2026-10-11T19:46:59Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33992074 2026-09-25T04:25:59Z category_388 portal_316 item_type_3 month_year_09_2026

Table 1_CT-based deep learning auto-segmentation of high-risk clinical target volume in CT-guided cervical cancer brachytherapy: a single-center pragmatic study.doc Chen-ying Ma (24234966) Yi Fu (315254) Lu Zhang (50563) Lou Liu (24234960) Yu Wang (12152) Le-cheng Jia (25107115) Wei-qi Xiong (25107118) Wei Zhang (405) Xiao-ting Xu (14650523) Ju-ying Zhou (24234963) Oncology and Carcinogenesis not elsewhere classified automated segmentation brachytherapy cervical cancer CT-guided workflow deep learning high-risk clinical target volume Introduction<p>Computed tomography (CT)-based high-risk clinical target volume (HR-CTV) auto-segmentation has been previously investigated, but evidence remains heterogeneous across applicators, target definitions, architectures, and clinical evaluation procedures. A pragmatic within-cohort benchmark of 2D U-Net, 3D U-Net, and nnFormer was performed in a CT-only, applicator-in-situ workflow.</p>Methods<p>CT images from 544 brachytherapy fractions in 182 patients were analyzed, including 509 fractions from 163 patients treated with tandem-and-ovoid applicators and 35 fractions from 19 patients treated with vaginal cylinders. All fractions from a patient remained in one partition (HR-CTV_c: 325/82/102 fractions; HR-CTV_v: 22/6/7 fractions). Only seven test fractions were available and thus the postoperative HR-CTV_v analysis was exploratory. Performance was assessed using Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (HD95), average surface distance (ASD), and physician consensus edit categories. Task-level CT normalization parameters were estimated exclusively from the training partition and fixed for validation and testing; spatial cropping was image centered and contour independent.</p>Results<p>In the intact-cervix test cohort, 3D U-Net showed the most favorable descriptive combination of overlap and surface agreement (DSC 0.848 ± 0.059; HD95 2.755 ± 1.688 mm; ASD 1.008 ± 0.622 mm). In the exploratory vaginal stump cohort, corresponding values were 0.788 ± 0.060, 4.724 ± 2.434 mm, and 2.917 ± 2.150 mm. On physician consensus review, 91/102 HR-CTV_c and 6/7 HR-CTV_v 3D U-Net contours required no or localized correction. In an ancillary 20-fraction independent-contouring analysis, physician-to-physician HR-CTV agreement was DSC 0.80 ± 0.06 and HD95 3.4 ± 1.8 mm.</p>Conclusions<p>In this internally validated CT-guided cohort, 3D U-Net provided the most favorable overall performance among the evaluated architectures for intact-cervix cases. The postoperative results provide a preliminary feasibility signal, and confirmation in a larger cohort is required. These findings support further physician-supervised implementation, followed by multicenter external validation and cohort-level dosimetric assessment.</p> 2026-09-25T04:25:59Z Dataset Dataset 10.3389/fonc.2026.1936913.s001 https://figshare.com/articles/dataset/Table_1_CT-based_deep_learning_auto-segmentation_of_high-risk_clinical_target_volume_in_CT-guided_cervical_cancer_brachytherapy_a_single-center_pragmatic_study_doc/33992074 CC BY 4.0