An LLM agent generated head and neck IMRT plans comparable to clinical plans
Reference-free LLM planning improved hotspot control and boost-target conformity while maintaining organ-at-risk sparing comparable to clinical plans.
Reference-free LLM planning improved hotspot control and boost-target conformity while maintaining organ-at-risk sparing comparable to clinical plans.
An open-source workflow structured 15 years of radiotherapy data, although reirradiation prediction showed only modest discrimination.
The Transformer calculated carbon-ion pencil-beam doses in 14 milliseconds with 98.0% gamma agreement at stringent 1%/1 mm criteria.
AI-assisted planning cut average planning time from about two hours to 30 minutes, but three of 12 plans required manual hotspot correction.
Patient-specific reinforcement learning improved moving-target coverage over static GTV plans while reducing some normal-tissue exposure compared with ITV planning.
A retrieval-augmented GPT-4.1 chatbot rapidly surfaced previous TrueBeam faults, but procedural, role-definition and safety errors remained.
Thoracic AI contours showed strong geometric and dosimetric agreement, but physicians still rejected some heart and oesophageal contours.
A center-specific federated learning model predicted grade 2 or higher radiation pneumonitis with stable cross-dataset performance.
Artificial intelligence planning produced clinically acceptable whole-brain radiotherapy plans in 14 of 15 independent test cases.
An artificial intelligence coronary artery surrogate strongly correlated with manual dose metrics in simulated lung stereotactic body radiotherapy.
98.98% of virtual contrast-enhanced MRI scans were rated suitable for diagnosis, and 92.33% for tumor delineation.
The neural model reduced phase-space storage from 3 gigabytes to 600 kilobytes while maintaining at least 89.9% gamma passing at 1%/1 mm.
The framework achieved 85.5% external-validation accuracy and reduced estimated review time from 822 hours to 2.3–4.8 hours.
Computed tomography-derived muscle measures ranked highly for toxicity and quality of life, but added little predictive value beyond established clinical factors.
A hybrid foundation-model framework achieved 94% lesion-wise sensitivity and was preferred over physician-generated brain metastasis contours in blinded, bias-adjusted comparisons.