深度学习在子宫内膜癌术后临床靶区自动分割中的应用

doi:10.13491/j.issn.1004-714X.2024.04.005

中国辐射卫生

2024, Vol. 33

Issue (4): 376-383 DOI: 10.13491/j.issn.1004-714X.2024.04.005

论著

本期目录 | 过刊浏览 | 高级检索

深度学习在子宫内膜癌术后临床靶区自动分割中的应用

薛娴¹, 王凯玥², 梁大柱³, 丁静静⁴, 江萍², 孙全富¹, 程金生¹, 戴相昆⁴, 付晓沙⁵, 朱静洋⁶, 周付根⁷

1. 中国疾病预防控制中心辐射防护与核安全医学所, 北京 100088;
2. 北京大学第三医院放疗科, 北京 100089;
3. 东北大学, 辽宁沈阳 110819;
4. 中国人民解放军总医院放疗科, 北京 100039;
5. 谢菲尔德哈勒姆大学, 英国谢菲尔德 S11WB;
6. 北京忠诚肿瘤医院肿瘤科, 北京 100161;
7. 北京航空航天大学, 北京 100083

Application of deep learning in automatic segmentation of clinical target volume in brachytherapy after surgery for endometrial carcinoma

XUE Xian¹, WANG Kaiyue², LIANG Dazhu³, DING Jingjing⁴, JIANG Ping², SUN Quanfu¹, CHENG Jinsheng¹, DAI Xiangkun⁴, FU Xiaosha⁵, ZHU Jingyang⁶, ZHOU Fugen⁷

1. National Institute for Radiological Protection, Chinese Center for Disease Control and Prevention (CDC), Beijing 100088 China;
2. Department of Radiotherapy, Peking University Third Hospital, Beijing 100089 China;
3. Northeastern University, Shenyang 110819 China;
4. Department of Radiotherapy, Chinese People’s Liberation Army (PLA) General Hospital, Beijing 100039 China;
5. Biomedical Research Centre, Sheffield Hallam University, Sheffield S11WB UK;
6. Department of radiation oncology, Zhongcheng Cancer center, Beijing 100160 China;
7. Beihang University, Beijing 100083 China

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (3081 KB) HTML ( )
输出: BibTeX | EndNote (RIS)

摘要目的评估3种深度学习（DL）算法在子宫内膜癌（EC）术后患者高剂量率近距离放射治疗（high-dose-rate brachytherapy， HDR BT）中，自动分割临床靶区（CTV）的应用结果。方法数据集由 306 名子宫内膜癌术后患者的计算机断层扫描（CT）图像组成，按比例分为训练集（246例）、验证集（30例）和测试集（30例）。比较3种深度卷积神经网络模型（3D U-Net、3D Res U-Net和 V-Net ）在CTV 分割上的性能。采用定量指标分别为戴斯相似性系数（DSC）、豪斯多夫距离（HD）、豪斯多夫距离第95 百分位数（HD95%）和交并比（IoU）。结果在测试阶段中，3D U-Net、3D Res U-Net 和 V-Net 分割CTV得到的DSC 平均值分别为 0.90 ± 0.07、0.95 ± 0.06 和 0.95 ± 0.06；HD平均值（mm）分别为2.51 ± 1.70、0.96 ± 1.01和0.98 ± 0.95；HD95%平均值（mm）分别为1.33 ± 1.02、0.65 ± 0.91和 0.40 ± 0.72，IoU 平均值分别为0.85 ± 0.11、0.91 ± 0.09 和0.92 ± 0.09。其中，V-Net分割结果与高级临床医生勾画结果更接近，CTV 的分割时间 < 3.2 s，节省了临床医生的工作时间。结论 V-Net 在 CTV 分割方面表现最佳，定量指标和临床评估均优于其他模型。该方法与基准真实值高度一致，有效减少医生间差异，缩短治疗时间。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	薛娴
	王凯玥
	梁大柱
	丁静静
	江萍
	孙全富
	程金生
	戴相昆
	付晓沙
	朱静洋
	周付根

关键词 ：深度学习模型, 子宫内膜癌术后, 高剂量率近距离放射治疗, 临床靶区自动分割

收稿日期: 2024-03-12

PACS:

R816

通讯作者: 孙全富，E-mail：sunquanfu@nirp.chinacdc.cn E-mail: sunquanfu@nirp.chinacdc.cn

作者简介: 薛娴（1982—），女，山西人，副研究员，从事放射医学研究工作。E-mail：xuexian@nirp.chinacdc.cn

引用本文:

薛娴, 王凯玥, 梁大柱, 丁静静, 江萍, 孙全富, 程金生, 戴相昆, 付晓沙, 朱静洋, 周付根. 深度学习在子宫内膜癌术后临床靶区自动分割中的应用[J]. 中国辐射卫生, 2024, 33(4): 376-383.
XUE Xian, WANG Kaiyue, LIANG Dazhu, DING Jingjing, JIANG Ping, SUN Quanfu, CHENG Jinsheng, DAI Xiangkun, FU Xiaosha, ZHU Jingyang, ZHOU Fugen. Application of deep learning in automatic segmentation of clinical target volume in brachytherapy after surgery for endometrial carcinoma. Chinese Journal of Radiological Health, 2024, 33(4): 376-383.

链接本文:

http://www.zgfsws.com/CN/10.13491/j.issn.1004-714X.2024.04.005 或 http://www.zgfsws.com/CN/Y2024/V33/I4/376

[1] Xia CF, Dong XS, Li H, et al. Cancer statistics in China and United States, 2022: profiles, trends, and determinants[J]. Chin Med J (Engl), 2022, 135（5）: 584-590.
[2] Sundar S, Balega J, Crosbie E, et al. BGCS uterine cancer guidelines: Recommendations for practice[J]. Eur J Obstet Gynecol Reprod Biol, 2017, 213: 71-97.
[3] Wortman BG, Astreinidou E, Laman MS, et al. Brachytherapy quality assurance in the PORTEC-4a trial for molecular-integrated risk profile guided adjuvant treatment of endometrial cancer[J]. Radiother Oncol, 2021, 155: 160-166.
[4] Ma CY, Zhou JY, Xu XT, et al. Deep learning-based auto-segmentation of clinical target volumes for radiotherapy treatment of cervical cancer[J]. J Appl Clin Med Phys, 2022, 23（2）: e13470.
[5] Liu ZK, 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.
[6] Liang F, Qian PJ, Su KH, et al. Abdominal, multi-organ, auto-contouring method for online adaptive magnetic resonance guided radiotherapy: An intelligent, multi-level fusion approach[J]. Artif Intell Med, 2018, 90: 34-41.
[7] Sharp G, Fritscher KD, Pekar V, et al. Vision 20/20: perspectives on automated image segmentation for radiotherapy[J]. Med Phys, 2014, 41（5）: 050902.
[8] Nouranian S, Mahdavi SS, Spadinger I, et al. A multi-atlas-based segmentation framework for prostate brachytherapy[J]. IEEE Trans Med Imaging, 2015, 34（4）: 950-961.
[9] Pekar V, Mcnutt TR, Kaus MR. Automated model-based organ delineation for radiotherapy planning in prostatic region[J]. Int J Radiat Oncol Biol Phys, 2004, 60（3）: 973-980.
[10] Cao RF, Pei X, Ge N, et al. Clinical target volume auto-segmentation of esophageal cancer for radiotherapy after radical surgery based on deep learning[J]. Technol Cancer Res Treat, 2021, 20: 15330338211034284. DOI: 10.1177/15330338211034284.
[11] 陶森. 基于深度学习的肾脏肿瘤分割方法研究[D]. 西安: 西安电子科技大学, 2021.
Tao S. Research on segmentation method of kidney tumor based on deep learning[D]. Xi’an: Xidian University, 2021.
[12] 徐思则, 刘威. 基于UNet网络的乳腺癌肿瘤细胞图像分割[J]. 电子设计工程，2022，30（12）：63-66,73.
Xu SZ, Liu W. UNet-based image segmentation of breast cancer tumor cells[J]. Electron Des Eng, 2022, 30（12）: 63-66,73.
[13] 徐旺旺, 许良凤, 李博凯, 等. TransAS-UNet: 融合Swin Transformer和UNet的乳腺癌区域分割[J]. 中国图象图形学报，2024，29（3）：741-754.
Xu WW, Xu LF, Li BK, et al. TransAS—UNet: regional segmentation of breast cancer Swin Transformer and of UNet algorithm[J]. J Image Graph, 2024, 29（3）: 741-754.
[14] Yu H, Li JQ, Zhang LX, et al. Design of lung nodules segmentation and recognition algorithm based on deep learning[J]. BMC Bioinformatics, 2021, 22（S5）: 314.
[15] Zhao C, Shi S, He Z, et al. Spatial-temporal V-Net for automatic segmentation and quantification of right ventricle on gated myocardial perfusion SPECT images[J]. Med Phys, 2023, 50（12）: 7415-7426.
[16] Yan JF, Qin X, Qiao CX, et al. Auto-segmentation of the clinical target volume using a domain-adversarial neural network in patients with gynaecological cancer undergoing postoperative vaginal brachytherapy[J]. Precis Radiat Oncol, 2023, 7（3）: 189-196.
[17] Xue X, Liang DZ, Wang KY, et al. A deep learning-based 3D Prompt-nnUnet model for automatic segmentation in brachytherapy of postoperative endometrial carcinoma[J]. J Appl Clin Med Phys, 2024: e14371. DOI: 10.1002/acm2.14371.
[18] Small W Jr, Beriwal S, Demanes DJ, et al. American Brachytherapy Society consensus guidelines for adjuvant vaginal cuff brachytherapy after hysterectomy[J]. Brachytherapy, 2012, 11（1）: 58-67.