Prediction of Radiation-Induced Hypothyroidism Using Radiomic Data Analysis Does Not Show Superiority over Standard Normal Tissue Complication Models

State-of-art normal tissue complication probability (NTCP) models do not take into account more complex individual anatomical variations, which can be objectively quantitated and compared in radiomic analysis. The goal of this project was development of radiomic NTCP model for radiation-induced hypo...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Urszula Smyczynska, Szymon Grabia, Zuzanna Nowicka, Anna Papis-Ubych, Robert Bibik, Tomasz Latusek, Tomasz Rutkowski, Jacek Fijuth, Wojciech Fendler, Bartlomiej Tomasik
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Acceso en línea:https://doaj.org/article/8323964c7a5042faa47514bc6845f293
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:8323964c7a5042faa47514bc6845f293
record_format dspace
spelling oai:doaj.org-article:8323964c7a5042faa47514bc6845f2932021-11-11T15:36:09ZPrediction of Radiation-Induced Hypothyroidism Using Radiomic Data Analysis Does Not Show Superiority over Standard Normal Tissue Complication Models10.3390/cancers132155842072-6694https://doaj.org/article/8323964c7a5042faa47514bc6845f2932021-11-01T00:00:00Zhttps://www.mdpi.com/2072-6694/13/21/5584https://doaj.org/toc/2072-6694State-of-art normal tissue complication probability (NTCP) models do not take into account more complex individual anatomical variations, which can be objectively quantitated and compared in radiomic analysis. The goal of this project was development of radiomic NTCP model for radiation-induced hypothyroidism (RIHT) using imaging biomarkers (radiomics). We gathered CT images and clinical data from 98 patients, who underwent intensity-modulated radiation therapy (IMRT) for head and neck cancers with a planned total dose of 70.0 Gy (33–35 fractions). During the 28-month (median) follow-up 27 patients (28%) developed RIHT. For each patient, we extracted 1316 radiomic features from original and transformed images using manually contoured thyroid masks. Creating models based on clinical, radiomic features or a combination thereof, we considered 3 variants of data preprocessing. Based on their performance metrics (sensitivity, specificity), we picked best models for each variant ((0.8, 0.96), (0.9, 0.93), (0.9, 0.89) variant-wise) and compared them with external NTCP models ((0.82, 0.88), (0.82, 0.88), (0.76, 0.91)). We showed that radiomic-based models did not outperform state-of-art NTCP models (<i>p</i> > 0.05). The potential benefit of radiomic-based approach is that it is dose-independent, and models can be used prior to treatment planning allowing faster selection of susceptible population.Urszula SmyczynskaSzymon GrabiaZuzanna NowickaAnna Papis-UbychRobert BibikTomasz LatusekTomasz RutkowskiJacek FijuthWojciech FendlerBartlomiej TomasikMDPI AGarticleradiomicsradiation-induced hypothyroidismNTCPheadneck cancerNeoplasms. Tumors. Oncology. Including cancer and carcinogensRC254-282ENCancers, Vol 13, Iss 5584, p 5584 (2021)
institution DOAJ
collection DOAJ
language EN
topic radiomics
radiation-induced hypothyroidism
NTCP
head
neck cancer
Neoplasms. Tumors. Oncology. Including cancer and carcinogens
RC254-282
spellingShingle radiomics
radiation-induced hypothyroidism
NTCP
head
neck cancer
Neoplasms. Tumors. Oncology. Including cancer and carcinogens
RC254-282
Urszula Smyczynska
Szymon Grabia
Zuzanna Nowicka
Anna Papis-Ubych
Robert Bibik
Tomasz Latusek
Tomasz Rutkowski
Jacek Fijuth
Wojciech Fendler
Bartlomiej Tomasik
Prediction of Radiation-Induced Hypothyroidism Using Radiomic Data Analysis Does Not Show Superiority over Standard Normal Tissue Complication Models
description State-of-art normal tissue complication probability (NTCP) models do not take into account more complex individual anatomical variations, which can be objectively quantitated and compared in radiomic analysis. The goal of this project was development of radiomic NTCP model for radiation-induced hypothyroidism (RIHT) using imaging biomarkers (radiomics). We gathered CT images and clinical data from 98 patients, who underwent intensity-modulated radiation therapy (IMRT) for head and neck cancers with a planned total dose of 70.0 Gy (33–35 fractions). During the 28-month (median) follow-up 27 patients (28%) developed RIHT. For each patient, we extracted 1316 radiomic features from original and transformed images using manually contoured thyroid masks. Creating models based on clinical, radiomic features or a combination thereof, we considered 3 variants of data preprocessing. Based on their performance metrics (sensitivity, specificity), we picked best models for each variant ((0.8, 0.96), (0.9, 0.93), (0.9, 0.89) variant-wise) and compared them with external NTCP models ((0.82, 0.88), (0.82, 0.88), (0.76, 0.91)). We showed that radiomic-based models did not outperform state-of-art NTCP models (<i>p</i> > 0.05). The potential benefit of radiomic-based approach is that it is dose-independent, and models can be used prior to treatment planning allowing faster selection of susceptible population.
format article
author Urszula Smyczynska
Szymon Grabia
Zuzanna Nowicka
Anna Papis-Ubych
Robert Bibik
Tomasz Latusek
Tomasz Rutkowski
Jacek Fijuth
Wojciech Fendler
Bartlomiej Tomasik
author_facet Urszula Smyczynska
Szymon Grabia
Zuzanna Nowicka
Anna Papis-Ubych
Robert Bibik
Tomasz Latusek
Tomasz Rutkowski
Jacek Fijuth
Wojciech Fendler
Bartlomiej Tomasik
author_sort Urszula Smyczynska
title Prediction of Radiation-Induced Hypothyroidism Using Radiomic Data Analysis Does Not Show Superiority over Standard Normal Tissue Complication Models
title_short Prediction of Radiation-Induced Hypothyroidism Using Radiomic Data Analysis Does Not Show Superiority over Standard Normal Tissue Complication Models
title_full Prediction of Radiation-Induced Hypothyroidism Using Radiomic Data Analysis Does Not Show Superiority over Standard Normal Tissue Complication Models
title_fullStr Prediction of Radiation-Induced Hypothyroidism Using Radiomic Data Analysis Does Not Show Superiority over Standard Normal Tissue Complication Models
title_full_unstemmed Prediction of Radiation-Induced Hypothyroidism Using Radiomic Data Analysis Does Not Show Superiority over Standard Normal Tissue Complication Models
title_sort prediction of radiation-induced hypothyroidism using radiomic data analysis does not show superiority over standard normal tissue complication models
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/8323964c7a5042faa47514bc6845f293
work_keys_str_mv AT urszulasmyczynska predictionofradiationinducedhypothyroidismusingradiomicdataanalysisdoesnotshowsuperiorityoverstandardnormaltissuecomplicationmodels
AT szymongrabia predictionofradiationinducedhypothyroidismusingradiomicdataanalysisdoesnotshowsuperiorityoverstandardnormaltissuecomplicationmodels
AT zuzannanowicka predictionofradiationinducedhypothyroidismusingradiomicdataanalysisdoesnotshowsuperiorityoverstandardnormaltissuecomplicationmodels
AT annapapisubych predictionofradiationinducedhypothyroidismusingradiomicdataanalysisdoesnotshowsuperiorityoverstandardnormaltissuecomplicationmodels
AT robertbibik predictionofradiationinducedhypothyroidismusingradiomicdataanalysisdoesnotshowsuperiorityoverstandardnormaltissuecomplicationmodels
AT tomaszlatusek predictionofradiationinducedhypothyroidismusingradiomicdataanalysisdoesnotshowsuperiorityoverstandardnormaltissuecomplicationmodels
AT tomaszrutkowski predictionofradiationinducedhypothyroidismusingradiomicdataanalysisdoesnotshowsuperiorityoverstandardnormaltissuecomplicationmodels
AT jacekfijuth predictionofradiationinducedhypothyroidismusingradiomicdataanalysisdoesnotshowsuperiorityoverstandardnormaltissuecomplicationmodels
AT wojciechfendler predictionofradiationinducedhypothyroidismusingradiomicdataanalysisdoesnotshowsuperiorityoverstandardnormaltissuecomplicationmodels
AT bartlomiejtomasik predictionofradiationinducedhypothyroidismusingradiomicdataanalysisdoesnotshowsuperiorityoverstandardnormaltissuecomplicationmodels
_version_ 1718435191793385472