Iterative training of an automated dosimetric planning model for stereotactic radiotherapy in thoracic and lumbar spine pathologies
Итеративное обучение модели автоматизированного дозиметрического планирования стереотаксической лучевой терапии патологий грудного и поясничного отделов позвоночника
2026-07-09
SCID: 54.1/ppcxrwzz
Discuss with AI
automated treatment planningdosimetric plan qualityiterative trainingmulti-criteria dose optimizationstereotactic spine radiotherapy
Figures from the paper
Abstract (AI)
The study presents the results of applying an iterative approach to optimizing automated multi-criteria ionizing radiation dose distribution models for stereotactic spine radiotherapy. Two models were used: SRT_Vert_BM (Baseline Multicriteria Model) and SRT_Vert_IM (Iterative Multicriteria Model). The former was built on a clinical dataset of dosimetric plans, while the latter was created using an iterative method where the training dataset was formed from plans generated by the baseline model. Validation demonstrated that SRT_Vert_IM provides statistically significant improvements in predictive performance (increased coefficient of determination R², reduced mean squared error MSE) and dosimetric parameters for bilateral parenchymal organs at risk ( p < 0.05) while maintaining clinically acceptable target volume coverage. Iterative training enhanced the reproducibility and reliability of dosimetric plan quality, confirming the potential of this approach for advancing automated treatment planning.
Key Findings
1
Iterative training improved the reproducibility and reliability of automated dosimetric plan quality.
2
SRT_Vert_IM significantly improved dosimetric parameters for bilateral parenchymal organs at risk while maintaining clinically acceptable target-volume coverage (p < 0.05).
3
The iterative model, SRT_Vert_IM, was trained using treatment plans generated by the baseline clinical-data model, SRT_Vert_BM.
4
The study developed an iterative method for optimizing automated multicriteria dose-distribution models for stereotactic radiotherapy of thoracic and lumbar spine pathologies.
5
Validation showed statistically significant improvements in predictive performance for SRT_Vert_IM, including higher R² and lower MSE.
Research Object
Automated multi-criteria ionizing-radiation dose-distribution models for stereotactic radiotherapy of thoracic and lumbar spine pathologies
Research Subject
Effects of iterative training on the models’ predictive performance, dosimetric quality, reproducibility, reliability, and target-volume coverage while respecting dose constraints for bilateral parenchymal organs at risk
Publication Details
Publication Date
2026-07-09
Journal
Publisher
ISSN
Cited by
0
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest