人工智能技术在鼻咽癌放疗危及器官自动勾画中的应用研究

doi:10.11904/j.issn.1002-3070.2021.02.007

实用肿瘤学杂志 ›› 2021, Vol. 35 ›› Issue (2): 137-141.doi: 10.11904/j.issn.1002-3070.2021.02.007

人工智能技术在鼻咽癌放疗危及器官自动勾画中的应用研究

吴哲¹, 庞亚², 明智¹, 刘可¹, 王东¹, 晏军¹

1.自贡市第一人民医院肿瘤科(自贡 643000);
2.自贡市第一人民医院护理部

收稿日期:2020-12-25 修回日期:2021-01-12 出版日期:2021-04-28 发布日期:2021-04-27
通讯作者: 晏军,E-mail:wuzhecqu@163.com
作者简介:吴哲,男,(1991-),硕士,物理师,从事肿瘤放射物理学的研究。

Application of artificial intelligence technology in automatic delineation of organs at risk in nasopharyngeal carcinoma radiotherapy

WU Zhe¹, PANG Ya², MING Zhi¹, LIU Ke¹, WANG Dong¹, YAN Jun¹

1. Department of Radiation Oncology,Zigong First People's Hospital,Zigong 643000,China;
2. Department of Nursing,Zigong First People's Hospital

Received:2020-12-25 Revised:2021-01-12 Online:2021-04-28 Published:2021-04-27

摘要/Abstract

摘要： 目的评估基于人工智能技术的放疗危及器官自动勾画软件在临床应用中的价值。方法选取2019年4月—2020年4月在自贡市第一人民医院肿瘤科治疗的30例鼻咽癌患者进行研究。首先,使用AccuContour软件勾画30例鼻咽癌患者的危及器官;然后使用瓦里安Eclipse v13.6计划系统人为手工勾画危及器官;最后将自动勾画的危及器官和手工勾画的危及器官在Eclipse系统上进行对比,通过比较体积差异、位置差异、重合性差异、相似性差异等参数,评估自动勾画软件的几何精度,验证其应用于临床的可行性。结果以医师手工勾画为基准,AccuContour软件勾画的危及器官与手工勾画相比,小体积的危及器官体积差异较大,达到0.8,但位置差异较小,大体积的危及器官重合性和相似性较大,基本在0.7以上。自动勾画的危及器官某些CT层面与人工勾画相比会有较大差距。结论基于人工智能技术的放疗危及器官自动勾画软件在鼻咽癌危及器官勾画精度较高,经略微修改可以用于临床工作,能提高临床工作效率。

关键词: 鼻咽癌, 自动勾画, 危及器官, 放疗, 精准度

Abstract: Objective The aim of this study was to evaluate the clinical value of the software for automatic delineation of organs at risk in radiotherapy based on artificial intelligence technology. Methods Thirty cases of nasopharyngeal carcinoma treated in the department of Oncology at Zigong First people's Hospital from April 2019 and April 2020 were selected for the study.First,the AccuContour software was used to delineate the organs at risk(OARs)of 30 nasopharyngeal cancer patients,and then the Varian Eclipse v13.6 treatment planning system was used to manually delineate the OARs.Finally,the OARs automatically sketched and manually sketched were compared on the Eclipse system,and the geometric accuracy of the automatic sketching software was evaluated by comparing the volume difference,location difference,coincidence difference,similarity difference and other parameters,so as to verify its feasibility in the clinical application. Results Compared with manual delineation,the volume difference of small-size organs was larger,reaching 0.8,but the location difference was smaller.The coincidence and similarity of large size organs were larger,basically above 0.7.There was a big gap between automatic delineation and manual one in some CT sections of OARs. Conclusion The software based on artificial intelligence technology has a high accuracy in the delineation of organs at risk in nasopharyngeal carcinoma,and can be used in clinical work with slight modification,which can improve the efficiency of clinical work.

Key words: Nasopharynx carcinoma;Automatic segmentation;Organs at risk;Radiotherapy;Accuracy

中图分类号:

R730.55

吴哲, 庞亚, 明智, 刘可, 王东, 晏军. 人工智能技术在鼻咽癌放疗危及器官自动勾画中的应用研究[J]. 实用肿瘤学杂志, 2021, 35(2): 137-141.

WU Zhe, PANG Ya, MING Zhi, LIU Ke, WANG Dong, YAN Jun. Application of artificial intelligence technology in automatic delineation of organs at risk in nasopharyngeal carcinoma radiotherapy[J]. Journal of Practical Oncology, 2021, 35(2): 137-141.

0
/ / 推荐

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: http://journal09.magtechjournal.com/Jwk3_syzlxzz/CN/10.11904/j.issn.1002-3070.2021.02.007

http://journal09.magtechjournal.com/Jwk3_syzlxzz/CN/Y2021/V35/I2/137

参考文献

1 Barton MB,Frommer M,Shafiq J.Role of radiotherapy in cancer control in low-income and middle-income countries[J].Lancet Oncol,2006,7(7):584-595.
2 Chen AM,Chin R,Beron P,et al.Inadequate target volume delineation and local-regional recurrence after intensity-modulated radiotherapy for human papillomavirus-positive oropharynx cancer[J].Radiother Oncol,2017,23(3):412-418.
3 Kosmin M,Ledsam J,Romera-Paredes B,et al.Rapid advances in auto-segmentation of organs at risk and target volumes in head and neck cancer[J].Radiother Oncol,2019,135:130-140.
4 Velker VM,Rodrigues GB,Dinniwell R,et al.Creation of RTOG compliant patient CT-atlases for automated atlas based contouring of local regional breast and high-risk prostate cancers[J].Radiat Oncol,2013,8(1):188.
5 Barley S,Antoine C,Webster G,et al.Atlas-based auto-contouring-balancing accuracy with efficiency in onQ rts[J].Eur Oncol and Haematol,2014,10(2):98-101.
6 张玉海,李月敏.人工智能在肿瘤放射治疗中的研究进展[J].实用肿瘤学杂志,2019,33(6):570-574.
7 李华玲,王沛沛,李金凯,等.体积对自动勾画软件勾画危及器官准确性的影响[J].中国医学物理学杂志,2020,37(7):797-802.
8 王沛沛,李金凯,李彩虹,等.基于人工智能技术的危及器官自动勾画在胸部肿瘤中的应用[J].中国医学物理学杂志,2019,36(11):1346-1349.
9 Macchia ML,Fellin F,Maurizio A.Systematic evaluation of three different commercial software solutions for automatic segmentation for adaptive therapy in head-and-neck,prostate and pleural cancer[J].Radiat Oncol,2012,7(1):160.
10 Ju ZJ,Wu QN,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.
11 Wang J,Chen W,Studenski M,et al.A semi-automated tool for treatment plan-quality evaluation and clinical trial quality assurance[J].Phys Med Biol,2013,58(13):181-187.
12 Tong N,Gou S,Yang S,et al.Fully automatic multi-organ segmentation for head and neck cancer radiotherapy using shape representation model constrained fully convolutional neural networks[J].Med Phys,2018,45(10):4558-4567.
13 Lin L,Dou Q,Jin YM,et al.Deep learning for automated contouring of primary tumor volumes by MRI for nasopharyngeal carcinoma[J].Radiology,2019,291(3):677-686.
14 Li S,Xiao J,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(2):1-8.
15 Stapleford LJ,Lawson J,Perkins C,et al.Evaluation of automatic atlas-based lymph node segmentation for head-and-neck cancer[J].Int J Radiat Oncol Biol Phys,2010,77(3):959-966.
16 Sims R,Isambert A,Gregoire V,et al.A pre-clinical assessment of an atlas-based automatic segmentation tool for the head and neck[J].Radiother Oncol,2009,93(3):474-478.
17 Hvid CA,Elstrom UV,Jensen K,et al.Accuracy of softwareassisted contour propagation from planning CT to cone beam CT in head and neck radiotherapy[J].Acta Oncol,2016,55(11):1324-1330.
18 Ciardo D,Gerardi MA,Vigorito S,et al.Atlas-based segmentation in breast cancer radiotherapy:evalution of specific and generic-purposed atlases[J].Breast,2017,4(32):44-52.

[1]	李佳星,曹辉,张瑜,李勇,王姿,景楚滢,黄立敏. 二代测序检测上行型与下行型鼻咽癌中高频突变基因的研究[J]. 实用肿瘤学杂志, 2021, 35(1): 28-34.
[2]	卢江岳, 张建鑫, 葛晓峰. 鼻咽癌同步推量同步放化疗与常规分割后缩野同步放化疗的疗效及毒性反应对比分析[J]. 实用肿瘤学杂志, 2020, 34(5): 440-445.
[3]	秦凯, 程熠, 袁响林, 简丹妮, 张菁, 黄乐. 超声膀胱容量监测技术在宫颈癌术后调强放疗中的应用价值[J]. 实用肿瘤学杂志, 2020, 34(3): 232-236.
[4]	邓俊, 袁媛, 罗璇, 谭惜颜, 于恩浩, 刘科, 吴崢, 周菊梅, 朱苏雨. 化放疗模式下早期弥漫大B细胞淋巴瘤缩小放疗野对生存预后的影响[J]. 实用肿瘤学杂志, 2020, 34(3): 237-243.
[5]	谢艺才, 高健全. 动态增强MRI成像在鼻咽癌诊疗中的应用价值[J]. 实用肿瘤学杂志, 2020, 34(3): 258-261.
[6]	阮鹏, 谭爱丽. 血清中microRNA-127对鼻咽癌患者化疗抗性的预测价值[J]. 实用肿瘤学杂志, 2019, 33(6): 508-512.
[7]	刘耿淳, 申良方. 血清长链非编码RNA MALAT1和AFAP1-AS1与鼻咽癌临床病理特征和预后的关系[J]. 实用肿瘤学杂志, 2019, 33(6): 513-518.
[8]	李剑, 徐向英, 吕研. 局限期小细胞肺癌首程治疗失败后再程治疗的相关研究[J]. 实用肿瘤学杂志, 2019, 33(6): 519-524.
[9]	陈光浩, 方靖萱, 彭素娟, 严炜薇, 王福海, 陈承哲, 陈泗川, 潘建基, 邱素芳. PNCK对鼻咽癌细胞增殖和凋亡作用的研究[J]. 实用肿瘤学杂志, 2019, 33(5): 397-401.
[10]	朱诗佳徐向英. 海马区保护治疗小细胞肺癌全脑照射的研究进展[J]. 实用肿瘤学杂志, 2019, 33(4): 380-383.
[11]	李嘉琪,栾瑾微,张,玉,李香兰. 763例三阴性乳腺癌临床病理特征及复发、转移影响因素分析[J]. 实用肿瘤学杂志, 2019, 33(3): 244-249.
[12]	张攀, 张迪综述, 戴晓波审校. 复发鼻咽癌再程放射治疗的研究进展[J]. 实用肿瘤学杂志, 2019, 33(1): 92-96.
[13]	张云艳, 刘亚琴, 王磊, 张琳, 成海燕, 杨姗姗. RIZ1蛋白表达与宫颈鳞状细胞癌临床病理参数及放疗敏感性的相关性研究[J]. 实用肿瘤学杂志, 2017, 31(5): 405-410.
[14]	王赫隆, 云惟康, 王业伟, 冯丽娜, 白彦灵. 三种照射技术在髓母细胞瘤放射治疗中的剂量学分析[J]. 实用肿瘤学杂志, 2017, 31(5): 436-440.
[15]	李丹，王勇. 微创外科治疗联合药物对局限性鼻咽癌微小浸润灶的近远期疗效分析[J]. 实用肿瘤学杂志, 2017, 31(3): 234-237.

人工智能技术在鼻咽癌放疗危及器官自动勾画中的应用研究

Application of artificial intelligence technology in automatic delineation of organs at risk in nasopharyngeal carcinoma radiotherapy

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价