Localized fine-tuning and clinical evaluation of deep-learning based auto-segmentation (DLAS) model for clinical target volume (CTV) and organs-at-risk (OAR) in rectal cancer radiotherapy

Table 1 Description of patient data grouping

Dataset name	Cohort volume, female/male	Age (min-max, median)	CT scanner	Image acquisition protocol (kVp, FOV, resolution)
Training	60, 21/39	33–83, 62	Siemens Sensation Open CT simulator	120, 65 cm, 1.27 × 1.27 × 5 mm³
External Validation (ExVal)	30, 10/20	37–86, 63	Siemens Sensation Open CT simulator	120, 65 cm, 1.27 × 1.27 × 5 mm³
Generalization Evaluation (GenEva)	30, 9/21	41–83, 66	Philips Big-bore RT simulator	120, 60 cm, 1.17 × 1.17 × 5 mm³

ISSN: 1748-717X