Motion Traces Research Articles

Delivered dose quantification in prostate radiotherapy using online 3D cine imaging and treatment log files on a combined 1.5T magnetic resonance imaging and linear accelerator system.

Monitoring the intrafraction motion and its impact on the planned dose distribution is of crucial importance in radiotherapy. In this work we quantify the delivered dose for the first prostate patients treated on a combined 1.5T Magnetic Resonance Imaging (MRI) and linear accelerator system in our clinic based on online 3D cine-MR and treatment log files. A prostate intrafraction motion trace was obtained with a soft-tissue based rigid registration method with six degrees of freedom from 3D cine-MR dynamics with a temporal resolution of 8.5-16.9s. For each fraction, all dynamics were also registered to the daily MR image used during the online treatment planning, enabling the mapping to this reference point. Moreover, each fraction's treatment log file was used to extract the timestamped machine parameters during delivery and assign it to the appropriate dynamic volume. These partial plans to dynamic volume combinations were calculated and summed to yield the delivered fraction dose. The planned and delivered dose distributions were compared among all patients for a total of 100 fractions. The clinical target volume underwent on average a decrease of 2.2%±2.9% in terms of D99% coverage while bladder V62Gy was increased by 1.6%±2.3% and rectum V62Gy decreased by 0.2%±2.2%. The first MR-linac dose reconstruction results based on prostate tracking from intrafraction 3D cine-MR and treatment log files are presented. Such a pipeline is essential for online adaptation especially as we progress to MRI-guided extremely hypofractionated treatments.

Trace2trace-A Feasibility Study on Neural Machine Translation Applied to Human Motion Trajectories.

Neural machine translation is a prominent field in the computational linguistics domain. By leveraging the recent developments of deep learning, it gave birth to powerful algorithms for translating text from one language to another. This study aims to assess the feasibility of transferring the neural machine translation approach into a completely different context, namely human mobility and trajectory analysis. Building a conceptual parallelism between sentences (sequences of words) and motion traces (sequences of locations), we aspire to translate individual trajectories generated by a certain category of users into the corresponding mobility traces potentially generated by a different category of users. The experiment is inserted in the background of tourist mobility analysis, with the goal of translating the motion behavior of tourists belonging to a specific nationality into the motion behavior of tourists belonging to a different nationality. The model adopted is based on the seq2seq approach and consists of an encoder–decoder architecture based on long short-term memory (LSTM) neural networks and neural embeddings. The encoder turns an input location sequence into a corresponding hidden vector; the decoder reverses the process, turning the vector into an output location sequence. The proposed framework, tested on a real-world large-scale dataset, explores an effective attempt of motion transformation between different entities, arising as a potentially powerful source of mobility information disclosure, especially in the context of crowd management and smart city services.

Validation of 4D Monte Carlo dose calculations using a programmable deformable lung phantom

PurposeTo validate the accuracy of 4D Monte Carlo (4DMC) simulations to calculate dose deliveries to a deforming anatomy in the presence of realistic respiratory motion traces. A previously developed deformable lung phantom comprising an elastic tumor was modified to enable programming of arbitrary motion profiles. 4D simulations of the dose delivered to the phantom were compared with the measurements. MethodsThe deformable lung phantom moving with irregular breathing patterns was irradiated using static and VMAT beam deliveries. Using the RADPOS 4D dosimetry system, point doses were measured inside and outside the tumor. Dose profiles were acquired using films along the motion path of the tumor (S-I). In addition to dose measurements, RADPOS was used to record the motion of the tumor during dose deliveries. Dose measurements were then compared against 4DMC simulations with EGSnrc/4DdefDOSXYZnrc using the recorded tumor motion. ResultsThe agreements between dose profiles from measurements and simulations were determined to be within 2%/2 mm. Point dose agreements were within 2σ of experimental and/or positional/dose reading uncertainties. 4DMC simulations were shown to accurately predict the sensitivity of delivered dose to the starting phase of breathing motions. We have demonstrated that our 4DMC method, combined with RADPOS, can accurately simulate realistic dose deliveries to a deforming anatomy moving with realistic breathing traces. This 4DMC tool has the potential to be used as a quality assurance tool to verify treatments involving respiratory motion. Adaptive treatment delivery is another area that may benefit from the potential of this 4DMC tool.

Prostate SBRT With Intrafraction Motion Management Using a Novel Linear Accelerator–Based MV-kV Imaging Method

PurposeThis study reports clinical experience using a linear accelerator-based MV-kV imaging system for intrafraction motion management during prostate stereotactic body radiation therapy (SBRT). Methods and MaterialsFrom June 2016 to August 2018, 193 prostate SBRT patients were treated using MV-kV motion management (median dose 40 Gy in 5 fractions). Patients had 3 fiducials implanted then simulated and treated with a full bladder and empty rectum. Pretreatment orthogonal kVs and cone beam computed tomography were used to position patients and evaluate internal anatomy. Motion was tracked during volumetric modulated arc therapy delivery using simultaneously acquired kV and MV images from standard on-board systems. Treatment was interrupted to reposition patients when motion >1.5-2 mm was detected. Motion traces were analyzed and compared with Calypso traces from a previously treated similar patient cohort. To evaluate “natural motion” (ie, if we had not interrupted treatment and repositioned), intrafraction couch corrections were removed from all traces. Clinical effectiveness of the MV-kV system was explored by evaluating toxicity (Common Terminology Criteria for Adverse Events v3.0) and biochemical recurrence rates (nadir + 2 ng/mL). ResultsMedian number of interruptions for patient repositioning was 1 per fraction (range, 0-9). Median overall treatment time was 8.2 minutes (range, 4.2-44.8 minutes). Predominant motion was inferior and posterior, and probability of motion increased with time. Natural motion >3 mm and >5 mm in any direction was observed in 32.3% and 10.2% of fractions, respectively. Calypso monitoring (n = 50) demonstrated similar motion results. In the 151 MV-kV patients with ≥3-month follow-up (median, 9.5 months; range, 3-26.5 months), grade ≥2 acute genitourinary/gastrointestinal and late genitourinary/gastrointestinal toxicity was observed in 9.9%/2.0% and 11.9%/2.7%, respectively. Biochemical control was 99.3% with a single failure in a high-risk patient. ConclusionsThe MV-kV system is an effective method to manage intrafraction prostate motion during SBRT, offering the opportunity to correct for prostate clinical target volume displacements that would have otherwise extended beyond typical planning target volume margins.

Fly-Navi: A Novel Indoor Navigation System With On-the-Fly Map Generation

Existing studies on indoor navigation often require such a pre-deployment as floor map, localization system and/or additional (customized) hardwares, or human motion traces, making them prohibitive when the situation deviates from these requirements (e.g., navigating a crowd of panicking people where no localization system or motion traces are available). The main observation inspiring our work without reliance on such pre-deployment is that when there are sufficient participants (e.g., a crowd of panicking people), the WiFi signatures collected by participants can serve as the fingerprints (referred to as location fingerprints) of their unknown locations. By computing relative positions of these location fingerprints we can connect them to form a global map. Such a map reflects the topology of the underlying walkable space and thus holds the potential of offering a navigation path for any intended users. Based on this observation, we design Fly-Navi, a crowdsourcing based indoor navigation system via on-the-fly map generation, and primarily designed for indoor environments with rectilinear and narrow corridors. Specifically, each participant uploads sensory data, and the server then generates a global map (on-the-fly map) through a series of operations such as local map generation, local map stitch and edge computation. On top of the global map, Fly-Navi computes a navigation path to the given destination and tracks the progress. We implement the prototype of Fly-Navi and our experiments show that Fly-Navi can quickly generate a correct global map with the 80-percentile of between-fingerprint distance error less than 3 meters, which is important for computing turning points of the map and hereon offering turn-by-turn instructions, and correctly navigate the intended users to their destinations.

Predictive Adaptive Streaming to Enable Mobile 360-Degree and VR Experiences

As 360-degree videos and virtual reality (VR) applications become popular for consumer and enterprise use cases, the desire to enable truly mobile experiences also increases. Delivering 360-degree videos and cloud/edge-based VR applications require ultra-high bandwidth and ultra-low latency <xref ref-type="bibr" rid="ref1" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">[1]</xref> , challenging to achieve with mobile networks. A common approach to reduce bandwidth is streaming only the field of view (FOV). However, extracting and transmitting the FOV in response to user head motion can add high latency, adversely affecting user experience. In this paper, we propose a predictive adaptive streaming approach, where the predicted view with high predictive probability is adaptively encoded in relatively high quality according to bandwidth conditions and transmitted in advance, leading to a simultaneous reduction in bandwidth and latency. The predictive adaptive streaming method is based on a deep-learning-based viewpoint prediction model we develop, which uses past head motions to predict where a user will be looking in the 360-degree view. Using a very large dataset consisting of head motion traces from over 36,000 viewers for nineteen 360-degree/VR videos, we validate the ability of our predictive adaptive streaming method to offer high-quality view while simultaneously significantly reducing bandwidth.

Autocalibrated cardiac tissue phase mapping with multiband imaging and k-t acceleration.

To develop an autocalibrated multiband (MB) CAIPIRINHA acquisition scheme with in-plane k-taccelerationenabling multislice three-directional tissue phase mapping in one breath-hold. A k-tundersamplingscheme was integrated into a time-resolved electrocardiographic-triggered autocalibrated MB gradient-echo sequence. The sequence was used to acquire data on 4 healthy volunteers with MB factors of two (MB2) and three (MB3), which were reconstructed using a joint reconstruction algorithm that tackles both k-t and MB acceleration. Forward simulations of the imaging process were used to tune the reconstruction model hyperparameters. Direct comparisons between MB and single-band tissue phase-mapping measurements were performed. Simulations showed that the velocities could be accurately reproduced with MB2 k-t (average ± twice the SD of the RMS error of 0.08 ± 0.22cm/s and velocity peak reduction of 1.03% ± 6.47% compared with fully sampled velocities), whereas acceptable results were obtained with MB3 k-t (RMS error of 0.13 ± 0.58cm/s and peak reduction of 2.21% ± 13.45%). When applied to tissue phase-mapping data, the proposed technique allowed three-directional velocity encoding to be simultaneously acquired at two/three slices in a single breath-hold of 18 heartbeats. No statistically significant differences were detected between MB2/MB3 k-t and single-band k-t motion traces averaged over the myocardium. Regional differences were found, however, when using the American Heart Association model for segmentation. An autocalibratedMBk-tacquisition/reconstruction framework is presented that allows three-directional velocity encoding of the myocardial velocities at multiple slices in one breath-hold.

Technical Note: 3D localization of lung tumors on cone beam CT projections via a convolutional recurrent neural network.

To design a convolutional recurrent neural network (CRNN) that calculates three-dimensional (3D) positions of lung tumors from continuously acquired cone beam computed tomography (CBCT) projections, and facilitates the sorting and reconstruction of 4D-CBCT images. Under an IRB-approved clinical lung protocol, kilovoltage (kV) projections of the setup CBCT were collected in free-breathing. Concurrently, an electromagnetic signal-guided system recorded motion traces of three transponders implanted in or near the tumor. Convolutional recurrent neural network was designed to utilize a convolutional neural network (CNN) for extracting relevant features of the kV projections around the tumor, followed by a recurrent neural network for analyzing the temporal patterns of the moving features. Convolutional recurrent neural network was trained on the simultaneously collected kV projections and motion traces, subsequently utilized to calculate motion traces solely based on the continuous feed of kV projections. To enhance performance, CRNN was also facilitated by frequent calibrations (e.g., at 10° gantry rotation intervals) derived from cross-correlation-based registrations between kV projections and templates created from the planning 4DCT. Convolutional recurrent neural network was validated on a leave-one-out strategy using data from 11 lung patients, including 5500kV images. The root-mean-square error between the CRNN and motion traces was calculated to evaluate the localization accuracy. Three-dimensional displacement around the simulation position shown in the Calypso traces was 3.4±1.7mm. Using motion traces as ground truth, the 3D localization error of CRNN with calibrations was 1.3±1.4mm. CRNN had a success rate of 86±8% in determining whether the motion was within a 3D displacement window of 2mm. The latency was 20ms when CRNN ran on a high-performance computer cluster. CRNN is able to provide accurate localization of lung tumors with aid from frequent recalibrations using the conventional cross-correlation-based registration approach, and has the potential to remove reliance on the implanted fiducials.

Dosimetric impact of soft-tissue based intrafraction motion from 3D cine-MR in prostate SBRT

To investigate the dosimetric impact of intrafraction translation and rotation motion of the prostate, as extracted from daily acquired post-treatment 3D cine-MR based on soft-tissue contrast, in extremely hypofractionated (SBRT) prostate patients. Accurate dose reconstruction is performed by using a prostate intrafraction motion trace which is obtained with a soft-tissue based rigid registration method on 3D cine-MR dynamics with a temporal resolution of 11 s. The recorded motion of each time-point was applied to the planning CT, resulting in the respective dynamic volume used for dose calculation. For each treatment fraction, the treatment delivery record was generated by proportionally splitting the plan into 11 s intervals based on the delivered monitor units. For each fraction the doses of all partial plan/dynamic volume combinations were calculated and were summed to lead to the motion-affected fraction dose. Finally, for each patient the five fraction doses were summed, yielding the total treatment dose. Both daily and total doses were compared to the original reference dose of the respective patient to assess the impact of the intrafraction motion. Depending on the underlying motion of the prostate, different types of motion-affected dose distributions were observed. The planning target volumes (PTVs) ensured CTV_30 (seminal vesicles) D99% coverage for all patients, CTV_35 (prostate corpus) coverage for 97% of the patients and GTV_50 (local boost) for 83% of the patients when compared against the strict planning target D99% value. The dosimetric impact due to prostate intrafraction motion in extremely hypofractionated treatments was determined. The presented study is an essential step towards establishing the actual delivered dose to the patient during radiotherapy fractions.

The first prospective implementation of markerless lung target tracking in an experimental quality assurance procedure on a standard linear accelerator

The ability to track tumour motion without implanted markers on a standard linear accelerator (linac) could enable wide access to real-time adaptive radiotherapy for cancer patients. We previously have retrospectively validated a method for 3D markerless target tracking using intra-fractional kilovoltage (kV) projections acquired on a standard linac. This paper presents the first prospective implementation of markerless lung target tracking on a standard linac and its quality assurance (QA) procedure. The workflow and the algorithm developed to track the 3D target position during volumetric modulated arc therapy treatment delivery were optimised. The linac was operated in clinical QA mode, while kV projections were streamed to a dedicated computer using a frame-grabber software. The markerless target tracking accuracy and precision were measured in a lung phantom experiment under the following conditions: static localisation of seven distinct positions, dynamic localisation of five patient-measured motion traces, and dynamic localisation with treatment interruption. The QA guidelines were developed following the AAPM Task Group 147 report with the requirement that the tracking margin components, the margins required to account for tracking errors, did not exceed 5 mm in any direction. The mean tracking error ranged from 0.0 to 0.9 mm (left–right), −0.6 to −0.1 mm (superior–inferior) and −0.7 to 0.1 mm (anterior–posterior) over the three tests. Larger errors were found in cases with large left–right or anterior–posterior and small superior–inferior motion. The tracking margin components did not exceed 5 mm in any direction and ranged from 0.4 to 3.2 mm (left–right), 0.7 to 1.6 mm (superior–inferior) and 0.8 to 1.5 mm (anterior–posterior). This study presents the first prospective implementation of markerless lung target tracking on a standard linac and provides a QA procedure for its safe clinical implementation, potentially enabling real-time adaptive radiotherapy for a large population of lung cancer patients.

Motion Prediction and Pre-Rendering at the Edge to Enable Ultra-Low Latency Mobile 6DoF Experiences

As virtual reality (VR) applications become popular, the desire to enable high-quality, lightweight, and mobile VR can potentially be achieved by performing the VR rendering and encoding computations at the edge and streaming the rendered video to the VR glasses. However, if the rendering has to be performed after the edge gets to know of the user’s new head and body position, the ultra-low latency requirements of VR will not be met by the roundtrip delay. In this article, we introduce edge intelligence, wherein the edge can predict, pre-render and cache the VR video in advance, to be streamed to the user VR glasses as soon as needed. The edge-based predictive pre-rendering approach can address the challenging six Degrees of Freedom (6DoF) VR content. Compared to 360-degree videos and 3DoF (head motion only) VR, 6DoF VR supports both head and body motion, thus not only viewing direction but also viewing position can change. Hence, our proposed VR edge intelligence comprises of predicting both the head and body motions of a user accurately using past head and body motion traces. In this article, we develop a multi-task long short-term memory (LSTM) model for body motion prediction and a multi-layer perceptron (MLP) model for head motion prediction. We implement the deep learning-based motion prediction models and validate their accuracy and effectiveness using a dataset of over 840,000 samples for head and body motion.

Real-Time Infrared Motion Tracking Analysis for Patients Treated With Gated Frameless Image Guided Stereotactic Radiosurgery

The transition from frame-based brain stereotactic radiosurgery (SRS) to frameless delivery is supported by real-time intrafraction monitoring to ensure accurate delivery. The purpose of this study is to characterize these real-time motion traces in a large cohort of patients treated with frameless gated brain SRS and to develop patient-specific predictions of tolerance violations. SRS patients treated on the Gamma Knife Icon were immobilized using a device-specific thermoplastic head mask. A motion marker was fixed to the patient's nose, with gating and cone beam computed tomography (CBCT)-based corrections to the treatment at excursions from baseline exceeding 1.5 mm. The traces of 1446 fractions were analyzed according to magnitude (932 unique treatment plans for 462 unique individual patients), directional distribution of displacement, and stability. A neural network model was developed to predict interruptions based on a subset of trace data. The average displacement of the marker in the first fraction of all patients was 0.62 ± 0.25 mm with beam CBCT corrections, which would otherwise be modeled at 0.96 ± 0.96 mm without intrafraction motion correction (P < .0001). Twenty-nine percent of fractions delivered were interrupted, of which the Z-axis (superoinferior) motion was the largest contributor to excursion. Baseline corrections significantly compensated for the magnitude of motion in all 3 dimensions (P < .01). The motion relative to the first acquired CBCT was on average seen to consistently increase with treatment time, with the minimum P value occurring at 61.3 minutes. The neural network prediction model was able to predict treatment interruptions with 84% sensitivity on the first 5-minute sample of the trace. Corrections to marker position significantly decreased marker excursions in all 3 axes compared with a single CBCT alignment. Patient-specific modeling may aid in the optimization of cases selected for frameless radiosurgery to increase the accuracy of planned delivery.

Anonymous crowdsourcing-based WLAN indoor localization

In order to solve the problem of location privacy under big data and improve the user positioning experience, a new concept of anonymous crowdsourcing-based WLAN indoor localization is proposed by employing the Micro-Electro-Mechanical System (MEMS) motion sensors as well as WLAN module in off-the-shelf smartphones. First of all, the crowdsourced motion traces with similar Received Signal Strength(RSS) sequences are assembled into a motion graph. Second, the mobility map is constructed according to traces segmentation and clustering. Third, the pixel template matching is adopted to physically label the pre-constructed mobility map. Finally, the robust Extended Kalman Filter (EKF) is designed to perform localization by matching the newly-collected RSS measurements against the mobility map. The extensive experimental results show that the proposed approach is capable of constructing a physically-labeled mobility map from the sporadically-collected crowdsourced motion traces as well as achieving satisfactory localization accuracy in a cost-efficient manner.

JustWalk: A Crowdsourcing Approach for the Automatic Construction of Indoor Floorplans

Mapping and navigation applications are now considered popular services for mobile phones users. However, despite the fact that people spend most of their time indoors, these applications are still limited to indoor spaces due to the lack of large-scale indoor floorplan databases. In this paper, we present JustWalk: a crowd intelligence-based system for the automatic construction of buildings floorplans. JustWalk employs a participatory sensing approach using smartphones that are ubiquitously available with users who visit a building to automatically and transparently construct accurate motion traces. These accurate traces are generated by reducing the errors in the inertial motion traces by using the points of interest in the indoor environment (e.g., elevators and stairs, etc.) for error resetting. The collected traces are then processed by means of different mathematical and image processing techniques to detect the overall floorplan shape as well as higher level semantics such as detecting rooms and corridors shapes along with a variety of points of interest in the environment. In comparison to other approaches, our system depends only on the users walking patterns and motion traces. It does not require any explicit inputs or obtrusive actions (e.g., taking photos). Experimental evaluation of JustWalk using different android phones in three testbeds shows that it achieves high accuracy for the point of interest detection (0.6 percent false positive and 1 percent false negative rates). In addition, the proposed error resetting technique leads to more than 12 times enhancement in the median distance error compared to the state-of-the-art. Moreover, the detailed floorplan can be accurately estimated with a relatively small number of traces. This number is amortized over the number of users visiting the building. Finally, we show that JustWalk has a small energy footprint on cell-phones, and could be generalized to other buildings; highlighting its promise as a ubiquitous indoor mapping service.

Impact of intrafraction prostate motion on clinical target coverage in proton therapy: A simulation study of dosimetric differences in two delivery techniques.

PurposeTo investigate the dosimetric impact of prostate intrafraction motion on proton double‐scattering (DS) and uniform scanning (US) treatments using electromagnetic transponder‐based prostate tracking data in simulated treatment deliveries.MethodsIn proton DS delivery, the spread‐out Bragg peak (SOBP) is created almost instantaneously by the constant rotation of the range modulator. US, however, delivers each entire energy layer of the SOBP sequentially from distal to proximal direction in time, which can interplay with prostate intrafraction motion. This spatiotemporal interplay during proton treatment was simulated to evaluate its dosimetric impact. Prostate clinical target volume (CTV) dose was obtained by moving CTV through dose matrices of the energy layers according to prostate‐motion traces. Fourteen prostate intrafraction motion traces of each of 17 prostate patients were used in the simulated treatment deliveries. Both single fraction dose‐volume histograms (DVHs) and fraction‐cumulative DVHs were obtained for both 2 Gy per fraction and 7.25 Gy per fraction stereotactic body radiotherapy (SBRT).ResultsThe simulation results indicated that CTV dose degradation depends on the magnitude and direction of prostate intrafraction motion and is patient specific. For some individual fractions, prescription dose coverage decreased in both US and DS treatments, and hot and cold spots inside the CTV were observed in the US results. However, fraction‐cumulative CTV dose coverage showed much reduced dose degradation for both DS and US treatments for both 2 Gy per fraction and SBRT simulations.ConclusionsThis study indicated that CTV dose inhomogeneity may exist for some patients with severe prostate intrafraction motion during US treatments. However, there are no statistically significant dose differences between DS and US treatment simulations. Cumulative dose of multiple‐fractions significantly reduced dose uncertainties.

Event-by-event non-rigid data-driven PET respiratory motion correction methods: comparison of principal component analysis and centroid of distribution

Respiratory motion is a major cause of degradation of PET image quality. Respiratory gating and motion correction can be performed to reduce the effects of respiratory motion; these methods require motion information, typically obtained from external tracking systems. Various groups have studied data-driven (DD) motion estimation methods. Recently, a DD respiratory motion estimation method was established by calculating the centroid of distribution (COD) of listmode events, which was then used with event-by-event respiratory motion correction (EBE-MC) and showed results comparable to those with an external motion tracking device. The EBE-MC method only corrected for rigid motion, so that non-rigid components still contributed to motion-induced blurring. A non-rigid respiratory motion correction (NRMC) was later developed to overcome this problem, but was only evaluated using signals from an external monitor. Thus, it is desirable to further develop DD motion estimation to achieve the best respiratory motion correction results.We evaluated two DD respiratory motion detection methods, COD and principal component analysis (PCA), by comparing the extracted motion trace to that acquired by the Anzai system in dynamic studies with two tracers. PCA was chosen as a preliminary study indicated that it produced stable results than other DD methods. We then developed and performed DD-EBE-NRMC using either COD- or PCA-derived respiratory motion information. DD correction results were compared with Anzai-based results. For all tested studies, both COD and PCA showed a good-to-excellent match with Anzai signals, with PCA showing a higher correlation with Anzai signals. The DD-EBE-NRMC results showed that both COD and PCA provide comparable image quality improvement to the Anzai-based correction. Although COD showed a lower correlation with Anzai than PCA, COD-based NRMC results are comparable to those of PCA, both of which showed great reduction in motion-induced blurring.

Identifying Foreign Tourists’ Nationality from Mobility Traces via LSTM Neural Network and Location Embeddings

The interest in human mobility analysis has increased with the rapid growth of positioning technology and motion tracking, leading to a variety of studies based on trajectory recordings. Mapping the routes that people commonly perform was revealed to be very useful for location-based service applications, where individual mobility behaviors can potentially disclose meaningful information about each customer and be fruitfully used for personalized recommendation systems. This paper tackles a novel trajectory labeling problem related to the context of user profiling in “smart” tourism, inferring the nationality of individual users on the basis of their motion trajectories. In particular, we use large-scale motion traces of short-term foreign visitors as a way of detecting the nationality of individuals. This task is not trivial, relying on the hypothesis that foreign tourists of different nationalities may not only visit different locations, but also move in a different way between the same locations. The problem is defined as a multinomial classification with a few tens of classes (nationalities) and sparse location-based trajectory data. We hereby propose a machine learning-based methodology, consisting of a long short-term memory (LSTM) neural network trained on vector representations of locations, in order to capture the underlying semantics of user mobility patterns. Experiments conducted on a real-world big dataset demonstrate that our method achieves considerably higher performances than baseline and traditional approaches.

A six-degree-of-freedom robotic motion system for quality assurance of real-time image-guided radiotherapy

In this study we develop and characterise a six degree-of-freedom (6 DoF) robotic motion system for quality assurance of real-time image-guided radiotherapy techniques. The system consists of a commercially available robotic arm, an acrylic phantom with embedded Calypso markers, a custom base plate to mount the robot to the treatment couch, and control software implementing the appropriate sequence of transformations to reproduce measured tumour motion traces. The robotic motion system was evaluated in terms of the set-up and motion trace repeatability, static localization accuracy and dynamic localization accuracy. Four prostate, two liver and three lung motion traces, representing a range of tumor motion trajectories recorded in real patient treatments, were executed using the robotic motion system and compared with motion measurements from the clinical Calypso motion tracking system. System set-up and motion trace repeatability was better than 0.5 deg and 0.3 mm for rotation and translation, respectively. The static localization accuracy of the robotic motion system in the LR, SI and AP directions was 0.09 mm, 0.08 mm and 0.02 mm for translations, respectively, and 0.2°, 0.06° and 0.06° for rotations, respectively. The dynamic localization accuracy of the robotic motion system was <0.2 mm and <0.6° for translations and rotations, respectively. Thus, we have demonstrated the ability to accurately mimic rigid-body tumor motion using a robotically controlled phantom to provide precise geometric QA for advanced radiotherapy delivery approaches.

Assessment of 3D motion modeling performance for dose accumulation mapping on the MR-linac by simultaneous multislice MRI

Hybrid MR-linac systems enable intrafraction motion monitoring during radiation therapy. Since time-resolved 3D MRI is still challenging, various motion models have been developed that rely on time-resolved 2D imaging. Continuous validation of these models is important for accurate dose accumulation mapping. In this study we used 2D simultaneous multislice (SMS) imaging to improve the PCA-based motion modeling method developed previously (Stemkens et al 2016 Phys. Med. Biol. 61 5335–55). From the additional simultaneously acquired slices, several independent motion models could be generated, which allowed for an assessment of the sensitivity of the motion model to the location of the time-resolved 2D slices. Additionally, the best model could be chosen at every time-point, increasing the method’s robustness.Imaging experiments were performed in six healthy volunteers using three simultaneous slices, which generated three independent models per volunteer. For each model the motion traces of the liver tip and both kidneys were estimated. We found that the location of the 2D slices influenced the model’s error in five volunteers significantly with a p -value <0.05, and that selecting the best model at every time-point can improve the method. This allows for more accurate and robust motion characterization in MR-guided radiotherapy.

A novel deformable lung phantom with programably variable external and internal correlation.

Lung motion phantoms used to validate radiotherapy motion management strategies have fairly simplistic designs that do not adequately capture complex phenomena observed in human respiration such as external and internal deformation, variable hysteresis and variable correlation between different parts of the thoracic anatomy. These limitations make reliable evaluation of sophisticated motion management techniques quite challenging. In this work, we present the design and implementation of a programmable, externally and internally deformable lung motion phantom that allows for a reproducible change in external-internal and internal-internal correlation of embedded markers. An in-house-designed lung module, made from natural latex foam was inserted inside the outer shell of a commercially available lung phantom (RSD, Long Beach, CA, USA). Radiopaque markers were placed on the external surface and embedded into the lung module. Two independently programmable high-precision linear motion actuators were used to generate primarily anterior-posterior (AP) and primarily superior-inferior (SI) motion in a reproducible fashion in order to enable (a) variable correlation between the displacement of interior volume and the exterior surface, (b) independent changes in the amplitude of the AP and SI motions, and (c) variable hysteresis. The ability of the phantom to produce complex and variable motion accurately and reproducibly was evaluated by programming the two actuators with mathematical and patient-recorded lung tumor motion traces, and recording the trajectories of various markers using kV fluoroscopy. As an example application, the phantom was used to evaluate the performance of lung motion models constructed from kV fluoroscopy and 4DCT images. The phantom exhibited a high degree of reproducibility and marker motion ranges were reproducible to within 0.5mm. Variable correlation was observed between the displacements of internal-internal and internal-external markers. The SI and AP components of motion of a specific marker had a correlation parameter that varied from -11 to 17. Monitoring a region of interest on the phantom's surface to estimate internal marker motion led to considerably lower uncertainties than when a single point was monitored. We successfully designed and implemented a programmable, externally and internally deformable lung motion phantom that allows for a reproducible change in external-internal and internal-internal correlation of embedded markers.