Automated framework linked 99.76% of radiotherapy planning and delivery datasets
The framework linked complete planning and delivery data for 13,871 plans with 99.76% success across two clinics.
Tag
Technical relevance
Fraction 15 was optimal for one-time offline replanning in head and neck proton therapy
A single offline replan at fraction 15 captured most achievable dosimetric benefit in simulated head and neck proton therapy.
Surface-contacted 3D bolus plus MLC reduced proton PBS lateral penumbra
Surface-contacted 3D boluses generally narrowed lateral penumbra and reduced surrounding dose versus a nozzle-mounted range shifter in proton PBS.
Multidisciplinary radiopharmaceutical dosimetry changed management in one-third of selected patients
In 19 high-risk patients receiving 177Lu-PSMA-617, post-cycle 1 dosimetry changed management in 32%, prompting five activity reductions and one delay.
Bidirectional GAN preserved CT numbers and dose accuracy in head-and-neck planning CT
BiHU-GAN generated synthetic contrast and non-contrast CT with high contour agreement and at least 95% gamma pass rates at 2%/2 mm.
RapidPlan lung SBRT model used gEUD objectives for reproducible planning
A RapidPlan lung SBRT model generated clinically acceptable plans in 52% of validation cases on first optimization.
Single-field optimization improved proton LATTICE motion robustness
Single-field optimization improved proton LATTICE motion robustness
CT-guided online adaptation improved prostate SBRT dosimetry
CT-guided online adaptive prostate SBRT was feasible, with adapted plans selected in 95% of fractions and dosimetric improvements in 85%.
VMAT lattice SFRT was deliverable across Edge and Halcyon linacs
VMAT-based lattice SFRT achieved cross-platform deliverability with gamma pass rates above 90% and preserved peak-to-valley dose ratios.
MIM software accelerated sarcopenia screening during prostate radiotherapy planning
MIM-based skeletal muscle index measurement matched ImageJ while reducing processing time from 10 to 3.5 minutes.
Federated learning improved radiation pneumonitis prediction across lung cancer datasets
A center-specific federated learning model predicted grade 2 or higher radiation pneumonitis with stable cross-dataset performance.
Knowledge-based planning reduced organ-at-risk dose in head and neck and brain planning
RapidPlan reduced several organ-at-risk dose metrics while maintaining comparable target coverage in head and neck and brain radiotherapy planning.
SMART-BRAIN enabled proton-based non-target brain sparing in medulloblastoma planning
SMART-BRAIN proton planning spared portions of non-target brain while maintaining target coverage in five medulloblastoma cases.
Deep learning reduced head and neck auto-segmentation editing, but user variability persisted
Deep learning auto-segmentation reduced editing, but both minimal and excessive manual edits were associated with lower clinical acceptability.
Machine learning stratified survival after palliative radiotherapy for bone metastases
A decision tree model identified interleukin-8, hemoglobin, and lymphocyte count as key survival predictors after palliative radiotherapy.