Automatic synchrotron tomographic alignment schemes based on genetic algorithms and human-in-the-loop software.

Tomography imaging methods at synchrotron light sources keep evolving, pushing multi-modal characterization capabilities at high spatial and temporal resolutions. To achieve this goal, small probe size and multi-dimensional scanning schemes are utilized more often in the beamlines, leading to rising complexities and challenges in the experimental setup process. To avoid spending a significant amount of human effort and beam time on aligning the X-ray probe, sample and detector for data acquisition, most attention has been drawn to realigning the systems at the data processing stages. However, post-processing cannot correct everything, and is not time efficient. Here we present automatic alignment schemes of the rotational axis and sample pre- and during the data acquisition process using a software approach which combines the advantages of genetic algorithms and human intelligence. Our approach shows excellent sub-pixel alignment efficiency for both tasks in a short time, and therefore holds great potential for application in the data acquisition systems of future scanning tomography experiments.

Effect of metal implants and metal artifacts on back-projected two-dimensional entrance fluence determined by EPID dosimetry.

PURPOSE: To evaluate the errors caused by metal implants and metal artifacts in the two-dimensional entrance fluences reconstructed using the back-projection algorithm based on electronic portal imaging device (EPID) images. METHODS: The EPID in the Varian VitalBeam accelerator was used to acquire portal dose images (PDIs), and then commercial EPID dosimetry software was employed to reconstruct the two-dimensional entrance fluences based on computed tomography (CT) images of the head phantoms containing interchangeable metal-free/titanium/aluminum round bars. The metal-induced errors in the two-dimensional entrance fluences were evaluated by comparing the γ results and the pixel value errors in the metal-affected regions. We obtained metal-artifact-free CT images by replacing the voxel values of non-metal inserts with those of metal inserts in metal-free CT images to evaluate the metal-artifact-induced errors. RESULTS: The γ passing rates (versus PDIs obtained without a phantom in the beam field (PDIair ), 2%/2 mm) for the back-projected two-dimensional entrance fluences of phantoms containing titanium or aluminum (BPTi /BPAl ) were reduced from 92.4% to 90.5% and 90.6%, respectively, relative to the metal-free phantom (BPmetal-free ). Titanium causes more severe metal artifacts in CT images than aluminum, and its removal resulted in a 0.0022 CU (median) reduction in the pixel value of BPTi artifact-free relative to BPTi in the metal-affected region. Moreover, the mean absolute error (MAE) and root mean square error (RMSE) decreased from 0.0050 CU and 0.0063 CU to 0.0034 CU and 0.0040 CU, respectively (vs. BPmetal-free ). CONCLUSION: Metal implants increase the errors in back-projected two-dimensional entrance fluences, and metals with higher electron densities cause more errors. For high-electron-density metal implants that produce severe metal artifacts (e.g., titanium), removing metal artifacts from the CT images can improve the accuracy of the two-dimensional entrance fluences reconstructed by back-projection algorithms.

Improving synthetic CT accuracy by combining the benefits of multiple normalized preprocesses.

PURPOSE: To investigate the effect of different normalization preprocesses in deep learning on the accuracy of different tissues in synthetic computed tomography (sCT) and to combine their advantages to improve the accuracy of all tissues. METHODS: The cycle-consistent adversarial network (CycleGAN) model was used to generate sCT images from megavolt cone-beam CT (MVCBCT) images. In this study, 2639 head MVCBCT and CT image pairs from 203 patients were collected as a training set, and 249 image pairs from 29 patients were collected as a test set. We normalized the voxel values in images to 0 to 1 or -1 to 1, using two linear and five nonlinear normalization preprocessing methods to obtain seven data sets and compared the accuracy of different tissues in different sCT obtained from training these data. Finally, to combine the advantages of different normalization preprocessing methods, we obtained sCT_Blur by cropping, stitching, and smoothing (OpenCV's cv2.medianBlur, kernel size 5) each group of sCTs and evaluated its image quality and accuracy of OARs. RESULTS: Different normalization preprocesses made sCT more accurate in different tissues. The proposed sCT_Blur took advantage of multiple normalization preprocessing methods, and all tissues are more accurate than the sCT obtained using a single conventional normalization method. Compared with other sCT images, the structural similarity of sCT_Blur versus CT was improved to 0.906 ± 0.019. The mean absolute errors of the CT numbers were reduced to 15.7 ± 4.1 HU, 23.2 ± 7.1 HU, 11.5 ± 4.1 HU, 212.8 ± 104.6 HU, 219.4 ± 35.1 HU, and 268.8 ± 88.8 HU for the oral cavity, parotid, spinal cord, cavity, mandible, and teeth, respectively. CONCLUSION: The proposed approach combined the advantages of several normalization preprocessing methods to improve the accuracy of all tissues in sCT images, which is promising for improving the accuracy of dose calculations based on CBCT images in adaptive radiotherapy.

Towards full-stack deep learning-empowered data processing pipeline for synchrotron tomography experiments.

Synchrotron tomography experiments are transitioning into multifunctional, cross-scale, and dynamic characterizations, enabled by new-generation synchrotron light sources and fast developments in beamline instrumentation. However, with the spatial and temporal resolving power entering a new era, this transition generates vast amounts of data, which imposes a significant burden on the data processing end. Today, as a highly accurate and efficient data processing method, deep learning shows great potential to address the big data challenge being encountered at future synchrotron beamlines. In this review, we discuss recent advances employing deep learning at different stages of the synchrotron tomography data processing pipeline. We also highlight how applications in other data-intensive fields, such as medical imaging and electron tomography, can be migrated to synchrotron tomography. Finally, we provide our thoughts on possible challenges and opportunities as well as the outlook, envisioning selected deep learning methods, curated big models, and customized learning strategies, all through an intelligent scheduling solution.

A general image misalignment correction method for tomography experiments.

Tomography experiments generate three-dimensional (3D) reconstructed slices from a series of two-dimensional (2D) projection images. However, the mechanical system generates joint offsets that result in unaligned 2D projections. This misalignment affects the reconstructed images and reduces their actual spatial resolution. In this study, we present a novel method called outer contour-based misalignment correction (OCMC) for correcting image misalignments in tomography. We use the sample's outer contour structure as auxiliary information to estimate the extent of misalignment in each image. This method is generic and can be used with various tomography imaging techniques. We validated our method with five datasets collected from different samples and across various tomography techniques. The OCMC method demonstrated significant advantages in terms alignment accuracy and time efficiency. As an end-to-end correction method, OCMC can be easily integrated into an online tomography data processing pipeline and facilitate feedback control in future synchrotron tomography experiments.

A novel approach for eliminating metal artifacts based on MVCBCT and CycleGAN.

Purpose: To develop a metal artifact reduction (MAR) algorithm and eliminate the adverse effects of metal artifacts on imaging diagnosis and radiotherapy dose calculations. Methods: Cycle-consistent adversarial network (CycleGAN) was used to generate synthetic CT (sCT) images from megavoltage cone beam CT (MVCBCT) images. In this study, there were 140 head cases with paired CT and MVCBCT images, from which 97 metal-free cases were used for training. Based on the trained model, metal-free sCT (sCT_MF) images and metal-containing sCT (sCT_M) images were generated from the MVCBCT images of 29 metal-free cases and 14 metal cases, respectively. Then, the sCT_MF and sCT_M images were quantitatively evaluated for imaging and dosimetry accuracy. Results: The structural similarity (SSIM) index of the sCT_MF and metal-free CT (CT_MF) images were 0.9484, and the peak signal-to-noise ratio (PSNR) was 31.4 dB. Compared with the CT images, the sCT_MF images had similar relative electron density (RED) and dose distribution, and their gamma pass rate (1 mm/1%) reached 97.99% ± 1.14%. The sCT_M images had high tissue resolution with no metal artifacts, and the RED distribution accuracy in the range of 1.003 to 1.056 was improved significantly. The RED and dose corrections were most significant for the planning target volume (PTV), mandible and oral cavity. The maximum correction of Dmean and D50 for the oral cavity reached 90 cGy. Conclusions: Accurate sCT_M images were generated from MVCBCT images based on CycleGAN, which eliminated the metal artifacts in clinical images completely and corrected the RED and dose distributions accurately for clinical application.