PocketNet matched nnU-Net segmentation with 40-fold lower model storage
PocketNet matched nnU-Net accuracy for cervical MRI segmentation while using 40-fold less storage and approximately half the training time.
Latest
Prostate focal boost review defines MRI-based contouring and isotoxic planning
MRI-defined biopsy-confirmed lesions can be boosted safely when robust image guidance and normal-tissue constraints take priority over complete boost coverage.
CyberKnife dose models found size-dependent but non-monotonic brain metastasis control
Tumour-size strata showed non-monotonic BED–control relationships, while machine-learning performance remained unvalidated outside a single retrospective centre.
A 55-gene hypoxia signature identified poor-prognosis cervical cancer across cohorts
A 55-gene hypoxia classifier independently predicted worse survival and retained prognostic value across Manchester, Seoul, and Norwegian cervical cancer cohorts.
Breast brachytherapy review defines practical standards for APBI delivery
Successful breast brachytherapy depends on careful patient selection, suitable cavity anatomy, sound implant geometry, accurate reconstruction, and rigorous treatment QA.
Iodine-125 brachytherapy achieved short-term control in previously irradiated cervical nodal metastases
Iodine-125 seed implantation produced 90% three-month disease control, but median local progression-free survival was nine months.
Different factors predicted cardiac-event subtypes after hypofractionated breast radiotherapy
Planning-CT calcification and age predicted atherosclerotic events, while anthracyclines and respiratory toxicity predicted other cardiac complications.
Higher pretreatment LMR weakly predicted cervical tumour shrinkage after EBRT
Pretreatment lymphocyte-to-monocyte ratio was independently associated with cervical tumour shrinkage, but its standalone discrimination was poor.
Exit-dose gamma alerts identified head-and-neck replanning needs on Halcyon-E
Strict exit-dose gamma thresholds correlated with anatomical change and identified all clinically replanned patients in a retrospective validation cohort.
Reinforcement learning adapted proton spot delivery across respiratory phases
Patient-specific reinforcement learning improved moving-target coverage over static GTV plans while reducing some normal-tissue exposure compared with ITV planning.
Oral copper chelation preserved salivary gland function after irradiation in mice
Systemic tetrathiomolybdate reduced collagen deposition and preserved saliva secretion after irradiation of mouse submandibular glands.
ESTRO defined minimum standards for prostate SBRT implementation
ESTRO recommends prostate SBRT for selected intermediate-risk disease with MRI-based contouring, rigorous quality assurance, and daily image guidance.
Immune-sparing lung SBRT planning reduced lymphocyte loss in a randomized phase II trial
Optimizing dose to blood- and immune-rich structures reduced lymphocyte depletion and prevented grade 3 lymphopenia after early-stage lung SBRT.
Modelled actinium-225 delivery reduced glioblastoma clonogens but had limited spatial reach
Convection-enhanced actinium-225 markedly reduced modelled clonogenic survival, but effective coverage extended only about 1.4 cm from each catheter.
Probabilistic coronary habitats enabled artery-focused cardiac sparing without angiography
Automatically predicted coronary habitats captured most arteries and enabled substantial dose reductions in three retrospectively replanned thoracic cases.