Xiaoli Tang

TL;DR: This work proposes a marker tracking system that can track multiple markers simultaneously, without confusing them, and that is also robust enough to continue tracking even when the markers are moving behind bony anatomy, and compares it to that of a conventional tracking system.

TL;DR: In this paper, a long short-term memory (LSTM)-based generalized model was proposed for predicting respiratory signal in thoracic and abdominal tumors using real-time position management (RPM) data.

TL;DR: In this series, the authors have Dr Xiaoli Tang arguing for the proposition that “AI will reduce the need for clinical medical physicists” and Dr. Brian Wang arguing against it.

TL;DR: The obtained model achieved superior accuracy over conventional artificial neural network (ANN) models: with the prediction window equaling to 500 ms, the LSTM model achieved an average relative mean absolute error (MAE) of 0.037 and the MAE of the optimized model results decreased by 20%, indicating the importance of tuning the hyper-parameters of L STM models to obtain superior accuracies.

TL;DR: Data visualization technique was applied to analyze the daily QA results of photon and electron beams of Varian Trilogy Linac equipped with dual photon energies and five electron energies to predict the trend of the Linac and take actions proactively.