LGEANet: LSTM-global temporal convolution-external attention network for respiratory motion prediction

To develop a deep learning network that treats the three-dimensional respiratory motion signals as a whole and considers the inter-dimensional correlation between signals of different directions for accurate respiratory tumor motion prediction.

We propose a deep learning framework, named as LSTM-Global Temporal Convolution-External Attention Network (LGEANet). In LGEANet, we first feed each of the univariate time series into the Long Short-Term Memory (LSTM) module respectively and utilize the strength of the global temporal convolutional layer to discover the temporal pattern of the univariate signals from hidden states of the LSTM. Then, External attention is adopted to capture the dynamic dependence of the multiple time series. Also, a traditional autoregressive linear model in parallel to the non-linear neural network part was integrated to mitigate the scale insensitivity of the networks. A total of 304 motion traces for 31 patients are acquired from a public dataset in the experiments and four representative cases were selected for model evaluation. The respiratory signals were sampled at intervals of about 37.5 ms (26 frames per second) for an average duration of 71 min.

The proposed LGEANet achieved better performance with higher empirical correlation coefficient value (CORRs) and lower mean absolute error value (MAEs) and relative squared error value (RSEs) than other investigated models. For the four representative datasets, when the response time is less than 231 ms, the model can achieve CORRs more than 0.96. And the averaged position error reduction by using the proposed model was about 67% in the superior-inferior (SI) direction, 41% in the anterior-posterior (AP) direction and 38% in the right-left (RL) direction compared to that without prediction. The proposed network achieved the greatest error reduction in the SI direction, which is the main direction of tumor motion.

The LGEANet achieves promising performance in minimizing the prediction error due to system latencies during real-time tumor motion tracking.