CASIA OpenIR  > 脑图谱与类脑智能实验室  > 脑网络组研究
Multi-task autoencoder based classification-regression model for patient-specific VMAT QA
Wang, Le1,2,4; Li, Jiaqi3,5; Zhang, Shuming3; Zhang, Xile3; Zhang, Qilin3; Chan, Maria F.6; Yang, Ruijie3; Sui, Jing1,2,4
Source PublicationPHYSICS IN MEDICINE AND BIOLOGY
ISSN0031-9155
2020-12-07
Volume65Issue:23Pages:12
Abstract

Patient-specific quality assurance (PSQA) of volumetric modulated arc therapy (VMAT) to assure accurate treatment delivery is resource-intensive and time-consuming. Recently, machine learning has been increasingly investigated in PSQA results prediction. However, the classification performance of models at different criteria needs further improvement and clinical validation (CV), especially for predicting plans with low gamma passing rates (GPRs). In this study, we developed and validated a novel multi-task model called autoencoder based classification-regression (ACLR) for VMAT PSQA. The classification and regression were integrated into one model, both parts were trained alternatively while minimizing a defined loss function. The classification was used as an intermediate result to improve the regression accuracy. Different tasks of GPRs prediction and classification based on different criteria were trained simultaneously. Balanced sampling techniques were used to improve the prediction accuracy and classification sensitivity for the unbalanced VMAT plans. Fifty-four metrics were selected as inputs to describe the plan modulation-complexity and delivery-characteristics, while the outputs were PSQA GPRs. A total of 426 clinically delivered VMAT plans were used for technical validation (TV), and another 150 VMAT plans were used for CV to evaluate the generalization performance of the model. The ACLR performance was compared with the Poisson Lasso (PL) model and found significant improvement in prediction accuracy. In TV, the absolute prediction error (APE) of ACLR was 1.76%, 2.60%, and 4.66% at 3%/3 mm, 3%/2 mm, and 2%/2 mm, respectively; whereas the APE of PL was 2.10%, 3.04%, and 5.29% at 3%/3 mm, 3%/2 mm, and 2%/2 mm, respectively. No significant difference was found between CV and TV in prediction accuracy. ACLR model set with 3%/3 mm can achieve 100% sensitivity and 83% specificity. The ACLR model could classify the unbalanced VMAT QA results accurately, and it can be readily applied in clinical practice for virtual VMAT QA.

KeywordVMAT QA patient-specific QA deep learning radiotherapy
DOI10.1088/1361-6560/abb31c
WOS KeywordQUALITY-ASSURANCE ; RADIOMIC ANALYSIS ; IMRT ; MODULATION ; COMPLEXITY ; RADIOTHERAPY ; RAPIDARC ; BEAMS
Indexed BySCI
Language英语
Funding ProjectStrategic Priority Research Program of Chinese Academy of Science Capital's Funds for Health Improvement and Research[XDB32040100] ; National Natural Science Foundation of China[81071237] ; National Natural Science Foundation of China[61773380] ; Beijing Municipal Commission of science and technology collaborative innovation project[Z201100005620012] ; Capital's Funds for Health Improvement and Research[2020-2Z-40919] ; Natural Science Foundation of Beijing[7202223] ; Interdisciplinary Medicine Seed Found of Peking University[BMU20160585] ; NIH/NCI P30 Cancer Center Support Grant[CA008748]
Funding OrganizationStrategic Priority Research Program of Chinese Academy of Science Capital's Funds for Health Improvement and Research ; National Natural Science Foundation of China ; Beijing Municipal Commission of science and technology collaborative innovation project ; Capital's Funds for Health Improvement and Research ; Natural Science Foundation of Beijing ; Interdisciplinary Medicine Seed Found of Peking University ; NIH/NCI P30 Cancer Center Support Grant
WOS Research AreaEngineering ; Radiology, Nuclear Medicine & Medical Imaging
WOS SubjectEngineering, Biomedical ; Radiology, Nuclear Medicine & Medical Imaging
WOS IDWOS:000592683300001
PublisherIOP PUBLISHING LTD
Sub direction classification人工智能+医疗
Citation statistics
Cited Times:25[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/41666
Collection脑图谱与类脑智能实验室_脑网络组研究
Corresponding AuthorYang, Ruijie; Sui, Jing
Affiliation1.Chinese Acad Sci, Brainnetome Ctr, Beijing, Peoples R China
2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China
3.Peking Univ Third Hosp, Dept Radiat Oncol, Beijing, Peoples R China
4.Chinese Acad Sci, Univ Chinese Acad Sci, CAS Ctr Excellence Brain Sci & Intelligence Techn, Inst Automat, Beijing, Peoples R China
5.Capital Med Univ, Beijing Childrens Hosp, Beijing, Peoples R China
6.Mem Sloan Kettering Canc Ctr, Dept Med Phys, New York, NY 10021 USA
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Wang, Le,Li, Jiaqi,Zhang, Shuming,et al. Multi-task autoencoder based classification-regression model for patient-specific VMAT QA[J]. PHYSICS IN MEDICINE AND BIOLOGY,2020,65(23):12.
APA Wang, Le.,Li, Jiaqi.,Zhang, Shuming.,Zhang, Xile.,Zhang, Qilin.,...&Sui, Jing.(2020).Multi-task autoencoder based classification-regression model for patient-specific VMAT QA.PHYSICS IN MEDICINE AND BIOLOGY,65(23),12.
MLA Wang, Le,et al."Multi-task autoencoder based classification-regression model for patient-specific VMAT QA".PHYSICS IN MEDICINE AND BIOLOGY 65.23(2020):12.
Files in This Item: Download All
File Name/Size DocType Version Access License
22dfe72352d36e93c2fa(926KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang, Le]'s Articles
[Li, Jiaqi]'s Articles
[Zhang, Shuming]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang, Le]'s Articles
[Li, Jiaqi]'s Articles
[Zhang, Shuming]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang, Le]'s Articles
[Li, Jiaqi]'s Articles
[Zhang, Shuming]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 22dfe72352d36e93c2fa1ebd99fd7df7_326118b9f876ef9910c3596f60d57962_8.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.