EUVIMEDEUVIMED entdecken
Open Access

Dose-Incorporated Deep Ensemble Learning for Improving Brain Metastasis Stereotactic Radiosurgery Outcome Prediction

Jingtong Zhao, Eugene Vaios, Yuqi Wang, Zhenyu Yang, Yunfeng Cui, Zachary J Reitman, Kyle J Lafata, Peter Fecci, John Kirkpatrick, Fang- Fang Yin, Scott Floyd, Chunhao Wang

International Journal of Radiation Oncology*Biology*Physics · 2024-10 · 120 (2) · 603-613

DOI: 10.1016/j.ijrobp.2024.04.006 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Radiation Oncology*Biology*Physics, 2024-10. Verfasst von Jingtong Zhao und 11 weiteren Autor:innen. Beteiligte Einrichtung: Duke University Medical Center, Durham, North Carolina. Hauptthemen laut MEDLINE: Brain Neoplasms, Radiosurgery, Deep Learning, Radiotherapy Dosage. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NCI NIH HHS, National Institutes of Health, National Cancer Institute.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE: To develop a novel deep ensemble learning model for accurate prediction of brain metastasis (BM) local control outcomes after stereotactic radiosurgery (SRS). METHODS AND MATERIALS: A total of 114 brain metastases (BMs) from 82 patients were evaluated, including 26 BMs that developed biopsy-confirmed local failure post-SRS. The SRS spatial dose distribution (Dmap) of each BM was registered to the planning contrast-enhanced T1 (T1-CE) magnetic resonance imaging (MRI). Axial slices of the Dmap, T1-CE, and planning target volume (PTV) segmentation (PTVseg) intersecting the BM center were extracted within a fixed field of view determined by the 60% isodose volume in Dmap. A spherical projection was implemented to transform planar image content onto a spherical surface using multiple projection centers, and the resultant T1-CE/Dmap/PTVseg projections were stacked as a 3-channel variable. Four Visual Geometry Group (VGG-19) deep encoders were used in an ensemble design, with each submodel using a different spherical projection formula as input for BM outcome prediction. In each submodel, clinical features after positional encoding were fused with VGG-19 deep features to generate logit results. The ensemble's outcome was synthesized from the 4 submodel results via logistic regression. In total, 10 model versions with random validation sample assignments were trained to study model robustness. Performance was compared with (1) a single VGG-19 encoder, (2) an ensemble with a T1-CE MRI as the sole image input after projections, and (3) an ensemble with the same image input design without clinical feature inclusion. RESULTS: The ensemble model achieved an excellent area under the receiver operating characteristic curve (AUCROC: 0.89 ± 0.02) with high sensitivity (0.82 ± 0.05), specificity (0.84 ± 0.11), and accuracy (0.84 ± 0.08) results. This outperformed the MRI-only VGG-19 encoder (sensitivity: 0.35 ± 0.01, AUCROC: 0.64 ± 0.08), the MRI-only deep ensemble (sensitivity: 0.60 ± 0.09, AUCROC: 0.68 ± 0.06), and the 3-channel ensemble without clinical feature fusion (sensitivity: 0.78 ± 0.08, AUCROC: 0.84 ± 0.03). CONCLUSIONS: Facilitated by the spherical image projection method, a deep ensemble model incorporating Dmap and clinical variables demonstrated excellent performance in predicting BM post-SRS local failure. Our novel approach could improve other radiation therapy outcome models and warrants further evaluation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Brain NeoplasmsRadiosurgeryDeep LearningRadiotherapy DosageMagnetic Resonance ImagingHumansRadiotherapy Planning, Computer-AssistedTreatment OutcomeMaleFemaleMiddle AgedAged

Autor:innen und Institutionen

  • Duke University Medical Center, Durham, North Carolina.
  • Duke University Medical Center, Durham, North Carolina. Electronic address: chunhao.wang@duke.edu.

Förderung

  • NCI NIH HHS
  • National Institutes of Health
  • National Cancer Institute

Zitieren

APA

Zhao, J., Vaios, E., Wang, Y., Yang, Z., Cui, Y., Reitman, Z. J., Lafata, K. J., Fecci, P., Kirkpatrick, J., Fang Yin, F., Floyd, S., & Wang, C. (2024). Dose-Incorporated Deep Ensemble Learning for Improving Brain Metastasis Stereotactic Radiosurgery Outcome Prediction. International Journal of Radiation Oncology*Biology*Physics, 120(2), 603-613. https://doi.org/10.1016/j.ijrobp.2024.04.006

Vancouver

Zhao J, Vaios E, Wang Y, Yang Z, Cui Y, Reitman ZJ, et al. Dose-Incorporated Deep Ensemble Learning for Improving Brain Metastasis Stereotactic Radiosurgery Outcome Prediction. International Journal of Radiation Oncology*Biology*Physics. 2024;120(2):603-613. doi:10.1016/j.ijrobp.2024.04.006

BibTeX
@article{Zhao2024,
  author = {Zhao, Jingtong and Vaios, Eugene and Wang, Yuqi and Yang, Zhenyu and Cui, Yunfeng and Reitman, Zachary J and Lafata, Kyle J and Fecci, Peter and Kirkpatrick, John and Fang Yin, Fang- and Floyd, Scott and Wang, Chunhao},
  title = {Dose-Incorporated Deep Ensemble Learning for Improving Brain Metastasis Stereotactic Radiosurgery Outcome Prediction},
  journal = {International Journal of Radiation Oncology*Biology*Physics},
  year = {2024},
  volume = {120},
  number = {2},
  pages = {603--613},
  doi = {10.1016/j.ijrobp.2024.04.006}
}
Kostenlos starten →