[1]张珠祥,王丽娜,王宁,等.AccuLearning系统在宫颈癌放疗中自动勾画性能评估[J].中国医学物理学杂志,2026,43(7):847-851.[doi:DOI:10.3969/j.issn.1005-202X.2026.07.002]
　ZHANG Zhuxiang,WANG Lina,WANG Ning,et al.Performance evaluation of the AccuLearning system for automated delineation in cervical cancer radiotherapy[J].Chinese Journal of Medical Physics,2026,43(7):847-851.[doi:DOI:10.3969/j.issn.1005-202X.2026.07.002]
点击复制

AccuLearning系统在宫颈癌放疗中自动勾画性能评估()

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
43卷
期数:
2026年第7期
页码:
847-851
栏目:
医学放射物理
出版日期:
2026-07-22

文章信息/Info

Title:
Performance evaluation of the AccuLearning system for automated delineation in cervical cancer radiotherapy
文章编号:
1005-202X（2026）07-0847-05
作者:
张珠祥; 王丽娜; 王宁; 张鹏程; 祁宁
兰州大学第一医院（第一临床医学院）放疗科， 甘肃 兰州 730000
Author(s):
ZHANG Zhuxiang;  WANG Lina;  WANG Ning;  ZHANG Pengcheng;  QI Ning
Department of Radiation Oncology, the First Hospital of Lanzhou University (the First School of Clinical Medicine), Lanzhou 730000, China
关键词:
宫颈癌; 放射治疗; AccuLearning系统; 自动勾画; 手动勾画
Keywords:
Keywords: cervical cancer radiotherapy AccuLearning system automated delineation manual delineation
分类号:
R318；R811.1
DOI:
DOI:10.3969/j.issn.1005-202X.2026.07.002
文献标志码:
A
摘要:
目的：评估AccuLearning系统在宫颈癌放疗中自动勾画的性能。方法：回顾性纳入兰州大学第一医院2022年5月~2025年5月接受放疗的120名宫颈癌患者定位CT影像及手动勾画结构。随机选取80例作为训练集，用于开发和训练自动勾画模型，并对剩余40例作为独立测试集，生成自动勾画结果。对比测试集上生成的自动勾画和“金标准”手动勾画的几何学差异［戴斯相似系数（DSC）、豪斯多夫距离（HD95）、体积差异（RAVD）、质心偏差（DC）］。将基于手动勾画制定的原始放疗计划映射至测试集生成自动勾画的结构上，评估临床靶区（CTV）和危及器官（OAR）上两种勾画方式效率（耗时）及关键剂量学参数差异，包括CTV参数：D98、D2、V90、V95、Dmean、HI；OAR参数：肠袋和直肠的V30、V40、V50与Dmean；膀胱的V50和Dmean，以及骨髓、双侧股骨头的Dmean。结果：AccuLearning系统自动勾画时间显著短于手动勾画（P<0.05）；自动勾画几何学参数结果显示，右侧股骨头DSC值最高，直肠DSC值最低，DSC均值均≥0.80；肠袋DC值最大，骨髓DC值最小。肠袋HD95值最大，骨髓HD95值最小。肠袋RAVD值最大，骨髓RAVD值最小；剂量学参数比较结果显示，自动勾画与手动勾画CTV的D98、V90、V95、Dmean和HI差异具有统计学意义（P<0.05），在OAR方面，肠袋的V40、V50以及膀胱的V50差异具有统计学意义（P<0.05）。结论：基于AccuLearning自动勾画系统显著提高宫颈癌勾画效率，几何学相似性高，对OAR具有较高的应用潜力，CTV仍需进一步修改以保持精度。
Abstract:
Abstract: Objective To evaluate the performance of the AccuLearning system for automated delineation in cervical cancer radiotherapy. Methods Planning CT images and manually delineated structures from 120 cervical cancer patients who received radiotherapy at the First Hospital of Lanzhou University between May 2022 and May 2025 were retrospectively included. Eighty cases were randomly selected as the training set to develop and train the automated delineation model, and the remaining 40 cases served as the independent test set to generate the automated delineation results. Geometric differences between automated delineation and gold-standard manual delineation from the test set were compared using the Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), relative absolute volume difference (RAVD), and deviation of centroid (DC). The original radiotherapy plan based on manual delineation was mapped to the automatically delineated contours from the test set. The efficiency (delineation time) and key dosimetric parameters of the two delineation methods for clinical target volume (CTV) and organs-at-risk (OAR) were evaluated. The assessed dosimetric parameters included CTV parameters (D98, D2, V90, V95, Dmean, and HI) and OAR parameters (V30, V40, V50 and Dmean for the intestinal pouch and rectum, V50 and Dmean for the bladder, and the Dmean for the bone marrow and bilateral femoral head). Results The time required for automated delineation by the AccuLearning system was significantly shorter than that for manual delineation (P<0.05). Geometric evaluation of automated delineation results showed the maximum DSC value for the right femoral head and the minimum DSC value for the rectum, with all average DSC value ≥ 0.80. The intestinal pouch demonstrated the maximum CD, HD95, and RAVD, whereas bone marrow had the minimum CD, HD95, and RAVD. Dosimetric comparison revealed statistically significant differences in the D98, V90, V95, Dmean and HI of CTV between automated delineation and manual delineation (P<0.05). For OAR, statistically significant differences were observed in V40 and V50 of the intestinal pouch and V50 of the bladder (P<0.05). Conclusion Automated delineation using the AccuLearning system can significantly improve the delineation efficiency for cervical cancer and achieve high geometric similarity. Additionally, this system exhibits promising application potential for OAR, yet further optimization is required to preserve delineation accuracy for the CTV.

相似文献/References:

[1]武 杰,袁杭英,欧阳蓓蕾.内旋式放射治疗用面罩固定装置的设计[J].中国医学物理学杂志,2015,32(02):265.[doi:10.3969/j.issn.1005-202X.2015.02.027]
[2]戴相昆,杨丰蔚,杜 镭,等.等效均匀剂量优化法在宫颈癌调强计划中的应用[J].中国医学物理学杂志,2015,32(02):290.[doi:10.3969/j.issn.1005-202X.2015.02.033]
[3]司 森,吴鑫全,包尚联,等.基于GPU的蒙特卡洛放疗剂量模拟[J].中国医学物理学杂志,2015,32(01):1.[doi:10.3969/j.issn.1005-202X.2015.01.001]
[4]王 文,程梦云,杨 琪,等.基于MCNP源子程序的放射治疗剂量计算验证方法[J].中国医学物理学杂志,2015,32(01):13.[doi:10.3969/j.issn.1005-202X.2015.01.004]
[5]张一戈,邱小平,陈维军,等.基于图像引导技术对头颈部肿瘤临床摆位误差的剂量学影响[J].中国医学物理学杂志,2015,32(01):25.[doi:10.3969/j.issn.1005-202X.2015.01.007]
[6]孟慧鹏,孙小喆,王 昊,等.胸部偏后背肿瘤RapidArc采用仰卧位设计治疗计划的可行性分析[J].中国医学物理学杂志,2015,32(01):31.[doi:10.3969/j.issn.1005-202X.2015.01.008]
[7]刘 浩,王 新,李公平,等.宫颈癌放疗高危临床靶区变化及其对累计吸收剂量的影响[J].中国医学物理学杂志,2015,32(03):379.[doi:10.3969/j.issn.1005-202X.2015.03.017]
[8]庞皓文,孙小扬.基于快速自由形变的弹性配准算法在放疗CT中的应用[J].中国医学物理学杂志,2015,32(03):404.[doi:10.3969/j.issn.1005-202X.2015.03.023]
[9]孙晓欢,周咏春,谭丽娜,等.容积旋转调强与固定野调强在宫颈癌术后放疗中的剂量学比较[J].中国医学物理学杂志,2014,31(01):4604.[doi:10.3969/j.issn.1005-202X.2014.01.003]
[10]贾卫娟,周一兵,谭维维,等.利用模拟机及挡铅托架进行放疗前的治疗模拟[J].中国医学物理学杂志,2014,31(01):4622.[doi:10.3969/j.issn.1005-202X.2014.01.007]
[11]刘娟,李双双,高山宝,等. 宫颈癌螺旋断层放疗与静态调强技术的剂量学比较[J].中国医学物理学杂志,2019,36(1):23.[doi:DOI:10.3969/j.issn.1005-202X.2019.01.005]
　LIU Juan,LI Shuangshuang,GAO Shanbao,et al. Dosimetric comparison of helical tomotherapy versus fixed-field intensity-modulated radiotherapy for cervical cancer[J].Chinese Journal of Medical Physics,2019,36(7):23.[doi:DOI:10.3969/j.issn.1005-202X.2019.01.005]
[12]王金媛,徐寿平,杨微,等.算法和匹配数目对宫颈癌危及器官自动勾画的影响[J].中国医学物理学杂志,2019,36(11):1243.[doi:DOI:10.3969/j.issn.1005-202X.2019.11.001]
　WANG Jinyuan,XU Shouping,YANG Wei,et al.Effects of algorithm and matching number on the auto-segmentation of organs-at-risk in patients with cervical cancer[J].Chinese Journal of Medical Physics,2019,36(7):1243.[doi:DOI:10.3969/j.issn.1005-202X.2019.11.001]
[13]黄洋洋,李家兵,田玉龙,等.宫颈癌直线加速器放疗时保卵巢对靶区和危及器官的影响[J].中国医学物理学杂志,2020,37(9):1115.[doi:10.3969/j.issn.1005-202X.2020.09.007]
　HUANG Yangyang,LI Jiabing,TIAN Yulong,et al.Effects of ovaries sparing on planning target volume and organs-at-risk during linearaccelerator radiotherapy for cervical cancer[J].Chinese Journal of Medical Physics,2020,37(7):1115.[doi:10.3969/j.issn.1005-202X.2020.09.007]
[14]梁黎,李勇.体质量指数对锥形束CT引导的宫颈癌放疗分次间摆位误差的影响[J].中国医学物理学杂志,2023,40(2):144.[doi:DOI:10.3969/j.issn.1005-202X.2023.02.003]
　LIANG Li,LI Yong.Effect of body mass index on inter-fractional setup errors in cone beam CT-guided radiotherapy of cervical cancer[J].Chinese Journal of Medical Physics,2023,40(7):144.[doi:DOI:10.3969/j.issn.1005-202X.2023.02.003]
[15]许晨迪,姜晓勃,王亚娟,等.基于扇形束CT研究不同固定体位下宫颈癌术后放疗中膀胱体积改变对膀胱和小肠受照剂量的影响[J].中国医学物理学杂志,2023,40(5):529.[doi:DOI:10.3969/j.issn.1005-202X.2023.05.001]
　XU Chendi,JIANG Xiaobo,WANG Yajuan,et al.Effects of bladder volume variation on doses to bladder and small bowel in postoperative radiotherapy for cervical cancer in different patient positioning: an analysis based on FBCT[J].Chinese Journal of Medical Physics,2023,40(7):529.[doi:DOI:10.3969/j.issn.1005-202X.2023.05.001]

备注/Memo

备注/Memo:
【收稿日期】2026-03-21 【基金项目】甘肃省科技计划基础研究计划（25JRRA557） 【作者简介】张珠祥，主管技师，研究方向：放射治疗，E-mail: 13321314321@163.com
更新日期/Last Update: 2026-07-22