Predictive local receptive fields based respiratory motion tracking for motion-adaptive radiotherapy.

Extracranial robotic radiotherapy employs external markers and a correlation model to trace the tumor motion caused by the respiration. The real-time tracking of tumor motion however requires a prediction model to compensate the latencies induced by the software (image data acquisition and processing) and hardware (mechanical and kinematic) limitations of the treatment system. A new prediction algorithm based on local receptive fields extreme learning machines (pLRF-ELM) is proposed for respiratory motion prediction. All the existing respiratory motion prediction methods model the non-stationary respiratory motion traces directly to predict the future values. Unlike these existing methods, the pLRF-ELM performs prediction by modeling the higher-level features obtained by mapping the raw respiratory motion into the random feature space of ELM instead of directly modeling the raw respiratory motion. The developed method is evaluated using the dataset acquired from 31 patients for two horizons in-line with the latencies of treatment systems like CyberKnife. Results showed that pLRF-ELM is superior to that of existing prediction methods. Results further highlight that the abstracted higher-level features are suitable to approximate the nonlinear and non-stationary characteristics of respiratory motion for accurate prediction.

Real-time physiological tremor estimation using recursive singular spectrum analysis.

Physiological hand tremor causes undesirable vibration of hand-held surgical instruments which results in imprecisions and poor surgical outcomes. Existing tremor cancellation algorithms are based on detection of the tremulous component from the whole motion; then adding an anti-phase tremor signal to the whole motion to cancel it out. These techniques are based on adaptive filtering algorithms which need a reference signal that is highly correlated with the actual tremor signal. Hence, such adaptive approaches use a non-linear phase filter to pre-filter the tremor signal either offline or in real-time. However, pre-filtering causes unnecessary delays and non-linear phase distortions as the filter has frequency selective delays. Consequently, the anti-phase tremor signal cannot be generated accurately which results in poor tremor cancellation. In this paper, we present a new technique based on singular spectrum analysis (SSA) and its recursive version, that is, recursive singular spectrum analysis (RSSA). These algorithms decompose the whole motion into dominant voluntary components corresponding to larger eigenvalues and oscillatory tremor components having smaller eigenvalues. By selecting a group of specific decomposed signals based on their eigenvalues and spectral range, both voluntary and tremor signals can be reconstructed accurately. We test the SSA and RSSA algorithms using recorded tremor data from five novice subjects. This new approach shows the tremor signal can be estimated from the whole motion with an accuracy of up to 85% offline. In real-time, tolerating a delay of ≈ 72ms, the tremor signal can be estimated with at least 70% accuracy. This delay is found to be one-tenth of the delay caused by a conventional linear-phase bandpass filter to achieve similar performance in real-time.

Automatic Identification of Systolic Time Intervals in Seismocardiogram.

Continuous and non-invasive monitoring of hemodynamic parameters through unobtrusive wearable sensors can potentially aid in early detection of cardiac abnormalities, and provides a viable solution for long-term follow-up of patients with chronic cardiovascular diseases without disrupting the daily life activities. Electrocardiogram (ECG) and siesmocardiogram (SCG) signals can be readily acquired from light-weight electrodes and accelerometers respectively, which can be employed to derive systolic time intervals (STI). For this purpose, automated and accurate annotation of the relevant peaks in these signals is required, which is challenging due to the inter-subject morphological variability and noise prone nature of SCG signal. In this paper, an approach is proposed to automatically annotate the desired peaks in SCG signal that are related to STI by utilizing the information of peak detected in the sliding template to narrow-down the search for the desired peak in actual SCG signal. Experimental validation of this approach performed in conventional/controlled supine and realistic/challenging seated conditions, containing over 5600 heart beat cycles shows good performance and robustness of the proposed approach in noisy conditions. Automated measurement of STI in wearable configuration can provide a quantified cardiac health index for long-term monitoring of patients, elderly people at risk and health-enthusiasts.

Ensemble framework based real-time respiratory motion prediction for adaptive radiotherapy applications.

Successful treatment of tumors with motion-adaptive radiotherapy requires accurate prediction of respiratory motion, ideally with a prediction horizon larger than the latency in radiotherapy system. Accurate prediction of respiratory motion is however a non-trivial task due to the presence of irregularities and intra-trace variabilities, such as baseline drift and temporal changes in fundamental frequency pattern. In this paper, to enhance the accuracy of the respiratory motion prediction, we propose a stacked regression ensemble framework that integrates heterogeneous respiratory motion prediction algorithms. We further address two crucial issues for developing a successful ensemble framework: (1) selection of appropriate prediction methods to ensemble (level-0 methods) among the best existing prediction methods; and (2) finding a suitable generalization approach that can successfully exploit the relative advantages of the chosen level-0 methods. The efficacy of the developed ensemble framework is assessed with real respiratory motion traces acquired from 31 patients undergoing treatment. Results show that the developed ensemble framework improves the prediction performance significantly compared to the best existing methods.

A Quaternion Weighted Fourier Linear Combiner for Modeling Physiological Tremor.

GOAL: This paper offers a new approach to model physiological tremor aiming at attenuating undesired vibrations of the tip of microsurgical instruments. METHOD: Several tremor modeling algorithms, such as the weighted Fourier linear combiner (wFLC), have proved effective. They, however, treat the three-dimensional (3-D) tremor signal as three independent 1-D signals in the x-, y-, and z-axes. In addition, the force f by which a surgeon holds the instrument has never been taken into account in modeling. Hence, conventional algorithms are inherently blind to any potential multidimensional couplings. RESULTS: We first show that there exists statistically significant subject- and task-dependent coherence between data in the x-, y-, z -, and f-axes. We hypothesize that a filter that models the tremor in 4-D ( x , y, z, and f ) yields a more accurate model of tremor. We, therefore, developed a quaternion version of the wFLC algorithm and termed it QwFLC. We tested the proposed QwFLC algorithm with real physiological tremor data that were recorded from five novice subjects and four experienced microsurgeons. Although compared to wFLC, QwFLC requires six times larger computational resources, we showed that QwFLC can improve the modeling by up to 67% and that the improvement is proportional to the total coherence between the tremor in xyz and the force signal. CONCLUSION: By taking into account interactions of the 3-D tremor and the force data, the tremor modeling performance enhances significantly.

Automatic annotation of peaks in seismocardiogram for systolic time intervals.

Siemocardiography is a non-invasive technique for cardiomechanical assessment by analyzing the local vibrations on chest surface which can be readily acquired from cost-effective accelerometers. The peaks in siesmocardiogram (SCG) signal correspond to underlying mechanical events in heart cycle and have numerious potential clinical and health-awareness applications. However, utilization of SCG signal requires annotation of these peaks that is challenging due to variations in inter-subject morphology and noise prone characteristics of SCG signal. In this paper, we propose an approach to automatically annotate the desired peaks in SCG signal that are required for systolic time intervals (STI). The approach is based on formulating sliding template for the oncoming beat which is less noisier and hence desired peak detection is easier. The information of peak detected in the sliding template is then used to narrow-down the search of desired peak in actual signal.

Three-dimensional modeling of physiological tremor for hand-held surgical robotic instruments.

Hand-held robotic instruments are developed to compensate physiological tremor in real-time while augmenting the required precision and dexterity into normal microsurgical work-flow. The hardware (sensors and actuators) and software (causal linear filters) employed for tremor identification and filtering introduces time-varying unknown phase-delay that adversely affects the device performance. The current techniques that focus on three-dimensions (3D) tip position control involves modeling and canceling the tremor in 3-axes (x, y, and z axes) separately. Our analysis with the tremor data recorded from surgeons and novice subjects show that there exists significant correlation in tremor motion across the dimensions. Motivated by this, a new multi-dimensional modeling approach based on extreme learning machines (ELM) is proposed in this paper to correct the phase delay and to accurately model tremulous motion in three dimensions simultaneously. A study is conducted with tremor data recorded from the microsurgeons to analyze the suitability of proposed approach.

Multistep prediction of physiological tremor based on machine learning for robotics assisted microsurgery.

For effective tremor compensation in robotics assisted hand-held device, accurate filtering of tremulous motion is necessary. The time-varying unknown phase delay that arises due to both software (filtering) and hardware (sensors) in these robotics instruments adversely affects the device performance. In this paper, moving window-based least squares support vector machines approach is formulated for multistep prediction of tremor to overcome the time-varying delay. This approach relies on the kernel-learning technique and does not require the knowledge of prediction horizon compared to the existing methods that require the delay to be known as a priori. The proposed method is evaluated through simulations and experiments with the tremor data recorded from surgeons and novice subjects. Comparison with the state-of-the-art techniques highlights the suitability and better performance of the proposed method.

Real-time prediction of respiratory motion traces for radiotherapy with ensemble learning.

In this paper, we introduce a hybrid method for prediction of respiratory motion to overcome the inherent delay in robotic radiosurgery while treating lung tumors. The hybrid method adopts least squares support vector machine (LS-SVM) based ensemble learning approach to exploit the relative advantages of the individual methods local circular motion (LCM) with extended Kalman filter (EKF) and autoregressive moving average (ARMA) model with fading memory Kalman filter (FMKF). The efficiency the proposed hybrid approach was assessed with the real respiratory motion traces of 31 patients while treating with CyberKnife(TM). Results show that the proposed hybrid method improves the prediction accuracy by approximately 10% for prediction horizons of 460 ms compared to the existing methods.

Multistep prediction of physiological tremor for surgical robotics applications.

Accurate canceling of physiological tremor is extremely important in robotics-assisted surgical instruments/procedures. The performance of robotics-based hand-held surgical devices degrades in real time due to the presence of phase delay in sensors (hardware) and filtering (software) processes. Effective tremor compensation requires zero-phase lag in filtering process so that the filtered tremor signal can be used to regenerate an opposing motion in real time. Delay as small as 20 ms degrades the performance of human-machine interference. To overcome this phase delay, we employ multistep prediction in this paper. Combined with the existing tremor estimation methods, the procedure improves the overall accuracy by 60% for tremor estimation compared to single-step prediction methods in the presence of phase delay. Experimental results with developed methods for 1-DOF tremor estimation highlight the improvement.

A hybrid approach for short-term forecasting of wind speed.

We propose a hybrid method for forecasting the wind speed. The wind speed data is first decomposed into intrinsic mode functions (IMFs) with empirical mode decomposition. Based on the partial autocorrelation factor of the individual IMFs, adaptive methods are then employed for the prediction of IMFs. Least squares-support vector machines are employed for IMFs with weak correlation factor, and autoregressive model with Kalman filter is employed for IMFs with high correlation factor. Multistep prediction with the proposed hybrid method resulted in improved forecasting. Results with wind speed data show that the proposed method provides better forecasting compared to the existing methods.