Fiducial Marker Tracking Research Articles

Real-time nonstandard-shaped gold fiducial marker tracking on x-ray fluoroscopic images for prostate radiotherapy

Objective. The prostate moves in accordance with the movement of surrounding organs. Tumor position can change by ≥3 mm during radiotherapy. Given the difficulties of visualizing the prostate fluoroscopically, fiducial markers are generally implanted into the prostate to monitor its motion during treatment. Recently, internally motion guidance methods of the prostate using a 99.5% gold/0.5% iron flexible notched wire fiducial marker (Gold Anchor® , Naslund Medical AB, Huddinge, Sweden), which requires a 22 gauge needle, has been used. However, because the notched wire can retain its linear shape, acquire a spiral shape, or roll into an irregular ball, detecting it on fluoroscopic images in real-time incurs higher computation costs. Approach. We developed a fiducial tracking algorithm to achieve real-time computation. The marker is detected on the first image frame using a shape filter that employs inter-class variance for the marker likelihood calculated by the filter, focusing on the large difference in densities between the marker and its surroundings. After the second frame, the marker is tracked by adding to the shape filter the similarity to the template cropped from the area around the marker position detected in the first frame. We retrospectively evaluated the algorithm’s marker tracking accuracy for ten prostate cases, analyzing two fractions in each case. Main results. Tracking positional accuracy averaged over all patients was 0.13 ± 0.04 mm (mean ± standard deviation, Euclidean distance) and 0.25 ± 0.09 mm (95th percentile). Computation time was 2.82 ± 0.20 ms/frame averaged over all frames. Significance. Our algorithm successfully and stably tracked irregularly-shaped markers in real time.

End-to-end validation of fiducial tracking accuracy in robotic radiosurgery using MRI-only simulation imaging.

Image-guided radiation-therapy (IGRT)-based robotic radiosurgery using magnetic resonance imaging (MRI)-only simulation could allow for improved target definition with highly conformal radiotherapy treatments. Fiducial marker (FM)-based alignment is used with robotic radiosurgery treatments of sites such as the prostate because it aids in accurate target localization. Synthetic CT (sCT) images are generated in the MRI-only workflow but FMs used for IGRT appear as signal voids in MRIs and do not appear in MR-generated sCTs, hindering the ability to use sCTs for fiducial-based IGRT. In this study we evaluate the fiducial tracking accuracy for a novel artificial fiducial insertion method in sCT images that allows for fiducial marker tracking in robotic radiosurgery, using MRI-only simulation imaging (MRI-only workflow). Artificial fiducial markers were inserted into sCT images at the site of the real marker implantation as visible in MRI. Two phantoms were used in this study. A custom anthropomorphic pelvis phantom was designed to validate the tracking accuracy for a variety of artificial fiducials in an MRI-only workflow. A head phantom containing a hidden target and orthogonal film pair inserts was used to perform end-to-end tests of artificial fiducial configurations inserted in sCT images. The setup and end-to-end targeting accuracy of the MRI-only workflow were compared to the computed tomography (CT)-based standard. Each phantom had six FMs implanted with a minimum spacing of 2cm. For each phantom a bulk-density sCT was generated, and artificial FMs were inserted at the implantation location. Several methods of FM insertion were tested including: (1) replacing HU with a fixed value (10000HU) (voxel-burned); (2) using a representative fiducial image derived from a linear combination of fiducial templates (composite-fiducial); (3) computationally simulating FM signal voids using a digital phantom containing FMs and inserting the corresponding signal void into sCT images (simulated-fiducial). All tests were performed on a CyberKnife system (Accuray, Sunnyvale, CA). Treatment plans and digital-reconstructed-radiographs were generated from the original CT and sCTs with embedded fiducials and used to align the phantom on the treatment couch. Differences in the initial phantom alignment (3D translations/rotations) and tracking parameters between CT-based plans and sCT-based plans were analyzed. End-to-end plans for both scenarios were generated and analyzed following our clinical protocol. For all plans, the fiducial tracking algorithm was able to identify the fiducial locations. The mean FM-extraction uncertainty for the composite and simulated FMs was below 48% for fiducials in both the anthropomorphic pelvis and end-to-end phantoms, which is below the 70% treatment uncertainty threshold. The total targeting error was within tolerance (<0.95mm) for end-to-end tests of sCT images with the composite and head-on simulated FMs (0.26, 0.44, and 0.35mm for the composite fiducial in sCT, head-on simulated fiducial in sCT, and fiducials in original CT, respectively. MRI-only simulation for robotic radiosurgery could potentially improve treatment accuracy and reduce planning margins. Our study has shown that using a composite-derived or simulated FM in conjunction with sCT images, MRI-only workflow can provide clinically acceptable setup accuracy in line with CT-based standards for FM-based robotic radiosurgery.

Evaluation of kV Triggered Fiducial Tracking for Prostate SBRT Intrafraction Motion Management.

Stereotactic body radiation therapy (SBRT) is a safe and effective treatment for localized prostate cancer. Given the high dose per fraction, a high degree of precision is needed during SBRT treatment delivery. Fiducial marker tracking is a means of monitoring intrafraction motion, ensuring precise treatment delivery and potentially allowing for decreased planning target volume (PTV) margins. We present a 5-year single institution experience to characterize the performance of fiducial tracking. We analyzed 132 consecutive patients treated at our institution with prostate SBRT between July 2017 and November 2022 using fiducial tracking with the TrueBeam Auto Beam Hold feature. Patients were treated using a 5-fraction dose escalation protocol, with many receiving a simultaneous integrated boost to the GTV up to 45 Gy. All patients underwent pre-treatment cone-beam CT and planar kV imaging with rigid registration to the fiducial markers. Cine kV images were acquired every 3-5 seconds during treatment delivery and the beam was paused when a fiducial deviated from a given 4 mm diameter tolerance region. Additional intrafraction 2D or 3D imaging techniques were then used to realign the fiducials. Data was retrieved from the record and verify system including: number and type of intrafraction images, number of treatment interruptions, number of and magnitude of shifts, and total treatment time. The average number of cine kV images acquired per fraction and for the total 5 fraction SBRT course were 86.6 ± 26.8 and 425.6 ± 136.8 respectively. Assuming 1.3 mGy/kV image, the fiducial tracking process delivered an average additional 55.3 cGy over the full treatment course. On average, the beam was paused 5.0 ± 2.5 times per fraction (range 1-21 interruptions) and shifts were applied 4.1 ± 2.1 times (range 0-10.2 times) per fraction. Over the 2560 total shifts applied for all the patients, the average(max) translations were 0.6 (12) mm vrt, 0.7 (22) mm lng, and 0.9 (5) mm lat and the average(max) rotations were 0.19 (5.9)° pitch, 0.01 (2.4)° roll, and 0.16 (6.4)° rtn. Overall, 2.4% of shifts were greater than the 4 mm PTV margin and 4.2% of vertical shifts were greater than the 2.5 mm posterior margin. Average fraction treatment time was 27 ± 9.7 minutes. Fiducial tracking affords the potential to increase daily treatment precision when delivering prostate SBRT. Our data indicate that the beam is typically paused several times during a prostate SBRT fraction, with occasional large shifts required, suggesting the importance of intrafraction motion management. Downsides of kV triggered fiducial tracking include extension of treatment times and delivery of additional radiation dose to the patient. We are investigating if this method of motion management might allow for a reduction in PTV margins to reduce normal tissue dosing.

An unsupervised image registration method employing chest computed tomography images and deep neural networks

BackgroundDeformable image registration is crucial for multiple radiation therapy applications. Fast registration of computed tomography (CT) lung images is challenging because of the large and nonlinear deformation between inspiration and expiration. With advancements in deep learning techniques, learning-based registration methods are considered efficient alternatives to traditional methods in terms of accuracy and computational cost. MethodIn this study, an unsupervised lung registration network (LRN) with cycle-consistent training is proposed to align two acquired CT-derived lung datasets during breath-holds at inspiratory and expiratory levels without utilizing any ground-truth registration results. Generally, the LRN model uses three loss functions: image similarity, regularization, and Jacobian determinant. Here, LRN was trained on the CT datasets of 705 subjects and tested using 10 pairs of public CT DIR-Lab datasets. Furthermore, to evaluate the effectiveness of the registration technique, target registration errors (TREs) of the LRN model were compared with those of the conventional algorithm (sum of squared tissue volume difference; SSTVD) and a state-of-the-art unsupervised registration method (VoxelMorph). ResultsThe results showed that the LRN with an average TRE of 1.78 ± 1.56 mm outperformed VoxelMorph with an average TRE of 2.43 ± 2.43 mm, which is comparable to that of SSTVD with an average TRE of 1.66 ± 1.49 mm. In addition, estimating the displacement vector field without any folding voxel consumed less than 2 s, demonstrating the superiority of the learning-based method with respect to fiducial marker tracking and the overall soft tissue alignment with a nearly real-time speed. ConclusionsTherefore, this proposed method shows significant potential for use in time-sensitive pulmonary studies, such as lung motion tracking and image-guided surgery.

Feasibility Study of Removable Fiducial Marker Implantation with the Intelligent Navigation Bronchoscopy Technology in Robotic Radiosurgery System Tracking

<h3>Purpose/Objective(s)</h3> To investigate the feasibility of removable fiducial marker implantation with the intelligent navigation bronchoscopy technology in a frameless robotic radiosurgery system tracking. <h3>Materials/Methods</h3> CT scans of an inflatable anti-corruption pig lung were acquired, and two simulated tumor lesion sites were designed in the left and right lung lobes by intelligent navigation software, respectively. According to the principle of fiducial marker implantation, 24 removable fiducial markers were implanted around each simulated tumor lesion via bronchus after intelligent guiding. Simulating the end-expiratory state, the pig lung was scanned again to obtain CT images of the implanted removable fiducial markers and the number of successfully implanted fiducial markers was recorded. Six deliverable treatment plans were designed using the planning system, and then the pig lung plans were delivered based on the simulated respiratory movements. After the treatment, the implanted removable fiducial markers were retrieved through bronchoscopy, and the number of successful retrievals was recorded. The rigid body error and translation error were extracted and analyzed from the log file. <h3>Results</h3> No removed fiducial markers slipped and fell off during the experiment. 24 removable fiducial markers were successfully implanted under bronchoscopic intelligent magnetic navigation guidance, with a 100% implantation success rate (24/24) and 100% removable success rate (24/24). The fiducial marker tracking rate was 83.33% (20/24), with 4 fiducial markers being too far away from the simulated tumor location to be used during the tracking process. The data from the log file displayed that the mean rigid body error for 6 groups was 1.45 mm, the mean translation error was 1.78 mm. <h3>Conclusion</h3> The technology of bronchoscopy intelligent navigation and implantation of removable fiducial marker is feasible, and the tracking accuracy of the frameless robotic radiosurgery system can meet the clinical requirements, which has a good clinical application and teaching application prospect.

A feasibility study on the development and use of a deep learning model to automate real-time monitoring of tumor position and assessment of interfraction fiducial marker migration in prostate radiotherapy patients * *Deep Learning Fiducial Marker Localisation.

Purpose. The aim of this study was to assess the feasibility of the development and training of a deep learning object detection model for automating the assessment of fiducial marker migration and tracking of the prostate in radiotherapy patients. Methods and Materials. A fiducial marker detection model was trained on the YOLO v2 detection framework using approximately 20,000 pelvis kV projection images with fiducial markers labelled. The ability of the trained model to detect marker positions was validated by tracking the motion of markers in a respiratory phantom and comparing detection data with the expected displacement from a reference position. Marker migration was then assessed in 14 prostate radiotherapy patients using the detector for comparison with previously conducted studies. This was done by determining variations in intermarker distance between the first and subsequent fractions in each patient. Results. On completion of training, a detection model was developed that operated at a 96% detection efficacy and with a root mean square error of 0.3 pixels. By determining the displacement from a reference position in a respiratory phantom, experimentally and with the detector it was found that the detector was able to compute displacements with a mean accuracy of 97.8% when compared to the actual values. Interfraction marker migration was measured in 14 patients and the average and maximum standard deviation marker migration were found to be and respectively. Conclusion. This study demonstrates the benefits of pairing deep learning object detection, and image-guided radiotherapy and how a workflow to automate the assessment of organ motion and seed migration during prostate radiotherapy can be developed. The high detection efficacy and low error make evident the advantages of using a pre-trained model to automate the assessment of the target volume positional variation and the migration of fiducial markers between fractions.

Investigation of fiducial marker recognition possibility by water equivalent length in real-time tracking radiotherapy.

Real-time tumor tracking radiotherapy (RTRT) systems typically use fiducial markers implanted near the tumor to track the target using X-ray fluoroscopy. Template pattern matching, used in tracking, is often used to automatically localize the fiducial markers. In radiotherapy of the liver, the thickness of the body that can recognize the fiducial markers must be clinically assessed. The purpose of this study was to quantify the recognition of fiducial markers according to body thickness in stereotactic body radiotherapy of the liver using clinical images obtained using SyncTraX FX4. The recognition scores of fiducial markers were examined in relation to water equivalent length (WEL), tube current, and each flat panel detector. The relationship between the contrast ratio of the fiducial marker and the background and the WEL was also investigated. The average recognition score was found to be less than 20 when the WEL was greater than 25cm. The probability of successful tracking of image recognition was mostly smaller than 0.8 when the WEL was over 30cm. The relationship between WEL and tube current did not significantly differ between 100 and 140mA, but there was a significant difference (p < 0.05) for all other combinations. To ensure tracking of fiducial markers during SBRT, if the WEL representing body thickness is longer than 25cm, the X-ray fluoroscopy arrangement should be determined based on the WEL.

Feasibility study of fiducial marker localization using microwave radar.

We explore the potential use of radar technology for fiducial marker tracking for monitoring of respiratory tumor motion during radiotherapy. Historically microwave radar technology has been widely deployed in various military and civil aviation applications to provide detection, position, and tracking of single or multiples objects from far away and even through barriers. Recently, due to many advantages of the microwave technology, it has been successfully demonstrated to detect breast tumor, and to monitor vital signs in real time such as breathing signals or heart rates. We demonstrate a proof-of-concept for radar-based fiducial marker tracking through the synthetic human tissue phantom. We performed a series of experiments with the vector network analyzer (VNA) and wideband directional horn antenna. We considered the frequency range from 2.0 to 6.0GHz, with a maximum power of 3dBm. A horn antenna, transmitting and receiving radar pulses, was connected to the vector network analyzer to probe a gold fiducial marker through a customized synthetic human tissue phantom, consisting of 1-mm thickness of skin, 5-mm fat, and 25-mm muscle layers. A 1.2 × 10-mm gold fiducial marker was exploited as a motion surrogate, which was placed behind the phantom and statically positioned with an increment of 12.7mm to simulate different marker displacements. The returned signals from the marker were acquired and analyzed to evaluate the localization accuracy as a function of the marker position. The fiducial marker was successfully localized at various measurement positions through a simplified phantom study. The averaged localization accuracy across measurements was 3.5 ± 1.3mm, with a minimum error of 1.9mm at the closest measurement location and a maximum error of 4.9mm at the largest measurement location. We demonstrated that the 2-6GHz radar can penetrate through the attenuating tissues and localize a fiducial marker. This successful feasibility study establishes a foundation for further investigation of radar technology as a non-ionizing tumor localization device for radiotherapy.

Inter- and Intra-Fraction Movement of Prostate and Seminal Vesicles: Analysis from MR-Guided Hypo-Fractioned Radiotherapy

Modest to extreme hypo-fractionated radiotherapy has become standard of care for low to intermediate grade prostate cancer. With advances in soft-tissue image verification such as MR-guided has led to a reduction in PTV margins compared to conventional radiotherapy. Therefore, a detailed knowledge of prostate movement is required to ensure that PTV margins remain valid. Tracking of fiducial markers has been used previously to assess prostate motion during radiotherapy, but this cannot assess all regions of the prostate or a change in prostate shape. MR-guided radiotherapy gives a much higher degree of tracking accuracy and greater precision to identify intra- and inter-fraction prostate movement. This prospective study aims to determine inter- and intra-fraction movement of prostate and seminal vesicles (SV) and its impact on daily adaptation by evaluating changes in dominant intra-prostatic lesions (DIL) which occur during radiotherapy courses. Twenty patients with low to intermediate grade prostate cancer were treated with 36.25 Gy in 5 fractions using daily adapted, MR-guided radiotherapy. The prostate clinical target volume (CTV) and organs at risk (OARs) were re-contoured each fraction. The variation in prostate shape from the baseline planning MR scan was compared with each fraction to assess the inter-fraction movement. Tracking markers were set at the level of seminal vesicles root, apex of prostate and anterior and posterior aspects of the prostate to measure intra-fraction movement. Average treatment time for each adapted fraction was under 60 minutes. Initial results show a greater degree of movement and change of shape of SV compared to the apical region. The position of the prostate also altered considerably on the live cine-MRI compared to the pre-verification MRI image. Daily adaptation demonstrated significant geometrical alteration of SV position on an inter-fraction basis. A detailed model of inter- and intra-fraction prostate motion allows validation of the reduced PTV margins used in hypo-fractionated radiotherapy.

Real-time Linear Fiducial Marker Tracking in Respiratory-gated Radiotherapy With a Deep Neural Network

To achieve high treatment accuracy in respiratory-gated radiotherapy, it is important to obtain a mobile tumor position in 3D space. Instead of tracking a tumor, Mylonas et al. proposed the method of detecting linear fiducial markers in fluoroscopic images with convolutional neural network (CNN) models (Mylonas et al. Med Phys. 2019; 46 2286-97). However, it is difficult to prepare the many marker images required for training the model. Therefore, we propose a method to train a CNN model with 3D simulated training marker images. Furthermore, the proposed model tracks the markers in a pair of orthogonal fluoroscopic images. Owing to no need of taking fluoroscopic images of implanted markers, our method can build the model for the arbitrary-shaped marker more efficiently. To make training images, we cropped patch images, whose size was 31x31x2 pixels, from the position such that 3D points were projected onto the paired fluoroscopic images of non-implanted patients. These patch images were labeled “not-marker images”. The simulated “marker images” were generated by drawing the shape of the marker, which was virtually put at the 3D points with any posture, projected onto the patch images. We built a CNN model by training 1000 marker and not-marker images. The model consisted of four convolutional layers with two max-pooling layers and lastly a fully connected layer to output the marker likelihood. Each convolutional layer has a batch normalization layer and a rectified linear unit. For tracking the marker, the trained model calculated the likelihood of each 3D point by inputting the cropped image from where the 3D point was projected onto the fluoroscopic images and the marker position in 3D space was determined with the likelihood-weighted average of the positions. To reduce the number of calculated 3D points, we used a particle filter. The method was evaluated using three liver fluoroscopic image datasets with an implanted linear fiducial marker 0.5 mm in diameter by 3.0 mm in length. Each dataset consisted of at least one respiratory phase. The positional error of each marker was calculated between the tracked position and the ground truth position in 3D space. In addition, the calculation time was measured on a workstation (Intel Xeon® CPU @ 3.6 GHz). The mean positional error for three patients was measured to be 0.32 mm with a standard deviation of 0.17 mm. The worst positional error was 1.1 mm. For the first, second and third patient, the mean errors were 0.38, 0.26 and 0.32 mm with a standard deviation of 0.16, 0.13 and 0.16 mm, respectively. The calculation time was within 50.4 milliseconds per frame. We presented real-time linear fiducial marker tracking for respiratory-gated radiotherapy with a DNN framework. We performed experiments involving three live patients with our proposed method and obtained high accuracy and short computation time.

Correction to: PDCAT: a framework for fast, robust, and occlusion resilient fiducial marker tracking

In the original publication of the article, the family name of the 1st author has been changed to Araar.

Improved Position Accuracy of Foot-Mounted Inertial Sensor by Discrete Corrections from Vision-Based Fiducial Marker Tracking.

In this paper, we present a novel pedestrian indoor positioning system that uses sensor fusion between a foot-mounted inertial measurement unit (IMU) and a vision-based fiducial marker tracking system. The goal is to provide an after-action review for first responders during training exercises. The main contribution of this work comes from the observation that different walking types (e.g., forward walking, sideways walking, backward walking) lead to different levels of position and heading error. Our approach takes this into account when accumulating the error, thereby leading to more-accurate estimations. Through experimentation, we show the variation in error accumulation and the improvement in accuracy alter when and how often to activate the camera tracking system, leading to better balance between accuracy and power consumption overall. The IMU and vision-based systems are loosely coupled using an extended Kalman filter (EKF) to ensure accurate and unobstructed positioning computation. The motion model of the EKF is derived from the foot-mounted IMU data and the measurement model from the vision system. Existing indoor positioning systems for training exercises require extensive active infrastructure installation, which is not viable for exercises taking place in a remote area. With the use of passive infrastructure (i.e., fiducial markers), the positioning system can accurately track user position over a longer duration of time and can be easily integrated into the environment. We evaluated our system on an indoor trajectory of 250 m. Results show that even with discrete corrections, near a meter level of accuracy can be achieved. Our proposed system attains the positioning accuracy of 0.55 m for a forward walk, 1.05 m for a backward walk, and 1.68 m for a sideways walk with a 90% confidence level.

PDCAT: a framework for fast, robust, and occlusion resilient fiducial marker tracking

Square binary patterns have become the de facto fiducial marker for most computer vision applications. Existing tracking solutions suffer a number of limitations, such as the low frame-rate and sensitivity to partial occlusions. This work aims at overcoming these limitations, by exploiting temporal information in video-sequences. We propose a parallel detection, compensation and tracking (PDCAT) framework, which can be integrated into any binary marker system. Our solution is capable of recovering markers even when they become mostly occluded. Furthermore, the low processing time of the tracking task makes PDCAT more than an order of magnitude faster than a track-by-detect solution. This is particularly important for embedded computer vision applications, wherein the detection run at a very low frame rate. In the experiments conducted on an embedded computer, the processing frame rate of the track-by-detect solution was merely 11 FPS. Our solution, on the other hand, was capable of processing more than 100 FPS.

Optimizing Coded Aperture Imaging techniques to allow for online tracking of fiducial markers with high-energy scattered radiation from treatment beam.

Real-time visualization of target motion using fiducial markers during radiation therapy treatment will allow for more accurate dose delivery. The purpose of this study was to optimize techniques for online fiducial marker tracking by detecting the scattered treatment beam through coded aperture imaging (CAI). Coded aperture imaging is a novel imaging technique that can allow target tracking in real time during treatment, and do so without adding any additional radiation dose, by making use of the scattered treatment beam radiation. Radiotherapy beams of various energies, incident on phantoms containing gold fiducial markers were modeled using MCNP6.2 Monte Carlo transport code. Orthogonal scatter radiographs were collected through a CAI geometry. After decoding the simulated radiograph data, the centroid location and FWHM/SNR of the fiducial signals were analyzed. The effects of properties related to the CA (rank, pattern, and physical dimensions), detector (dimensions and pixel count), position (CA and phantom), and the incident beam (spectrum and direction) were investigated. These variables were evaluated by quantifying the positional accuracy, resolution, and SNR of the fiducials' signal. The effects of phantom scatter and decoding artifacts were reduced via Fourier filtering to avoid treatment interruption and physical interaction with the coded mask. The method was able to accurately localize the markers to within 1 pixel of a simulated radiograph. A 10×10×2cm tungsten mask was chosen to attenuate >99 % of incident scatter through opaque elements, while minimizing collimation artifacts which arise from vignetting of the coded radiograph. Clear separation of centroids from fiducial signals with 2.5mm separation was maintained, and initial optimization of parameters has produced an aperture which decodes the location of multiple fiducial markers inside a human phantom properly with a high SNR in the final radiograph image. Current results show a proof of concept for a novel real-time imaging method. Coded aperture imaging is a promising technique for extracting the fiducial scatter signal from a broader Compton-scatter background. These results can be used to further optimize the CAI parameter space and guide fabrication and testing of a clinical device.

4D-CT deformable image registration using multiscale unsupervised deep learning

Deformable image registration (DIR) of 4D-CT images is important in multiple radiation therapy applications including motion tracking of soft tissue or fiducial markers, target definition, image fusion, dose accumulation and treatment response evaluations. It is very challenging to accurately and quickly register 4D-CT abdominal images due to its large appearance variances and bulky sizes. In this study, we proposed an accurate and fast multi-scale DIR network (MS-DIRNet) for abdominal 4D-CT registration. MS-DIRNet consists of a global network (GlobalNet) and local network (LocalNet). GlobalNet was trained using down-sampled whole image volumes while LocalNet was trained using sampled image patches. MS-DIRNet consists of a generator and a discriminator. The generator was trained to directly predict a deformation vector field (DVF) based on the moving and target images. The generator was implemented using convolutional neural networks with multiple attention gates. The discriminator was trained to differentiate the deformed images from the target images to provide additional DVF regularization. The loss function of MS-DIRNet includes three parts which are image similarity loss, adversarial loss and DVF regularization loss. The MS-DIRNet was trained in a completely unsupervised manner meaning that ground truth DVFs are not needed. Different from traditional DIRs that calculate DVF iteratively, MS-DIRNet is able to calculate the final DVF in a single forward prediction which could significantly expedite the DIR process. The MS-DIRNet was trained and tested on 25 patients’ 4D-CT datasets using five-fold cross validation. For registration accuracy evaluation, target registration errors (TREs) of MS-DIRNet were compared to clinically used software. Our results showed that the MS-DIRNet with an average TRE of 1.2 ± 0.8 mm outperformed the commercial software with an average TRE of 2.5 ± 0.8 mm in 4D-CT abdominal DIR, demonstrating the superior performance of our method in fiducial marker tracking and overall soft tissue alignment.

Soft-tissue prostate intrafraction motion tracking in 3D cine-MR for MR-guided radiotherapy

To develop a method to automatically determine intrafraction motion of the prostate based on soft tissue contrast on 3D cine-magnetic resonance (MR) images with high spatial and temporal resolution. Twenty-nine patients who underwent prostate stereotactic body radiotherapy (SBRT), with four implanted cylindrical gold fiducial markers (FMs), had cine-MR imaging sessions after each of five weekly fractions. Each cine-MR session consisted of 55 sequentially obtained 3D data sets (‘dynamics’) and was acquired over an 11 s period, covering a total of 10 min. The prostate was delineated on the first dynamic of every dataset and this delineation was used as the starting position for the soft tissue tracking (SST). Each subsequent dynamic was rigidly aligned to the first dynamic, based on the contrast of the prostate. The obtained translation and rotation describes the intrafraction motion of the prostate. The algorithm was applied to 6270 dynamics over 114 scans of 29 patients and the results were validated by comparing to previously obtained fiducial marker tracking data of the same dataset. Our proposed tracking method was also retro-perspectively applied to cine-MR images acquired during MR-guided radiotherapy of our first prostate patient treated on the MR-Linac. The difference in the 3D translation results between the soft tissue and marker tracking was below 1 mm for 98.2% of the time. The mean translation at 10 min were X: 0.0 0.8 mm, Y: 1.0 1.8 mm and Z: mm. The mean rotation results at 10 min were X: , Y: 0.1 0.6° and Z: 0.0 0.7°. A fast, robust and accurate SST algorithm was developed which obviates the need for FMs during MR-guided prostate radiotherapy. To our knowledge, this is the first data using full 3D cine-MR images for real-time soft tissue prostate tracking, which is validated against previously obtained marker tracking data.

Safety and efficacy of fiducial marker implantation for robotic stereotactic body radiation therapy with fiducial tracking

PurposeThe purpose of this study was to assess the feasibility, efficacy and toxicity of fiducial marker implantation and tracking in CyberKnife® stereotactic radiation therapy (SBRT) applied to extracranial locations.Materials and methodThis is a retrospective, single-centre, observational study to collect the data of all patients treated by stereotactic radiation therapy with fiducial marker tracking at extracranial locations, conducted between June 2014 and November 2017. Information regarding the implantation procedure, the types of toxicity related to marker implantation and the number of markers implanted/tracked during treatment were collected. Complication rates were evaluated using the CTCAE v4 [Common Terminology Criteria for Adverse Events] scale. The technical success rate was based on the ability to optimally track the tumor throughout all treatment fractions.ResultsOut of 2505 patients treated by stereotactic radiation therapy, 25% received treatment with fiducial marker tracking. The total number of implantation procedures was 616 and 1543 fiducial markers were implanted. The implantation-related complication rate was 3%, with 16 Grade 1 events and 4 Grade 2 events. The number of treated patients and the number of implanted markers has gradually increased since the technique was first implemented. The median treatment time was 27 min (range 10–76). 1295 fiducials were effectively tracked throughout all treatment fractions, corresponding to a technical success rate of 84%. The difference between the number of fiducials implanted and those tracked during treatment decreased significantly as the site’s experience increased.ConclusionFiducial marker implantation and tracking is feasible, well-tolerated, and technically effective technique in SBRT for extracranial tumors.

Real-time Linear Fiducial Marker Tracking in Respiratory-gated Radiotherapy for Hepatocellular Carcinoma

Real-time Linear Fiducial Marker Tracking in Respiratory-gated Radiotherapy for Hepatocellular Carcinoma

Retrospective assessment of a single fiducial marker tracking regimen with robotic stereotactic body radiation therapy for liver tumours

To investigate tumour motion tracking uncertainties in the CyberKnife Synchrony system with single fiducial marker in liver tumours. In the fiducial-based CyberKnife real-time tumour motion tracking system, multiple fiducial markers are generally used to enable translation and rotation corrections during tracking. However, sometimes a single fiducial marker is employed when rotation corrections are not estimated during treatment. Data were analysed for 32 patients with liver tumours where one fiducial marker was implanted. Four-dimensional computed tomography (CT) scans were performed to determine the internal target volume (ITV). Before the first treatment fraction, the CT scans were repeated and the marker migration was determined. Log files generated by the Synchrony system were obtained after each treatment and the correlation model errors were calculated. Intra-fractional spine rotations were examined on the spine alignment images before and after each treatment. The mean (standard deviation) ITV margin was 4.1 (2.3)mm, which correlated weakly with the distance between the fiducial marker and the tumour. The mean migration distance of the marker was 1.5 (0.7)mm. The overall mean correlation model error was 1.03 (0.37)mm in the radial direction. The overall mean spine rotations were 0.27° (0.31), 0.25° (0.22), and 0.23° (0.26) for roll, pitch, and yaw, respectively. The treatment time was moderately associated with the correlation model errors and weakly related to spine rotation in the roll and yaw planes. More caution and an additional safety margins are required when tracking a single fiducial marker.

FunPianoAR: A Novel AR Application for Piano Learning Considering Paired Play Based on Multi-Marker Tracking

This paper describes the design and implementation of a novel augmented reality application, referred as FunPianoAR, that aiming to activate the interests of user and improve the experience of piano learning. The FunPianoAR with a user-friendly interface considers the paired play to further reduce the difficulty of playing the piano for adult novices. For the paired play, one user plays the melody and the other plays the harmony part. The app is developed by using Android Studio 3.0 and artoolkitX 1.0, an open source augmented reality SDK, and installed on the AR smart glasses, Epson Moverio BT300. Due to the textureless features of real piano and registration precision, the application is implemented by using the fiducial marker tracking instead of the markerless recognition. Besides, we divided the piano keyboard into four zones and each zone used a separate marker for tracking to solve the limited field of view (FOV) to some extent. The virtual keys can be accurately superimposed on the piano keys by using multi-marker tracking. An evaluation was also conducted to compare the effects of two types of augmented reality information superimposed, i.e., the instant way without the hints for the next note to be played and the FunPianoAR with the hints for the coming notes to be played. The correctness rate was calculated and the time differences between the notes that two players should play at the same time were collected. The FunPianoAR shows more advantages over the instant way based on the evaluation results.