Audit logs measured artificial intelligence contour correction time with 0.93 concordance
Treatment-planning audit logs closely reproduced manual contour-edit timing and exposed major structure-specific differences in correction workload.
Latest
Longitudinal muscle loss and myocardial remodeling tracked worse survival after non-small cell lung cancer radiotherapy
Skeletal muscle loss and substantial left ventricular mass changes on follow-up imaging were strongly associated with poorer survival after curative radiotherapy.
Twice-daily radiotherapy was associated with longer survival in younger limited-stage small cell lung cancer
Among patients under 70, twice-daily chemoradiotherapy was associated with 36.0 versus 22.2 months median survival, without higher acute toxicity.
Radiotherapy benefit and side-effect expectations were largely independent before treatment
Patients generally expected high radiotherapy benefit, but expectations of benefit and adverse events were not significantly correlated.
THUNDER-2 used early tumor regression to guide adaptive rectal cancer dose escalation
ERI-guided escalation to 60.1 Gy produced a 21.9% complete response rate in patients predicted to respond poorly.
Daily adaptation supported 17-fraction definitive chemoradiotherapy for cervical cancer
Daily online adaptation improved pelvic target coverage during 17-fraction cervical chemoradiotherapy, with 10% grade ≥3 gastrointestinal toxicity.
Diaphragm motion was less reliable than fiducials for markerless tumor tracking
Tumor–diaphragm geometry varied by approximately 4.5 mm during breathing, substantially more than tumor–fiducial relationships.
Eye tracking and imaging features predicted uncertainty in manual brain tumor contours
Behavioral and image-derived features explained 39% of interobserver contour uncertainty during manual brain tumor delineation.
CHAF1A promotes DNA repair and tumor radioresistance through RAD51 and KU70
CHAF1A supported homologous recombination and non-homologous end joining, while its depletion increased radiosensitivity in xenograft models.
Heart dose rises during esophageal IMPT but adaptive replanning limits the increase
Mean heart dose increased during esophageal IMPT, while heart-dose–triggered replanning reduced the excess dose in patients requiring adaptation.
Chemoradiotherapy and immunoradiotherapy reshape distinct esophageal cancer microenvironment programs
Chemoradiotherapy suppressed LAMC2–macrophage signalling, while immunoradiotherapy enriched CCL5-positive CD8 T cells in preclinical esophageal squamous-cell carcinoma models.
Most European proton candidates still face critical access shortages
More than 56,000 theoretically eligible European patients lived in areas with no proton access or critical capacity shortages in 2025.
Interpretable AI separated three-year anal cancer relapse risk after chemoradiotherapy
An explainable model separated three-year local relapse rates of 11% versus 39%, but lacks independent external validation.
Danish head and neck risk model generalized to an Australian radiotherapy cohort
The model retained moderate discrimination for recurrence and metastasis, but predicted non-cancer death less reliably, especially in older patients.
Calling it “radiation therapy” reduced treatment preference compared with “radiotherapy”
In a randomized US survey, “radiation therapy” reduced selection of the same treatment by 8.3 percentage points versus “radiotherapy.”