Time series prediction of lung cancer patients' breathing pattern based on nonlinear dynamics

Real-Time 2D MR Cine From Beam Eye's View With Tumor-Volume Projection to Ensure Beam-to-Tumor Conformality for MR-Guided Radiotherapy of Lung Cancer

Purpose

To minimize computation latency using a predictive strategy to retrieve and project tumor volume onto 2D MR beam eye’s view (BEV) cine from time-resolved four-dimensional magnetic resonance imaging (TR-4DMRI) libraries (inhalation/exhalation) for personalized MR-guided intensity-modulated radiotherapy (IMRT) or volumetric-modulated arc therapy (VMAT).

Methods

Two time-series forecasting algorithms, autoregressive (AR) modeling and deep-learning-based long short-term memory (LSTM), were applied to predict the diaphragm position in the next 2D BEV cine to identify a motion-matched and hysteresis-accounted image to retrieve the tumor volume from the inhalation/exhalation TR-4DMRI libraries. Three 40-s TR-4DMRI (2 Hz, 3 × 80 images) per patient of eight lung cancer patients were used to create patient-specific inhalation/exhalation 4DMRI libraries, extract diaphragmatic waveforms, and interpolate them to f = 4 and 8 Hz to match 2D cine frame rates. Along a (40•f)-timepoint waveform, 30•f training timepoints were moved forward to produce 3×(10•f-1) predictions. The accuracy of position prediction was assessed against the waveform ground truth. The accuracy of tumor volume projections was evaluated using the center-of-mass difference (∆COM) and Dice similarity index against the TR-4DMRI ground truth for both IMRT (six beam angles, 30° interval) and VMAT (240/480 beam angles, 1.5°/0.75° interval, at 4/8 Hz, respectively).

Results

The accuracy of the first-timepoint prediction is 0.36 ± 0.10 mm (AR) and 0.62 ± 0.21 mm (LSTM) at 4 Hz and 0.06 ± 0.02 mm (AR) and 0.18 ± 0.06 mm (LSTM) at 8 Hz. A 10%–20% random error in prediction-library matching increases the overall uncertainty slightly. For both IMRT and VMAT, the accuracy of projected tumor volume contours on 2D BEV cine is ∆COM = 0.39 ± 0.13 mm and DICE = 0.97 ± 0.02 at 4 Hz and ∆COM = 0.10 ± 0.04 mm and DICE = 1.00 ± 0.00 at 8Hz.

Conclusion

This study demonstrates the feasibility of accurately predicting respiratory motion during 2D BEV cine imaging, identifying a motion-matched and hysteresis-accounted tumor volume, and projecting tumor volume contour on 2D BEV cine for real-time assessment of beam-to-tumor conformality, promising for optimal personalized MR-guided radiotherapy.

Adaptive respiratory signal prediction using dual multi-layer perceptron neural networks

PURPOSE

To improve the prediction accuracy of respiratory signals by adapting the multi-layer perceptron neural network (MLP-NN) model to changing respiratory signals. We have previously developed an MLP-NN to predict respiratory signals obtained from a real-time position management (RPM) device. Preliminary testing results indicated that poor prediction accuracy may be observed after several seconds for irregular breathing patterns as only a set of fixed data was used in one-time training. To improve the prediction accuracy, we introduced a continuous learning technique using the updated training data to replace one-time learning using the fixed training data. We carried on this new prediction using an adaptation approach with dual MLP-NNs rather than single MLP-NN. When one MLP-NN was performing prediction of the respiratory signals, another one was being trained using the updated data and vice versa. The predicted performance was evaluated by root-mean-square-error (RMSE) between the predicted and true signals from 202 patients' respiratory patterns each with 1 min recording length. The effects of adding an additional network, training parameter, and respiratory signal irregularity on the performance of the new predictor were investigated based on four different network configurations: a single MLP-NN, high-computation dual MLP-NNs (U1), two different combinations of high- and low-computation dual MLP-NNs (U2 and U3). The RMSEs using U1 method were reduced by 34%, 19%, and 10% compared to those using MLP-NN, U2 and U3 methods, respectively. Continuous training of an MLP-NN based on a dual-network configuration using updated respiratory signals improved prediction accuracy compared to one-time training of an MLP-NN using fixed signals.

Analysis of Muscle Load-Sharing in Patients With Lateral Epicondylitis During Endurance Isokinetic Contractions Using Non-linear Prediction

The aim of this paper is to analyze muscle load-sharing in patients with Lateral Epicondylitis during dynamic endurance contractions by means of non-linear prediction of surface EMG signals. The proposed non-linear cross-prediction scheme was used to predict the envelope of an EMG signal and is based on locally linear models built in a lag-embedded Euclidean space. The results were compared with a co-activation index, a common measure based on the activation of a muscle pair. Non-linear prediction revealed changes in muscle coupling, that is load-sharing, over time both in a control group and Lateral Epicondylitis (p < 0.05), even when subjects did not report pain at the end of the exercise. These changes were more pronounced in patients, especially in the first part of the exercise and up to 50% of the total endurance time (p < 0.05). By contrast, the co-activation index showed no differences between groups. Results reflect the changing nature of muscular activation strategy, presumably because of the mechanisms triggered by fatigue. Strategies differ between controls and patients, pointing to an altered coordination in Lateral Epicondylitis.