Digital Tomosynthesis Reconstruction Research Articles

Metal artefact reduction in digital tomosynthesis using component decomposition

We propose a technique for metal artefact reduction in digital tomosynthesis reconstruction. Although the problem was addressed earlier in the literature, we suggest another approach, which is, in our opinion, simpler, and easier to implement. It is a two-stage algorithm. At the first stage, attenuation images are segmented by decomposing their intensity distributions into gaussian-like components. Statistical information contained in each component is used for pixel classification. Components corresponding to metallic objects are identified, and a pixel threshold value separating regions occupied by metal objects from the rest of the image is found. Based on this value, at the second stage, a smooth mapping of image intensity is applied. This makes dense regions transparent, resulting in the artefact reduction in reconstruction. The methodology is demonstrated by several examples.

Accuracy of the independent atom approximation in digital tomosynthesis Monte Carlo simulations

Monte Carlo (MC) codes serve as the gold standard simulation tool during design and optimisation of x-ray imaging systems. Such simulations often model Rayleigh scattering based on the Independent Atom Approximation Model (IAM). This model neglects the low range molecular interference (MI) effects of non-crystalline materials such as human tissues. Previous work has found discrepancies in the simulated images of planar x-ray images between IAM and MI models. However, insignificant differences were found for computed tomography (CT) reconstructions. In this work we present Geant4 MC simulations of a flat panel source digital tomosynthesis (DT) system for human extremities. Results show that with a 1:9 scatter to primary ratio (SPR) in the x-ray projections, the DT reconstructions are insensitive to the differences of the IAM and MI models. Therefore, MC codes that use the IAM model are sufficient for the study of DT systems. That is because DT algorithms have a larger effect on image quality than the few percent change in the noise due to a physical model and noise suppression methods make this change even less important. Dependency of this conclusion on SPR must be considered in other DT modalities where SPR might be larger.

Dynamically-Collimated Digital Tomosynthesis Reconstruction by Using a Compressed-Sensing Based Algorithm

Conventional digital tomosynthesis (DTS) reconstruction by using the filtered-backprojection algorithm requires a full field-of-view scan and relatively dense projections to obtain high-quality images, which results in a high radiation dose to patients. Interior DTS (iDTS) with a proper collimator offers a possible imaging modality for reducing the dose of radiation delivered because the X-ray beam is able to target a small region-of-interest (ROI) containing the target area. Collimators for iDTS often have a fixed rectangular shape, but focusing the X-ray beam on an arbitrarily shaped ROI would be preferable because it further reduces the excessive radiation dose. In this study, we propose a new iDTS scan method to create an ROI with an arbitrary shape to minimize the radiation dose at each angle of view. We used a compressed-sensing-based algorithm for accurate iDTS reconstruction. To validate the proposed method, we performed a systematic simulation and an experiment, and we investigated the image characteristics. Our results indicate that the proposed method may effectively reduce radiation dose in iDTS in real imaging systems.

Image improvement in digital tomosynthesis (DTS) using a deep convolutional neural network

Digital tomosynthesis (DTS) is a geometric tomography technique using a limited-angle scan. It has been popularly used in both medical and industrial x-ray imaging applications. DTS provides the tomographic benefits of computed tomography with reduced dose and time. However, conventional DTS reconstruction based on the computationally cheap filtered back-projection (FBP) method typically produces poor image quality due to limited angular samplings. To overcome these difficulties, iterative reconstruction methods are often used in DTS reconstruction as they have the potential to provide multiplanar images of higher quality than conventional FBP-based methods. However, they require enormous computational cost in the iterative process, which remains an obstacle to practical applications. In this study, we propose a method for effectively reducing limited-angle artifacts in conventional FBP reconstruction, using a state-of-the-art deep learning scheme with a convolutional neural network. Our results indicate that the proposed DTS reconstruction method effectively minimized limited-angle artifacts, thus improving image performance in DTS, and that further it provided good image quality in both sagittal and coronal views (as in computed tomography) as well as in axial view.

Analytic digital tomosynthesis reconstruction in partial sampling with a multislit collimator using a prior sinogram interpolation method

This study investigated analytic digital tomosynthesis (DTS) reconstruction in partial sampling with a multislit collimator that partially blocks the x-ray beam to the patient during projection data acquisition, thereby reducing excessive radiation dose to patients. Partially-sampled DTS images reconstructed using the analytic filtered-backprojection (FBP) algorithm usually suffer from severe bright-band artifacts around multislit edges of the collimator due to incomplete spatial sampling. In this study, a new prior sinogram interpolation method was introduced to the analytic DTS reconstruction in partial sampling to alleviate such artifacts. To verify the proposed DTS method, we conducted a systematic simulation and investigated image characteristics. Three multislit collimator layouts of C(2/2), C(3/3), and C(4/4) with a 50% duty cycle were designed and used in the simulation. Here C(n/n) denotes a collimator layout that blocks the x-ray beam over n detector pixels vertically with a n-pixel interval. All projections were obtained at a tomographic angle of θ = ±40̂ and an angle step of Δθ = 2̂ and used to reconstruct DTS images using the FBP algorithm. Our results indicate that the proposed sinogram interpolation method effectively minimized bright-band artifacts in analytic DTS reconstruction in partial sampling, thus maintaining the image quality.

Projection-based dual-energy digital tomosynthesis and its image characteristics

Digital tomosynthesis (DTS) images reconstructed from the limited-angle scanned projections are often limited in image performance due mainly to superimposed shadow artifacts caused by high attenuation of dense material of the examined object, which makes image contrast of soft tissue distorted. In this study, we investigated a projection-based dual-energy DTS method incorporated with a new software scheme for scatter correction, the so-called weighted l1-norm contextual regularization algorithm, in an attempt to solve the image contrast problem of soft tissue in conventional DTS. The proposed dual-energy DTS process consisted of two main steps: creation of a scatter-corrected decomposition function and separation for soft- and dense-material images in the projection domain followed by DTS reconstruction. We implemented the proposed algorithm and performed a simulation and experiment to demonstrate the feasibility of using the algorithm in DTS. Two sets of projection images were acquired at an angular range of θ = ±40° and X-ray tube voltages of 80 kVp and 140 kVp and scatter-corrected prior to the filtered-backprojection-based DTS reconstruction. The results indicate that our proposed dual-energy DTS method produced cross-sectional images of better contrast characteristics for soft tissue than the conventional single-energy DTS method.

Simulation of Single Grid-based Phase-contrast Digital Tomosynthesis (PC-DTS)

Digital tomosynthesis (DTS) is a geometric tomography technique by a limited-angle scan which has been popularly used in both medical and industrial X-ray imaging applications. However, conventional DTS remains limited by low contrast especially in imaging samples of low atomic number Z such as breast and cartilage tissues. In this work, we applied the recently proposed phase-contrast imaging (PCI) technique, the so-called single grid-based PCI, to DTS in attempt to overcome this limitation. PCI has superior soft-tissue imaging capability while DTS has improved image contrast. Combining the two techniques can therefore considerably improve the X-ray imaging performance. We developed a useful simulation platform for single grid-based phase-contrast DTS reconstruction and performed a systematic simulation using a three-dimensional (3D) numerical breast phantom. In the simulation, an X-ray grid having a lead strip density of 200 lines/inch was used and the DTS scan comprised 41 projections within an angle range of θ = ±40° at an X-ray energy of 25 keV. We successfully reconstructed DTS images of much improved contrast, compared to conventional DTS images, which demonstrates the viability of the proposed approach.

Feasibility study on low-dosage digital tomosynthesis (DTS) using a multislit collimation technique

In this study, we investigated an effective low-dose digital tomosynthesis (DTS) where a multislit collimator placed between the X-ray tube and the patient oscillates during projection data acquisition, partially blocking the X-ray beam to the patient thereby reducing the radiation dosage. We performed a simulation using the proposed DTS with two sets of multislit collimators both having a 50% duty cycle and investigated the image characteristics to demonstrate the feasibility of this proposed approach. In the simulation, all projections were taken at a tomographic angle of θ=±50° and an angle step of Δθ=2°. We utilized an iterative algorithm based on a compressed-sensing (CS) scheme for more accurate DTS reconstruction. Using the proposed DTS, we successfully obtained CS-reconstructed DTS images with no bright-band artifacts around the multislit edges of the collimator, thus maintaining the image quality. Therefore, the use of multislit collimation in current real-world DTS systems can reduce the radiation dosage to patients.

Application of a dual-resolution voxelization scheme to compressed-sensing (CS)-based iterative reconstruction in digital tomosynthesis (DTS)

In recent digital tomosynthesis (DTS), iterative reconstruction methods are often used owing to the potential to provide multiplanar images of superior image quality to conventional filtered-backprojection (FBP)-based methods. However, they require enormous computational cost in the iterative process, which has still been an obstacle to put them to practical use. In this work, we propose a new DTS reconstruction method incorporated with a dual-resolution voxelization scheme in attempt to overcome these difficulties, in which the voxels outside a small region-of-interest (ROI) containing target diagnosis are binned by 2×2×2 while the voxels inside the ROI remain unbinned. We considered a compressed-sensing (CS)-based iterative algorithm with a dual-constraint strategy for more accurate DTS reconstruction. We implemented the proposed algorithm and performed a systematic simulation and experiment to demonstrate its viability. Our results indicate that the proposed method seems to be effective for reducing computational cost considerably in iterative DTS reconstruction, keeping the image quality inside the ROI not much degraded. A binning size of 2×2×2 required only about 31.9% computational memory and about 2.6% reconstruction time, compared to those for no binning case. The reconstruction quality was evaluated in terms of the root-mean-square error (RMSE), the contrast-to-noise ratio (CNR), and the universal-quality index (UQI).

Comparison of analytic and iterative digital tomosynthesis reconstructions for thin slab objects

For digital x-ray tomosynthesis of thin slab objects, we compare the tomographic imaging performances obtained from the filtered backprojection (FBP) and simultaneous algebraic reconstruction (SART) algorithms. The imaging performance includes the in-plane molulation-transfer function (MTF), the signal difference-to-noise ratio (SDNR), and the out-of-plane blur artifact or artifact-spread function (ASF). The MTF is measured using a thin tungsten-wire phantom, and the SDNR and the ASF are measured using a thin aluminum-disc phantom embedded in a plastic cylinder. The FBP shows a better MTF performance than the SART. On the contrary, the SART outperforms the FBP with regard to the SDNR and ASF performances. Detailed experimental results and their analysis results are described in this paper. For a more proper use of digital tomosynthesis technique, this study suggests to use a reconstuction algorithm suitable for application-specific purposes.

Digital x-ray tomosynthesis with interpolated projection data for thin slab objects

In relation with a thin slab-object inspection, we propose a digital tomosynthesis reconstruction with fewer numbers of measured projections in combinations with additional virtual projections, which are produced by interpolating the measured projections. Hence we can reconstruct tomographic images with less few-view artifacts. The projection interpolation assumes that variations in cone-beam ray path-lengths through an object are negligible and the object is rigid. The interpolation is performed in the projection-space domain. Pixel values in the interpolated projection are the weighted sum of pixel values of the measured projections considering their projection angles. The experimental simulation shows that the proposed method can enhance the contrast-to-noise performance in reconstructed images while sacrificing the spatial resolving power.

Image reconstruction in region-of-interest (or interior) digital tomosynthesis (DTS) based on compressed-sensing (CS)

Background and objectiveDigital tomosynthesis (DTS) based on filtered-backprojection (FBP) reconstruction requires a full field-of-view (FOV) scan and relatively dense projections, which results in high doses for medical imaging purposes. To overcome these difficulties, we investigated region-of-interest (ROI) or interior DTS reconstruction where the x-ray beam span covers only a small ROI containing a target area. MethodsAn iterative method based on compressed-sensing (CS) scheme was compared with the FBP-based algorithm for ROI-DTS reconstruction. We implemented both algorithms and performed a systematic simulation and experiments on body and skull phantoms. The image characteristics were evaluated and compared. ResultsThe CS-based algorithm yielded much better reconstruction quality in ROI-DTS compared to the FBP-based algorithm, preserving superior image homogeneity, edge sharpening, and in-plane resolution. The image characteristics of the CS-reconstructed images in ROI-DTS were not significantly different from those in full-FOV DTS. The measured CNR value of the CS-reconstructed ROI-DTS image was about 12.3, about 1.9 times larger than that of the FBP-reconstructed ROI-DTS image. ConclusionsROI-DTS images of substantially high accuracy were obtained using the CS-based algorithm and at reduced imaging doses and less computational cost, compared to typical full-FOV DTS images. We expect that the proposed method will be useful for the development of new DTS systems.

Evaluation of digital tomosynthesis reconstruction algorithms used to reduce metal artifacts for arthroplasty: A phantom study

To investigate methods to reduce metal artifacts during digital tomosynthesis for arthroplasty, we evaluated five algorithms with and without metal artifact reduction (MAR)-processing tested under different radiation doses (0.54, 0.47, and 0.33mSv): adaptive steepest descent projection onto convex sets (ASD-POCS), simultaneous algebraic reconstruction technique total variation (SART-TV), filtered back projection (FBP), maximum likelihood expectation maximization (MLEM), and SART. The algorithms were assessed by determining the artifact index (AI) and artifact spread function (ASF) on a prosthesis phantom. The AI data were statistically analyzed by two-way analysis of variance. Without MAR-processing, the greatest degree of effectiveness of the MLEM algorithm for reducing prosthetic phantom-related metal artifacts was achieved by quantification using the AI (MLEM vs. ASD-POCS, SART-TV, SART, and FBP; all P<0.05). With MAR-processing, the greatest degree of effectiveness of the MLEM, ASD-POCS, SART-TV, and SART algorithms for reducing prosthetic phantom-related metal artifacts was achieved by quantification using the AI (MLEM, ASD-POCS, SART-TV, and SART vs. FBP; all P<0.05). When assessed by ASF, metal artifact reduction was largest for the MLEM algorithm without MAR-processing and ASD-POCS, SART-TV, and SART algorithm with MAR-processing. In ASF, the effect of metal artifact reduction was always greater at reduced radiation doses, regardless of which reconstruction algorithm with and without MAR-processing was used. In this phantom study, the MLEM algorithm without MAR-processing and ASD-POCS, SART-TV, and SART algorithm with MAR-processing gave improved metal artifact reduction.

Feasibility Study for Improving the Image Characteristics in Digital Tomosynthesis (DTS) Using a Compressed-Sensing (Cs)-Based Pre-Deblurring Scheme

ABSTRACTDigital tomosynthesis (DTS) has been widely used in both industrial nondestructive testing and medical x-ray imaging as a popular multiplanar imaging modality. However, although it provides some of the tomographic benefits of computed tomography (CT) at reduced dose and imaging time, the image characteristics are relatively poor due to blur artifacts originated from incomplete data sampling for a limited angular range and also aspects inherent to imaging system, including finite focal spot size of the x-ray source, detector resolution, etc. In this work, in order to overcome these difficulties, we propose an intuitive method in which a compressed-sensing (CS)-based deblurring scheme is applied to the projection images before common DTS reconstruction. We implemented the proposed deblurring algorithm and performed a systematic experiment to demonstrate its viability for improving the image characteristics in DTS. According to our results, the proposed method appears to be effective for the blurring problems in DTS and seems to be promising to our ongoing application to x-ray nondestructive testing.

Application of a compressed-sensing (CS)-based deblurring scheme to digital tomosynthesis (DTS) for improved x-ray nondestructive testing: Simulation and experimental studies

In this work, we investigated a compressed-sensing (CS)-based deblurring scheme for image deblurring of high accuracy in digital tomosynthesis (DTS). We implemented the proposed deblurring scheme and performed a systematic simulation to demonstrate its viability for improved x-ray nondestructive testing. We also performed an experiment by using a table-top setup which consists of an x-ray tube (90kVp, 6mAs) and a CMOS-type flat-panel detector having a 198-μm pixel resolution. In both the simulation and the experiment, 51 projection images were taken with a tomographic angle range of θ=60° and an angle step of Δθ=1.2° and then deblurred by using the proposed algorithm before performing the common filtered-backprojection (FBP)-based DTS reconstruction. Our results indicate that the proposed deblurring scheme appears to be effective for the blurring problems in DTS and is applicable to improve the image characteristics in the present x-ray nondestructive testing.

A software tool of digital tomosynthesis application for patient positioning in radiotherapy.

Digital Tomosynthesis (DTS) is an image modality in reconstructing tomographic images from two‐dimensional kV projections covering a narrow scan angles. Comparing with conventional cone‐beam CT (CBCT), it requires less time and radiation dose in data acquisition. It is feasible to apply this technique in patient positioning in radiotherapy. To facilitate its clinical application, a software tool was developed and the reconstruction processes were accelerated by graphic processing unit (GPU). Two reconstruction and two registration processes are required for DTS application which is different from conventional CBCT application which requires one image reconstruction process and one image registration process. The reconstruction stage consists of productions of two types of DTS. One type of DTS is reconstructed from cone‐beam (CB) projections covering a narrow scan angle and is named onboard DTS (ODTS), which represents the real patient position in treatment room. Another type of DTS is reconstructed from digitally reconstructed radiography (DRR) and is named reference DTS (RDTS), which represents the ideal patient position in treatment room. Prior to the reconstruction of RDTS, The DRRs are reconstructed from planning CT using the same acquisition setting of CB projections. The registration stage consists of two matching processes between ODTS and RDTS. The target shift in lateral and longitudinal axes are obtained from the matching between ODTS and RDTS in coronal view, while the target shift in longitudinal and vertical axes are obtained from the matching between ODTS and RDTS in sagittal view. In this software, both DRR and DTS reconstruction algorithms were implemented on GPU environments for acceleration purpose. The comprehensive evaluation of this software tool was performed including geometric accuracy, image quality, registration accuracy, and reconstruction efficiency. The average correlation coefficient between DRR/DTS generated by GPU‐based algorithm and CPU‐based algorithm is 0.99. Based on the measurements of cube phantom on DTS, the geometric errors are within 0.5 mm in three axes. For both cube phantom and pelvic phantom, the registration errors are within 0.5 mm in three axes. Compared with reconstruction performance of CPU‐based algorithms, the performances of DRR and DTS reconstructions are improved by a factor of 15 to 20. A GPU‐based software tool was developed for DTS application for patient positioning of radiotherapy. The geometric and registration accuracy met the clinical requirement in patient setup of radiotherapy. The high performance of DRR and DTS reconstruction algorithms was achieved by the GPU‐based computation environments. It is a useful software tool for researcher and clinician in evaluating DTS application in patient positioning of radiotherapy.PACS number(s): 87.57.nf

Compressed-sensing (CS)-based Image Deblurring Scheme with a Total Variation Regularization Penalty for Improving Image Characteristics in Digital Tomosynthesis (DTS)

In this work, we considered a compressed-sensing (CS)-based image deblurring scheme with a total-variation (TV) regularization penalty for improving image characteristics in digital tomosynthesis (DTS). We implemented the proposed image deblurring algorithm and performed a systematic simulation to demonstrate its viability. We also performed an experiment by using a table-top setup which consists of an x-ray tube operated at 90 kV p, 6 mAs and a CMOS-type flat-panel detector having a 198-μm pixel resolution. In the both simulation and experiment, 51 projection images were taken with a tomographic angle range of θ=60 o and an angle step of Δθ =1.2 o and then deblurred by using the proposed deblurring algorithm before performing the common filtered-backprojection (FBP)-based DTS reconstruction. According to our results, the image sharpness of the recovered x-ray images and the reconstructed DTS images were significantly improved and the cross-plane spatial resolution in DTS was also improved by a factor of about 1.4. Thus the proposed deblurring scheme appears to be effective for the blurring problems in both conventional radiography and DTS and is applicable to improve the present image characteristics.

SU-E-J-56: Static Gantry Digital Tomosynthesis From the Beam's-Eye-View

Purpose We have designed a novel TumoTrak™ x-ray system that delivers 19 distinct kV views with the linac gantry stationary. It images MV treatment beam above and below the patient with a kV tomosysthesis slice image from the therapy beam’s-eye-view. Results will be high quality images without MLC shadowing for notable improvements relative to conventional fluoroscopic MV imaging and fluoroscopic kV imaging. Methods A complete design has a kV electron beam multisource X-ray tube that fits around the MV treatment beam path, with little interference with normal radiotherapy and unblocked by the multi-leaf-collimator. To simulate digital tomosynthesis, we used cone-beam CT projection data from a lung SBRT patient. These data were acquired at 125 kVp and 11 fps (0.4 mAs per projection). We chose 19 projections evenly spaced over 27° around one of the treatment angles (240°). Digital tomosynthesis reconstruction of a slice through the tumor was performed using iterative reconstruction. The visibility of the lesion was assessed for the reconstructed digital tomosynthesis (DTS), using fluoroscopy MV images acquired during radiation therapy, and a kV single projection image acquired at the same angle as the treatment field (240°). Results The fluoroscopic DTS images provide the best tumor contrast, surpassing themore » conventional radiographic and the in-treatment MV portal images. The electron beam multisource X-ray tube design has been completed and the tube is being fabricated. The estimated time to cycle through all 19 projections is 700 ms, enabling high frame-rate imaging. While the initial proposed use case is for image guided and gated treatment delivery, the enhanced imaging will also deliver superior radiographic images for patient setup. Conclusion The proposed device will deliver high quality planar images from the beam’s-eye-view without MLC obstruction. The prototype has been designed and is being assembled with first imaging scheduled for May 2015. L. Partain, J. Kwon, D. Boyd: NIH/SBIR R43CA192489-01. J. Rottmann, G. Zentai, R. Berbeco: NIH/NCI 1R01CA188446-01. R. Berbeco: E. Research Grant, Varian Medical Systems.« less

WE-AB-303-01: FEATURED PRESENTATION: A Dual-Detector Phase-Matched Digital Tomosynthesis (DTS) Imaging Scheme Using Aggregated KV and MV Projections for Intra-Treatment Lung Tumor Tracking

Purpose: To develop a dual-detector phase-matched DTS technique for continuous and fast intra-treatment lung tumor localization. Methods: Tumor localization accuracy of limited-angle DTS imaging is affected by low inter-slice resolution. The dual-detector DTS technique aims to overcome this limitation through combining orthogonally acquired beam's eye view MV projections and kV projections for intra-treatment DTS reconstruction and localization. To aggregate the kV and MV projections for reconstruction, the MV projections were linearly converted to synthesize corresponding kV projections. To further address the lung motion induced localization errors, this technique uses respiratory phase-matching to match the motion information between on-board DTS and reference DTS to offset the adverse effects of motion blurriness in tumor localization.A study was performed using the CIRS008A lung phantom to simulate different on-board target variation scenarios for localization. The intra-treatment kV and MV acquisition was achieved through the Varian TrueBeam Developer Mode. Four methods were compared for their localization accuracy: 1. the proposed dual-detector phase-matched DTS technique; 2. the single-detector phase-matched DTS technique; 3. the dual-detector 3D-DTS technique without phase-matching; and 4. the single-detector 3D-DTS technique without phase-matching. Results: For scan angles of 2.5°, 5°, 10°, 20° and 30°, the dual-detector phase-matched DTS technique localized the tumor with average(±standard deviations) errors of 0.4±0.3 mm, 0.5±0.3 mm, 0.6±0.2 mm, 0.9±0.4 mm and 1.0±0.3 mm, respectively. The corresponding values of single-detector phase-matched DTS technique were 4.0±2.5 mm, 2.7±1.1 mm, 1.7±1.2 mm, 2.2±0.9 mm and 1.5±0.8 mm, respectively. The values of dual-detector 3D-DTS technique were 6.2±1.7 mm, 6.3±1.2 mm, 5.3±1.3 mm, 2.0±2.2 mm and 1.5±0.5 mm, respectively. And the values of single-detector 3D-DTS technique were 9.7±8.9 mm, 9.8±8.8 mm, 10.0±9.7 mm, 3.9±2.7 mm and 2.2±1.3 mm, respectively. Conclusion: The dual-detector phase-matched DTS technique substantially improves the tumor localization accuracy, which can be applied to real-time intra-treatment lung tumor localization. The research was funded by the National Institutes of Health Grant No. R01-CA184173 and a grant from Varian Medical Systems.

SU‐E‐J‐91: Developing Platform for Online Registration Using Digital Tomosynthesis

Purpose: To meet the needs of fast registration of on‐board digital tomosynthesis (DTS), a platform was developed in assisting the task of intensive DTS reconstruction and analysis. Methods: this platform consists of four parts: pre‐processing, reconstruction, post‐processing, and registration. These four software parts were integrated into one platform and developed using Java programming language. The pre‐processing part handles the procedure of cone‐beam extracting and projection image filtering. The reconstruction part provides the function of FDK‐based cone‐beam reconstruction. Three types of reconstruction algorithms (CPU‐based, OpenGL‐based, and CUDA‐based) were provided to facilitate the processing of DTS in various application scenarios. The post‐processing part handles the procedure of image realignment, DICOM reformatting, and XML file setup for image registration. The image registration part provides both manual and automatic methods, many tools are provided to assist this procedure. Results: several clinical patient cases were tested on this platform. The need of current study which requires fast and intensive reconstruction of DTS from cone‐beam projection is met. Conclusion: this platform demonstrates a clinical available on‐board DTS registration software in assisting current image guided radiotherapy. In the future, additional functions will be added to this platform in order to handle more complex clinical cases.