鼻咽癌放疗临床靶区人工智能勾画模型的训练及验证研究

何容; 陈川; 李梦侠; 肖何; 钟良志; 张岸梅; 谭本旭; 田仁昭; 耿明英

doi:10.16016/j.2097-0927.202110030

您当前的位置：

首页 >

文章列表页 >

鼻咽癌放疗临床靶区人工智能勾画模型的训练及验证研究

临床医学 | 更新时间：2026-01-09

- 鼻咽癌放疗临床靶区人工智能勾画模型的训练及验证研究
- Development of intelligent delineation model for clinical target volume of nasopharyngeal carcinoma based on integrated clinical health care system
- 陆军军医大学学报 2022年44卷第9期页码：906-912
- 作者机构：
  
  1.400042重庆，陆军特色医学中心肿瘤科
  2.400037 重庆，陆军军医大学(第三军医大学)第二附属医院肿瘤科
  3.400010 重庆，重庆医科大学附属第二医院肿瘤科
  4.401120 重庆，重庆医科大学附属第三医院肿瘤科
- 作者简介：
  
  [耿明英，E-mail: 380904661@qq.com GENG Mingying, E-mail: 380904661@qq.com
- 基金信息：
  
  国家科技部数字诊疗装备研发专项(2018YFC0114402)
- DOI：10.16016/j.2097-0927.202110030
  中图分类号： R319;R730.55;R739.63
- 收稿：2021-10-11，
  
  修回：2021-12-10，
  
  纸质出版：2022-05-15
- 稿件说明：
移动端阅览
何容, 陈川, 李梦侠, 等. 鼻咽癌放疗临床靶区人工智能勾画模型的训练及验证研究[J]. 陆军军医大学学报, 2022,44(9):906-912.

Rong HE, Chuan CHEN, Mengxia LI, et al. Development of intelligent delineation model for clinical target volume of nasopharyngeal carcinoma based on integrated clinical health care system[J]. Journal of Army Medical University, 2022, 44(9): 906-912.
何容, 陈川, 李梦侠, 等. 鼻咽癌放疗临床靶区人工智能勾画模型的训练及验证研究[J]. 陆军军医大学学报, 2022,44(9):906-912. DOI： 10.16016/j.2097-0927.202110030.

Rong HE, Chuan CHEN, Mengxia LI, et al. Development of intelligent delineation model for clinical target volume of nasopharyngeal carcinoma based on integrated clinical health care system[J]. Journal of Army Medical University, 2022, 44(9): 906-912. DOI： 10.16016/j.2097-0927.202110030.

摘要

目的

利用人工智能(artificial intelligence，AI)技术创建一套鼻咽癌临床靶区(clinical target volume

CTV)勾画模型，即AI+CTV模型，以提高鼻咽癌勾画效率和不同层级放疗单位、不同技术层次放疗医生鼻咽癌CTV勾画的准确性。

方法

选取2020年9月至2021年5月陆军特色医学中心肿瘤科放疗中心收治的分期较早(T1~2N2)且淋巴结较小(≤2 cm)的鼻咽癌患者30例，其中男性20例，女性10例；中位年龄52岁；按2017年鼻咽癌CTV勾画国际指南勾画CTV并进行深度学习，获得AI+CTV模型。利用陆军特色医学中心肿瘤科10例(男性7例，女性3例；中位年龄54岁)及3所教学医院6例(男性4例，女性2例；中位年龄46岁)鼻咽癌手动勾画CTV分别对该模型进行验证，对比分析其相似系数(dice similarity coefficient，DSC)、豪斯多夫距离(hausdorff distance，HD)、对称位置平均表面距离(average symmetric surface distance，ASSD)、最大对称表面距离(maximum symmetric surface distance，MSSD)和相对/绝对体积比(relative absolute volume difference，RAVD)，以评估AI勾画的可行性和准确性。

结果

该AI+CTV模型的准确性较高，平均DSC值为0.865，且内部验证显示高危区(CTV1)和低危区(CTV2)的中位DSC值均较高，分别为0.886和0.842。CTV1和CTV2的中位HD、ASSD、MSSD和RAVD均较低，分别为7.789 mm和6.144 mm、1.683 mm和1.467 mm、20.52 mm和14.03 mm及16.30%和15.14%。6例外部验证结果显示：CTV1勾画一致性高于CTV2。除1例患者的CTV2-DSC值接近0.7外，6例患者CTV1和其余5例患者CTV2勾画一致性较好(DSC值均>0.7)。

结论

基于小样本的AI+CTV模型在分期较早(T1~2N2)且淋巴结较小(≤2 cm)的鼻咽癌患者放疗CTV勾画中的临床应用基本可行。

Abstract

Objective

To established an intelligent delineation model of clinical target volume (CTV) for nasopharyngeal carcinoma (NPC) using artificial intelligence (AI) technology to improve the efficiency and the accuracy of CTV delineation among various radiotherapy institutes and clinicians with different technical levels.

Methods

Thirty NPC patients (20 males and 10 females

at a median age of 52 years) with early stage (T1~2N2) and small lymph nodes (≤ 2 cm) admitted in our Army Medical Center of PLA from September 2020 to May 2021 were collected in this study. CTV was delineated according to the International Guideline of CTV Delineation for NPC in 2017

and a deep learning model was trained to obtain AI+CTV model. The model was subsequently tested with manually segmented CTV in 10 NPC cases (7 males and 3 females

at a median age of 54 years) in our medical center and 6 cases (4 males and 2 females

at a median age of 46 years) from the teaching hospitals. Dice similarity coefficient (DSC)

Hausdorff distance (HD)

average symmetric surface distance (ASSD)

maximum symmetric surface distance (MSSD) and relative absolute volume difference (RAVD) were analyzed to evaluate the feasibility and accuracy of AI delineation.

Results

Our established AI+CTV model obtained quite high accuracy

with an average DSC value of 0.865

and median DSC values of high-risk areas (CTV1) and low-risk areas (CTV2) of 0.886 and 0.842

respectively. The median HD

ASSD

MSSD and RAVD of CTV1 and CTV2 were all quite low

that is

7.789 and 6.144 mm

1.683 and 1.467 mm

20.52 and 14.03 mm

16.30% and 15.14%

respectively. The results of external verification showed that CTV1 delineation had higher consistency than CTV2. CTV1 of 6 patients and CTV2 of 5 patients were well delineated (DSC value was greater than 0.7) except CTV2-DSC value of 1 case was close to 0.7.

Conclusion

Our AI+CTV model based on small samples is basically feasible for the clinical application of CTV delineation in NPC patients with early stage (T1~2N2) and small lymph nodes (≤2 cm).

关键词

Keywords

references

BRAY F, FERLAY J, SOERJOMATARAM I, et al . Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J ] . CA Cancer J Clin, 2018, 68(6): 394-424. DOI: 10.3322/caac.21492.

ZHANG L, HUANG Y, HONG S D, et al . Gemcitabine plus cisplatin versus fluorouracil plus cisplatin in recurrent or metastatic nasopharyngeal carcinoma: a multicentre, randomised, open-label, phase 3 trial[J ] . Lancet, 2016, 388(10054): 1883-1892. DOI: 10.1016/S0140-6736(16)31388-5.

LANG J Y, HU C S, LU T X. Chinese expert consensus on diagnosis and treatment of nasopharyngeal carcinoma: evidence from current practice and future perspectives. Cancer Manag Res. 2019.10(11): 6365-6376.

DAS I J, MOSKVIN V, JOHNSTONE P A. Analysis of treatment planning time among systems and planners for intensity-modulated radiation therapy[J]. J Am Coll Radiol, 2009, 6(7): 514-517. DOI: 10.1016/j.jacr.2008.12.013.

FENG M, DEMIROZ C, VINEBERG K A, et al . Normal tissue anatomy for oropharyngeal cancer: contouring variability and its impact on optimization[J ] . Int J Radiat Oncol Biol Phys, 2012, 84(2): e245-e249. DOI: 10.1016/j.ijrobp.2012.03.031.

BREEN S L, PUBLICOVER J, DE S S, et al . Intraobserver and inter observer variability in GTV delineation on FDG-PET-CT images of head and neck cancers[J ] . Int J Radiat Oncol Biol Phys, 2007, 68(3): 763-770.

YAMAZAKI H, SHIOMI H, TSUBOKURA T, et al . Quantitative assessment of inter-observer variability in target volume delineation on stereotactic radiotherapy treatment for pituitary adenoma and meningioma near optic tract[J ] . Radiat Oncol, 2011, 6: 10. DOI: 10.1186/1748-717X-6-10.

VINOD S K, MIN M, JAMESON M G, et al . A review of interventions to reduce inter-observer variability in volume delineation in radiation oncology[J ] . J Med Imaging Radiat Oncol, 2016, 60(3): 393-406. DOI: 10.1111/1754-9485.12462.

CARAVATTA L, MACCHIA G, MATTIUCCI G C, et al . Inter-observer variability of clinical target volume delineation in radiotherapy treatment of pancreatic cancer: a multi-institutional contouring experience[J ] . Radiat Oncol, 2014, 9: 198. DOI: 10.1186/1748-717X-9-198.

杜国波, 蒋利华, 郭飞, 等. ABAS软件自动勾画技术在鼻咽癌调强放疗中的应用研究[J]. 中华放射肿瘤学杂志, 2014, 23(1): 63-64.

DU G B, JIANG L H, GUO F, et al . Application of ABAS software automatic sketching technology in intensity modulated radiotherapy for nasopharyngeal carcinoma[J ] . Chin J Radiat Oncol, 2014, 23(1): 63-64.

LIN L, DOU Q, JIN Y M, et al . Deep learning for automated contouring of primary tumor volumes by MRI for nasopharyngeal carcinoma[J ] . Radiology, 2019, 291(3): 677-686. DOI: 10.1148/radiol.2019182012.

LI S H, XIAO J H, HE L, et al . The tumor target segmentation of nasopharyngeal cancer in CT images based on deep learning methods[J ] . Technol Cancer Res Treat, 2019, 18: 1533033819884561.

XUE X D, QIN N N, HAO X Y, et al . Sequential and iterative auto-segmentation of high-risk clinical target volume for radiotherapy of nasopharyngeal carcinoma in planning CT images[J ] . Front Oncol, 2020, 23(10): 1134.

YOUNG A V, WORTHAM A, WERNICK I, et al . Atlas-based segmentation improves consistency and decreases time required for contouring postoperative endometrial cancer nodal volumes[J ] . Int J Radiat Oncol Biol Phys, 2011, 79(3): 943-947. DOI: 10.1016/j.ijrobp.2010.04.063.

GRÉGOIRE V, ANG K, BUDACH W, et al . Delineation of the neck node levels for head and neck tumors: a 2013 update. DAHANCA, EORTC, HKNPCSG, NCIC CTG, NCRI, RTOG, TROG consensus guidelines[J ] . Radiother Oncol, 2014, 110(1): 172-181. DOI: 10.1016/j.radonc.2013.10.010.

LEE A W, NG W T, PAN J J, et al . International guideline for the delineation of the clinical target volumes (CTV) for nasopharyngeal carcinoma[J ] . Radiother Oncol, 2018, 126(1): 25-36.

罗京伟, 徐国镇, 高黎. 头颈部肿瘤放射治疗图谱(第3版)。人民卫生出版社.

LUO J W, XU G Z, GAO L. Atlas of radiotherapy for head and neck tumors (3rd Edition). Beijing: People′s Health Publishing House.

ALLOZI R, LI X A, WHITE J, et al . Tools for consensus analysis of experts′ contours for radiotherapy structure definitions[J ] . Radiother Oncol, 2010, 97(3): 572-578. DOI: 10.1016/j.radonc.2010.06.009.

MEN K, CHEN X Y, ZHU J, et al . Continual improvement of nasopharyngeal carcinoma segmentation with less labeling effort[J ] . Physica Medica, 2020, 80: 347-351. DOI: 10.1016/j.ejmp.2020.11.005.

ZIJDENBOS A P, DAWANT B M, MARGOLIN R A, et al . Morphometric analysis of white matter lesions in MR images: method and validation[J ] . IEEE Trans Med Imaging, 1994, 13(4): 716-724. DOI: 10.1109/42.363096.

MEN K, CHEN X Y, ZHANG Y, et al . Deep deconvolutional neural network for target segmentation of nasopharyngeal cancer in planning computed tomography images[J ] . Front Oncol. 2017, 20(7): 315. DOI: 10.3389/fonc.2017.00315.

JIANG C Y, GAO H, ZHANG L, et al . Distribution pattern and prognosis of metastatic lymph nodes in cervical posterior to level V in nasopharyngeal carcinoma patients[J ] . BMC Cancer, 2020, 20(1): 667. DOI: 10.1186/s12885-020-07146-z.

JIANG C, GONG B, GAO H, et al . Correlation analysis of neck node levels in 960 cases of Nasopharyngeal carcinoma (NPC)[J ] . Radiother Oncol, 2021, 161: 23-28. DOI: 10.1016/j.radonc.2021.05.020.

WANG X S, HU C S, YING H M, et al . Patterns of lymph node metastasis from nasopharyngeal carcinoma based on the 2013 updated consensus guidelines for neck node levels[J ] . Radiother Oncol, 2015, 115(1): 41-45. DOI: 10.1016/j.radonc.2015.02.017.

LIN L, LU Y, WANG X J, et al . Delineation of neck clinical target volume specific to nasopharyngeal carcinoma based on lymph node distribution and the international consensus guidelines[J ] . Int J Radiat Oncol Biol Phys, 2018, 100(4 ): 891-902. DOI:10.1016/j.ijrobp.2017.11.004.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

局部晚期鼻咽癌辅助化疗的临床疗效分析

利用支持向量机预测重症监护室患者死亡风险的研究

人工智能在临床领域的研究进展及前景展望

研精覃思，见微知著——人工智能开启精准病理诊断新时代

鼻咽癌类器官疾病模型的建立与药敏初步试验