Objective.The aim of this study was to reconstruct volumetric computed tomography (CT) images in real-time from ultra-sparse two-dimensional x-ray projections, facilitating easier navigation and positioning during image-guided radiation therapy.Approach.Our approach leverages a voxel-sapce-searching Transformer model to overcome the limitations of conventional CT reconstruction techniques, which require extensive x-ray projections and lead to high radiation doses and equipment constraints.Main results.The proposed XTransCT algorithm demonstrated superior performance in terms of image quality, structural accuracy, and generalizability across different datasets, including a hospital set of 50 patients, the large-scale public LIDC-IDRI dataset, and the LNDb dataset for cross-validation. Notably, the algorithm achieved an approximately 300% improvement in reconstruction speed, with a rate of 44 ms per 3D image reconstruction compared to former 3D convolution-based methods.Significance.The XTransCT architecture has the potential to impact clinical practice by providing high-quality CT images faster and with substantially reduced radiation exposure for patients. The model\'s generalizability suggests it has the potential applicable in various healthcare settings.

OBJECTIVE: Respiratory motion-induced displacement of internal organs poses a significant challenge in image-guided radiation therapy, particularly affecting liver landmark tracking accuracy.
METHODS: Addressing this concern, we propose a self-supervised method for robust landmark tracking in long liver ultrasound sequences. Our approach leverages a Siamese-based context-aware correlation filter network, trained by using the consistency loss between forward tracking and back verification. By effectively utilizing both labeled and unlabeled liver ultrasound images, our model, Siam-CCF , mitigates the impact of speckle noise and artifacts on ultrasonic image tracking by a context-aware correlation filter. Additionally, a fusion strategy for template patch feature helps the tracker to obtain rich appearance information around the point-landmark.
RESULTS: Siam-CCF achieves a mean tracking error of 0.79 ± 0.83 mm at a frame rate of 118.6 fps, exhibiting a superior speed-accuracy trade-off on the public MICCAI 2015 Challenge on Liver Ultrasound Tracking (CLUST2015) 2D dataset. This performance won the 5th place on the CLUST2015 2D point-landmark tracking task.
CONCLUSIONS: Extensive experiments validate the effectiveness of our proposed approach, establishing it as one of the top-performing techniques on the CLUST2015 online leaderboard at the time of this submission.

UNASSIGNED: Cone-beam computed tomography (CBCT) plays a key role in image-guided radiotherapy (IGRT), however its poor image quality limited its clinical application. In this study, we developed a deep-learning based approach to translate CBCT image to synthetic CT (sCT) image that preserves both CT image quality and CBCT anatomical structures.
UNASSIGNED: A novel synthetic CT generative adversarial network (sCTGAN) was proposed for CBCT-to-CT translation via disentangled representation. The approach of disentangled representation was employed to extract the anatomical information shared by CBCT and CT image domains. Both on-board CBCT and planning CT of 40 patients were used for network learning and those of another 12 patients were used for testing. Accuracy of our network was quantitatively evaluated using a series of statistical metrics, including the peak signal-to-noise ratio (PSNR), mean structural similarity index (SSIM), mean absolute error (MAE), and root-mean-square error (RMSE). Effectiveness of our network was compared against three state-of-the-art CycleGAN-based methods.
UNASSIGNED: The PSNR, SSIM, MAE, and RMSE between sCT generated by sCTGAN and deformed planning CT (dpCT) were 34.12 dB, 0.86, 32.70 HU, and 60.53 HU, while the corresponding values between original CBCT and dpCT were 28.67 dB, 0.64, 70.56 HU, and 112.13 HU. The RMSE (60.53±14.38 HU) of sCT generated by sCTGAN was less than that of sCT generated by all the three comparing methods (72.40±16.03 HU by CycleGAN, 71.60±15.09 HU by CycleGAN-Unet512, 64.93±14.33 HU by CycleGAN-AG).
UNASSIGNED: The sCT generated by our sCTGAN network was closer to the ground truth (dpCT), in comparison to all the three comparing CycleGAN-based methods. It provides an effective way to generate high-quality sCT which has a wide application in IGRT and adaptive radiotherapy.

BACKGROUND: Magnetic resonance-guided stereotactic body radiotherapy (MRgSBRT) offers the potential for achieving better prostate cancer (PC) treatment outcomes. This study reports the preliminary clinical results of 1.5T MRgSBRT in localized PC, based on both clinician-reported outcome measurement (CROM) and patient-reported outcome measurement (PROM).
METHODS: Fifty-one consecutive localized PC patients were prospectively enrolled with a median follow-up of 199 days. MRgSBRT was delivered in five fractions of 7.25-8 Gy with daily online adaptation. Clinician-reported gastrointestinal (GI) and genitourinary (GU) adverse events based on the Common Terminology Criteria for Adverse Events (CTCAE) Scale v. 5.0 were assessed. The Expanded Prostate Cancer Index Composite Questionnaire was collected at baseline, 1 month, and every 3 months thereafter. Serial prostate-specific antigen measurements were longitudinally recorded.
RESULTS: The maximum cumulative clinician-reported grade ≥ 2 acute GU and GI toxicities were 11.8% (6/51) and 2.0% (1/51), respectively, while grade ≥ 2 subacute GU and GI toxicities were 2.3% (1/43) each. Patient-reported urinary, bowel, and hormonal domain summary scores were reduced at 1 month, then gradually returned to baseline levels, with the exception of the sexual domain. Domain-specific subscale scores showed similar longitudinal changes. All patients had early post-MRgSBRT biochemical responses.
CONCLUSIONS: The finding of low toxicity supports the accumulation of clinical evidence for 1.5T MRgSBRT in localized PC.

A long-standing problem in image-guided radiotherapy is that inferior intraoperative images present a difficult problem for automatic registration algorithms. Particularly for digital radiography (DR) and digitally reconstructed radiograph (DRR), the blurred, low-contrast, and noisy DR makes the multimodal registration of DR-DRR challenging. Therefore, we propose a novel CNN-based method called CrossModalNet to exploit the quality preoperative modality (DRR) for handling the limitations of intraoperative images (DR), thereby improving the registration accuracy. The method consists of two parts: DR-DRR contour predictions and contour-based rigid registration. We have designed the CrossModal Attention Module and CrossModal Refine Module to fully exploit the multiscale crossmodal features and implement the crossmodal interactions during the feature encoding and decoding stages. Then, the predicted anatomical contours of DR-DRR are registered by the classic mutual information method. We collected 2486 patient scans to train CrossModalNet and 170 scans to test its performance. The results show that it outperforms the classic and state-of-the-art methods with 95th percentile Hausdorff distance of 5.82 pixels and registration accuracy of 81.2%. The code is available at https://github.com/lc82111/crossModalNet.

Image-guided radiation therapy using magnetic resonance imaging (MRI) is a new technology that has been widely studied and developed in recent years. The technology combines the advantages of MRI imaging, and can offer online real-time tracking of tumor and adjacent organs at risk, as well as real-time optimization of radiotherapy plan. In order to provide a comprehensive understanding of this technology, and to grasp the international development and trends in this field, this paper reviews and summarizes related researches, so as to make the researchers and clinical personnel in this field to understand recent status of this technology, and carry out corresponding researches. This paper summarizes the advantages of MRI and the research progress of MRI linear accelerator (MR-Linac), online guidance, adaptive optimization, and dosimetry-related research. Possible development direction of these technologies in the future is also discussed. It is expected that this review can provide a certain reference value for clinician and related researchers to understand the research progress in the field.
利用磁共振成像（MRI）进行图像引导放射治疗（简称：放疗）是近年来受到广泛关注并取得一定研究进展的新技术。该技术结合了 MRI 成像的优点，具有在线实时追踪肿瘤和临近危及器官以及实时优化放疗计划方案的功能。为了能对该技术的研究有全方位的认识和了解，对国际上在此方面开展的研究进展和动态有所掌握，本文对相关研究进行了综述和概括，以便于让该领域的研究者和医师对此技术的近况有所了解，并展开相应研究。本文就 MRI 的优点、核磁加速器的研究发展、剂量学相关研究进展和在线引导、自适应优化研究进展等方面进行综述，同时也探讨了这些技术今后可能的发展方向，期望本文综述能为临床医生和相关研究人员了解领域内的研究进展提供一定的参考。.

To investigate the safety and efficacy of 3-dimensional (3D) printing non-coplanar templates (PNCT) assisted computer tomography (CT) guided radioactive 125I seed implantation (RISI) for the treatment of recurrent cervical carcinoma (RCC) after external beam radiotherapy (EBRT).
A total of 103 patients with inoperable post-EBRT RCC were included in this retrospective study. A total of 111 lesions received RISI. Eight lesions were at the pelvic center, 75 lesions were at the pelvic lateral, and 28 lesions were extra-pelvic metastasis. The median prescription dose was 120 Gy. The primary end points were adverse events and local control (LC), and the secondary end points were overall survival (OS) and progression-free survival.
Grade 2 adverse events of acute nausea, diarrhea, and pollakiuria occurred in 1, 2, and 1 patient, respectively. One patient suffered from grade 3 acute proctitis. Late toxicity was observed in 2 patients with rectovaginal fistula. No grade 5 toxicity occurred. The 3-year LC and OS rates were 75.1% and 20.8%, respectively. The median OS was 17 months. The multivariate analysis showed that the minimum dose received by the \"hottest\" 90% of the gross tumor volume (D90) ≥130 Gy, squamous cell carcinoma, hemoglobin ≥80 g/L and good short-term efficacy (complete response or partial response) were independent predictors of LC and OS (all p<0.05).
3D-PNCT assisted CT-guided RISI is a safe, effective, and minimally invasive modality for RCC. The hemoglobin level, pathological type, dose distribution and short-term efficacy are considered as independent factors for clinical outcomes.

OBJECTIVE: To develop the method for ultrasound (US)-guided intra-operative electron beam radiation therapy (IOERT).
METHODS: We first established the simulation, planning, and delivery methods for US-guided IOERT and constructed appropriate hardware (the multi-function applicator, accessories, and US phantom). We tested our US-guided IOERT method using this hardware and the Monte Carlo simulation IOERT treatment planning system (TPS). The IOERT TPS used a compensator to build the conformal dose distribution. Then, we used the TPS to evaluate the effect of setup uncertainty on target coverage by introducing phantom setup error ranging from 0 mm to 10 mm to the plans with and without the compensator.
RESULTS: The simulation, planning, and delivery methods for US-guided IOERT were introduced and validated on a phantom. A complete technique for US-guided IOERT was established. Target coverage decreased by about 12% and 29% as the phantom setup error increased to 5 mm and 10 mm for the plans with compensator, respectively. Without compensator, the corresponding target coverage decreases were 2% and 13%, respectively.
CONCLUSIONS: In our study, we developed the multi-function applicator, US Phantom, and TPS for IOERT. The procedures included not only dose distribution planning, but also intraoperative US imaging, which provided the information necessary during surgery to improve IOERT quality assurance. Target coverage was more sensitive to setup errors with compensator compared to no compensator. Further studies are needed to validate the clinical efficacy of this US-guided IOERT method.

OBJECTIVE: As affordable equipment, electronic portal imaging devices (EPIDs) are wildly used in radiation therapy departments to verify patients\' positions for accurate radiotherapy. However, these devices tend to produce visually ambiguous and low-contrast planar digital radiographs under megavoltage x ray (MV-DRs), which poses a tremendous challenge for clinicians to perform multimodal registration between the MV-DRs and the kilovoltage digital reconstructed radiographs (KV-DRRs) developed from the planning computed tomography. Furthermore, the existent of strong appearance variations also makes accurate registration beyond the reach of current automatic algorithms.
METHODS: We propose a novel modality conversion approach to this task that first synthesizes KV images from MV-DRs, and then registers the synthesized and real KV-DRRs. We focus on the synthesis technique and develop a conditional generative adversarial network with information bottleneck extension (IB-cGAN) that takes MV-DRs and nonaligned KV-DRRs as inputs and outputs synthesized KV images. IB-cGAN is designed to address two main challenges in deep-learning-based synthesis: (a) training with a roughly aligned dataset suffering from noisy correspondences; (b) making synthesized images have real clinical meanings that faithfully reflects MV-DRs rather than nonaligned KV-DRRs. Accordingly, IB-cGAN employs (a) an adversarial loss to provide training supervision at semantic level rather than the imprecise pixel level; (b) an IB to constrain the information from the nonaligned KV-DRRs.
RESULTS: We collected 2698 patient scans to train the model and 208 scans to test its performance. The qualitative results demonstrate realistic KV images can be synthesized allowing clinicians to perform the visual registration. The quantitative results show it significantly outperforms current nonmodality conversion methods by 22.37% (P = 0.0401) in terms of registration accuracy.
CONCLUSIONS: The modality conversion approach facilitates the downstream MV-KV registration for both clinicians and off-the-shelf registration algorithms. With this approach, it is possible to benefit the developing countries where inexpensive EPIDs are widely used for the image-guided radiation therapy.

To evaluate the benefits of adaptive imaging with automatic correction compared to periodic surveillance strategies with either manual or automatic correction.
Using Calypso trajectories from 54 patients with prostate cancer at 2 institutions, we simulated 5-field intensity-modulated radiation therapy and dual-arc volumetric-modulated arc therapy with periodic imaging at various frequencies and with continuous adaptive imaging, respectively. With manual/automatic correction, we assumed there was a 30/1 second delay after imaging to determine and apply couch shift. For adaptive imaging, real-time \"dose-free\" cine-MV images during beam delivery are used in conjunction with online-updated motion pattern information to estimate 3D displacement. Simultaneous MV-kV imaging is only used to confirm the estimated overthreshold motion and calculate couch shift, hence very low additional patient dose from kV imaging.
Without intrafraction intervention, the prostates could on average have moved out of a 3-mm margin for ∼20% of the beam-on time after setup imaging in current clinical situation. If the time interval from the setup imaging to beam-on can be reduced to only 30 seconds, the mean over-3 mm percentage can be reduced to ∼7%. For intensity-modulated radiation therapy simulation, with manual correction, 110 and 70 seconds imaging periods both reduced the mean over-3 mm time to ∼4%. Automatic correction could give another 1% to 2% improvement. However, with either manual or automatic correction, the maximum patient-specific over-3 mm time was still relatively high (from 6.4% to 12.6%) and those patients are actually clinically most important. In contrast, adaptive imaging with automatic intervention significantly reduced the mean percentage to 0.6% and the maximum to 2.7% and averagely only ∼1 kV image and ∼1 couch shift were needed per fraction. The results of volumetric-modulated arc therapy simulation show a similar trend to that of intensity-modulated radiation therapy.
Adaptive continuous monitoring with automatic motion compensation is more beneficial than periodic imaging surveillance at similar or even less imaging dose.