S729
Clinical – Lower GI
ESTRO 2026
2 DSC for CTV45, CTV50, and GTV, showing distribution across 20 patients. The dotted line indicates the clinical threshold of 0.8. Conclusion: The AIO approach enables a fully automated, time- efficient, and clinically feasible radiotherapy workflow for rectal cancer. High target conformity, stable plan quality, and promising early outcomes support its potential for broader clinical adoption. References: [1] Yu L, Zhao J, Zhang Z, Wang J, Hu W. Commissioning of and preliminary experience with a new fully integrated computed tomography linac. J Appl Clin Med Phys. 2021;22(7):208-223. [2] Han M, Yao G, Zhang W, et al. Segmentation of CT thoracic organs by multi-resolution VB-nets. SegTHOR@ISBI 2019[3] Shi F,Hu W,Wu J, et al. Deep learning empowered volume
Short-term toxicities, surgical outcomes, and tumor regression grades (TRG) were assessed at follow-up. Results: The entire AIO workflow was successfully completed in all patients. The median total treatment time was 37.5±6.9 minutes, with auto-segmentation and planning being the most time-consuming steps. The AIO auto-planning system achieved clinically acceptable target coverage and dose control in most cases, reflecting stable and reproducible plan quality across the cohort. The mean DSC for GTV, CTV45, and CTV50 were 0.83, 0.95, and 0.89, respectively. Gamma analysis showed excellent plan quality, with 3D pass rates exceeding 95% in all patients, and 2D pass rates across gantry angles ranging from 83.98% to 100.0% (3%/3 mm). Hematologic toxicity was the most common adverse event, with leukopenia in 55.0% of patients. Among 20 patients who completed follow-up, 19 underwent surgery and 1 achieved clinical complete response. The overall complete response (CR) rate was 15.0%, and 68.4% of surgical patients achieved TRG 0-1.
delineation of whole-body organs-at-risk for accelerated radiotherapy. Nat Commun.
2022;13(1):6566. [4] Zhong Y,Yu L,Zhao J, et al.Clinical implementation of automated treatment planning for rectum intensity-modulated radiotherapy using voxel- based dose prediction and post-optimization strategies. Front Oncol. 2021;11:697995. Keywords: One-stop RT, Automatic workflow, Rectal cancer Digital Poster 3845 Baseline Phenotyping of Weak Supervision Eligibility in an All-in-One Radiotherapy Workflow for Rectal Cancer Luqi Wang 1 , Ran Peng 1 , Xuemin Li 1 , Mengying Yang 2 , Yuxi Pan 1 , Mingqing Wang 1 , Wei Zhang 2 , Lecheng Jia 2 , Hao Wang 1 1 Radiation Oncology, Peking University Third Hospital, Beijing, China. 2 RT BU, Shanghai United Imaging Healthcare Co., Ltd., Shanghai, China Purpose/Objective: To characterize baseline phenotypes associated with weak supervision eligibility in an All-in-One (AIO) radiotherapy workflow for rectal cancer, combining CT simulation, auto-segmentation, auto-planning, and treatment on a CT-linac platform. Material/Methods: Weak supervision was defined by a point-based plan- quality rubric. PTV45 and PTV50 were the planning target volumes prescribed to 45 Gy and 50 Gy, respectively. Two mandatory hard-stop constraints— V45Gy ≥ 95% (PTV45) and V50Gy ≥ 95% (PTV50) —each contributed 30 points (total 60) and both had to be satisfied before applying a 16-item checklist (2.5 points per item; 40 points). Eligibility required a composite score ≥ 85/100 with no hard-stop violations (Table 1). Baseline candidate predictors comprised pre-
Fig.1 Mean absolute time (seconds) for each step, averaged across 20 patients.
Fig.
Made with FlippingBook - Share PDF online