Real-time Tracking System Research Articles

A multiple closed-loops robotic calibration for accurate surgical puncture.

Robotic puncture system increasingly demands stringent standard in target location accuracy. The positional and orientational transformation relationships among all components of the system are supposed to be calibrated and identified preoperatively. The target location performance is directly determined by the calibration result. Therefore, a multiple closed-loops calibration approach is proposed to achieve high-level calibration accuracy in robotic puncture system. MATERIALS& METHODS: This method takes as input the three-dimensional position information of the retro-reflective markers mounted on the surgical tool, which is detected by the optical tracking system in real time during robotic movement. There is less complicated mathematical derivation and calculation in the presented algorithm by applying the closed-loop principle. Experimental results validate that it can achieve accurate robotic target location with less input data and computation-cost, satisfying the clinical puncture requirements. The spatial calibration between robotic arm and optical tracking system efficiently realised by the presented approach present an alternative which can be safely applied to the robotic puncture system for accurate insertion. Overall, a multiple closed-loops calibration approach is proposed in this work, which may increase surgical efficiency.

A Wearable Body Condition Sensor System with Wireless Feedback Alarm Functions.

Emerging feedback systems based on tracking body conditions can save human lives. In particular, vulnerable populations such as disabled people, elderly, and infants often require special care. For example, the high global mortality of infants primarily owing to sudden infant death syndrome while sleeping makes request for extraordinary attentions in neonatal intensive care units or daily lives. Here, a versatile laser-induced graphene (LIG)-based integrated flexible sensor system, which can wirelessly monitor the sleeping postures, respiration rate, and diaper moisture with feedback alarm notifications, is reported. A tilt sensor based on confining a liquid metal droplet inside a cavity can track at least 18 slanting orientations. A rapid and scalable laser direct writing method realizes LIG patterning in both the in-plane and out-of-plane configurations as well as the formation of nonstick conductive structures to the liquid metal. By rationally merging the LIG-based tilt, strain, and humidity sensors on a thin flexible film, the multimodal sensor device is applied to a diaper as a real-time feedback tracking system of the sleeping posture, respiration, and wetness toward secure and comfortable lives. User-friendly interfaces, which incorporate alarming functions, provide timely feedback for caregivers tending to vulnerable populations with limited self-care capabilities.

Target localization during respiration motion based on LSTM: A pilot study on robotic puncture system

In the needle biopsy, the respiratory motion causes the displacement of thoracic-abdominal soft tissues, which brings great difficulty to accurate localization. Based on internal target motion and external marker motion, the existing methods need to establish a correlation model or a prediction model to compensate the respiratory movement, which can hardly achieve required accuracy in clinic use due to the complexity of the internal tissue motion. In order to improve the tracking accuracy and reduce the number of models, we propose a framework for target localization based on long short-term memory (LSTM) method. Combined with the correlation model and the prediction model by using LSTM, we adopted the principal component of time-series features of external surrogate signals to predict the trajectory of the internal tumour target. Additionally, based on the electromagnetic tracking system and Universal Robots 3 robotic arm, we applied the proposed approach to a prototype of robotic puncture system for real-time tumour tracking. To verify the proposed method, experiments on both public datasets and customized motion phantom for respiratory simulation were performed. In the public dataset study, an average mean absolute error, and an average root-mean-square error of predictive results of 0.44 and 0.58 mm were achieved, respectively. In the motion phantom study, an average root mean square of puncturing error resulted in 0.65 mm. The experimental results demonstrate the proposed method improves the accuracy of target localization during respiratory movement and appeals the potentials applying to clinical application.

Robustify Hand Tracking by Fusing Generative and Discriminative Methods

With the development of virtual reality (VR) technology and its applications in many fields, creating simulated hands in the virtual environment is an e ective way to replace the controller as well as to enhance user experience in interactive processes. Therefore, hand tracking problem is gaining a lot of research attention, making an important contribution in recognizing hand postures as well as tracking hand motions for VR’s input or human machine interaction applications. In order to create a markerless real-time hand tracking system suitable for natural human machine interaction, we propose a new method that combines generative and discriminative methods to solve the hand tracking problem using a single RGBD camera. Our system removes the requirement of the user having to wear to color wrist band and robustifies the hand localization even in di cult tracking scenarios.
 KeywordsHand tracking, generative method, discriminative method, human performance capture
 References[1] Malik, A. Elhayek, F. Nunnari, K. Varanasi, Tamaddon, A. Heloir, D. Stricker, Deephps: End-to-end estimation of 3d hand pose and shape by learning from synthetic depth, CoRR abs/1808.09208, 2018.
 URL http://arxiv.org/abs/1808.09208.
 [2] Glauser, S. Wu, D. Panozzo, O. Hilliges, Sorkine-Hornung, Interactive hand pose estimation using a stretch-sensing soft glove, ACM Trans, Graph. 38(4) (2019) 1-15.[3] Jiang, H. Xia, C. Guo, A model-based system for real-time articulated hand tracking using a simple data glove and a depth camera, Sensors 19 (2019) 4680. https://doi.org/10.3390/s19214680.[4] Cao, G. Hidalgo, T. Simon, S. Wei, Y. Sheikh, Openpose: Realtime multi-person 2d pose estimation using part a nity fields, CoRR abs/1812.08008, 2018.[5] Tagliasacchi, M. Schroder, A. Tkach, S. Bouaziz, M. Botsch, M. Pauly, Robust articulated-icp for real-time hand tracking, Computer Graphics Forum 34, 2015.[6] Qian, X. Sun, Y. Wei, X. Tang, J. Sun, Realtime and robust hand tracking from depth, in: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.[7] Tomasi, Petrov, Sastry, 3d tracking = classification + interpolation, in: Proceedings Ninth IEEE International Conference on Computer Vision 2 (2003) 1441-1448.[8] Sharp, C. Keskin, D. Robertson, J. Taylor, J. Shotton, D. Kim, C. Rhemann, I. Leichter, A. Vinnikov, Y. Wei, et al., Accurate, robust, and flexible real-time hand tracking, in: Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems, 2015, pp. 3633-3642.[9] Sridhar, F. Mueller, A. Oulasvirta, C. Theobalt, Fast and robust hand tracking using detection-guided optimization, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.[10] Oikonomidis, N. Kyriazis, A.A. Argyros, Tracking the articulated motion of two strongly interacting hands, in: 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012, pp. 1862-1869.[11] Melax, L. Keselman, S. Orsten, Dynamics based 3d skeletal hand tracking, CoRR abs/1705.07640, 2017.[12] Wang, S. Paris, J. Popovic, 6d hands: Markerless hand tracking for computer aided design, 2011, pp. 549-558.
 https://doi.org/10.1145/2047196.2047269.[13]Tang, T. Yu, T. Kim, Real-time articulated hand pose estimation using semi-supervised transductive regression forests, in: 2013 IEEE International Conference on Computer Vision, 2013, pp. 3224-3231.[14] Oberweger, P. Wohlhart, V. Lepetit, Generalized feedback loop for joint hand-object pose estimation, 2019, CoRR abs/1903.10883. URL http://arxiv.org/abs/1903.10883.[15] Malik, A. Elhayek, F. Nunnari, K. Varanasi, K. Tamaddon, A. Heloir,´ D. Stricker, Deephps: End-to-end estimation of 3d hand pose and shape by learning from synthetic depth, 2018, pp. 110-119. https://doi.org/10.1109/3DV.2018.00023.[16] A. Mohammed, J.L.M. Islam, A deep learning-based end-to-end composite system for hand detection and gesture recognition, Sensors 19 (2019) 5282. https://doi.org/10.3390/s19235282.

Clinical Implementation and Initial Experience of Real-Time Motion Tracking With Jaws and Multileaf Collimator During Helical Tomotherapy Delivery

PurposeThis work reports the clinical implementation of a real-time motion tracking and correction system using dynamic multileaf collimator and jaws during helical tomotherapy delivery (Synchrony on Radixact; Accuray, Inc). Methods and MaterialsThe first clinical Synchrony on Radixact system was recently installed and tested at our institution. Various clinical workflows, including fiducial implantation, computed tomography simulation, treatment planning, delivery quality assurance, treatment simulation, and delivery, for both fiducial-free and fiducial-based motion tracking methods were developed. Treatment planning and delivery data from initial patients, including dosimetric benefits, real-time target detection, model building, motion tracking accuracy, delivery smoothness, and extra dose from real-time radiographic imaging, were analyzed. ResultsThe Synchrony on Radixact system was tested to be within its performance specifications and has been used to treat 10 lung (fiducial-free) and 5 prostate (fiducial-based) patients with cancer so far in our clinic. The success of these treatments, especially for fiducial-free tracking, depends on multiple factors, including careful selection of the patient, appropriate setting of system parameters, appropriate positioning of the patient and skin markers, and use of treatment simulation. For the lung tumor cases, difficulties in model building, due primarily to the changes of target detectability or respiration patterns, were observed, which led to important system upgrades, including the addition of a treatment delivery simulation capability. Motion tracking metrics for all treated patients were within specifications, for example, (1) delivery quality assurance passing rates >95%; (2) extra dose from radiograph <0.5% of the prescription dose; and (3) average Potential Diff, measured Δ, and Rigid Body were within 6.5, 2.9, and 3.9 mm, respectively. ConclusionsPractical workflows for the use of the first clinical motion tracking and correction system in helical tomotherapy delivery have been developed, and the system has now been successfully implemented in our clinic for treating patients with lung and prostate cancer.

MultEYE: Monitoring System for Real-Time Vehicle Detection, Tracking and Speed Estimation from UAV Imagery on Edge-Computing Platforms

We present MultEYE, a traffic monitoring system that can detect, track, and estimate the velocity of vehicles in a sequence of aerial images. The presented solution has been optimized to execute these tasks in real-time on an embedded computer installed on an Unmanned Aerial Vehicle (UAV). In order to overcome the limitation of existing object detection architectures related to accuracy and computational overhead, a multi-task learning methodology was employed by adding a segmentation head to an object detector backbone resulting in the MultEYE object detection architecture. On a custom dataset, it achieved 4.8% higher mean Average Precision (mAP) score, while being 91.4% faster than the state-of-the-art model and while being able to generalize to different real-world traffic scenes. Dedicated object tracking and speed estimation algorithms have been then optimized to track reliably objects from an UAV with limited computational effort. Different strategies to combine object detection, tracking, and speed estimation are discussed, too. From our experiments, the optimized detector runs at an average frame-rate of up to 29 frames per second (FPS) on frame resolution 512 × 320 on a Nvidia Xavier NX board, while the optimally combined detector, tracker and speed estimator pipeline achieves speeds of up to 33 FPS on an image of resolution 3072 × 1728. To our knowledge, the MultEYE system is one of the first traffic monitoring systems that was specifically designed and optimized for an UAV platform under real-world constraints.

Real-Time Multiple Object Visual Tracking for Embedded GPU Systems

Real-time visual object tracking provides every object of interest with a unique identity and a trajectory across video frames. This is a fundamental task of many video analytics applications, such as traffic monitoring or video surveillance in general. The development of real-time multiple object tracking systems on low-power edge devices as IoT nodes, without compromising accuracy, is a challenge due to the limited computing capacity of said devices. This might rule out the best in-class computer vision solutions, which, nowadays, are based on deep learning, and thus, they are very hardware demanding. This article meets this challenge with a multiple object detection and tracking system that employs cutting-edge deep learning architectures on an embedded GPU while operating in real time. For this purpose, a system has been designed that extends a joint architecture of tracking and detection by adding a module comprised of appearance-based and movement-based trackers that allow to maintain the identity of the objects of interest for longer periods of time while alleviating the burden of the detector. Our system is mapped onto an embedded GPU platform, cutting down power consumption significantly with respect to a server GPU. Tracking performance metrics show a 51.1% in multiple object tracking accuracy (MOTA) on the MOT16 data set. This, in conjunction with a real-time processing speed of 25.2 FPS for up to 45 simultaneous objects and low-power consumption of 15 W, make our system an ideal solution for a wide range of video analytics applications.

Smart surveillance system for real-time multi-person multi-camera tracking at the edge

In this work, we have presented an end-to-end multi-person multi-camera tracking (MPMCT) surveillance system and implemented it on edge analytics platform for real-time performance. The proposed MPMCT framework is both privacy-aware and scalable supporting a processing pipeline on the edge consisting of person detection, tracking and robust person re-identification. A realistic and large dataset has been created to train and evaluate the surveillance system that has been employed to track people inside the institute campus throughout the entire day. Appropriate deep-learning algorithms and real-time implementation strategies have been employed to realize the MPMCT system on NVIDIA Jetson TX2 embedded platform with real-time performance. The proposed system has an IDF1 score of 90.97 on our dataset and outperforms the current state-of-the-art real-time algorithms. The performance up to 30 FPS is achieved for the person detection algorithm, whereas an average latency of 90 ms is achieved for the re-identification algorithm.

Understanding the influence of safety climate and productivity pressure on non-helmet use behavior at construction sites: a case study

PurposeNeglecting to wear a safety helmet can result in serious injuries at construction sites, but the cause of such unsafe behavior has not been fully understood. Therefore, the purpose of this paper is to provide a means of systematically understanding on the causes of non-helmet use behaviors at construction sites.Design/methodology/approachThis paper utilizes the system dynamics (SD) modeling to portray the construction system works at project, management and individual levels to understand the relative importance of safety climate and productivity pressures. A real-time helmet use behavior tracking system (the Eye on Project (EOP)) is developed to provide an objective record of helmet use practices. Using the data collected from the EOP, the proposed SD model can be calibrated to simulate the influence of safety climate and productivity pressures on the non-helmet use behaviors of construction workers.FindingsThe data collected from 91 responses through the questionnaire survey were utilized to develop the SD model, which consists of two balancing loops and two reinforced loops. The mean absolute percentage error is further used to evaluate the model. The results show that a positive safety climate significantly reduced the rate of non-helmet use behavior.Originality/valueThis study divided the primary contributors of non-helmet use behavior into three levels for the SD model development. The SD model can be used to develop policies for mitigating helmet misuse, which in turn improves the safety performance of construction sites.

Exploring the lengthiest ambulatory breast surgery clinic appointments: is the patient the problem?

Prolonged outpatient clinic appointments can disrupt schedules, impacting patients and providers. We sought to define features of the longest ambulatory appointments in a breast surgery clinic, and to ascertain whether patients attending these appointments consistently have protracted appointments. A single-institution retrospective cohort study was conducted of breast surgery clinic patients, January 2017 to May 2019, and the longest 1% of appointments identified using a real-time patient tracking system. A primary chart review was performed, and data abstracted. Other appointments attended by these patients were identified, and the ratio of appointments >75th percentile duration (protracted appointments) to the total appointments during the study period was calculated, enabling comparison for patients with consistently protracted (ratio >50%) vs. sporadically protracted appointments (≤50%). Descriptive analysis was performed, and results reported as medians with inter-quartile ranges. A total of 15,265 clinic appointments were identified, and the longest 148 (exceeding 244 minutes) analyzed. Median appointment length was 264 minutes (inter-quartile range: 253-290). 70% were new patient appointments, and 54% of patients underwent a test/investigation that day. A minority were obese (39%), smokers (41%), diagnosed with a psychiatric comorbidity (34%), had a genetic cancer syndrome (22%), or received unexpected news at their appointment (16%). Of 118 patients with multiple appointments, 26% had consistently protracted appointments and 74% sporadically protracted appointments. The lengthiest appointments are usually newly diagnosed cancer patients. Only a minority of patients have consistently protracted appointments, implying that a patient's previously prolonged appointment may not predict future long appointments.

Study on robust aerial docking mechanism with deep learning based drogue detection and docking

This paper proposes a simple and a robust bistable docking system with a deep learning based real-time drogue detection and tracking system for Unmanned Aircraft Systems (UAS) for mid-air autonomous aerial docking. Secure aerial docking mechanisms between the leader and follower aerial vehicles with effective drogue detection and tracking strategies are fundamental challenges during the air-to-air docking phase of autonomous aerial docking. To confront those issues, this paper not only presents the design of a bistable-based aerial docking mechanism, but also proposes effective deep learning based real-time drogue detection using a convolutional neural network (CNN) and real-time tracking algorithm using a point cloud algorithm. To ensure novelty and robustness for the aerial docking mechanism, a foldable bistable gripper-type mechanism is designed to increase the grasping performance with simplicity and adaptability. The proposed gripper acts as a drogue by itself to grasp a probe which is attached to the follower aerial vehicle. To employ an effective drogue detection method, the deep learning based real-time object detection algorithm, YOLOv3, is used to implement the drogue detection system. The proposed new probe-and-drogue type bistable docking system has the advantages of being simple and robust. The deep learning based real-time drogue detection method increases the detection rate. Moreover, the real-time tracking algorithm with a depth camera system does not require a GPS/INS system and many other sensors to follow the drogue movement in the air.

Evaluating Sustainable Last-Mile Delivery (LMD) in B2C E-Commerce Using Two-Stage Fuzzy MCDM Approach: A Case Study From Vietnam

As the world attempts to control the spread of COVID-19 and adapt to shifting limitations, routines, and best practices, online ordering is an absolute necessity. With e-commerce activities surging, businesses in the last-mile delivery (LMD) industry find that their services are needed now more than ever before. Higher expectations of customers for speed, convenience, and sustainability have underlined the importance of reliable last-mile providers. This study aims to evaluate some key LMD companies in Vietnam regarding their sustainability performance. For this evaluation, the present research proposes a fuzzy multi-criteria decision-making (FMCDM) based framework combining the fuzzy analytic hierarchy process (FAHP) and the fuzzy weighted aggregated sum product assessment (FWASPAS), and triangular fuzzy numbers are applied to express the linguistic evaluation statements of experts. FAHP was utilized for the determination of criteria weights, then based on the most impactful criteria, FWASPAS was used to prioritize the companies. Delivery time, order fulfillment, decarbonization, convenience of payment, and real-time tracking systems have been ranked as the most impactful criteria in the LMD sector. The robustness of the proposed model was tested by conducting a sensitivity analysis. The results reach common rankings, in which Grab Express is the best performing company in the LMD landscape. The obtained results can be utilized as a guideline for the LMD managers and decision-makers to take in-depth consideration on their businesses under broader aspects to win customers and compete with other competitors.

A Traceable and Reliable Electronic Supply Chain System Based on Blockchain Technology

Electronic supply chain (ESC) is a network among the parties of a supply chain system, such as manufacturers, suppliers, and retailers. It recodes all the processes involved in the distribution of specific products until transported to final customers. Blockchain (BC) technology is a decentralized network that records all the transactions in real-time and is used in many areas such as cryptocurrency. In this paper, we work on an ESC system that records all the transactions based on BC technology using a drug supply chain system as a case study. The recording of the transactions consists of three main stages. First, all the parties of the ESC system are represented in the BC network as clients with unique identities. Second, all the information related to a specific drug is recorded inside the transaction and each transaction has its own signature. Finally, all the transactions of the drug from the manufacture to the patient are recorded inside a block with a unique identity for each block. These steps inside the BC are performed based on security cryptography mechanisms, such as rivest-shamir-adleman (RSA) and secure hash algorithm SHA. The results illustrate that the proposed approach protects the drugs from counterfeiting, ensures the reliability, and provides a real-time tracking system for the transactions that have occurred among ESC parties.

Characterization of swine behavior and production using measurements collected via indoor positioning system

Legislative and market initiatives are requiring that gestating sows move from individual housing to group settings. Little information is known about coping of individual sows in these more socially complex environments and thus the impact of different behaviors on sow reproductive success was investigated. The movements of 70 sows during periods of reintroduction into large pen gestational housing following insemination was measured using Smartbow indoor positioning technology (Smartbow, Smartbow GmbH, Weibern, Austria) that tracked animal location and accelerations. Principle component analysis (PCA) was used to establish composite variables characterizing each animal’s behavioral response to social reintroduction and revealed the presence of two new variables accounting for over 60 % of the variance in behaviors: one pertaining to total movement and the other pertaining to social dominance/rapid movements. Component scores of total movement predicted measures of reproductive success whereas social dominance/rapid movements predicted piglet birth weight. These findings suggest that differences in behavioral variables as measured by Smartbow’s automated, non-invasive, real time tracking system are correlated with productivity of sows housing in socially complex settings.

A real-time system using deep learning to detect and track ureteral orifices during urinary endoscopy

Background and objectiveTo automatically identify and locate various types and states of the ureteral orifice (UO) in real endoscopy scenarios, we developed and verified a real-time computer-aided UO detection and tracking system using an improved real-time deep convolutional neural network and a robust tracking algorithm. MethodsThe single-shot multibox detector (SSD) was refined to perform the detection task. We trained both the SSD and Refined-SSD using 447 resectoscopy images with UO and tested them on 818 ureteroscopy images. We also evaluated the detection performance on endoscopy video frames, which comprised 892 resectoscopy frames and 1366 ureteroscopy frames. UOs could not be identified with certainty because sometimes they appeared on the screen in a closed state of peristaltic contraction. To mitigate this problem and mimic the inspection behavior of urologists, we integrated the SSD and Refined-SSD with five different tracking algorithms. ResultsWhen tested on 818 ureteroscopy images, our proposed UO detection network, Refined-SSD, achieved an accuracy of 0.902. In the video sequence analysis, our detection model yielded test sensitivities of 0.840 and 0.922 on resectoscopy and ureteroscopy video frames, respectively. In addition, by testing Refined-SSD on 1366 ureteroscopy video frames, the sensitivity achieved a value of 0.922, and a lowest false positive per image of 0.049 was obtained. For UO tracking performance, our proposed UO detection and tracking system (Refined-SSD integrated with CSRT) performed the best overall. At an overlap threshold of 0.5, the success rate of our proposed UO detection and tracking system was greater than 0.95 on 17 resectoscopy video clips and achieved nearly 0.95 on 40 ureteroscopy video clips. ConclusionsWe developed a deep learning system that could be used for detecting and tracking UOs in endoscopy scenarios in real time. This system can simultaneously maintain high accuracy. This approach has great potential to serve as an excellent learning and feedback system for trainees and new urologists in clinical settings.

A Real-time Face Tracking and Recognition System Based on SeetaFace

A real-time face tracking and recognition system is constructed based on Seetaface, and it is proposed to use Gamma correction to reduce the impact of illumination changes on the detection and recognition results. First, the system has face detection function, then by using OpenCV to get the image in front of the camera, the system completes the function of real-time face tracking, users can also upload local images to make face comparison. If a stranger’s face is detected, the system can collect information and train it. The system achieves multiple face tracking as well as recognition. Through the analysis and evaluation on public datasets. The improved face tracking and recognition system has a satisfactory accuracy and performance.

First experimental investigation of simultaneously tracking two independently moving targets on an MRI-linac using real-time MRI and MLC tracking.

High quality radiotherapy is challenging in cases where multiple targets with independent motion are simultaneously treated. A real-time tumor tracking system that can simultaneously account for the motion of two targets was developed and characterized. The multitarget tracking system was implemented on a magnetic resonance imaging (MRI)-linac and utilized multi-leaf collimator (MLC) tracking to adapt the radiation beam to phantom targets reproducing motion with prostate and lung motion traces. Multitarget tracking consisted of three stages: (a) pretreatment aperture segmentation where the treatment aperture was divided into segments corresponding to each target, (b) MR imaging where the positions of the two targets were localized, and (c) MLC tracking where an updated treatment aperture was calculated. Electronic portal images (EPID) acquired during irradiation were analyzed to characterize geometric uncertainty and tracking latency. Multitarget MLC tracking effectively accounted for the motion of both targets during treatment. The root-mean-square error between the centers of the targets and the centers of the corresponding MLC leaves were reduced from 5.5mm without tracking to 2.7mm with tracking for lung motion traces and reduced from 4.2 to 1.4mm for prostate motion traces. The end-to-end latency of tracking was measured to be 328±44ms. We have demonstrated the first experimental implementation of MLC tracking for multiple targets having independent motion. This technology takes advantage of the imaging capabilities of MRI-linacs and would allow treatment margins to be reduced in cases where multiple targets are simultaneously treated.

Going “ITV-free”: First-in-clinic Experience With a Real Time Motion Tracking Technique for Lung SBRT Delivery

Respiratory motion often necessitates volume expansions to account for tumor range of motion. Larger expansions include added normal tissue. There are several methods of reducing respiratory (i.e. ITV/iGTV) expansions including breath-hold, compression, and respiratory-gating; each has unique challenges and can prolong treatment (tx) delivery. Within our institution, we employed a novel, real-time motion synchronization tracking and correction (RMSTC) system for helical tomotherapy delivery for stereotactic body radiation therapy (SBRT) lung tx. We sought to assess accuracy, safety, clinical feasibility and to establish appropriate patient (pt) selection. The first commercially-available RMSTC system for tomotherapy tx was installed in our clinic. Commissioning was within specifications; delivery accuracy of PTV and organs-at-risk doses in 10 test plans were within 1% on respiratory phantoms. Initial clinical pt selection (n = 5) included pts with small (<3cm), non-central lung tumors, not directly abutting adjacent structures, and with motion <4cm. All pts had standard SBRT (ITV+PTV expansions) and RMSTC SBRT plans (no ITV, PTV expansion only) created. Prior to tx, we confirmed tumors had HU >460 relative to surrounding lung. After tx, dose was reconstructed based on MVCT to assess accuracy. Workflows were implemented to ensure standardization and safety. External sensors (LEDs) were used to help model respiratory motion. RMSTC was done using kV radiographs perpendicular to the tx beam to instruct jaw sweeping and MLC shifting to account for target motion; radiographic dose was <1 cGy for a typical RMSTC delivery. Delivery time with RMSTC was similar to standard delivery without pauses which occurred if additional model building was required (Range:0-16). Compared to standard plans (n = 4), PTV of RMSTC plans were, on average, 28.8%±3.8 smaller and V20 was reduced by 20.0%±10. Reconstructed doses showed planned doses were correctly delivered. In the 1st three pts, RMSTC tx was ultimately aborted for two due to difficulty detecting the target on radiographs (n = 1 artifact from stent, n = 1 abrupt change of motion pattern). Based on these findings, additional modelling functionality was added. Afterward, one additional pt was treated with less pauses (Pre-update:8±6.2, Post:1.6±1.5). Another pt was attempted, but difficulty identifying the lesion near the diaphragm led to tx being aborted and gating plan being initiated. Among those with follow up (n = 4, mean:4 mo, R:1-6 mo), no pts displayed any grade 2 or higher toxicities. We report the first RMSTC for helical tomotherapy delivery in pts. Accuracy and safety of tx delivery was confirmed. Early experience has informed workflow. Appropriate pt selection is evolving, further evaluation is needed for lesions near the diaphragm. Additional study and follow up is warranted and planned.

Does Active Coaching Reduce Overall Treatment Duration For Mask-Based, Frameless Gamma Knife Stereotactic Radiosurgery?

Frameless stereotactic radiosurgery (SRS) has become a preferred supplement to frame-based Gamma Knife SRS due to its non-invasive nature and allowance for fractionation. To account for intra-fraction motion, radiation is automatically gated whenever a real-time tracking system detects patient displacement larger than a user-specified threshold. Treatment delivery pauses and a cone-beam CT is acquired to verify patient position if the excess displacement persists. This gating technique, although effective with high accuracy, is sensitive to patient’s involuntary motions. Overall treatment duration is increased with each pause, and this can result in a prolonged treatment duration. The purpose of this study is to investigate whether active coaching during frameless SRS can reduce overall treatment duration. Patients treated at a single institution with frameless SRS on a Gamma Knife Icon from 2017 to 2020 were retrospectively identified. Beginning in January 2019, all patients treated with frameless SRS were actively coached: Prior to treatment, each patient was instructed on how to adjust his/her head position following prompts from staff. During treatment, the patient motion was closely monitored. Once a large displacement was observed, the patient was instructed to gently tuck/untuck or tilt his/her chin to reduce the displacement. Patient characteristics and treatment plans were compared between the cohorts of patients treated with and without active coaching. Linear regressions between the planned and overall treatment duration were performed on either cohort. ANOVA and Wilcoxon tests were used with a p-value less than 0.05 considered as significant. A total of 45 patients and 107 frameless SRS treatment sessions were identified, 27 (60.0%) of which underwent 51 (47.7%) frameless SRS treatment sessions with active coaching. There was no significant difference in patient characteristics or treatment plans between two cohorts (p<0.001). Patients treated with active coaching underwent significantly fewer CBCTs during sessions (Median: 1 vs. 2; p<0.01). The median planned and overall treatment durations were 27.1 min (range: 12.2-110.9) and 41.3 min (range: 13.7-202.2) for the non-coached cohort, and 30.9 min (range: 10.6-89.5) and 41.6 min (range: 10.6-144.4) for the coached cohort. Linear regressions analysis revealed that the overall treatment duration was 1.29 times longer than the planned beam-on duration with active coaching (R2 = 0.95) and 1.60 times without (R2 = 0.75). The difference between the slopes was statistically significant (p<0.001), which indicated a significant reduction in the overall treatment duration with active coaching. Our results suggested that active coaching was associated with significant reductions of overall treatment duration. This simple intervention can be clinically implemented to improve clinical efficiency and possibly patient comfort during frameless Gamma Knife SRS.

The IMPLEMENTATION OF TRACKING SYSTEM IN THE REAL TIME OF ANDROID FOR SENDING PERSONEL COORDINATION BASED ON MQTT.

Abstract: In the world of technology that is increasing, then as humans we will not be separated from the process improvement that occurs. From year to year, it is certain that this increase will certainly. Increasingly rapidly occurring in communication technology. Communication technology has also penetrated the military world, especially in MQTT-based communications. In this research, MQTT-based technology is applied to implement real time tracking system on android. This system is used to send the longitude and latitude coordinates of the personnel so that these points can be known directly via android. From this pure experimental research method, the coordinate point data will continue to be monitored and the existence can be known continuously. This system is designed on a VPS server or Virtual Private Server, so that all devices even though none of the networks can communicate with each other as long as they have access rights for application user.