|Table of Contents|

Application of artificial intelligence to auto-segmentation organ at risk in radiotherapy for nasopharyngeal carcinoma

Journal Of Modern Oncology[ISSN:1672-4992/CN:61-1415/R]

Issue:
2023 15
Page:
2899-2903
Research Field:
Publishing date:

Info

Title:
Application of artificial intelligence to auto-segmentation organ at risk in radiotherapy for nasopharyngeal carcinoma
Author(s):
LI Lujun; YOU Yan; XIE Jinlian; GAO Jianquan
Department of Oncology,Wuzhou Red Cross Hospital,Guangxi Wuzhou 543000,China.
Keywords:
artificial intelligence; organ at risk; nasopharyngeal carcinoma; automatic segmentation
PACS:
R730.55
DOI:
10.3969/j.issn.1672-4992.2023.15.025
Abstract:
Objective:To explore the feasibility of using automatic segmentation of organ at risk (OARs) by PV-iCurve artificial intelligence (AI) system in treatment planning for nasopharyngeal carcinoma.Methods:52 nasopharyngeal carcinoma cases were included in this study,taking manual segmentation of OARs (OARs-M) by radiotherapist as reference standard,Dice similarity coefficient (DSC) and volume difference (VD) were used to evaluate the geometric accuracy of PV-iCurve AI system for automatic segmentation of OARs (OARs-A).Plans-M were optimized based on OARs-M,and Plans-A were optimized based on OARs-A.To compare the conformity index (CI) and heterogeneity index (HI) of PCTV2 and PGTVnx between Plans-A and Plans-M,and compare the OARs absorbed dose between the two groups.Results:For brainstem,spinal cord,eye,oral cavity,mandible,parotid,larynx and other large-sized OARs of AI auto-segmentation,the DSC values were all above 0.7,and the VD values were closer to 0.For lens,optic nerve,optic chiasma and other small-sized OARs of AI auto-segmentation,the DSC values were all below 0.7,and the VD values were farther away from 0.Compare the CI of PCTV2 of Plan-A and of Plan-M：0.84±0.02 vs 0.84±0.02 (P＞0.05).Compare the CI of PGTVnx of Plan-A and of Plan-M：0.84±0.04 vs 0.86±0.02 (P＜0.05).Compare the HI of PGTVnx of Plan-A and of Plan-M：0.07±0.02 vs 0.06±0.02 (P＜0.05).In terms of OAR absorbed dose,compared with the absorbed dose of OAR-M of Plan-M,the absorbed dose of other OAR-M except the mandible and left optic nerve was higher in Plan-A,and the difference between the two groups of six OAR-M,such as spinal cord,oral cavity,left parotid gland,larynx,left and right lens,was statistically significant (P＜0.05).Conclusion:The AI system is a high accuracy in segmentation large-sized OARs in the head and neck,but it is lacking in small-sized OARs.Using OAR-A in intensity-modulated radiotherapy will lead to high dose of OAR-M,which will increase the probability of complications in normal tissues.In order to accurately reflect the absorbed dose of OARs,it is suggested that necessary examination and modification to should be made before it is used to intensity-modulated radiotherapy treatment planning for nasopharyngeal carcinoma.

References:

［1］ZHU W,HUANG Y,ZENG L,et al.AnatomyNet:Deep learning for fast and fully automated whole-volume segmentation of head and neck anatomy［J］.Med Phys,2019,46(2):576-589.
［2］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.
［3］GOU S,TONG N,QI S,et al.Self-channel-and-spatial-attention neural network for automated multi-organ segmentation on head and neck CT images［J］.Phys Med Biol,2020,65(24):245034.
［4］VRTOVEC T,MOCNIK D,STROJAN P,et al.Auto-segmentation of organs at risk for head and neck radiotherapy planning:From atlas-based to deep learning methods［J］.Med Phys,2020,47(9):e929-e950.
［5］WONG J,HUANG V,WELLS D,et al.Implementation of deep learning-based auto-segmentation for radiotherapy planning structures:a workflow study at two cancer centers［J］.Radiat Oncol,2021,16(1):101.
［6］LI Y,RAO S,CHEN W,et al.Evaluating automatic segmentation for swallowing-related organs for head and neck cancer［J］.Technol Cancer Res Treat,2022,21:15330338221105724.
［7］WONG LM,AI QYH,MO FKF,et al.Convolutional neural network in nasopharyngeal carcinoma:how good is automatic delineation for primary tumor on a non-contrast-enhanced fat-suppressed T2-weighted MRI［J］.Jpn J Radiol,2021,39(6):571-579.
［8］LIAO W,HE J,LUO X,et al.Automatic delineation of gross tumor volume based on magnetic resonance imaging by performing a novel semisupervised learning framework in nasopharyngeal carcinoma［J］.Int J Radiat Oncol Biol Phys,2022,113(4):893-902.
［9］D'AVIERO A,RE A,CATUCCI F,et al.Clinical validation of a deep-learning segmentation software in head and neck:An early analysis in a developing radiation oncology center［J］.Int J Environ Res Public Health,2022,19(15):9057.
［10］KAWAHARA D,TSUNEDA M,OZAWA S,et al.Deep learning-based auto segmentation using generative adversarial network on magnetic resonance images obtained for head and neck cancer patients［J］.J Appl Clin Med Phys,2022,23(5):e13579.
［11］张富利,崔德琪,王秋生,等.基于深度学习和图谱库方法自动勾画肿瘤放疗中危及器官的比较［J］.中国医学物理学杂志,2019,36(12):1486-1490. ZHANG FL,CUI DQ,WANG QS,et al.Comparative study of deep learning- versus atlas-based auto-segmentation of organs-at-risk in tumor radiotherapy［J］.Chinese Journal of Medical Physics,2019,36(12):1486-1490.
［12］AHN SH,YEO AU,KIM KH,et al.Comparative clinical evaluation of atlas and deep-learning-based auto-segmentation of organ structures in liver cancer［J］.Radiat Oncol,2019,14(1):213.
［13］NIKOLOV S,BLACKWELL S,ZVEROVITCH A,et al.Clinically applicable segmentation of head and neck anatomy for radiotherapy:Deep learning algorithm development and validation study［J］.J Med Internet Res,2021,23(7):e26151.
［14］KORTE JC,HARDCASTLE N,NG SP,et al.Cascaded deep learning-based auto-segmentation for head and neck cancer patients:Organs at risk on T2-weighted magnetic resonance imaging［J］.Med Phys,2021,48(12):7757-7772.
［15］CLAESSENS M,VANREUSEL V,DE KERF G,et al.Machine learning-based detection of aberrant deep learning segmentations of target and organs at risk for prostate radiotherapy using a secondary segmentation algorithm［J］.Phys Med Biol,2022,67(11):115014.
［16］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.
［17］ZIJDENBOS AP,DAWANT BM,MARGOLIN RA,et al.Morphometric analysis of white matter lesions in MR images:method and validation［J］.IEEE Trans Med Imaging,1994,13:716-724.
［18］ZOU KH,WARFIELD SK,BHARATHA A,et al.Statistical validation of image segmentation quality based on a spatial overlap index［J］.Acad Radiol,2004,11(2):178-189.
［19］薛涛,吴迪,卢晓岩,等.RT-Mind自动勾画技术应用于鼻咽癌放射治疗可行性研究［J］.中国医学物理学杂志,2022,39(06):661-665. XUE T,WU D,LU XY,et al.Feasibility of RT-Mind auto-segmentation technique in radiotherapy for nasopharyngeal carcinoma ［J］.Chinese Journal of Medical Physics,2022,39(06):661-665.
［20］侯东梅,赵永瑞,殷旭君,等.两种自动勾画系统勾画头部小体积危及器官的对比［J］.中国医学物理学杂志,2022,39(06):676-681. HOU DM,ZHAO YR,YIN XJ,et al.Comparison of two different systems for automatic segmentation of small-sized organs-at-risk in the head［J］.Chinese Journal of Medical Physics,2022,39(06):676-681.
［21］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. LI HL,WANG PP,LI JK,et al.Effect of volume on the accuracy of organs-at-risk segmentation by automatic segmentation software［J］.Chinese Journal of Medical Physics,2020,37(7):797-802.
［22］吴哲,庞亚,明智,等.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 Z,PANG Y,MING Z,et al.Application of artificial intelligence technology in automatic delineation of organs at risk in nasopharyngeal carcinoma radiotherapy［J］.Practical Oncology Journal,2021,35(2):137-141.
［23］汪志,常艳奎,吴昊天,等.基于深度学习的危及器官自动勾画软件系统DeepViewer在放疗中的应用及评估［J］.中国医学物理学杂志,2020,37(08):1071-1075. WANG Z,CHANG YK,WU HT,et al.Application and evaluation of deep learning-based DeepViewer system for automatic segmentation of organs-at-risk［J］.Chinese Journal of Medical Physics,2020,37(08):1071-1075.
［24］郭红博,王佳舟,杨翠,等.基于深度学习的直肠癌放疗危及器官自动勾画的几何学和剂量学评估［J］.辐射研究与辐射工艺学报,2022,40(02):62-70. GUO HB,WANG JZ,YANG C,et al.Geometric and dosimetric evaluation of deep learning-based organs at risk auto-segmentation for rectal cancer［J］.Journal of Radiation Research and Radiation Processing,2022,40(02):62-70.

Memo

Memo:
广西壮族自治区梧州市科技计划项目（编号：202002140）
Last Update: 2023-06-30