EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

Experimental comparison of linear regression and LSTM motion prediction models for MLC‐tracking on an MRI‐linac

Elia Lombardo, Paul Z Y Liu, David E J Waddington, James Grover, Brendan Whelan, Esther Wong, Michael Reiner, Stefanie Corradini, Claus Belka, Marco Riboldi, Christopher Kurz, Guillaume Landry and 1 more

Medical Physics · 2023

DOI: 10.1002/mp.16770 ↗

At a glance

Journal article in Medical Physics, 2023. Written by Elia Lombardo and 12 co-authors. Institution: Department of Radiation Oncology, LMU University Hospital, LMU Munich, Munich, Germany. Major MEDLINE topics: Lung Neoplasms. Cited 23 times so far (Crossref); 44 references. The full text is freely available (open access, CC BY 4.0). Funded by: Deutsche Forschungsgemeinschaft, Cancer Institute NSW.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Background

Magnetic resonance imaging (MRI)‐guided radiotherapy with multileaf collimator (MLC)‐tracking is a promising technique for intra‐fractional motion management, achieving high dose conformality without prolonging treatment times. To improve beam‐target alignment, the geometric error due to system latency should be reduced by using temporal prediction.

Purpose

To experimentally compare linear regression (LR) and long‐short‐term memory (LSTM) motion prediction models for MLC‐tracking on an MRI‐linac using multiple patient‐derived traces with different complexities.

Methods

Experiments were performed on a prototype 1.0 T MRI‐linac capable of MLC‐tracking. A motion phantom was programmed to move a target in superior‐inferior (SI) direction according to eight lung cancer patient respiratory motion traces. Target centroid positions were localized from sagittal 2D cine MRIs acquired at 4 Hz using a template matching algorithm. The centroid positions were input to one of four motion prediction models. We used (1) a LSTM network which had been optimized in a previous study on patient data from another cohort ( offline LSTM). We also used (2) the same LSTM model as a starting point for continuous re‐optimization of its weights during the experiment based on recent motion ( offline + online LSTM). Furthermore, we implemented (3) a continuously updated LR model, which was solely based on recent motion ( online LR). Finally, we used (4) the last available target centroid without any changes as a baseline (no‐predictor). The predictions of the models were used to shift the MLC aperture in real‐time. An electronic portal imaging device (EPID) was used to visualize the target and MLC aperture during the experiments. Based on the EPID frames, the root‐mean‐square error (RMSE) between the target and the MLC aperture positions was used to assess the performance of the different motion predictors. Each combination of motion trace and prediction model was repeated twice to test stability, for a total of 64 experiments.

Results

The end‐to‐end latency of the system was measured to be (389 ± 15) ms and was successfully mitigated by both LR and LSTM models. The offline + online LSTM was found to outperform the other models for all investigated motion traces. It obtained a median RMSE over all traces of (2.8 ± 1.3) mm, compared to the (3.2 ± 1.9) mm of the offline LSTM, the (3.3 ± 1.4) mm of the online LR and the (4.4 ± 2.4) mm when using the no‐predictor. According to statistical tests, differences were significant (p‐value

Subjects

MeSH terms (MEDLINE)

Lung NeoplasmsHumansLinear ModelsMotionAlgorithmsPhantoms, ImagingMagnetic Resonance ImagingRadiotherapy Planning, Computer-Assisted

Author keywords

MLC-trackingMRI-linaclinear regressionlong short-term memorymotion predictionrespiratory motion

Authors and institutions

  • Department of Radiation Oncology, LMU University Hospital, LMU Munich, Munich, Germany.
  • Image X Institute, University of Sydney Central Clinical School, Sydney, New South Wales, Australia.
  • Department of Medical Physics, Ingham Institute of Applied Medical Research, Liverpool, New South Wales, Australia.
  • German Cancer Consortium (DKTK), partner site Munich, a partnership between DKFZ and LMU University Hospital Munich, Munich, Germany.
  • Bavarian Cancer Research Center (BZKF), Munich, Germany.
  • Department of Medical Physics, Faculty of Physics, Ludwig-Maximilians-Universität München, Garching, Germany.

Funding

  • Deutsche Forschungsgemeinschaft
  • Cancer Institute NSW

Cite

APA

Lombardo, E., Liu, P. Z. Y., Waddington, D. E. J., Grover, J., Whelan, B., Wong, E., Reiner, M., Corradini, S., Belka, C., Riboldi, M., Kurz, C., Landry, G., & Keall, P. J. (2023). Experimental comparison of linear regression and LSTM motion prediction models for MLC‐tracking on an MRI‐linac. Medical Physics. https://doi.org/10.1002/mp.16770

Vancouver

Lombardo E, Liu PZY, Waddington DEJ, Grover J, Whelan B, Wong E, et al. Experimental comparison of linear regression and LSTM motion prediction models for MLC‐tracking on an MRI‐linac. Medical Physics. 2023. doi:10.1002/mp.16770

BibTeX
@article{Lombardo2023,
  author = {Lombardo, Elia and Liu, Paul Z Y and Waddington, David E J and Grover, James and Whelan, Brendan and Wong, Esther and Reiner, Michael and Corradini, Stefanie and Belka, Claus and Riboldi, Marco and Kurz, Christopher and Landry, Guillaume and Keall, Paul J},
  title = {Experimental comparison of linear regression and LSTM motion prediction models for MLC‐tracking on an MRI‐linac},
  journal = {Medical Physics},
  year = {2023},
  doi = {10.1002/mp.16770}
}
Start for free →