Radiomics analysis of EPID measurements for patient positioning error detection in thyroid associated ophthalmopathy radiotherapy
Copyright © 2021 Associazione Italiana di Fisica Medica. Published by Elsevier Ltd. All rights reserved..
PURPOSE: Electronic portal imaging detector (EPID)-based patient positioning verification is an important component of safe radiotherapy treatment delivery. In computer simulation studies, learning-based approaches have proven to be superior to conventional gamma analysis in the detection of positioning errors. To approximate a clinical scenario, the detectability of positioning errors via EPID measurements was assessed using radiomics analysis for patients with thyroid-associated ophthalmopathy.
METHODS: Treatment plans of 40 patients with thyroid-associated ophthalmopathy were delivered to a solid anthropomorphic head phantom. To simulate positioning errors, combinations of 0-, 2-, and 4-mm translation errors in the left-right (LR), superior-inferior (SI), and anterior-posterior (AP) directions were introduced to the phantom. The positioning errors-induced dose differences between measured portal dose images were used to predict the magnitude and direction of positioning errors. The detectability of positioning errors was assessed via radiomics analysis of the dose differences. Three classification models-support vector machine (SVM), k-nearest neighbors (KNN), and XGBoost-were used for the detection of positioning errors (positioning errors larger or smaller than 3 mm in an arbitrary direction) and direction classification (positioning errors larger or smaller than 3 mm in a specific direction). The receiver operating characteristic curve and the area under the ROC curve (AUC) were used to evaluate the performance of classification models.
RESULTS: For the detection of positioning errors, the AUC values of SVM, KNN, and XGBoost models were all above 0.90. For LR, SI, and AP direction classification, the highest AUC values were 0.76, 0.91, and 0.80, respectively.
CONCLUSIONS: Combined radiomics and machine learning approaches are capable of detecting the magnitude and direction of positioning errors from EPID measurements. This study is a further step toward machine learning-based positioning error detection during treatment delivery with EPID measurements.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2021 |
---|---|
Erschienen: |
2021 |
Enthalten in: |
Zur Gesamtaufnahme - volume:90 |
---|---|
Enthalten in: |
Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB) - 90(2021) vom: 15. Okt., Seite 1-5 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Zhang, Xiangbin [VerfasserIn] |
---|
Links: |
---|
Themen: |
EPID dosimetry |
---|
Anmerkungen: |
Date Completed 02.11.2021 Date Revised 02.11.2021 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1016/j.ejmp.2021.08.014 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM330631179 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM330631179 | ||
003 | DE-627 | ||
005 | 20231225211716.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231225s2021 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1016/j.ejmp.2021.08.014 |2 doi | |
028 | 5 | 2 | |a pubmed24n1102.xml |
035 | |a (DE-627)NLM330631179 | ||
035 | |a (NLM)34521015 | ||
035 | |a (PII)S1120-1797(21)00297-0 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Zhang, Xiangbin |e verfasserin |4 aut | |
245 | 1 | 0 | |a Radiomics analysis of EPID measurements for patient positioning error detection in thyroid associated ophthalmopathy radiotherapy |
264 | 1 | |c 2021 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 02.11.2021 | ||
500 | |a Date Revised 02.11.2021 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a Copyright © 2021 Associazione Italiana di Fisica Medica. Published by Elsevier Ltd. All rights reserved. | ||
520 | |a PURPOSE: Electronic portal imaging detector (EPID)-based patient positioning verification is an important component of safe radiotherapy treatment delivery. In computer simulation studies, learning-based approaches have proven to be superior to conventional gamma analysis in the detection of positioning errors. To approximate a clinical scenario, the detectability of positioning errors via EPID measurements was assessed using radiomics analysis for patients with thyroid-associated ophthalmopathy | ||
520 | |a METHODS: Treatment plans of 40 patients with thyroid-associated ophthalmopathy were delivered to a solid anthropomorphic head phantom. To simulate positioning errors, combinations of 0-, 2-, and 4-mm translation errors in the left-right (LR), superior-inferior (SI), and anterior-posterior (AP) directions were introduced to the phantom. The positioning errors-induced dose differences between measured portal dose images were used to predict the magnitude and direction of positioning errors. The detectability of positioning errors was assessed via radiomics analysis of the dose differences. Three classification models-support vector machine (SVM), k-nearest neighbors (KNN), and XGBoost-were used for the detection of positioning errors (positioning errors larger or smaller than 3 mm in an arbitrary direction) and direction classification (positioning errors larger or smaller than 3 mm in a specific direction). The receiver operating characteristic curve and the area under the ROC curve (AUC) were used to evaluate the performance of classification models | ||
520 | |a RESULTS: For the detection of positioning errors, the AUC values of SVM, KNN, and XGBoost models were all above 0.90. For LR, SI, and AP direction classification, the highest AUC values were 0.76, 0.91, and 0.80, respectively | ||
520 | |a CONCLUSIONS: Combined radiomics and machine learning approaches are capable of detecting the magnitude and direction of positioning errors from EPID measurements. This study is a further step toward machine learning-based positioning error detection during treatment delivery with EPID measurements | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a EPID dosimetry | |
650 | 4 | |a Machine learning | |
650 | 4 | |a Multifactorial error sources | |
650 | 4 | |a Positioning error detection | |
650 | 4 | |a Radiomics analysis | |
700 | 1 | |a Dai, Guyu |e verfasserin |4 aut | |
700 | 1 | |a Zhong, Renming |e verfasserin |4 aut | |
700 | 1 | |a Zhou, Li |e verfasserin |4 aut | |
700 | 1 | |a Xiao, Qing |e verfasserin |4 aut | |
700 | 1 | |a Wang, Xuetao |e verfasserin |4 aut | |
700 | 1 | |a Lai, Jialu |e verfasserin |4 aut | |
700 | 1 | |a Zhao, Jianling |e verfasserin |4 aut | |
700 | 1 | |a Li, Guangjun |e verfasserin |4 aut | |
700 | 1 | |a Bai, Sen |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB) |d 1997 |g 90(2021) vom: 15. Okt., Seite 1-5 |w (DE-627)NLM092554024 |x 1724-191X |7 nnns |
773 | 1 | 8 | |g volume:90 |g year:2021 |g day:15 |g month:10 |g pages:1-5 |
856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.ejmp.2021.08.014 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 90 |j 2021 |b 15 |c 10 |h 1-5 |