EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Assessment of simulated respiratory gating based on external‐to‐internal motion prediction using a hybrid, adaptive deep‐learning network

Andrew Milewski, Xingyu Nie, Guang Li

Journal of Applied Clinical Medical Physics · 2026-12 · 27 (12)

DOI: 10.1002/acm2.70905 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Applied Clinical Medical Physics, online erschienen am 17.11.2026. Verfasst von Andrew Milewski und 2 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Memorial Sloan-Kettering Cancer Center.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To assess the accuracy, safety, and efficiency of respiratory‐gated radiotherapy (RGRT) based on internal respiratory waveforms predicted by a hybrid long short‐term memory (LSTM) deep‐learning network, which adapts to breathing irregularities through the application of time‐domain cross‐correlation (TCC) to check and correct any residual phase/time shift in the LSTM predictions.

Methods

The adaptive LSTM‐TCC model was built in two steps: (1) subject‐specific LSTM models were trained to predict internal diaphragm motion from external bellows motion using each of 10 subjects’ concurrent waveforms (≥20 Hz, 3–10 min) acquired from four‐dimensional magnetic resonance imaging (4DMRI) protocol scans and (2) near real‐time TCC was applied to the LSTM predictions to check and correct any residual phase/time shifts to safeguard against new breathing irregularities beyond the training data in the mid‐term (3–10 min) and long‐term (20–30 min) datasets. The testing datasets comprised both the mid‐term and long‐term concurrent motion waveforms, and the external‐to‐internal motion predictions and gating quality assessments for each subject were evaluated and validated with the actual internal motion as the ground truth. The hybrid LSTM‐TCC models were compared with LSTM, TCC, and native external‐to‐internal correlation models. The temporal gating accuracy (beam‐off and beam‐on) and beam‐gating quality (missing‐target rate: %harm, and beam‐on efficiency: %effic) of the hybrid LSTM‐TCC model were evaluated and compared with LSTM, TCC, and native predictions.

Results

The hybrid LSTM‐TCC models produced the highest long‐term sustained correlations (C > 0.8, within 30 min), yielding the lowest %harm = 5 ± 6% and the highest %effic = 67 ± 15%, compared with the LSTM (%harm = 8 ± 8%, %effic = 65 ± 16%), the TCC (%harm = 29 ± 31%, %effic = 43 ± 19%), and the native (%harm = 37 ± 23%, %effic = 38 ± 14%). The hybrid LSTM‐TCC models produced a high, sustained performance (C = 0.9 ± 0.1) without remodeling, regardless of new breathing irregularities, and the average temporal error of the predicted gating windows was ∆ t < 0.3 s.

Conclusion

This study assesses the simulated respiratory‐gating qualities of four methods, demonstrating that the hybrid LSTM‐TCC approach outperforms the native waveforms, the TCC method, and the LSTM models, yielding the highest correlation, gating accuracy, and %effic, but the least %harm. The hybrid LSTM‐TCC model can safeguard LSTM predictions and gating accuracy against major breathing irregularities, demonstrating a strong potential for future clinical applications.

Förderung

  • Memorial Sloan-Kettering Cancer Center

Zitieren

APA

Milewski, A., Nie, X., & Li, G. (2026). Assessment of simulated respiratory gating based on external‐to‐internal motion prediction using a hybrid, adaptive deep‐learning network. Journal of Applied Clinical Medical Physics, 27(12). https://doi.org/10.1002/acm2.70905

Vancouver

Milewski A, Nie X, Li G. Assessment of simulated respiratory gating based on external‐to‐internal motion prediction using a hybrid, adaptive deep‐learning network. Journal of Applied Clinical Medical Physics. 2026;27(12). doi:10.1002/acm2.70905

BibTeX
@article{Milewski2026,
  author = {Milewski, Andrew and Nie, Xingyu and Li, Guang},
  title = {Assessment of simulated respiratory gating based on external‐to‐internal motion prediction using a hybrid, adaptive deep‐learning network},
  journal = {Journal of Applied Clinical Medical Physics},
  year = {2026},
  volume = {27},
  number = {12},
  doi = {10.1002/acm2.70905}
}
Kostenlos starten →