中国医学科学院北京协和医学院北京协和医院放疗科;
目的：开发一种基于深度学习的施源器自动重建系统，以实现CT引导妇科近距离治疗中Fletcher施源器高效准确地自动重建。方法：施源器自动重建系统分为两个部分：应用2.5D的DpnUNet分割CT图像上的施源器掩膜；通过三维连通区域算法以及骨骼提取算法获取数字化的施源器管道中心线。选取2022年7月至2023年7月在北京协和医院接受妇科近距离放射治疗的68例患者资料，将其中10例患者CT计划作为测试集，将58例患者CT计划采用十折交叉验证方法用于训练，对开发的施源器自动重建系统结果与手动重建结果进行几何一致性比较，并通过三维后装逆向优化计划设计获取剂量学指标高风险临床靶体积(HR-CTV)、90%和98%靶区体积剂量(D90、D98)，膀胱、直肠、乙状结肠和小肠的接受最大照射剂量的2 cc体积内的最小剂量(D2cc)，探究自动重建系统的临床可用性。结果：在10例测试集患者数据中，自动重建与手动重建的宫腔管以及左右穹窿管中心线顶端平均距离分别为0.335、0.361和0.362 mm，中心线之间的平均豪斯多夫距离(HD)分别为0.398、0.367和0.324 mm；保持驻留位置和驻留时间一致的情况下，两种计划的剂量体积直方图(DVH)参数差异均<2%，具有很高的几何一致性以及临床价值。结论：施源器自动重建系统能够实现高精度的Fletcher施源器的全自动重建，降低潜在的人为错误概率，并提升临床工作效率。
| 55 | 0 | 19 |
| 下载次数 | 被引频次 | 阅读次数 |
[1]Sung H,Ferlay J,Siegel RL,et al.Global Cancer Statistics 2020:GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in185 Countries[J].CA Cancer J Clin,2021,71(3):209-249.DOI:10.3322/caac.21660.
[2]中国抗癌协会妇科肿瘤专业委员会,中国抗癌协会肿瘤多学科诊疗(MDT)专业委员会,中国医师协会肿瘤多学科诊疗专业委员会.妇科恶性肿瘤多学科诊疗中国专家共识(2022年版)[J].中国癌症杂志,2022,32(8):747-756.DOI:10.19401/j.cnki.1007-3639.2022.08.010.
[3]Viswanathan AN,Beriwal S,De Los Santos JF,et al.American Brachytherapy Society consensus guidelines for locally advanced carcinoma of the cervix.Part II:High-dose-rate brachytherapy[J].Brachytherapy,2012,11(1):47-52.DOI:10.1016/j.brachy.2011.07.002.
[4]Mahantshetty U,Poetter R,Beriwal S,et al.IBS-GEC ESTRO-ABS recommendations for CT based contouring in image guided adaptive brachytherapy for cervical cancer[J].Radiother Oncol,2021,160:273-284.DOI:10.1016/j.radonc.2021.05.010.
[5]De Leeuw AAC,Moerland MA,Nomden C,et al.Applicator reconstruction and applicator shifts in 3D MR-based PDR brachytherapy of cervical cancer[J].Radiother Oncol,2009,93(2):341-346.DOI:10.1016/j.radonc.2009.05.003.
[6]Zunair H,Ben Hamza A.Sharp U-Net:Depthwise convolutional network for biomedical image segmentation[J].Comput Biol Med,2021,136:104699.DOI:10.1016/j.compbiomed.2021.104699.
[7]Arganda-Carreras I,Turaga SC,Berger DR,et al.Crowdsourcing the creation of image segmentation algorithms for connectomics[J].Front Neuroanat,2015,9:142.DOI:10.3389/fnana.2015.00142.
[8]Liu Z,Liu X,Guan H,et al.Development and validation of a deep learning algorithm for auto-delineation of clinical target volume and organs at risk in cervical cancer radiotherapy[J].Radiother Oncol,2020,153:172-179.DOI:10.1016/j.radonc.2020.09.060.
[9]Michaud AL,Benedict S,Montemayor E,et al.Workflow efficiency for the treatment planning process in CT-guided high-dose-rate brachytherapy for cervical cancer[J].Brachytherapy,2016,15(5):578-583.DOI:10.1016/j.brachy.2016.06.001.
[10]Tian X,Li C,Hou Y,et al.Artificial intelligence in brachytherapy for cervical cancer[J].J Cancer Res Ther,2022,18(5):1241.DOI:10.4103/jcrt.jcrt_2322_21.
[11]Hellebust TP,Kirisits C,Berger D,et al.Recommendations from Gynaecological(GYN)GEC-ESTRO Working Group:Considerations and pitfalls in commissioning and applicator reconstruction in 3D image-based treatment planning of cervix cancer brachytherapy[J].Radiother Oncol,2010,96(2):153-160.DOI:10.1016/j.radonc.2010.06.004.
[12]Damato AL,Viswanathan AN,Don SM,et al.A system to use electromagnetic tracking for the quality assurance of brachytherapy catheter digitization:Electromagnetic tracking for digitization QA[J].Med Phys,2014,41(10):101702.DOI:10.1118/1.4894710.
[13]Deufel CL,Tian S,Yan BB,et al.Automated applicator digitization for high-dose-rate cervix brachytherapy using image thresholding and density-based clustering[J].Brachytherapy,2020,19(1):111-118.DOI:10.1016/j.brachy.2019.09.002.
[14]Zhou J,Sebastian E,Mangona V,et al.Realtime catheter tracking for high-dose-rate prostate brachytherapy using an electromagnetic3D-guidance device:A preliminary performance study:Electromagnetic tracking of catheters in brachytherapy[J].Med Phys,2013,40(2):021716.DOI:10.1118/1.4788641.
[15]Poulin E,Racine E,Binnekamp D,et al.Fast,automatic,and accurate catheter reconstruction in HDR brachytherapy using an electromagnetic3D tracking system:Catheter reconstruction using an EM 3D tracking system[J].Med Phys,2015,42(3):1227-1232.DOI:10.1118/1.4908011.
[16]Jung H,Shen C,Gonzalez Y,et al.Deep-learning assisted automatic digitization of interstitial needles in 3D CT image based high doserate brachytherapy of gynecological cancer[J].Phys Med Biol,2019,64(21):215003.DOI:10.1088/1361-6560/ab3fcb.
[17]Zhang Y,Tian Z,Lei Y,et al.Automatic multineedle localization in ultrasound images using large margin mask RCNN for ultrasoundguided prostate brachytherapy[J].Phys Med Biol,2020,65(20):205003.DOI:10.1088/1361-6560/aba410.
[18]Weishaupt LL,Sayed HK,Mao X,et al.Approaching automated applicator digitization from a new angle:Using sagittal images to improve deep learning accuracy and robustness in high-dose-rate prostate brachytherapy[J].Br achytherapy,2022,21(4):520-531.DOI:10.1016/j.brachy.2022.02.005.
[19]Mcbride SE,Rogers WA,Fisk AD.Understanding human management of automation errors[J].Theor Issues Ergon Sci,2014,15(6):545-577.DOI:10.1080/1463922X.2013.817625.
[20]Mayadev J,Qi L,Lentz S,et al.Implant time and process efficiency for CT-guided highdose-rate brachytherapy for cervical cancer[J].Brachytherapy,2014,13(3):233-239.DOI:10.1016/j.brachy.2014.01.004.
基本信息:
DOI：
中图分类号:R197.39;TP18
引用信息:
[1]张文君,于浪,张杰等.基于深度学习的新型妇科后装施源器自动重建系统研发[J].中国医学装备,2024,21(04):7-12+27.
基金信息:
中央高水平医院临床科研项目近距离放射治疗创新技术的研发和临床应用(2022-PUMCH-B-052); 北京协和医院中央高水平医院临床科研专项2022年青年培优计划项目(2022-PUMCH-A-101)~~