in radiation treatment planning

Modern treatment planning systems provide accurate dosimetry in heterogeneous media (such as a patient' body) with the help of tissue characterization based on computed tomography (CT) number. However, CT number depends on the type of scanner, tube voltage, field of view (FOV), reconstruction algorithm including artifact reduction and processing filters. The impact of these parameters on CT to electron density (ED) conversion had been subject of investigation for treatment planning in various clinical situations. This is usually performed with a tissue characterization phantom with various density plugs acquired with different tube voltages (kilovoltage peak), FOV reconstruction and different scanners to generate CT number to ED tables. This article provides an overview of inhomogeneity correction in the context of CT scanning and a new evaluation tool, difference volume dose-volume histogram (DVH), dV-DVH. It has been concluded that scanner and CT parameters are important for tissue characterizations, but changes in ED are minimal and only pronounced for higher density materials. For lungs, changes in CT number are minimal among scanners and CT parameters. Dosimetric differences for lung and prostate cases are usually insignificant (<2%) in three-dimensional conformal radiation therapy and < 5% for intensity-modulated radiation therapy (IMRT) with CT parameters. It could be concluded that CT number variability is dependent on acquisition parameters, but its dosimetric impact is pronounced only in high-density media and possibly in IMRT. In view of such small dosimetric changes in low-density medium, the acquisition of additional CT data for financially difficult clinics and countries may not be warranted.

Direction-modulated brachytherapy for high-dose-rate treatment of cervical cancer. I: theoretical design

PURPOSE

To demonstrate that utilization of the direction-modulated brachytherapy (DMBT) concept can significantly improve treatment plan quality in the setting of high-dose-rate (HDR) brachytherapy for cervical cancer.

METHODS AND MATERIALS

The new, MRI-compatible, tandem design has 6 peripheral holes of 1.3-mm diameter, grooved along a nonmagnetic tungsten-alloy rod (ρ = 18.0 g/cm(3)), enclosed in Delrin tubing (polyoxymethylene, ρ = 1.41 g/cm(3)), with a total thickness of 6.4 mm. The Monte Carlo N-Particle code was used to calculate the anisotropic (192)Ir dose distributions. An in-house-developed inverse planning platform, geared with simulated annealing and constrained-gradient optimization algorithms, was used to replan 15 patient cases (total 75 plans) treated with a conventional tandem and ovoids (T&O) applicator. Prescription dose was 6 Gy. For replanning, we replaced the conventional tandem with that of the new DMBT tandem for optimization but left the ovoids in place and kept the dwell positions as originally planned. All DMBT plans were normalized to match the high-risk clinical target volume V100 coverage of the T&O plans.

RESULTS

In general there were marked improvements in plan quality for the DMBT plans. On average, D2cc for the bladder, rectum, and sigmoid were reduced by 0.59 ± 0.87 Gy (8.5% ± 28.7%), 0.48 ± 0.55 Gy (21.1% ± 27.2%), and 0.10 ± 0.38 Gy (40.6% ± 214.9%) among the 75 plans, with best single-plan reductions of 3.20 Gy (40.8%), 2.38 Gy (40.07%), and 1.26 Gy (27.5%), respectively. The high-risk clinical target volume D90 was similar, with 6.55 ± 0.96 Gy and 6.59 ± 1.06 Gy for T&O and DMBT, respectively.

CONCLUSIONS

Application of the DMBT concept to cervical cancer allowed for improved organ at risk sparing while achieving similar target coverage on a sizeable patient population, as intended, by maximally utilizing the anatomic information contained in 3-dimensional imaging. A series of mechanical and clinical validations are to be followed.