Feature selection strongly affected radiomics prediction of xerostomia after head-and-neck RT
T1 MRI with R-MRmr reached AUC 0.96 for early xerostomia, while late sticky-saliva prediction remained substantially weaker.
Tag
radiomics
MRI radiomics did not robustly outperform clinical predictors after head and neck chemoradiotherapy
A best MRI model reached AUC 0.91, but across 366 configurations radiomics did not consistently outperform a simple clinical model.
OmicsMap improved CT-based distant metastasis prediction across head and neck cancer cohorts
Modeling relationships between CT radiomic features improved distant-metastasis prediction over conventional radiomics across independent head and neck cancer cohorts.
Multimodal AI predicted radiation proctitis across different CT devices with 0.865 AUC
Combined radiomics, foundation-model and clinical features predicted grade ≥2 radiation proctitis with 0.865 AUC on an independent imaging device.
Planning-CT radiomics improved pretreatment prediction of poor rectal cancer response
Adding CTV radiomics increased internal AUROC from 0.507 to 0.754 for predicting poor response to rectal chemoradiotherapy.
CT imaging features improved local and distant control prediction in nasopharyngeal carcinoma
Planning CT features added prognostic information for local and distant control but did not significantly improve overall or progression-free survival prediction.
Planning computed tomography radiomics predicted recurrence in human papillomavirus-positive oropharyngeal cancer
A multi-regional clinical-radiomics model reached an external-test area under the curve of 0.908 for 5-year recurrence prediction.
Magnetic resonance imaging radiomics model stratified survival risk after Gamma Knife for brain metastases
A multimodal imaging, radiomics, and clinical deep learning model showed moderate external validation for survival risk after Gamma Knife radiosurgery.
Radiomics reproducibility depended on preprocessing in low-field magnetic resonance-guided radiotherapy
N4 bias correction with z-score normalization produced the most stable radiomic features on a 0.35 tesla magnetic resonance linear accelerator.
Computed tomography radiomics showed exploratory recurrence signals in mandibular osteoradionecrosis
In 24 surgically confirmed cases, three radiomic features differed nominally between pure osteoradionecrosis and osteoradionecrosis with recurrence.