Predicting radiotherapy-induced xerostomia in head and neck cancer patients using day-to-day kinetics of radiomics features

Thomas Berger; David J. Noble; Leila E.A. Shelley; Thomas McMullan; Amy Bates; Simon Thomas; Linda J. Carruthers; George Beckett; Aileen Duffton; Claire Paterson; Raj Jena; Duncan B. McLaren; Neil G. Burnet; William H. Nailon

doi:10.1016/j.phro.2022.10.004

Predicting radiotherapy-induced xerostomia in head and neck cancer patients using day-to-day kinetics of radiomics features

Thomas Berger^*, David J. Noble, Leila E.A. Shelley, Thomas McMullan, Amy Bates, Simon Thomas, Linda J. Carruthers, George Beckett, Aileen Duffton, Claire Paterson, Raj Jena, Duncan B. McLaren, Neil G. Burnet, William H. Nailon

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract / Description of output

Background and purpose: The images acquired during radiotherapy for image-guidance purposes could be used to monitor patient-specific response to irradiation and improve treatment personalisation. We investigated whether the kinetics of radiomics features from daily mega-voltage CT image-guidance scans (MVCT) improve prediction of moderate-to-severe xerostomia compared to dose/volume parameters in radiotherapy of head-and-neck cancer (HNC). Materials and Methods: All included HNC patients (N = 117) received 30 or more fractions of radiotherapy with daily MVCTs. Radiomics features were calculated on the contra-lateral parotid glands of daily MVCTs. Their variations over time after each complete week of treatment were used to predict moderate-to-severe xerostomia (CTCAEv4.03 grade ≥ 2) at 6, 12 and 24 months post-radiotherapy. After dimensionality reduction, backward/forward selection was used to generate combinations of predictors. Three types of logistic regression model were generated for each follow-up time: 1) a pre-treatment reference model using dose/volume parameters, 2) a combination of dose/volume and radiomics-based predictors, and 3) radiomics-based predictors. The models were internally validated by cross-validation and bootstrapping and their performance evaluated using Area Under the Curve (AUC) on separate training and testing sets. Results: Moderate-to-severe xerostomia was reported by 46 %, 33 % and 26 % of the patients at 6, 12 and 24 months respectively. The selected models using radiomics-based features extracted at or before mid-treatment outperformed the dose-based models with an AUC_train/AUC_test of 0.70/0.69, 0.76/0.74, 0.86/0.86 at 6, 12 and 24 months, respectively. Conclusion: Our results suggest that radiomics features calculated on MVCTs from the first half of the radiotherapy course improve prediction of moderate-to-severe xerostomia in HNC patients compared to a dose-based pre-treatment model.

Original language	English
Pages (from-to)	95-101
Number of pages	7
Journal	Physics and Imaging in Radiation Oncology
Volume	24
DOIs	https://doi.org/10.1016/j.phro.2022.10.004
Publication status	Published - 4 Nov 2022

Keywords / Materials (for Non-textual outputs)

Head and neck cancer
Mega-voltage CT
Parotid gland
Radiomics
Xerostomia

Access to Document

10.1016/j.phro.2022.10.004Licence: Creative Commons: Attribution (CC-BY)

https://www.sciencedirect.com/science/article/pii/S2405631622000902Licence: Creative Commons: Attribution (CC-BY)

Cite this

Berger, T., Noble, D. J., Shelley, L. E. A., McMullan, T., Bates, A., Thomas, S., Carruthers, L. J., Beckett, G., Duffton, A., Paterson, C., Jena, R., McLaren, D. B., Burnet, N. G., & Nailon, W. H. (2022). Predicting radiotherapy-induced xerostomia in head and neck cancer patients using day-to-day kinetics of radiomics features. Physics and Imaging in Radiation Oncology, 24, 95-101. https://doi.org/10.1016/j.phro.2022.10.004

@article{0e3f0947e0c046079025091be9e5fb8c,

title = "Predicting radiotherapy-induced xerostomia in head and neck cancer patients using day-to-day kinetics of radiomics features",

abstract = "Background and purpose: The images acquired during radiotherapy for image-guidance purposes could be used to monitor patient-specific response to irradiation and improve treatment personalisation. We investigated whether the kinetics of radiomics features from daily mega-voltage CT image-guidance scans (MVCT) improve prediction of moderate-to-severe xerostomia compared to dose/volume parameters in radiotherapy of head-and-neck cancer (HNC). Materials and Methods: All included HNC patients (N = 117) received 30 or more fractions of radiotherapy with daily MVCTs. Radiomics features were calculated on the contra-lateral parotid glands of daily MVCTs. Their variations over time after each complete week of treatment were used to predict moderate-to-severe xerostomia (CTCAEv4.03 grade ≥ 2) at 6, 12 and 24 months post-radiotherapy. After dimensionality reduction, backward/forward selection was used to generate combinations of predictors. Three types of logistic regression model were generated for each follow-up time: 1) a pre-treatment reference model using dose/volume parameters, 2) a combination of dose/volume and radiomics-based predictors, and 3) radiomics-based predictors. The models were internally validated by cross-validation and bootstrapping and their performance evaluated using Area Under the Curve (AUC) on separate training and testing sets. Results: Moderate-to-severe xerostomia was reported by 46 %, 33 % and 26 % of the patients at 6, 12 and 24 months respectively. The selected models using radiomics-based features extracted at or before mid-treatment outperformed the dose-based models with an AUCtrain/AUCtest of 0.70/0.69, 0.76/0.74, 0.86/0.86 at 6, 12 and 24 months, respectively. Conclusion: Our results suggest that radiomics features calculated on MVCTs from the first half of the radiotherapy course improve prediction of moderate-to-severe xerostomia in HNC patients compared to a dose-based pre-treatment model.",

keywords = "Head and neck cancer, Mega-voltage CT, Parotid gland, Radiomics, Xerostomia",

author = "Thomas Berger and Noble, {David J.} and Shelley, {Leila E.A.} and Thomas McMullan and Amy Bates and Simon Thomas and Carruthers, {Linda J.} and George Beckett and Aileen Duffton and Claire Paterson and Raj Jena and McLaren, {Duncan B.} and Burnet, {Neil G.} and Nailon, {William H.}",

note = "Funding Information: The authors gratefully acknowledge the support of 1) the VoxTox and computational Oncology group at the University of Cambridge and 2) the staff in the Department of Oncology Physics at the Edinburgh Cancer Centre and the Institute for Digital Communications, College of Science and Engineering at the University of Edinburgh. VoxTox was supported by a CRUK grant (ref C8857\A13405) with ethics approval: 13/EE/0008. The work was generously supported by the Chief Scientist Office (CSO) Scotland grant (TCS/17/26 - CSO Award), IMAGE-INE: Analysing IMAGE guIdance scaNs to prEdict late toxicity after radiotherapy in head and neck cancer patients. DJN was supported by a CRUK Clinical Research Fellowship (Ref: C20/A20917). CP is supported by Beatson Cancer Charity, CRUK RadNet Glasgow and an NRS fellowship, chief scientist office/NHS Greater Glasgow & Clyde. AD is Beatson Cancer Charity funded. Funding Information: CP is supported by Beatson Cancer Charity, CRUK RadNet Glasgow and an NRS fellowship, chief scientist office/NHS Greater Glasgow & Clyde. Funding Information: DJN was supported by a CRUK Clinical Research Fellowship (Ref: C20/A20917). Funding Information: The authors gratefully acknowledge the support of 1) the VoxTox and computational Oncology group at the University of Cambridge and 2) the staff in the Department of Oncology Physics at the Edinburgh Cancer Centre and the Institute for Digital Communications, College of Science and Engineering at the University of Edinburgh. VoxTox was supported by a CRUK grant (ref C8857\A13405) with ethics approval: 13/EE/0008. The work was generously supported by the Chief Scientist Office (CSO) Scotland grant (TCS/17/26 - CSO Award), IMAGE-INE: Analysing IMAGE guIdance scaNs to prEdict late toxicity after radiotherapy in head and neck cancer patients. Publisher Copyright: {\textcopyright} 2022",

year = "2022",

month = nov,

day = "4",

doi = "10.1016/j.phro.2022.10.004",

language = "English",

volume = "24",

pages = "95--101",

journal = "Physics and Imaging in Radiation Oncology",

issn = "2405-6316",

publisher = "Elsevier",

}

Berger, T, Noble, DJ, Shelley, LEA, McMullan, T, Bates, A, Thomas, S, Carruthers, LJ, Beckett, G, Duffton, A, Paterson, C, Jena, R, McLaren, DB, Burnet, NG & Nailon, WH 2022, 'Predicting radiotherapy-induced xerostomia in head and neck cancer patients using day-to-day kinetics of radiomics features', Physics and Imaging in Radiation Oncology, vol. 24, pp. 95-101. https://doi.org/10.1016/j.phro.2022.10.004

TY - JOUR

T1 - Predicting radiotherapy-induced xerostomia in head and neck cancer patients using day-to-day kinetics of radiomics features

AU - Berger, Thomas

AU - Noble, David J.

AU - Shelley, Leila E.A.

AU - McMullan, Thomas

AU - Bates, Amy

AU - Thomas, Simon

AU - Carruthers, Linda J.

AU - Beckett, George

AU - Duffton, Aileen

AU - Paterson, Claire

AU - Jena, Raj

AU - McLaren, Duncan B.

AU - Burnet, Neil G.

AU - Nailon, William H.

N1 - Funding Information: The authors gratefully acknowledge the support of 1) the VoxTox and computational Oncology group at the University of Cambridge and 2) the staff in the Department of Oncology Physics at the Edinburgh Cancer Centre and the Institute for Digital Communications, College of Science and Engineering at the University of Edinburgh. VoxTox was supported by a CRUK grant (ref C8857\A13405) with ethics approval: 13/EE/0008. The work was generously supported by the Chief Scientist Office (CSO) Scotland grant (TCS/17/26 - CSO Award), IMAGE-INE: Analysing IMAGE guIdance scaNs to prEdict late toxicity after radiotherapy in head and neck cancer patients. DJN was supported by a CRUK Clinical Research Fellowship (Ref: C20/A20917). CP is supported by Beatson Cancer Charity, CRUK RadNet Glasgow and an NRS fellowship, chief scientist office/NHS Greater Glasgow & Clyde. AD is Beatson Cancer Charity funded. Funding Information: CP is supported by Beatson Cancer Charity, CRUK RadNet Glasgow and an NRS fellowship, chief scientist office/NHS Greater Glasgow & Clyde. Funding Information: DJN was supported by a CRUK Clinical Research Fellowship (Ref: C20/A20917). Funding Information: The authors gratefully acknowledge the support of 1) the VoxTox and computational Oncology group at the University of Cambridge and 2) the staff in the Department of Oncology Physics at the Edinburgh Cancer Centre and the Institute for Digital Communications, College of Science and Engineering at the University of Edinburgh. VoxTox was supported by a CRUK grant (ref C8857\A13405) with ethics approval: 13/EE/0008. The work was generously supported by the Chief Scientist Office (CSO) Scotland grant (TCS/17/26 - CSO Award), IMAGE-INE: Analysing IMAGE guIdance scaNs to prEdict late toxicity after radiotherapy in head and neck cancer patients. Publisher Copyright: © 2022

PY - 2022/11/4

Y1 - 2022/11/4

N2 - Background and purpose: The images acquired during radiotherapy for image-guidance purposes could be used to monitor patient-specific response to irradiation and improve treatment personalisation. We investigated whether the kinetics of radiomics features from daily mega-voltage CT image-guidance scans (MVCT) improve prediction of moderate-to-severe xerostomia compared to dose/volume parameters in radiotherapy of head-and-neck cancer (HNC). Materials and Methods: All included HNC patients (N = 117) received 30 or more fractions of radiotherapy with daily MVCTs. Radiomics features were calculated on the contra-lateral parotid glands of daily MVCTs. Their variations over time after each complete week of treatment were used to predict moderate-to-severe xerostomia (CTCAEv4.03 grade ≥ 2) at 6, 12 and 24 months post-radiotherapy. After dimensionality reduction, backward/forward selection was used to generate combinations of predictors. Three types of logistic regression model were generated for each follow-up time: 1) a pre-treatment reference model using dose/volume parameters, 2) a combination of dose/volume and radiomics-based predictors, and 3) radiomics-based predictors. The models were internally validated by cross-validation and bootstrapping and their performance evaluated using Area Under the Curve (AUC) on separate training and testing sets. Results: Moderate-to-severe xerostomia was reported by 46 %, 33 % and 26 % of the patients at 6, 12 and 24 months respectively. The selected models using radiomics-based features extracted at or before mid-treatment outperformed the dose-based models with an AUCtrain/AUCtest of 0.70/0.69, 0.76/0.74, 0.86/0.86 at 6, 12 and 24 months, respectively. Conclusion: Our results suggest that radiomics features calculated on MVCTs from the first half of the radiotherapy course improve prediction of moderate-to-severe xerostomia in HNC patients compared to a dose-based pre-treatment model.

AB - Background and purpose: The images acquired during radiotherapy for image-guidance purposes could be used to monitor patient-specific response to irradiation and improve treatment personalisation. We investigated whether the kinetics of radiomics features from daily mega-voltage CT image-guidance scans (MVCT) improve prediction of moderate-to-severe xerostomia compared to dose/volume parameters in radiotherapy of head-and-neck cancer (HNC). Materials and Methods: All included HNC patients (N = 117) received 30 or more fractions of radiotherapy with daily MVCTs. Radiomics features were calculated on the contra-lateral parotid glands of daily MVCTs. Their variations over time after each complete week of treatment were used to predict moderate-to-severe xerostomia (CTCAEv4.03 grade ≥ 2) at 6, 12 and 24 months post-radiotherapy. After dimensionality reduction, backward/forward selection was used to generate combinations of predictors. Three types of logistic regression model were generated for each follow-up time: 1) a pre-treatment reference model using dose/volume parameters, 2) a combination of dose/volume and radiomics-based predictors, and 3) radiomics-based predictors. The models were internally validated by cross-validation and bootstrapping and their performance evaluated using Area Under the Curve (AUC) on separate training and testing sets. Results: Moderate-to-severe xerostomia was reported by 46 %, 33 % and 26 % of the patients at 6, 12 and 24 months respectively. The selected models using radiomics-based features extracted at or before mid-treatment outperformed the dose-based models with an AUCtrain/AUCtest of 0.70/0.69, 0.76/0.74, 0.86/0.86 at 6, 12 and 24 months, respectively. Conclusion: Our results suggest that radiomics features calculated on MVCTs from the first half of the radiotherapy course improve prediction of moderate-to-severe xerostomia in HNC patients compared to a dose-based pre-treatment model.

KW - Head and neck cancer

KW - Mega-voltage CT

KW - Parotid gland

KW - Radiomics

KW - Xerostomia

UR - http://www.scopus.com/inward/record.url?scp=85141338253&partnerID=8YFLogxK

U2 - 10.1016/j.phro.2022.10.004

DO - 10.1016/j.phro.2022.10.004

M3 - Article

AN - SCOPUS:85141338253

SN - 2405-6316

VL - 24

SP - 95

EP - 101

JO - Physics and Imaging in Radiation Oncology

JF - Physics and Imaging in Radiation Oncology

ER -

Predicting radiotherapy-induced xerostomia in head and neck cancer patients using day-to-day kinetics of radiomics features

Abstract / Description of output

Keywords / Materials (for Non-textual outputs)

Access to Document

Other files and links

Fingerprint

IMAGE-INE: Analysing IMAGE Guidance ScaNs To PrEdict Late Toxicity After Radiotherapy In Head And Neck Cancer Patients

Cite this

Predicting radiotherapy-induced xerostomia in head and neck cancer patients using day-to-day kinetics of radiomics features

Abstract / Description of output

Keywords / Materials (for Non-textual outputs)

Access to Document

Other files and links

Fingerprint

Projects

IMAGE-INE: Analysing IMAGE Guidance ScaNs To PrEdict Late Toxicity After Radiotherapy In Head And Neck Cancer Patients

Cite this