DRACO: differentiable reconstruction for arbitrary CBCT orbits

BackgroundImage‐guided particle therapy (IGPT) has significantly advanced in recent years, particularly in the context of proton therapy. However, imaging solutions for carbon‐ion radiotherapy (C‐ion RT) remain limited.PurposeThis study introduces sliding‐gantry cone‐beam computed tomography (CBCT) and dual‐panel digital radiography (DR) systems, both mechanically independent of carbon‐ion delivery nozzles. We aim to evaluate the image quality metrics and verify the positioning accuracy of the imaging systems.MethodsImage quality was evaluated in terms of spatial resolution, low contrast resolution, image uniformity, and effective imaging area using a multi‐purpose imaging phantom, Catphan 700 phantom, and ImageJ software. The influences of planning computed tomography (CT) slice thicknesses (1–5 mm), radiation quality settings (90–130 kV), and registration algorithms (bony, grayscale, and fiducial marker registrations) on positioning accuracy were assessed using anthropomorphic head‐neck and thoracoabdominal phantom images. The clinical feasibility of both systems was validated in 22 enrolled patients.ResultsThe CBCT exhibited a lower in‐plane spatial resolution (2.50 line pairs per millimeter (lp/mm)) than DR (2.80 lp/mm). Spatial resolution of the CBCT system was measured at 0.90 lp/mm using the CTP 714 module of the Catphan 700 phantom. Both systems achieved a low contrast resolution of 2.30%. DR provided superior image uniformity (1.12%–1.40%) compared with CBCT (2.20%). The effective imaging areas were comparable between the CBCT and DR systems (99.30%–99.50%). Positioning accuracy varied with planning CT slice thicknesses, radiation quality settings, and registration algorithms, showing mean translation displacements ranging from 0.01 to 0.48 mm. CBCT achieved inter‐fraction translational positioning errors within 2 mm in 42.3% (22/52) of fractions and rotational positioning errors within 2° in 80.8% (42/52) of fractions, and DR achieved 33.8% (24/71) and 73.2% (52/71), respectively.ConclusionThe developed CBCT and DR systems achieved superior image quality and sub‐0.5 mm positioning accuracy. These findings support the clinical feasibility of integrating CBCT and DR imaging systems into the C‐ion RT workflow.

BackgroundAccurate Hounsfield units (HU) are critical for dose calculation and anatomical visualization, but are often affected by dental artifacts in head and neck (H&N) cancer patients. The HyperSight cone‐beam computed tomography (CBCT) platform provides improved image quality over previous CBCT platforms and offers metal artifact reduction (iCBCT MAR) reconstruction.PurposeThis study evaluates the quality of HyperSight CBCT images compared to current clinical standards: TrueBeam CBCT for image guidance and fan‐beam CT (FBCT) from a CT simulator for treatment planning, using images captured during H&N cancer treatment.MethodsImages for 30 H&N cancer patients were acquired on a HyperSight CBCT, conventional TrueBeam and FBCT, with 24 patients exhibiting metal dental artifacts. The HyperSight images were reconstructed using iCBCT MAR and iterative (iCBCT Acuros) algorithms. The four image sets were rigidly registered and compared using the artifact index (AI) measured in the oral cavity and the percentile range (PR) measured in the oral cavity, brain, brainstem and eyes to assess image non‐uniformity. The HU accuracy was calculated relative to FBCT (baseline) for soft tissues (oral cavity, brainstem, submandibular and parotid glands), and bone (mandible). The contrast relative to baseline was evaluated between the oral cavity and nearby structures. Image‐based metrics were computed relative to FBCT including structural similarity index measure (SSIM), mean‐square error (MSE) and peak signal‐to‐noise ratio (PSNR).ResultsThe HyperSight iCBCT MAR images showed a significant reduction in AI values compared to the other images (p < 0.0004), but higher PR values indicating decreased HU uniformity compared to HyperSight iCBCT Acuros and FBCT (p < 0.0002). The soft‐tissue HU and contrast values were significantly closer to baseline in both HyperSight images compared to TrueBeam (HU: p < 0.001, contrast: p < 0.001). For soft‐tissue the HU mean absolute deviation (MAD) from baseline was 16 ± 10 HU for HyperSight iCBCT Acuros, 15 ± 10 HU for HyperSight iCBCT MAR, and 35 ± 22 HU for TrueBeam. For bone, the HU MAD from baseline was 153 ± 233 HU, 185 ± 268 HU, and 214 ± 212 HU, respectively. The HyperSight iCBCT Acuros algorithm achieved significantly superior SSIM, MSE, and PSNR metrics compared to TrueBeam and HyperSight iCBCT MAR in regions with large amounts of bone and air.ConclusionsHyperSight iCBCT MAR significantly reduced artifacts compared to HyperSight iCBCT Acuros, TrueBeam and FBCT, making it particularly beneficial for patients with metal implants. Both HyperSight reconstructions demonstrated improved soft‐tissue HU accuracy and contrast compared to TrueBeam, however the iCBCT Acuros algorithm may be preferred when metal‐induced artifacts are not a concern. These results support the suitability of HyperSight images in adaptive treatment workflows requiring accurate image quality, even with severe metal artifacts.

Cone beam computed tomography (CBCT) allows for rapid and accessible acquisition of three-dimensional images with a lower radiation dose compared to conventional computed tomography (CT) scans. However, the quality of CBCT images is limited by a variety of artifacts. This systematic review attempts to explore different artificial intelligence-based solutions for enhancing the quality of CBCT scans and reducing different types of artifacts in these three-dimensional images. PubMed, Web of Science, Scopus, Embase, Cochrane, and Google Scholar were searched up to March 2025. Risk of bias of included studies was assessed using the QUADAS-II tool. Extracted data included bibliographic information, aim, imaging modality, anatomical site of interest, artificial intelligence modeling approach and details, data and dataset details, qualitative and quantitative performance metrics, and main findings. A total of 27 papers from 2018 to 2025 were included. These studies focused on five areas: metal artifact reduction, scatter correction, image reconstruction improvement, motion artifact reduction, and noise reduction. Artificial intelligence models mainly used U-Net variants, though hybrid and transformer-based models were also explored. The thoracic region was the most analyzed, and the structural similarity index measure and peak signal-to-noise-ratio were common performance metrics. Data availability was limited, with only 26% of studies providing public access and 15% sharing model source codes. Artificial intelligence-driven approaches have demonstrated promising results for CBCT artifact reduction. This review highlights a wide variability in performance assessments and that most studies have not received diagnostic validation, limiting conclusions on the true clinical impact of these artificial intelligence-based improvements.

The main purpose of this work was to quantify patient organ doses from the two kilovoltage cone beam computed tomography (CBCT) systems currently available on medical linear accelerators, namely the X‐ray Volumetric Imager (XVI, Elekta Oncology Systems) and the On‐Board Imager (OBI, Varian Medical Systems). Organ dose measurements were performed using a fiber‐optic coupled (FOC) dosimetry system along with an adult male anthropomorphic phantom for three different clinically relevant scan sites: head, chest, and pelvis. The FOC dosimeter was previously characterized at diagnostic energies by Hyer et al. [Med Phys 2009;36(5):1711–16] and a total uncertainty of approximately 4% was found for in‐phantom dose measurements. All scans were performed using current manufacturer‐installed clinical protocols and appropriate bow‐tie filters. A comparison of image quality between these manufacturer‐installed protocols was also performed using a Catphan 440 image quality phantom. Results indicated that for the XVI, the dose to the lens of the eye (1.07 mGy) was highest in a head scan, thyroid dose (19.24 mGy) was highest in a chest scan, and gonad dose (29 mGy) was highest in a pelvis scan. For the OBI, brain dose (3.01 mGy) was highest in a head scan, breast dose (5.34 mGy) was highest in a chest scan, and gonad dose (34.61 mGy) was highest in a pelvis scan. Image quality measurements demonstrated that the OBI provided superior image quality for all protocols, with both better spatial resolution and low‐contrast detectability. The measured organ doses were also used to calculate a reference male effective dose to allow further comparison of the two machines and imaging protocols. The head, chest, and pelvis scans yielded effective doses of 0.04, 7.15, and 3.73 mSv for the XVI, and 0.12, 1.82, and 4.34 mSv for the OBI, respectively.PACS number: 87.57.uq

The aim of this study is to remove scattered photons and beam hardening effect in cone beam CT (CBCT) images and make an image available for treatment planning. To remove scattered photons and beam hardening effect, a convolutional neural network (CNN) was used, and trained with distorted projection data including scattered photons and beam hardening effect and supervised projection data calculated with monochromatic X-rays. The number of training projection data was 17,280 with data augmentation and that of test projection data was 540. The performance of the CNN was investigated in terms of the number of photons in the projection data used in the training of the network. Projection data of pelvic CBCT images (32 cases) were calculated with a Monte Carlo simulation with six different count levels ranging from 0.5 to 3 million counts/pixel. For the evaluation of corrected images, the peak signal-to-noise ratio (PSNR), the structural similarity index measure (SSIM), and the sum of absolute difference (SAD) were used. The results of simulations showed that the CNN could effectively remove scattered photons and beam hardening effect, and the PSNR, the SSIM, and the SAD significantly improved. It was also found that the number of photons in the training projection data was important in correction accuracy. Furthermore, a CNN model trained with projection data with a sufficient number of photons could yield good performance even though a small number of photons were used in the input projection data.

In the sphere of Cone Beam Computed Tomography (CBCT), acquiring X-ray projections from sufficient angles is indispensable for traditional image reconstruction methods to accurately reconstruct 3D anatomical intricacies. However, this acquisition procedure for the linear accelerator-mounted CBCT systems in radiotherapy takes approximately one minute, impeding its use for ultra-fast intra-fractional motion monitoring during treatment delivery. To address this challenge, we introduce the Patient-specific Cycle-domain Geometric-integrated Denoising Diffusion Probabilistic Model (CG-DDPM). This model aims to leverage patient-specific priors from patient's CT/4DCT images, which are acquired for treatment planning purposes, to reconstruct 3D CBCT from a single-view 2D CBCT projection of any arbitrary angle during treatment, namely single-view reconstructed CBCT (svCBCT). The CG-DDPM framework encompasses a dual DDPM structure: the Projection-DDPM for synthesizing comprehensive full-view projections and the CBCT-DDPM for creating CBCT images. A key innovation is our Cycle-Domain Geometry-Integrated (CDGI) method, incorporating a Cone Beam X-ray Geometric Transformation Module (GTM) to ensure precise, synergistic operation between the dual DDPMs, thereby enhancing reconstruction accuracy and reducing artifacts. Evaluated in a study involving 37 lung cancer patients, the method demonstrated its ability to reconstruct CBCT not only from simulated X-ray projections but also from real-world data. The CG-DDPM significantly outperforms existing V-shape convolutional neural networks (V-nets), Generative Adversarial Networks (GANs), and DDPM methods in terms of reconstruction fidelity and artifact minimization. This was confirmed through extensive voxel-level, structural, visual, and clinical assessments. The capability of CG-DDPM to generate high-quality reconstructed CBCT from a single-view projection at any arbitrary angle using a single model opens the door for ultra-fast, in-treatment volumetric imaging. This is especially beneficial for radiotherapy at motion-associated cancer sites and image-guided interventional procedures.

Monitoring Dosimetric Impact of Weight Loss With Kilovoltage (KV) Cone Beam CT (CBCT) During Parotid-Sparing IMRT and Concurrent Chemotherapy

Introduction: Advances in medical imaging have led to the widespread use of Cone Beam Computed Tomography (CBCT) and Fan Beam Computed Tomography (FBCT) for three-dimensional anatomical imaging with reduced radiation exposure. Understanding the balance between image quality and radiation dose is critical for optimizing clinical outcomes and patient safety. Methods: This systematic review follows PRISMA guidelines to compare image quality and radiation dose between CBCT and FBCT. A systematic search identified 20 relevant studies, which were analyzed for study characteristics, imaging parameters, and key findings. Results: CBCT consistently offered superior imaging with lower radiation doses compared to FBCT. However, FBCT showed advantages in noise reduction, particularly in complex body regions. Most studies were of moderate to high quality, but protocol variability was noted. Conclusion: CBCT provides superior imaging with lower radiation doses than FBCT, while FBCT excels in noise reduction. Optimizing protocols and considering clinical requirements are crucial for selecting the appropriate modality. Future research should address protocol standardization and broader clinical aspects for enhanced utilization.

Foreign objects lodged in the mandibular bone often result from trauma or dental procedures. Accurate localization of these foreign objects is crucial for guided surgical removal, especially when patients present with persistent pain. Conventional imaging modalities like periapical and panoramic radiographs may not provide sufficient detail for precise localization. Cone beam computed tomography (CBCT) has emerged as a valuable tool for guided surgical interventions owing to its superior imaging capabilities. We present two cases of foreign objects lodged in the mandible, where patients complained of prolonged pain, soreness, and numbness in the right mandible extending to the head and behind the ear. Both patients had undergone previous right mandibular tooth extractions and received treatment from a neurologist without resolution of symptoms. Both cases showed the control improvement in complaints, and no paresthesia or postoperative complications were found. CBCT-guided surgical removal was performed in both cases, revealing a metal specimen measuring 6 × 3 × 1 mm3 in the first patient and a remaining root measuring 5 × 3 × 2 mm3 in the second patient. Diagnosing foreign objects in the mandible poses challenges due to their varied size, composition, and proximity to vital structures. CBCT offers superior imaging resolution, enabling precise localization and assessment of anatomical relationships, such as the distance to the inferior alveolar nerve and surrounding boundaries. CBCT emerges as the preferred imaging modality for diagnosing and guiding the surgical removal of foreign objects in the mandible. Its advantages include accurate localization, low radiation exposure, and cost-effectiveness. Compared with CT scans, CBCT also offers faster scanning times, making it a valuable tool in clinical practice for managing such cases

The purpose of this study was to investigate and compare microcalcification detectability using Digital Tomosynthesis (DTS), Dual Energy Mammography (DEM) and Cone Beam Computed Tomography (CBCT) with a flat-panel detector. A simulated 3D uncompressed breast approximating the medium sized breast, with 50% adipose and 50% glandular tissue was used. Microcalcifications were modeled as calcium carbonate spheres/ellipsoids with size in full range of 0.1 to 1mm. An amorphous-silicon CsI flatdetector, 2048 × 2048 mm2 at 0.1mm resolution was modeled. Images from the above phantom were simulated using three acquisition protocols for DTS, DEM and CBCT. For DTS, projections data were acquired for an acquisition arc from −200 to 200 with 20 sampling step, and the 3D reconstructed volume was obtained using a Multiple Projection Algorithm (MPA), with a 0.1 mm width between successive tomograms. In the DEM case, two synthetic projection images at 21 and 52 KeV respectively were simulated. A weighted subtraction of low and high — energy digital X-ray images was performed, allowing the removal of background morphology and enhancement of the obscured details. For the last method (CBCT), 181 projections acquired every 20 over a full circular scanning path were used for 3D breast volume reconstruction using the well-known FDK algorithm. The image quality of the reconstructed tomograms was visually assessed and quantified in terms of contrast to noise ratio (CNR), relative detail contrast (RC), as well as Artifacts Spread Function (ASF). The results show that microcalcifications with diameter equal or greater than 0.1mm can be detected, with the CBCT and DTS techniques. Superior quality is demonstrated by CBCT technique in comparison with DTS and DE by means of better microcalcification detection.Keywordsdual energy mammographytomosynthesiscone beam breast CT

ObjectiveIn this study, the accuracy of deep learning-based models developed for synthetic CT (sCT) generation from conventional Cone Beam Computed Tomography (CBCT) images of prostate cancer patients was evaluated. The clinical applicability of these sCTs in treatment planning and their potential to support adaptive radiotherapy decision-making were also investigated.MethodsA total of 50 CBCT-CT mappings were obtained for each of 10 retrospectively selected prostate cancer patients, including one planning CT (pCT) and five CBCT scans taken on different days during the treatment process. All images were preprocessed, anatomically matched and used as input to the U-Net and ResU-Net models trained with PyTorch after z-score normalisation. The sCT outputs obtained from model outputs were quantitatively compared with the pCT with metrics such as SSIM, PSNR, MAE, and HU difference distribution.ResultsBoth models produced sCT images with higher similarity to pCT compared to CBCT images. The mean SSIM value was 0.763 ± 0.040 for CBCT-CT matches, 0.840 ± 0.026 with U-Net and 0.851 ± 0.026 with ResU-Net, with a significant increase in both models (p < 0.05). PSNR values were 21.55 ± 1.38 dB for CBCT, 24.74 ± 1.83 dB for U-Net, and 25.24 ± 1.61 dB for ResU-Net. ResU-Net provided a statistically significant higher PSNR value compared to U-Net (p < 0.05). In terms of MAE, while the mean error in CBCT-CT matches was 75.2 ± 18.7 HU, the U-Net model reduced this value to 65.3 ± 14.8 HU and ResU-Net to 61.8 ± 13.7 HU (p < 0.05).ConclusionDeep learning models trained with simple architectures such as U-Net and ResU-Net provide effective and feasible solutions for the generation of clinically relevant sCT from CBCT images, supporting accurate dose calculation and facilitating adaptive radiotherapy workflows in prostate cancer management.

The size of pixels in a digital recording device, such as a CCD array, limits the spatial resolution in images obtained by an optical imaging system, thereby degrading the image quality. Digital super-resolution (DSR) techniques are used to reconstruct a high-resolution (HR) image from multiple sub-pixel-shifted low-resolution images in order to improve the image quality. In this article, we formulate a mathematical framework for DSR using the generalized sampling theorem (GST). The GST-based DSR method’s performance is evaluated by comparing it to existing resolution enhancement methods on the basis of evaluation metrics like percentage mean square error (%MSE), structural similarity index measure (SSIM), and peak signal-to-noise ratio (PSNR). The GST DSR method exhibits an overall superior quality image reconstruction based on quantitative analysis (with a near zero %MSE, SSIM around one, and improved PSNR in dB) and qualitative comparison. The robustness of the GST DSR method is further demonstrated in the presence of frame-to-frame shift estimation error using %MSE and SSIM by comparing it with multi-frame interpolation approaches.

The use of cone-beam computed tomography (CBCT) to inspect objects containing aluminum, Inconel and other metals is a challenge due to high amounts of scattered radiation in the projection data. Following in the footsteps of VSHARP, our kernel-based two-dimensional (2D) software scatter correction algorithm that operates on x-ray projection data, we introduce three-dimensional (3D) VSHARP designed to offer improved accuracy and flexibility. The core of 3D VSHARP is fast finite element Linear Boltzmann Transport Equation (LBTE) solver that models photon transport within the object-of-interest and computes the scatter component of the projection data with Monte Carlo-like accuracy but greatly reduced computation times. 3D VSHARP utilizes an object model consisting of 3D material density maps based on a first pass reconstruction, and an imaging chain model describing the system geometry, the x-ray source components (polychromatic spectrum, beam filtration, and collimation hardware), and the x-ray detector components (flat-panel imager in this case). The 3D material density maps making up the object model may be further informed by Computer Aided Design (CAD) files. Validation against Monte Carlo (MC) simulations of overlapping metal blocks showed that 3D VSHARP- and MC-computed scatter fractions agreed to within 3% RMS. The 3D VSHARP execution time was less than 1 sec per projection using a single NVidia TitanXp GPU (NVidia Inc., Santa Clara CA) while the MC simulations took 1566 CPU-hours using two Intel-Silver-Xenon, 2.2 GHz, 10x core CPU (Intel Inc., Santa Clara CA), in a Dell 7920 workstation (Dell Inc., Austin TX). Experimental CBCT scans were taken of an aluminum motorcycle cylinder head and Inconel turbine blade at 450kVp. Results showed that high quality reconstructions and volume renderings were obtained which may open up the possibility of in-line CBCT applications.

Robotic C-arms are capable of complex orbits that can increase field of view, reduce artifacts, improve image quality, and/or reduce dose; however, it can be challenging to obtain accurate, reproducible geometric calibration required for image reconstruction for such complex orbits. This work presents a method for geometric calibration for an arbitrary source-detector orbit by registering 2D projection data to a previously acquired 3D image. It also yields a method by which calibration of simple circular orbits can be improved. The registration uses a normalized gradient information similarity metric and the covariance matrix adaptation-evolution strategy optimizer for robustness against local minima and changes in image content. The resulting transformation provides a ‘self-calibration’ of system geometry. The algorithm was tested in phantom studies using both a cone-beam CT (CBCT) test-bench and a robotic C-arm (Artis Zeego, Siemens Healthcare) for circular and non-circular orbits. Self-calibration performance was evaluated in terms of the full-width at half-maximum (FWHM) of the point spread function in CBCT reconstructions, the reprojection error (RPE) of steel ball bearings placed on each phantom, and the overall quality and presence of artifacts in CBCT images. In all cases, self-calibration improved the FWHM—e.g. on the CBCT bench, FWHM = 0.86 mm for conventional calibration compared to 0.65 mm for self-calibration (p < 0.001). Similar improvements were measured in RPE—e.g. on the robotic C-arm, RPE = 0.73 mm for conventional calibration compared to 0.55 mm for self-calibration (p < 0.001). Visible improvement was evident in CBCT reconstructions using self-calibration, particularly about high-contrast, high-frequency objects (e.g. temporal bone air cells and a surgical needle). The results indicate that self-calibration can improve even upon systems with presumably accurate geometric calibration and is applicable to situations where conventional calibration is not feasible, such as complex non-circular CBCT orbits and systems with irreproducible source-detector trajectory.

&#xD;Newer generation linear accelerators (Linacs) allow 20 second cone-beam CT (CBCT) acquisition which reduces radiation therapy treatment time. However, the current clinical application of these rapid scans is only 3DCBCT. In this paper we propose a novel data-driven rapid 4DCBCT reconstruction method for new generation linacs.&#xD;Approach:&#xD;This method relies on estimating the magnitude of the diaphragm motion from an initial 3D reconstruction. This estimated motion is used to linearly approximate a deformation vector field (DVF) for each respiration phase. These DVFs are then used for motion compensated Feldkamp-Davis-Kress (MCFDK) reconstructions. This method, named MCFDK Data Driven (MCFDK-DD), was compared to a MCFDK reconstruction using a prior motion model (MCFDK-Prior), a 3D-FDK reconstruction, and a conventional acquisition (4 mins) conventional reconstruction 4DCBCT (4D-FDK). The data used in this paper were derived from 4DCT volumes from 13 patients from The Cancer Imaging Archives. The analysis metrics were the Mean Square Error (MSE), Structural Similarity Index Measurement (SSIM) and Tissue Interface Width (TIW).&#xD;Main Results:&#xD;The MCFDK-DD, MCFDK-Prior and 3D-FDK had median MSE values of 1.23×10-6mm-1, 1.14×10-6mm-1 and 1.19×10-6mm-1 respectively. The corresponding median SSIM values were 0.92, 0.92 and 0.92 respectively. These metrics indicated the MCFDK-DD had good agreement with the conventional 4D-FDK and were similar to the MCFDK-Prior reconstructions. The calculated TIW values from the MCFDK-DD reconstructions (median 18.7 mm) were not significantly different to the MCFDK-Prior (median 23.1 mm, p=0.087) and conventional 4D-FDK (median 21.4 mm, p=0.62) reconstruction methods. The TIW was also significantly reduced for the MCFDK-DD method compared to the 3D-FDK reconstructions (median 24.2 mm, p=0.01).&#xD;Significance:&#xD;These results demonstrate the feasibility of creating accurate data-driven 4DCBCT images for rapid scans on new generation linacs. These findings could lead to increased clinical usage of 4D information on newer generation linacs.&#xD.