Novel dosimetric validation of a commercial CT scanner based deep learning automated contour solution for prostate radiotherapy

被引：0
|
作者：
Berenato, Salvatore [1 ]
Williams, Matthew [1 ]
Woodley, Owain [1 ]
Moehler, Christian [2 ]
Evans, Elin [3 ]
Millin, Anthony E. [1 ]
Wheeler, Philip A. [1 ]
机构：
[1] Velindre Canc Ctr, Radiotherapy Phys Dept, Cardiff CF14 2TL, Wales
[2] Siemens Healthineers, Forchheim, Germany
[3] Velindre Canc Ctr, Med Directorate, Cardiff, Wales
来源：
PHYSICA MEDICA-EUROPEAN JOURNAL OF MEDICAL PHYSICS | 2024年 / 122卷
关键词：
AI; Automation; Prostate cancer; VMAT; IMRT; Delineation; Segmentation; CT;
D O I：
10.1016/j.ejmp.2024.103339
中图分类号：
R8 [特种医学]; R445 [影像诊断学];
学科分类号：
1002 ; 100207 ; 1009 ;
摘要：
Purpose: OAR delineation accuracy influences: (i) a patient's optimised dose distribution (PD), (ii) the reported doses (RD) presented at approval, which represent plan quality. This study utilised a novel dosimetric validation methodology, comprehensively evaluating a new CT-scanner-based AI contouring solution in terms of PD and RD within an automated planning workflow. Methods: 20 prostate patients were selected to evaluate AI contouring for rectum, bladder, and proximal femurs. Five planning 'pipelines' were considered; three using AI contours with differing levels of manual editing (nominally none (AI(Std)), minor editing in specific regions (AI(MinEd)), and fully corrected (AI(FullEd))). Remaining pipelines were manual delineations from two observers (MDOb1, MDOb2). Automated radiotherapy plans were generated for each pipeline. Geometric and dosimetric agreement of contour sets AI(Std), AI(MinEd), AI(FullEd) and MDOb2 were evaluated against the reference set MDOb1. Non-inferiority of AI pipelines was assessed, hypothesising that compared to MDOb1, absolute deviations in metrics for AI contouring were no greater than that from MDOb2. Results: Compared to MDOb1, organ delineation time was reduced by 24.9 min (96 %), 21.4 min (79 %) and 12.2 min (45 %) for AI(Std), AI(MinEd) and AI(FullEd) respectively. All pipelines exhibited generally good dosimetric agreement with MDOb1. For RD, median deviations were within +/- 1.8 cm(3), +/- 1.7 % and +/- 0.6 Gy for absolute volume, relative volume and mean dose metrics respectively. For PD, respective values were within +/- 0.4 cm(3), +/- 0.5 % and +/- 0.2 Gy. Statistically (p < 0.05), AI(MinEd) and AI(FullEd) were dosimetrically non-inferior to MDOb2. Conclusions: This novel dosimetric validation demonstrated that following targeted minor editing (AI(MinEd)), AI contours were dosimetrically non-inferior to manual delineations, reducing delineation time by 79 %.
引用
收藏
页数：9
相关论文
共 50 条
  • [1] Evaluation of a CT scanner based deep learning auto-contouring solution for prostate radiotherapy
    Williams, M.
    Berenato, S.
    Woodley, O.
    Moehler, C.
    Evans, E.
    Millin, A.
    Wheeler, P.
    RADIOTHERAPY AND ONCOLOGY, 2023, 182 : S263 - S264
  • [2] Evaluation of a CT scanner based deep learning auto-contouring solution for lung radiotherapy
    Williams, M.
    Berenato, S.
    Moehler, C.
    Millin, A.
    Wheeler, P.
    RADIOTHERAPY AND ONCOLOGY, 2023, 182 : S1317 - S1318
  • [3] Deep Learning-Based Dosimetric Plan Quality Assessment for Prostate Radiotherapy
    Nomura, Y.
    Huang, C.
    Yang, Y.
    Kovalchuk, N.
    Surucu, M.
    Buyyounouski, M.
    Xing, L.
    MEDICAL PHYSICS, 2021, 48 (06)
  • [4] Fast VMAT planning for prostate radiotherapy: dosimetric validation of a deep learning-based initial segment generation method
    Ni, Yimin
    Chen, Shufei
    Hibbard, Lyndon
    Voet, Peter
    PHYSICS IN MEDICINE AND BIOLOGY, 2022, 67 (15):
  • [5] Clinical implementation of deep learning contour autosegmentation for prostate radiotherapy
    Cha, Elaine
    Elguindi, Sharif
    Onochie, Ifeanyirochukwu
    Gorovets, Daniel
    Deasy, Joseph O.
    Zelefsky, Michael
    Gillespie, Erin F.
    RADIOTHERAPY AND ONCOLOGY, 2021, 159 : 1 - 7
  • [6] Deep learning based conversion of CBCT to synthetic CT for prostate radiotherapy
    Zaffino, P.
    Raso, R.
    Angiocchi, M. C.
    Merola, M.
    Canino, S.
    Nonnis, M.
    Bavasso, A.
    Mezzotero, C.
    Anoja, R. A.
    Mazzei, E.
    Spadea, M. F.
    RADIOTHERAPY AND ONCOLOGY, 2020, 152 : S959 - S960
  • [7] MRI-based treatment planning for proton radiotherapy: dosimetric validation of a deep learning-based liver synthetic CT generation method
    Liu, Yingzi
    Lei, Yang
    Wang, Yinan
    Wang, Tonghe
    Ren, Lei
    Lin, Liyong
    McDonald, Mark
    Curran, Walter J.
    Liu, Tian
    Zhou, Jun
    Yang, Xiaofeng
    PHYSICS IN MEDICINE AND BIOLOGY, 2019, 64 (14):
  • [8] Commercial deep learning-based automated treatment planning validation for oropharyngeal cancer
    Dankers, F.
    Balasupramaniam, P.
    Brussee, M.
    Onderwater, A.
    de Jong, M.
    Astreinidou, E.
    RADIOTHERAPY AND ONCOLOGY, 2023, 182 : S1326 - S1327
  • [9] Dosimetric Analysis of Automated Treatment Planning for Whole Brain Radiotherapy with A Deep Learning Approach
    Han, E.
    Cardenas, C.
    Nguyen, C.
    Briere, T.
    Li, J.
    Yeboa, D.
    Wang, C.
    Court, L.
    Martel, M.
    Wen, Z.
    MEDICAL PHYSICS, 2020, 47 (06) : E606 - E606
  • [10] Evaluation of Automated Breast Cancer Contour Propagation From Planning CT to Cone Beam CT Based on Deep Learning
    Liang, X.
    Li, N.
    Zhou, X.
    Jin, H.
    Zhang, Z.
    Zhang, H.
    Dai, Z.
    Wang, X.
    Xie, Y.
    INTERNATIONAL JOURNAL OF RADIATION ONCOLOGY BIOLOGY PHYSICS, 2021, 111 (03): : E94 - E95
12345