Predicting radiotherapy-induced xerostomia in head and neck cancer patients using day-to-day kinetics of radiomics features
Noble, D. J.
Shelley, L. E. A.
Carruthers, L. J.
McLaren, D. B.
Burnet, Neil G
Nailon, W. H.
AffiliationDepartment of Oncology Physics, Edinburgh Cancer Centre, Western General Hospital, Crewe Road South, Edinburgh EH4 2XU
MetadataShow full item record
AbstractBackground 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.
CitationBerger T, Noble DJ, Shelley LEA, McMullan T, Bates A, Thomas S, et al. Predicting radiotherapy-induced xerostomia in head and neck cancer patients using day-to-day kinetics of radiomics features. Physics and imaging in radiation oncology. 2022 Oct;24:95-101. PubMed PMID: 36386445. Pubmed Central PMCID: PMC9647222. Epub 2022/11/18. eng.
JournalPhysics and Imaging in Radiation Oncology
- Predicting acute radiation induced xerostomia in head and neck Cancer using MR and CT Radiomics of parotid and submandibular glands.
- Authors: Sheikh K, Lee SH, Cheng Z, Lakshminarayanan P, Peng L, Han P, McNutt TR, Quon H, Lee J
- Issue date: 2019 Jul 29
- Early prediction of radiotherapy-induced parotid shrinkage and toxicity based on CT radiomics and fuzzy classification.
- Authors: Pota M, Scalco E, Sanguineti G, Farneti A, Cattaneo GM, Rizzo G, Esposito M
- Issue date: 2017 Sep
- Delta-radiomics features during radiotherapy improve the prediction of late xerostomia.
- Authors: van Dijk LV, Langendijk JA, Zhai TT, Vedelaar TA, Noordzij W, Steenbakkers RJHM, Sijtsema NM
- Issue date: 2019 Aug 28
- Parotid gland fat related Magnetic Resonance image biomarkers improve prediction of late radiation-induced xerostomia.
- Authors: van Dijk LV, Thor M, Steenbakkers RJHM, Apte A, Zhai TT, Borra R, Noordzij W, Estilo C, Lee N, Langendijk JA, Deasy JO, Sijtsema NM
- Issue date: 2018 Sep
- Validation of the (18)F-FDG PET image biomarker model predicting late xerostomia after head and neck cancer radiotherapy.
- Authors: Li Y, Sijtsema NM, de Vette SPM, Steenbakkers RJHM, Zhang F, Noordzij W, Van den Bosch L, Langendijk JA, van Dijk LV
- Issue date: 2023 Jan 3