Development and evaluation of ultrasound image tracking technology based on Mask R-CNN applied to respiratory motion compensation system.

Background: For respiration induced tumor displacement during a radiation therapy, a common method to prevent the extra radiation is image-guided radiation therapy. Moreover, mask region-based convolutional neural networks (Mask R-CNN) is one of the state-of-the-art (SOTA) object detection frameworks capable of conducting object classification, localization, and pixel-level instance segmentation. Methods: We developed a novel ultrasound image tracking technology based on Mask R-CNN for stable tracking of the detected diaphragm motion and applied to the respiratory motion compensation system (RMCS). For training Mask R-CNN, 1800 ultrasonic images of the human diaphragm are collected. Subsequently, an ultrasonic image tracking algorithm was developed to compute the mean pixel coordinates of the diaphragm detected by Mask R-CNN. These calculated coordinates are then utilized by the RMCS for compensation purposes. The tracking similarity verification experiment of mask ultrasonic imaging tracking algorithm (M-UITA) is performed. Results: The correlation between the input signal and the signal tracked by M-UITA was evaluated during the experiment. The average discrete Fréchet distance was less than 4 mm. Subsequently, a respiratory displacement compensation experiment was conducted. The proposed method was compared to UITA, and the compensation rates of three different respiratory signals were calculated and compared. The experimental results showed that the proposed method achieved a 6.22% improvement in compensation rate compared to UITA. Conclusions: This study introduces a novel method called M-UITA, which offers high tracking precision and excellent stability for monitoring diaphragm movement. Additionally, it eliminates the need for manual parameter adjustments during operation, which is an added advantage.

The feasibility of an approximate irregular field dose distribution simulation program applied to a respiratory motion compensation system.

PURPOSE: This study optimized our previously proposed simulation program for the approximate irregular field dose distribution (SPAD) and applied it to a respiratory motion compensation system (RMCS) and respiratory motion simulation system (RMSS). The main purpose was to rapidly analyze the two-dimensional dose distribution and evaluate the compensation effect of the RMCS during radiotherapy. METHODS: This study modified the SPAD to improve the rapid analysis of the dose distribution. In the experimental setup, four different respiratory signal patterns were input to the RMSS for actuation, and an ultrasound image tracking algorithm was used to capture the real-time respiratory displacement, which was input to the RMCS for actuation. A linear accelerator simultaneously irradiated the EBT3 film. The gamma passing rate was used to verify the dose similarity between the EBT3 film and the SPAD, and conformity index (CI) and compensation rate (CR) were used to quantify the compensation effect. RESULTS: The Gamma passing rates were 70.48-81.39% (2%/2mm) and 88.23-96.23% (5%/3mm) for various collimator opening patterns. However, the passing rates of the SPAD and EBT3 film ranged from 61.85% to 99.85% at each treatment time point. Under the four different respiratory signal patterns, CR ranged between 21% and 75%. After compensation, the CI for 85%, 90%, and 95% isodose constraints were 0.78, 0.57, and 0.12, respectively. CONCLUSIONS: This study has demonstrated that the dose change during each stage of the treatment process can be analyzed rapidly using the improved SPAD. After compensation, applying the RMCS can reduce the treatment errors caused by respiratory movements.

Fast Fourier transform combined with phase leading compensator for respiratory motion compensation system.

BACKGROUND: The reduction of the delaying effect in the respiratory motion compensation system (RMCS) is still impossible to completely correct the respiratory waveform of the human body due to each patient has a unique respiratory rate. In order to further improve the effectiveness of radiation therapy, this study evaluates our previously developed RMCS and uses the fast Fourier transform (FFT) algorithm combined with the phase lead compensator (PLC) to further improve the compensation rate (CR) of different respiratory frequencies and patterns of patients. METHODS: In this study, an algorithm of FFT automatic frequency detection was developed by using LabVIEW software, uisng FFT combined with PLC and RMCS to compensate the system delay time. Respiratory motion compensation experiments were performed using pre-recorded respiratory signals of 25 patients. During the experiment, the respiratory motion simulation system (RMSS) was placed on the RMCS, and the pre-recorded patient breathing signals were sent to the RMCS by using our previously developed ultrasound image tracking algorithm (UITA). The tracking error of the RMCS is obtained by comparing the encoder signals of the RMSS and RMCS. The compensation effect is verified by root mean squared error (RMSE) and system CR. RESULTS: The experimental results show that the patient's respiratory patterns compensated by the RMCS after using the proposed FFT combined with PLC control method, the RMSE is between 1.50-5.71 and 3.15-8.31 mm in the right-left (RL) and superior-inferior (SI) directions, respectively. CR is between 72.86-93.25% and 62.3-83.81% in RL and SI, respectively. CONCLUSIONS: This study used FFT combined with PLC control method to apply to RMCS, and used UITA for respiratory motion compensation. Under the automatic frequency detection, the best dominant frequency of the human respiratory waveform can be determinated. In radiotherapy, it can be used to compensate the tumor movement caused by respiratory motion and reduce the radiation damage and side effects of normal tissues nearby the tumor.

Tumor motion tracking based on a four-dimensional computed tomography respiratory motion model driven by an ultrasound tracking technique.

BACKGROUND: An ultrasound image tracking algorithm (UITA) was combined with four-dimensional computed tomography (4DCT) to create a real-time tumor motion-conversion model. The real-time position of a lung tumor phantom based on the real-time diaphragm motion trajectories detected by ultrasound imaging in the superior-inferior (SI) and medial-lateral (ML) directions were obtained. METHODS: Three different tumor motion-conversion models were created using a respiratory motion simulation system (RMSS) combined with 4DCT. The tumor tracking error was verified using cone-beam computed tomography (CBCT). The tumor motion-conversion model was produced by using the UITA to monitor the motion trajectories of the diaphragm phantom in the SI direction, and using 4DCT to monitor the motion trajectories of the tumor phantom in the SI and ML directions over the same time period, to obtain parameters for the motion-conversion model such as the tumor center position and the amplitude and phase ratios. RESULTS: The tumor movement was monitored for 90 s using CBCT to determine the real motion trajectories of the tumor phantom and using ultrasound imaging to simultaneously record the diaphragm movement. The absolute error of the motion trajectories of the real and estimated tumor varied between 0.5 and 2.1 mm in the two directions. CONCLUSIONS: This study has demonstrated the feasibility of using ultrasound imaging to track diaphragmatic motion combined with a 4DCT tumor motion-conversion model to track tumor motion in the SI and ML directions. The proposed method makes tracking a lung tumor feasible in real time, including under different breathing conditions.

Simulating the approximate irregular field dose distribution in radiotherapy using an ultrasound tracking technique.

PURPOSE: This study used an ultrasound image tracking algorithm (UITA) in combination with a proposed simulation program for the approximate irregular field dose distribution (SPAD) to assess the feasibility of performing dose distribution simulations for two-dimensional radiotherapy. METHODS: This study created five different types of multileaf collimator openings, and applied a SPAD to analyze the matrix position parameters for each regular field to generate a static program-simulation dose distribution map (PDDM), whose similarity was then compared with a static radiochromic film experimental-measurement dose distribution map (EDDM). A two-dimensional respiration motion simulation system (RMSS) was used to reproduce the respiration motion, and the UITA was used to capture the respiration signals. Respiration signals were input to the SPAD to generate two dynamic PDDMs, which were compared for similarity with the dynamic EDDM. RESULTS: In order to verify the dose distribution between different dose measurement techniques, the gamma passing rate with 2%/2 mm criterion was used for the EDDM and PDDM, the passing rates were between 94.31% and 99.71% in the static field analyses, and between 84.45% and 96.09% for simulations with the UITA signal input and between 89.35% and 97.78% for simulations with the original signal input in the dynamic field analyses. CONCLUSIONS: Static and dynamic dose distribution maps can be simulated based on the proposed matrix position parameters of various fields and by using the UITA to track respiration signals during radiation therapy. The present findings indicate that it is possible to develop a reusable and time-saving dose distribution measurement tool.

Prognostic and predictive factors for clinical and radiographic responses in patients with painful bone metastasis treated with magnetic resonance-guided focused ultrasound surgery.

Background: Magnetic resonance-guided focused ultrasound surgery (MRgFUS) is an alternative local therapy for patients with painful bone metastasis. However, little is known about the prognostic and predictive factors of MRgFUS in treating bone metastasis. Materials and methods: This retrospective study analyzed the performance status, treated site, pretreatment pain score, pretreatment tumor volume and lesion coverage volume factor (CVF) of 31 patients who underwent MRgFUS. A numerical rating scale for pain was used at the same time to assess the clinical response. Radiographic responses were evaluated using a modified version of The University of Texas MD Anderson Cancer Center criteria and reference to the MR imaging or computed tomography scans obtained 3 months after treatment. Univariate and multivariate logistic regression analyses were conducted to examine the effect of variables on clinical and radiographic responses. Results: The overall clinical response rate was 83.9% and radiographic response rate was 67.7%. Multivariate logistic regression analysis revealed that the better pretreatment Karnofsky performance status (KPS) (odds ratio: 1.220, 95% confidence interval (CI): 1.033-1.440; p = 0.019) was significantly associated with a more positive clinical response, and that the lesion CVF (odds ratio: 1.183, 95% CI: 1.029-1.183; p = 0.0055) was an independent prognostic factor for radiographic responses. The radiographic response of patients with lesion CVF ≥70% and CVF <70% were 91.7% and 52.6%, respectively (p = 0.0235). Conclusion: The pretreatment KPS was an independent prognostic factor for clinical responses, and lesion CVF was an independent prognostic factor for radiographic responses.

Adaptive control of phase leading compensator parameters applied to respiratory motion compensation system.

PURPOSE: This study evaluates the feasibility of our previously developed Respiratory Motion Compensation System (RMCS) combined with the Phase Lead Compensator (PLC) to eliminate system delays during the compensation of respiration-induced tumor motion. The study objective is to improve the compensation effect of RMCS and the efficay of radiation therapy to reduce its side effects to the patients. MATERIAL AND METHODS: In this study, LabVIEW was used to develop the proposed software for calculating real-time adaptive control parameters, combined with PLC and RMCS for the compensation of total system delay time. Experiments of respiratory motion compensation were performed using 6 pre-recorded human respiration patterns and 7 sets of different sine waves. During the experiments, a respiratory simulation device, Respiratory Motion Simulation System (RMSS), was placed on the RMCS, and the detected target motion signals by the Ultrasound Image Tracking Algorithm (UITA) were transmitted to the RMCS, and the compensation of respiration induced motion was started. Finally, the tracking error of the system is obtained by comparing the encoder signals bwtween RMSS and RMCS. The compensation efficacy is verified by the root mean squared error (RMSE) and the system compensation rate (CR). RESULTS: The experimental results show that the calcuated CR with the simulated respiration patterns is between 42.85% ∼3.53% and 33.76% ∼2.62% in the Right-Left (RL) and Superior-Inferior (SI), respectively, after the RMCS compensation of using the adaptive control parameters in PLC. For the compensation results of human respiration patterns, the CR is between 58.95% ∼8.56% and 62.87% ∼9.05% in RL and SI, respectively. CONCLUSIONS: During the respiratory motion compensation, the influence of the delay time of the entire system (RMCS+RMSS+UITA) on the compensation effect was improved by adding an adaptive control PLC, which reduces compensation error and helps improve efficacy of radiation therapy.

Experimental verification of a two-dimensional respiratory motion compensation system with ultrasound tracking technique in radiation therapy.

This study proposed respiratory motion compensation system (RMCS) combined with an ultrasound image tracking algorithm (UITA) to compensate for respiration-induced tumor motion during radiotherapy, and to address the problem of inaccurate radiation dose delivery caused by respiratory movement. This study used an ultrasound imaging system to monitor respiratory movements combined with the proposed UITA and RMCS for tracking and compensation of the respiratory motion. Respiratory motion compensation was performed using prerecorded human respiratory motion signals and also sinusoidal signals. A linear accelerator was used to deliver radiation doses to GAFchromic EBT3 dosimetry film, and the conformity index (CI), root-mean-square error, compensation rate (CR), and planning target volume (PTV) were used to evaluate the tracking and compensation performance of the proposed system. Human respiratory pattern signals were captured using the UITA and compensated by the RMCS, which yielded CR values of 34-78%. In addition, the maximum coronal area of the PTV ranged from 85.53 mm2 to 351.11 mm2 (uncompensated), which reduced to from 17.72 mm2 to 66.17 mm2 after compensation, with an area reduction ratio of up to 90%. In real-time monitoring of the respiration compensation state, the CI values for 85% and 90% isodose areas increased to 0.7 and 0.68, respectively. The proposed UITA and RMCS can reduce the movement of the tracked target relative to the LINAC in radiation therapy, thereby reducing the required size of the PTV margin and increasing the effect of the radiation dose received by the treatment target.

Evaluation of Clinical Application and Dosimetric Comparison of Treatment Plans of Gamma Knife and CyberKnife in Treating Arteriovenous Malformations.

PURPOSE: To analyze and compare the characteristics of dose distributions for Leksell Gamma Knife Perfexion (LGK-PFX) and CyberKnife (CK) in treating arteriovenous malformations (AVMs). SUBJECTS AND METHODS: Twenty-four patients with AVMs who received CK radiosurgery at a prescribed dose (PD) of 16-25 Gy in a single fraction were selected. A LGK-PFX treatment plan with the same PD was designed for each patient. Dosimetric values for both systems were compared with respect to the conformity index (CI); selectivity index (SI); gradient index (GI) of 75, 50, and 25% of the PD; heterogeneity index; volume of the brain tissue covered by doses of 10 and 12 Gy; maximum dose delivered to the brainstem; and beam-on time. RESULTS: The CIs of LGK-PFX and CK were 0.744 ± 0.075 and 0.759 ± 0.071 (p = 0.385), respectively. The SIs of LGK-PFX and CK were 0.764 ± 0.081 and 0.780 ± 0.076 (p = 0.424), respectively. The GI75%, GI50%, and GI25% values of LGK-PFX and CK were 1.028 ± 0.123 and 2.439 ± 0.338 (p < 0.001), 3.169 ± 0.265 and 4.972 ± 0.852 (p < 0.001), and 8.650 ± 0.914 and 14.261 ± 2.476 (p < 0.001), respectively. Volumes of the brain tissue covered by 10 Gy and 12 Gy for LGK-PFX and CK (p < 0.001) exhibited a significant difference. CONCLUSIONS: LGK-PFX and CK exhibited similar dose conformity. LGK-PFX showed superior normal tissue sparing.

Dosimetric and radiobiological comparison of Cyberknife and Tomotherapy in stereotactic body radiotherapy for localized prostate cancer.

BACKGROUND AND PURPOSE: As recent studies have suggested relatively low α/ß for prostate cancer, the interest in hypofractionated stereotactic body radiotherapy (SBRT) for prostate cancer is rising. The aim of this study is to compare dosimetric results of Cyberknife (CK) with Tomotherapy (HT) in SBRT for localized prostate cancer. Furthermore, the radiobiologic consequences of heterogeneous dose distribution are also analyzed. MATERIAL AND METHOD: A total of 12 cases of localized prostate cancer previously treated with SBRT were collected. Treatments had been planned and delivered using CK. Then HT plans were generated for comparison afterwards. The prescribed dose was 37.5Gy in 5 fractions. Dosimetric indices for target volumes and organs at risk (OAR) were compared. For radiobiological evaluation, generalized equivalent uniform dose (gEUD) and normal tissue complication probability (NTCP) were calculated and compared. RESULT: Both CK and HT achieved target coverage while meeting OAR constraints adequately. HT plans resulted in better dose homogeneity (Homogeneity index: 1.04±0.01 vs. 1.21±0.01; p = 0.0022), target coverage (97.74±0.86% vs. 96.56±1.17%; p = 0.0076) and conformity (new vonformity index: 1.16±0.05 vs. 1.21±0.04; p = 0.0096). HT was shown to predict lower late rectal toxicity as compared to CK. Integral dose to body was also significantly lower in HT plans (46.59±6.44 Gy'L vs 57.05±11.68 Gy'L; p = 0.0029). CONCLUSION: Based on physical dosimetry and radiobiologic considerations, HT may have advantages over CK, specifically in rectal sparing which could translate into clinical benefit of decreased late toxicities.

Volumetric intensity-modulated Arc (RapidArc) therapy for primary hepatocellular carcinoma: comparison with intensity-modulated radiotherapy and 3-D conformal radiotherapy.

BACKGROUND: To compare the RapidArc plan for primary hepatocellular carcinoma (HCC) with 3-D conformal radiotherapy (3DCRT) and intensity-modulated radiotherapy (IMRT) plans using dosimetric analysis. METHODS: Nine patients with unresectable HCC were enrolled in this study. Dosimetric values for RapidArc, IMRT, and 3DCRT were calculated for total doses of 45~50.4 Gy using 1.8 Gy/day. The parameters included the conformal index (CI), homogeneity index (HI), and hot spot (V107%) for the planned target volume (PTV) as well as the monitor units (MUs) for plan efficiency, the mean dose (Dmean) for the organs at risk (OAR) and the maximal dose at 1% volume (D1%) for the spinal cord. The percentage of the normal liver volume receiving ≥ 40, > 30, > 20, and > 10 Gy (V40 Gy, V30 Gy, V20 Gy, and V10 Gy) and the normal tissue complication probability (NTCP) were also evaluated to determine liver toxicity. RESULTS: All three methods achieved comparable homogeneity for the PTV. RapidArc achieved significantly better CI and V107% values than IMRT or 3DCRT (p < 0.05). The MUs were significantly lower for RapidArc (323.8 ± 60.7) and 3DCRT (322.3 ± 28.6) than for IMRT (1165.4 ± 170.7) (p < 0.001). IMRT achieved a significantly lower Dmean of the normal liver than did 3DCRT or RapidArc (p = 0.001). 3DCRT had higher V40Gy and V30 Gy values for the normal liver than did RapidArc or IMRT. Although the V10 Gy to the normal liver was higher with RapidArc (75.8 ± 13.1%) than with 3DCRT or IMRT (60.5 ± 10.2% and 57.2 ± 10.0%, respectively; p < 0.01), the NTCP did not differ significantly between RapidArc (4.38 ± 2.69) and IMRT (3.98 ± 3.00) and both were better than 3DCRT (7.57 ± 4.36) (p = 0.02). CONCLUSIONS: RapidArc provided favorable tumor coverage compared with IMRT or 3DCRT, but RapidArc is not superior to IMRT in terms of liver protection. Further studies are needed to establish treatment outcome differences between the three approaches.