Search

Background: Cone beam computed tomography (CBCT) provides critical anatomical information for adaptive radiotherapy (ART), especially for tumors in the pelvic region that undergo significant deformation. However, CBCT suffers from inaccurate Hounsfield Unit (HU) values and lower soft tissue contrast. These issues affect the accuracy of pelvic treatment plans and implementation of the treatment, hence requiring correction. Purpose: A novel stacked coarse‐to‐fine model combining Denoising Diffusion Probabilistic Model (DDPM) and spatial‐frequency domain convolution modules is proposed to enhance the imaging quality of CBCT images. Methods: The enhancement of low‐quality CBCT images is divided into two stages. In the coarse stage, the improved DDPM with U‐ConvNeXt architecture is used to complete the denoising task of CBCT images. In the fine stage, the deep convolutional network model jointly constructed by fast Fourier and dilated convolution modules is used to further enhance the image quality in local details and global imaging. Finally, the accurate pseudo‐CT (pCT) images consistent with the size of the original data are obtained. Two hundred fifty paired CBCT‐CT images from cervical and rectal cancer, combined with 200 public dataset cases, were used collectively for training, validation, and testing. Results: To evaluate the anatomical consistency between pCT and real CT, we have used the mean(std) of structure similarity index measure (SSIM), peak signal to noise ratio (PSNR), and normalized cross‐correlation (NCC). The numerical results for the above three metrics comparing the pCT synthesized by the proposed model against real CT for cervical cancer cases were 87.14% (2.91%), 34.02 dB (1.35 dB), and 88.01% (1.82%), respectively. For rectal cancer cases, the corresponding results were 86.06% (2.70%), 33.50 dB (1.41 dB), and 87.44% (1.95%). The paired t‐test analysis between the proposed model and the comparative models (ResUnet, CycleGAN, DDPM, and DDIM) for these metrics revealed statistically significant differences (p < 0.05). The visual results also showed that the anatomical structures between the real CT and the pCT synthesized by the proposed model were closer. For the dosimetric verification, mean absolute error of dosimetry (MAEdoes) values for the maximum dose (Dmax), the minimum dose (Dmin), and the mean dose (Dmean) in the planning target volume (PTV) were analyzed, with results presented as mean (lower quartile, upper quartile). The experimental results show that the values of the above three dosimetry indexes (Dmin, Dmax, and Dmean) for the pCT images synthesized by the proposed model were 0.90% (0.48%, 1.29%), 0.82% (0.47%, 1.17%), and 0.57% (0.44%, 0.67%). Compared with 10 cases of the original CBCT image by Mann–Whitney test (p < 0.05), it also proved that pCT can significantly improve the accuracy of HU values for the dose calculation. Conclusion: The pCT synthesized by the proposed model outperforms the comparative models in numerical accuracy and visualization, promising for ART of pelvic cancers. [ABSTRACT FROM AUTHOR]

Purpose: CT is routinely used to detect cranial abnormalities in pediatric patients with head trauma or craniosynostosis. This study aimed to develop a deep learning method to synthesize pseudo‐CT (pCT) images for MR high‐resolution pediatric cranial bone imaging to eliminating ionizing radiation from CT. Methods: 3D golden‐angle stack‐of‐stars MRI were obtained from 44 pediatric participants. Two patch‐based residual UNets were trained using paired MR and CT patches randomly selected from the whole head (NetWH) or in the vicinity of bone, fractures/sutures, or air (NetBA) to synthesize pCT. A third residual UNet was trained to generate a binary brain mask using only MRI. The pCT images from NetWH (pCTNetWH) in the brain area and NetBA (pCTNetBA) in the nonbrain area were combined to generate pCTCom. A manual processing method using inverted MR images was also employed for comparison. Results: pCTCom (68.01 ± 14.83 HU) had significantly smaller mean absolute errors (MAEs) than pCTNetWH (82.58 ± 16.98 HU, P < 0.0001) and pCTNetBA (91.32 ± 17.2 HU, P < 0.0001) in the whole head. Within cranial bone, the MAE of pCTCom (227.92 ± 46.88 HU) was significantly lower than pCTNetWH (287.85 ± 59.46 HU, P < 0.0001) but similar to pCTNetBA (230.20 ± 46.17 HU). Dice similarity coefficient of the segmented bone was significantly higher in pCTCom (0.90 ± 0.02) than in pCTNetWH (0.86 ± 0.04, P < 0.0001), pCTNetBA (0.88 ± 0.03, P < 0.0001), and inverted MR (0.71 ± 0.09, P < 0.0001). Dice similarity coefficient from pCTCom demonstrated significantly reduced age dependence than inverted MRI. Furthermore, pCTCom provided excellent suture and fracture visibility comparable to CT. Conclusion: MR high‐resolution pediatric cranial bone imaging may facilitate the clinical translation of a radiation‐free MR cranial bone imaging method for pediatric patients. [ABSTRACT FROM AUTHOR]

Recently,deep learning (DL)‐based methods for the generation of synthetic computed tomography (sCT) have received significant research attention as an alternative to classical ones. We present here a systematic review of these methods by grouping them into three categories, according to their clinical applications: (i) to replace computed tomography in magnetic resonance (MR) based treatment planning, (ii) facilitate cone‐beam computed tomography based image‐guided adaptive radiotherapy, and (iii) derive attenuation maps for the correction of positron emission tomography. Appropriate database searching was performed on journal articles published between January 2014 and December 2020. The DL methods' key characteristics were extracted from each eligible study, and a comprehensive comparison among network architectures and metrics was reported. A detailed review of each category was given, highlighting essential contributions, identifying specific challenges, and summarizing the achievements. Lastly, the statistics of all the cited works from various aspects were analyzed, revealing the popularity and future trends and the potential of DL‐based sCT generation. The current status of DL‐based sCT generation was evaluated, assessing the clinical readiness of the presented methods. [ABSTRACT FROM AUTHOR]

Purpose: To develop and evaluate a novel method for pseudo‐CT generation from multi‐parametric MR images using multi‐channel multi‐path generative adversarial network (MCMP‐GAN). Methods: Pre‐ and post‐contrast T1‐weighted (T1‐w), T2‐weighted (T2‐w) MRI, and treatment planning CT images of 32 nasopharyngeal carcinoma (NPC) patients were employed to train a pixel‐to‐pixel MCMP‐GAN. The network was developed based on a 5‐level Residual U‐Net (ResU‐Net) with the channel‐based independent feature extraction network to generate pseudo‐CT images from multi‐parametric MR images. The discriminator with five convolutional layers was added to distinguish between the real CT and pseudo‐CT images, improving the nonlinearity and prediction accuracy of the model. Eightfold cross validation was implemented to validate the proposed MCMP‐GAN. The pseudo‐CT images were evaluated against the corresponding planning CT images based on mean absolute error (MAE), peak signal‐to‐noise ratio (PSNR), Dice similarity coefficient (DSC), and Structural similarity index (SSIM). Similar comparisons were also performed against the multi‐channel single‐path GAN (MCSP‐GAN), the single‐channel single‐path GAN (SCSP‐GAN). Results: It took approximately 20 h to train the MCMP‐GAN model on a Quadro P6000, and less than 10 s to generate all pseudo‐CT images for the subjects in the test set. The average head MAE between pseudo‐CT and planning CT was 75.7 ± 14.6 Hounsfield Units (HU) for MCMP‐GAN, significantly (P‐values < 0.05) lower than that for MCSP‐GAN (79.2 ± 13.0 HU) and SCSP‐GAN (85.8 ± 14.3 HU). For bone only, the MCMP‐GAN yielded a smaller mean MAE (194.6 ± 38.9 HU) than MCSP‐GAN (203.7 ± 33.1 HU), SCSP‐GAN (227.0 ± 36.7 HU). The average PSNR of MCMP‐GAN (29.1 ± 1.6) was found to be higher than that of MCSP‐GAN (28.8 ± 1.2) and SCSP‐GAN (28.2 ± 1.3). In terms of metrics for image similarity, MCMP‐GAN achieved the highest SSIM (0.92 ± 0.02) but did not show significantly improved bone DSC results in comparison with MCSP‐GAN. Conclusions: We developed a novel multi‐channel GAN approach for generating pseudo‐CT from multi‐parametric MR images. Our preliminary results in NPC patients showed that the MCMP‐GAN method performed apparently superior to the U‐Net‐GAN and SCSP‐GAN, and slightly better than MCSP‐GAN. [ABSTRACT FROM AUTHOR]

Purpose: To describe a method for converting Zero TE (ZTE) MR images into X‐ray attenuation information in the form of pseudo‐CT images and demonstrate its performance for (1) attenuation correction (AC) in PET/MR and (2) dose planning in MR‐guided radiation therapy planning (RTP). Methods: Proton density‐weighted ZTE images were acquired as input for MR‐based pseudo‐CT conversion, providing (1) efficient capture of short‐lived bone signals, (2) flat soft‐tissue contrast, and (3) fast and robust 3D MR imaging. After bias correction and normalization, the images were segmented into bone, soft‐tissue, and air by means of thresholding and morphological refinements. Fixed Hounsfield replacement values were assigned for air (‐1000 HU) and soft‐tissue (+42 HU), whereas continuous linear mapping was used for bone. Results: The obtained ZTE‐derived pseudo‐CT images accurately resembled the true CT images (i.e., Dice coefficient for bone overlap of 0.73 ± 0.08 and mean absolute error of 123 ± 25 HU evaluated over the whole head, including errors from residual registration mismatches in the neck and mouth regions). The linear bone mapping accounted for bone density variations. Averaged across five patients, ZTE‐based AC demonstrated a PET error of ‐0.04 ± 1.68% relative to CT‐based AC. Similarly, for RTP assessed in eight patients, the absolute dose difference over the target volume was found to be 0.23 ± 0.42%. Conclusion: The described method enables MR to pseudo‐CT image conversion for the head in an accurate, robust, and fast manner without relying on anatomical prior knowledge. Potential applications include PET/MR‐AC, and MR‐guided RTP. [ABSTRACT FROM AUTHOR]

Purpose To characterize the spectral parameters of tissues with high spectral and spatial resolution magnetic resonance images to be used as a foundation for a classification-based synthetic CT algorithm. Methods A phantom was constructed consisting of a section of fresh beef leg with bone embedded in 1% agarose gel. The high spectral and spatial (HiSS) resolution MR imaging sequence used had 1.0 mm in-plane resolution and 11.1 Hz spectral resolution. This sequence was used to image the phantom and one patient. Post-processing was performed off-line with IDL and included Fourier transformation of the time-domain data, labeling of fat and water peaks, and fitting the magnitude spectra with Lorentzian functions. Images of the peak height and peak integral of both the water and fat resonances were generated and analyzed. Several regions-of-interest (ROIs) were identified in phantom: bone marrow, cortical bone, adipose tissue, muscle, agar gel, and air; in the patient, no agar gel was present but an ROI of saline in the bladder was analyzed. All spectra were normalized by the noise within each voxel; thus, all parameters are reported in terms of signal-to-noise (SNR). The distributions of tissue spectral parameters were analyzed and scatterplots generated. Water peak height in cortical bone was compared to air using a nonparametric t-test. Composition of the various ROIs in terms of water, fat, or fat and water was also reported. Results In phantom, the scatterplot of peak height (water versus fat) showed good separation of bone marrow and adipose tissue. Water versus fat integral scatterplot showed better separation of muscle and cortical bone than the peak height scatterplot. In the patient data, the distributions of water and fat peak heights were similar to that in phantom, with more overlap of bone marrow and cortical bone than observed in phantom. The relationship between bone marrow and cortical bone for peak integral was better separated than those of peak heights in the patient data. For both the phantom and patient, there was a significant amount of overlap in spectral parameters of cortical bone versus air. Conclusion These results show promising results for utilizing HiSS imaging in a classification-based synthetic CT algorithm. Cortical bone and air overlap was expected due to the short T2* of bone; reducing early echo times would improve the SNR in bone and image data from these early echoes could help differentiate these tissue types. Further studies need to be done with the goal of better separation of air and bone, and to extend the concept to volumetric imaging before it can be clinically applied. [ABSTRACT FROM AUTHOR]

Purpose: Magnetic resonance imaging (MRI)-only radiotherapy treatment planning requires accurate pseudo-CT (pCT) images for precise dose calculation. The current work introduced an atlas-based method combined with MR intensity information. pCT analyses and Monte Carlo dose calculations for intracranial stereotactic treatments were performed. Methods: Twenty-two patients, representing 35 tumor targets, were scanned using a 3D T1-weighted MRI sequence according to the clinical protocol. The MR atlas image was registered to the MR patient image using a deformable algorithm, and the deformation was then applied to the atlas CT. Two methods were applied. The first method (MRdef) was based on deformations only, while the second (MRint) also used the actual MR intensities. pCT analysis was performed using the mean (absolute) error, as well as an in-house tool based on a gamma index. Dose differences between pCT and true CT were analyzed using dose-volume histogram (DVH) parameters, statistical tests, the gamma index, and probability density functions. An unusual case, where the patient underwent an operation (part of the skull bone was removed), was studied in detail. Results: Soft tissues presented a mean error inferior to 50 HUs, while low-density tissues and bones presented discrepancies up to 600 HUs for hard bone. The MRdef method led to significant dose differences compared with the true CT (p-value < 0.05; Wilcoxon-signed-rank test). The MRint method performed better. The DVH parameter differences compared with CT were between -2.9% and 3.1%, except for two cases where the tumors were located within the sphenoid bone. For these cases, the dose errors were up to 6.6% and 5.4% (D98 and D95). Furthermore, for 85% of the tested patients, the mean dose to the planning target volume agreed within 2% with the calculation using the actual CT. Fictitious bone was generated in the unusual case using atlas-based methods. Conclusions: Generally, the atlas-based method led to acceptable dose distributions. The use of common T1 sequences allows the implementation of this method in clinical routine. However, unusual patient anatomy may produce large dose calculation errors. The detection of large anatomic discrepancies using MR image subtraction can be realized, but an alternative way to produce synthetic CT numbers in these regions is still required. [ABSTRACT FROM AUTHOR]

Purpose: In radiotherapy based only on magnetic resonance imaging (MRI), knowledge about tissue electron densities must be derived from the MRI. This can be achieved by converting the MRI scan to the so-called pseudo-computed tomography (pCT). An obstacle is that the voxel intensities in conventional MRI scans are not uniquely related to electron density. The authors previously demonstrated that a patch-based method could produce accurate pCTs of the brain using conventional T1-weighted MRI scans. The method was driven mainly by local patch similarities and relied on simple affine registrations between an atlas database of the co-registered MRI/CT scan pairs and the MRI scan to be converted. In this study, the authors investigate the applicability of the patch-based approach in the pelvis. This region is challenging for a method based on local similarities due to the greater inter-patient variation. The authors benchmark the method against a baseline pCT strategy where all voxels inside the body contour are assigned a water-equivalent bulk density. Furthermore, the authors implement a parallelized approximate patch search strategy to speed up the pCT generation time to a more clinically relevant level. Methods: The data consisted of CT and T1-weighted MRI scans of 10 prostate patients. pCTs were generated using an approximate patch search algorithm in a leave-one-out fashion and compared with the CT using frequently described metrics such as the voxel-wise mean absolute error (MAEvox) and the deviation in water-equivalent path lengths. Furthermore, the dosimetric accuracy was tested for a volumetric modulated arc therapy plan using dose-volume histogram (DVH) point deviations and γ-index analysis. Results: The patch-based approach had an average MAEvox of 54 HU; median deviations of less than 0.4% in relevant DVH points and a γ-index pass rate of 0.97 using a 1%/1 mm criterion. The patch-based approach showed a significantly better performance than the baseline water pCT in almost all metrics. The approximate patch search strategy was 70x faster than a brute-force search, with an average prediction time of 20.8 min. Conclusions: The authors showed that a patch-based method based on affine registrations and T1-weighted MRI could generate accurate pCTs of the pelvis. The main source of differences between pCT and CT was positional changes of air pockets and body outline. [ABSTRACT FROM AUTHOR]