Biological dosiomic features for the prediction of radiation pneumonitis in esophageal cancer patients

Abstract Objective The purpose of this study was to develop a model using dose volume histogram (DVH) and dosiomic features to predict the risk of radiation pneumonitis (RP) in the treatment of esophageal cancer with radiation therapy and to compare the performance of DVH and dosiomic features after...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Chanon Puttanawarut, Nat Sirirutbunkajorn, Suphalak Khachonkham, Poompis Pattaranutaporn, Yodchanan Wongsawat
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	Radiotherapy Dosiomic Machine learning Radiation pneumonitis Esophageal cancer Biological dose Medical physics. Medical radiology. Nuclear medicine R895-920 Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282
Acceso en línea:	https://doaj.org/article/2957cca70596408389c7c90987e36a79
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:2957cca70596408389c7c90987e36a79
record_format	dspace
spelling	oai:doaj.org-article:2957cca70596408389c7c90987e36a792021-11-21T12:14:04ZBiological dosiomic features for the prediction of radiation pneumonitis in esophageal cancer patients10.1186/s13014-021-01950-y1748-717Xhttps://doaj.org/article/2957cca70596408389c7c90987e36a792021-11-01T00:00:00Zhttps://doi.org/10.1186/s13014-021-01950-yhttps://doaj.org/toc/1748-717XAbstract Objective The purpose of this study was to develop a model using dose volume histogram (DVH) and dosiomic features to predict the risk of radiation pneumonitis (RP) in the treatment of esophageal cancer with radiation therapy and to compare the performance of DVH and dosiomic features after adjustment for the effect of fractionation by correcting the dose to the equivalent dose in 2 Gy (EQD2). Materials and methods DVH features and dosiomic features were extracted from the 3D dose distribution of 101 esophageal cancer patients. The features were extracted with and without correction to EQD2. A predictive model was trained to predict RP grade ≥ 1 by logistic regression with L1 norm regularization. The models were then evaluated by the areas under the receiver operating characteristic curves (AUCs). Result The AUCs of both DVH-based models with and without correction of the dose to EQD2 were 0.66 and 0.66, respectively. Both dosiomic-based models with correction of the dose to EQD2 (AUC = 0.70) and without correction of the dose to EQD2 (AUC = 0.71) showed significant improvement in performance when compared to both DVH-based models. There were no significant differences in the performance of the model by correcting the dose to EQD2. Conclusion Dosiomic features can improve the performance of the predictive model for RP compared with that obtained with the DVH-based model.Chanon PuttanawarutNat SirirutbunkajornSuphalak KhachonkhamPoompis PattaranutapornYodchanan WongsawatBMCarticleRadiotherapyDosiomicMachine learningRadiation pneumonitisEsophageal cancerBiological doseMedical physics. Medical radiology. Nuclear medicineR895-920Neoplasms. Tumors. Oncology. Including cancer and carcinogensRC254-282ENRadiation Oncology, Vol 16, Iss 1, Pp 1-9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Radiotherapy Dosiomic Machine learning Radiation pneumonitis Esophageal cancer Biological dose Medical physics. Medical radiology. Nuclear medicine R895-920 Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282
spellingShingle	Radiotherapy Dosiomic Machine learning Radiation pneumonitis Esophageal cancer Biological dose Medical physics. Medical radiology. Nuclear medicine R895-920 Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282 Chanon Puttanawarut Nat Sirirutbunkajorn Suphalak Khachonkham Poompis Pattaranutaporn Yodchanan Wongsawat Biological dosiomic features for the prediction of radiation pneumonitis in esophageal cancer patients
description	Abstract Objective The purpose of this study was to develop a model using dose volume histogram (DVH) and dosiomic features to predict the risk of radiation pneumonitis (RP) in the treatment of esophageal cancer with radiation therapy and to compare the performance of DVH and dosiomic features after adjustment for the effect of fractionation by correcting the dose to the equivalent dose in 2 Gy (EQD2). Materials and methods DVH features and dosiomic features were extracted from the 3D dose distribution of 101 esophageal cancer patients. The features were extracted with and without correction to EQD2. A predictive model was trained to predict RP grade ≥ 1 by logistic regression with L1 norm regularization. The models were then evaluated by the areas under the receiver operating characteristic curves (AUCs). Result The AUCs of both DVH-based models with and without correction of the dose to EQD2 were 0.66 and 0.66, respectively. Both dosiomic-based models with correction of the dose to EQD2 (AUC = 0.70) and without correction of the dose to EQD2 (AUC = 0.71) showed significant improvement in performance when compared to both DVH-based models. There were no significant differences in the performance of the model by correcting the dose to EQD2. Conclusion Dosiomic features can improve the performance of the predictive model for RP compared with that obtained with the DVH-based model.
format	article
author	Chanon Puttanawarut Nat Sirirutbunkajorn Suphalak Khachonkham Poompis Pattaranutaporn Yodchanan Wongsawat
author_facet	Chanon Puttanawarut Nat Sirirutbunkajorn Suphalak Khachonkham Poompis Pattaranutaporn Yodchanan Wongsawat
author_sort	Chanon Puttanawarut
title	Biological dosiomic features for the prediction of radiation pneumonitis in esophageal cancer patients
title_short	Biological dosiomic features for the prediction of radiation pneumonitis in esophageal cancer patients
title_full	Biological dosiomic features for the prediction of radiation pneumonitis in esophageal cancer patients
title_fullStr	Biological dosiomic features for the prediction of radiation pneumonitis in esophageal cancer patients
title_full_unstemmed	Biological dosiomic features for the prediction of radiation pneumonitis in esophageal cancer patients
title_sort	biological dosiomic features for the prediction of radiation pneumonitis in esophageal cancer patients
publisher	BMC
publishDate	2021
url	https://doaj.org/article/2957cca70596408389c7c90987e36a79
work_keys_str_mv	AT chanonputtanawarut biologicaldosiomicfeaturesforthepredictionofradiationpneumonitisinesophagealcancerpatients AT natsirirutbunkajorn biologicaldosiomicfeaturesforthepredictionofradiationpneumonitisinesophagealcancerpatients AT suphalakkhachonkham biologicaldosiomicfeaturesforthepredictionofradiationpneumonitisinesophagealcancerpatients AT poompispattaranutaporn biologicaldosiomicfeaturesforthepredictionofradiationpneumonitisinesophagealcancerpatients AT yodchananwongsawat biologicaldosiomicfeaturesforthepredictionofradiationpneumonitisinesophagealcancerpatients
_version_	1718419114291101696

Biological dosiomic features for the prediction of radiation pneumonitis in esophageal cancer patients

Ejemplares similares