EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

A Feasibility Study of Hybrid Deep-Learning Prediction with Online Adaptation of Breathing Irregularities for Long-Term Internal Organ Motion During Radiotherapy

Andrew Milewski, Uddin Fayed, Vyas Gupta, Xingyu Nie, Guang Li iD

Technology in Cancer Research & Treatment · 2026-04 · 25

DOI: 10.1177/15330338261420917 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Technology in Cancer Research & Treatment, online erschienen am 15.04.2026. Verfasst von Andrew Milewski und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, USA. Hauptthemen laut MEDLINE: Deep Learning, Respiration. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NCI NIH HHS, Clinical Center.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Although long short-term memory (LSTM) networks have been tested to predict short-term respiratory motion, their performance in long-term forecasting under breathing irregularities must be assessed. We aim to evaluate and enhance the long-term prediction of internal motion from an external surrogate using subject-specific LSTM models through a hybrid, adaptive approach.

Methods

Concurrent internal navigator and external bellows respiratory-motion waveforms were acquired for ten volunteers during two four-dimensional magnetic resonance imaging (4DMRI) scans lasting 3–10 min each. Approximately 20 min intervened between the first (mid-term) and second (long-term) scan. After training on the first half of the mid-term data, subject-specific LSTM models were applied to the remaining mid-term and entire long-term datasets to predict internal waveforms. The accuracy of a model's prediction was assessed with Pearson's correlation ( C ), referenced to the native waveforms, maximized through the time-domain cross-correlation (TCC), and enhanced by correcting residual phase shifts in the LSTM models using a hybrid (LSTM-TCC) approach. Hyperparameter selection by minimizing the root mean square error (RMSE) to identify high-performance ( C ≥ 0.8) LSTM models was evaluated by the area under the receiver operating characteristic curve (AUROC). The temporal accuracy of inspiratory-peak predictions was characterized.

Results

Compared to the native waveforms ( C = 0.42 ± 0.28) and TCC method ( C = 0.77 ± 0.09), the LSTM models yielded more accurate predictions ( C = 0.89 ± 0.07) in the mid-term scans. Over 20–30 min, LSTM predictions faltered ( C < 0.80) in two subjects but were rescued by LSTM-TCC ( C = 0.90 ± 0.09). The temporal error in predicting inspiratory peaks was smaller for LSTM-TCC (Δ t = 0.15 ± 0.11sec) than LSTM (Δ t = 0.18 ± 0.15sec). RMSE reliably identified high-performance models: A U R O C L S T M m i d − t e r m = 0.82 , A U R O C L S T M l o n g − t e r m = 0.74 , and A U R O C h y b r i d l o n g − t e r m = 0.83 .

Conclusion

The feasibility of a novel adaptive subject-specific LSTM-TCC modeling was tested in 10 subjects, demonstrating that high accuracy of external-to-internal motion predictions in 3–10 min can be extended to 30 min overcoming breathing irregularities without remodeling. Further investigations of the adaptive LSTM-TCC model are warranted as a potential clinical solution.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningRespirationHumansLong Short Term MemoryFeasibility StudiesMagnetic Resonance ImagingPredictive Learning ModelsPrediction AlgorithmsMovement

Stichwörter der Autor:innen

LSTM and hybrid LSTM deep learningartificial intelligenceexternal-internal motion correlationmotion management for treatment planningrespiratory motion prediction

Autor:innen und Institutionen

  • Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, USA.
  • Department of Anesthesiology, Weill Cornell Medicine, New York, NY, USA.
  • Department of Radiology, Kentucky University College of Medicine, Lexington, KY, USA.

ORCID-Profile: Guang Li

Förderung

  • NCI NIH HHS
  • Clinical Center

Zitieren

APA

Milewski, A., Fayed, U., Gupta, V., Nie, X., & Li, G. (2026). A Feasibility Study of Hybrid Deep-Learning Prediction with Online Adaptation of Breathing Irregularities for Long-Term Internal Organ Motion During Radiotherapy. Technology in Cancer Research & Treatment, 25. https://doi.org/10.1177/15330338261420917

Vancouver

Milewski A, Fayed U, Gupta V, Nie X, Li G. A Feasibility Study of Hybrid Deep-Learning Prediction with Online Adaptation of Breathing Irregularities for Long-Term Internal Organ Motion During Radiotherapy. Technology in Cancer Research & Treatment. 2026;25. doi:10.1177/15330338261420917

BibTeX
@article{Milewski2026,
  author = {Milewski, Andrew and Fayed, Uddin and Gupta, Vyas and Nie, Xingyu and Li, Guang},
  title = {A Feasibility Study of Hybrid Deep-Learning Prediction with Online Adaptation of Breathing Irregularities for Long-Term Internal Organ Motion During Radiotherapy},
  journal = {Technology in Cancer Research & Treatment},
  year = {2026},
  volume = {25},
  doi = {10.1177/15330338261420917}
}
Kostenlos starten →