专题报道:宫颈癌

AccuLearning自动勾画临床靶区和危及器官用于宫颈癌术后放疗的可行性研究

  • 陈飞 ,
  • 龚筱钦 ,
  • 余云鹏 ,
  • 游涛 ,
  • 王旭 ,
  • 戴春华 ,
  • 胡静
展开
  • 江苏大学附属医院放疗科 (江苏 镇江 212000 )

收稿日期: 2023-08-11

  网络出版日期: 2024-03-06

基金资助

江苏省卫生健康委员会医学科研重点项目(ZDB2020022);镇江市重点研发计划(社会发展)项目(SH2023002);镇江市社会发展指导性科技计划项目(FZ2020031)

Feasibility of automatic segmentation of CTV and OARs in postoperative radiotherapy for cervical cancer using AccuLearning

  • Fei CHEN ,
  • Xiaoqin GONG ,
  • Yunpeng YU ,
  • Tao YOU ,
  • Xu WANG ,
  • Chunhua DAI ,
  • Jing HU
Expand
  • Department of Radiotherapy,Affiliated Hospital of Jiangsu University,Zhenjiang 212000,China

Received date: 2023-08-11

  Online published: 2024-03-06

摘要

目的 从几何学和剂量学探讨AccuLearning(AL)建立宫颈癌术后临床靶区(CTV)和危及器官(OARs)自动勾画模型应用于临床的可行性。 方法 选取75例宫颈癌术后手动勾画CT数据,60例应用AL训练生成自动勾画模型,并对剩余15例进行自动勾画,同时将自动勾画图像上的放疗计划导入到手动勾画结构上,比较两种勾画方式的效率、戴斯相似系数(DSC)、豪斯多夫距离(HD)和剂量学差异。 结果 自动勾画时间明显小于手动勾画(P < 0.05);各结构DSC值≥ 0.87;肠袋和直肠的HD值在10 mm左右,其余结构小于5 mm;剂量学评估CTV(D98、V90%、V95%、Dmean、 HI)、肠袋(V50)和膀胱(V50)有显著性差异(P < 0.05)。 结论 基于AL形成的宫颈癌术后自动勾画模型提高了放疗效率,OARs具有直接应用于临床的可能性,CTV仍需进一步修改。

本文引用格式

陈飞 , 龚筱钦 , 余云鹏 , 游涛 , 王旭 , 戴春华 , 胡静 . AccuLearning自动勾画临床靶区和危及器官用于宫颈癌术后放疗的可行性研究[J]. 实用医学杂志, 2024 , 40(2) : 153 -157 . DOI: 10.3969/j.issn.1006-5725.2024.02.005

Abstract

Objective To explore the feasibility of automatic segmentation of clinical target volume (CTV) and organs at risk (OARs) for cervical cancer using AccuLearning (AL) based on geometric and dosimetric indices. Methods Seventy-five CT localization images with manual contouring data of postoperative cervical cancer were enrolled in this study. Sixty cases were randomly selected to trained to generate automatic segmentation model by AL, and the CTV and OARs of the remaining 15 cases were automatically contoured. Radiotherapy plans on the automatic segmentation contours were imported on the CT images of manual contours. The efficiency, Dice similarity coefficient (DSC), Hausdorff distance (HD) and dosimetric parameters were compared between the two methods. Results The time of automatic segmentation was significantly shorter than that of the manual contour(P < 0.05). The DSC of all structures were ≥ 0.87. The HD of bowel bag and rectum were about 10 mm, and that of the rest of OARs were less than 5 mm. CTV (D98, V90%, V95%, Dmean, HI), bowel bag (V50) and bladder (V50) had significant differences in dosimetric comparison(P < 0.05). Conclusion The automatic segmentation model based on AL can improve the efficiency of radiotherapy. Automatic segmentation of OARs has the potential of clinical application, while that of CTV still needs to be further modified.

参考文献

1 CHARGARI C, PEIGNAUX K, ESCANDE A, et al. Radiotherapy of cervical cancer[J]. Cancer Radiother, 2022, 26(1/2): 298-308. doi:10.1016/j.canrad.2021.11.009
2 POLGAR C, MAJOR T, VARGA S. Radiotherapy and radio-chemotherapy of cervical cancer[J].Magy Onkol, 2022, 66(4): 307-314.
3 GUO Q, WANG R, JIN D, et al. Comparison of adjuvant chemoradiotherapy versus radiotherapy in early-stage cervical cancer patients with intermediate-risk factors: A systematic review and meta-analysis[J]. Taiwan J Obstet Gyne, 2022, 61(1): 15-23. doi:10.1016/j.tjog.2021.11.006
4 FAYE M D, ALFIERI J. Advances in Radiation Oncology for the Treatment of Cervical Cancer[J]. Curr Oncol, 2022, 29(2): 928-944. doi:10.3390/curroncol29020079
5 陈默, 黄荣, 蒋军. 调强放射治疗条件下根治性宫颈癌的长期生存报道[J]. 实用医学杂志, 2020, 36(20): 2810-2814. doi:10.3969/j.issn.1006-5725.2020.20.013
6 CHOPRA S, GUPTA S, KANNAN S, et al. Late Toxicity After Adjuvant Conventional Radiation Versus Image-Guided Intensity-Modulated Radiotherapy for Cervical Cancer (PARCER): A Randomized Controlled Trial[J].J Clin Oncol, 2021, 39(33): 3682-3692. doi:10.1200/jco.20.02530
7 RIOS I, VASQUEZ I, CUERVO E, et al. Problems and solutions in IGRT for cervical cancer[J]. Rep Pract Oncol Radiother, 2018, 23(6): 517-527. doi:10.1016/j.rpor.2018.05.002
8 WANG J, CHEN Z, YANG C, et al. Evaluation Exploration of Atlas-Based and Deep Learning-Based Automatic Contouring for Nasopharyngeal Carcinoma[J]. Front Oncol, 2022, 12: 833816. doi:10.3389/fonc.2022.833816
9 KANO Y, IKUSHIMA H, SASAKI M, et al. Automatic contour segmentation of cervical cancer using artificial intelligence[J].J Radiat Res, 2021, 62(5): 934-944. doi:10.1093/jrr/rrab070
10 RADICI L, FERRARIO S, BORCA V C, et al. Implementation of a Commercial Deep Learning-Based Auto Segmentation Software in Radiotherapy: Evaluation of Effectiveness and Impact on Workflow[J]. Life (Basel), 2022, 12(12): 2088. doi:10.3390/life12122088
11 JU Z, WU Q, YANG W, et al. Automatic segmentation of pelvic organs-at-risk using a fusion network model based on limited training samples[J]. Acta Oncol, 2020, 59(8): 933-939. doi:10.1080/0284186x.2020.1775290
12 LIU Z, LIU X, GUAN H, et al. Development and validation of a deep learning algorithm for autodelineation 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
13 NIE S, WEI Y, ZHAO F, et al. A dual deep neural network for auto-delineation in cervical cancer radiotherapy with clinical validation[J]. Radiat Oncol, 2022, 17(1): 182. doi:10.1186/s13014-022-02157-5
14 XIAO C, JIN J, YI J, et al. RefineNet-based 2D and 3D automatic segmentations for clinical target volume and organs at risks for patients with cervical cancer in postoperative radiotherapy[J]. J Appl Clin Med Phys, 2022, 23(7): e13631. doi:10.1002/acm2.13631
15 DING Y, CHEN Z, WANG Z, et al. Three-dimensional deep neural network for automatic delineation of cervical cancer in planning computed tomography images[J]. J Appl Clin Med Phys, 2022, 23(4): e13566. doi:10.1002/acm2.13566
16 钱涵, 汪红艳, 王凡. 呼吸触发前瞻门控在早期非小细胞肺癌立体定向放射治疗中剂量学优势 [J]. 实用医学杂志, 2023, 39(1): 86-91.
17 TAN MBBS MRCP FRCR MD L T, TANDERUP PHD K, KIRISITS PHD C, et al. Image-guided Adaptive Radiotherapy in Cervical Cancer[J]. Semin Radiat Oncol, 2019, 29(3): 284-298. doi:10.1016/j.semradonc.2019.02.010
18 SHELLEY C E, BOLT M A, HOLLINGDALE R, et al. Implementing cone-beam computed tomography-guided online adaptive radiotherapy in cervical cancer[J].Clin Transl Radiat Oncol, 2023, 40: 100596. doi:10.1016/j.ctro.2023.100596
19 BRETO A L, SPIELER B, ZAVALA-ROMERO O, et al. Deep Learning for Per-Fraction Automatic Segmentation of Gross Tumor Volume (GTV) and Organs at Risk (OARs) in Adaptive Radiotherapy of Cervical Cancer[J]. Front Oncol, 2022, 12: 854349. doi:10.3389/fonc.2022.854349
20 CHOI M S, CHOI B S, CHUNG S Y, et al. Clinical evaluation of atlas- and deep learning-based automatic segmentation of multiple organs and clinical target volumes for breast cancer[J]. Radiother Oncol, 2020, 153: 139-145. doi:10.1016/j.radonc.2020.09.045
21 URAGO Y, OKAMOTO H, KANEDA T, et al. Evaluation of auto-segmentation accuracy of cloud-based artificial intelligence and atlas-based models[J]. Radiat Oncol, 2021, 16(1): 175. doi:10.1186/s13014-021-01896-1
22 CAO M, STIEHL B, YU V Y, et al. Analysis of geometric performance and dosimetric Impact of using automatic contour segmentation for radiotherapy planning[J]. Front Oncol, 2020, 10: 1762. doi:10.3389/fonc.2020.01762
23 ZHU J, CHEN X, YANG B, et al. Evaluation of Automatic Segmentation Model With Dosimetric Metrics for Radiotherapy of Esophageal Cancer[J]. Front Oncol, 2020, 10: 564737. doi:10.3389/fonc.2020.564737
24 KAWULA M, PURICE D, LI M, et al. Dosimetric impact of deep learning-based CT auto-segmentation on radiation therapy treatment planning for prostate cancer[J]. Radiat Oncol, 2022, 17(1): 21. doi:10.1186/s13014-022-01985-9
25 FUNG N T C, HUNG W M, SZE C K, et al. Automatic segmentation for adaptive planning in nasopharyngeal carcinoma IMRT: Time, geometrical, and dosimetric analysis[J]. Med Dosim, 2020, 45(1): 60-65. doi:10.1016/j.meddos.2019.06.002
26 何奕松,蒋家良,余行,等. 影像分割中Dice系数和Hausdorff距离的比较[J]. 中国医学物理学杂志,2019,36(11):1307-1311. doi:10.3969/j.issn.1005-202X.2019.11.012
文章导航

/