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

Cancers ◽  
2021 ◽  
Vol 13 (21) ◽  
pp. 5584
Author(s):  
Urszula Smyczynska ◽  
Szymon Grabia ◽  
Zuzanna Nowicka ◽  
Anna Papis-Ubych ◽  
Robert Bibik ◽  
...  

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 (p > 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.

2021 ◽  
Author(s):  
Urszula Smyczynska ◽  
Szymon Grabia ◽  
Zuzanna Nowicka ◽  
Anna Papis-Ubych ◽  
Robert Bibik ◽  
...  

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)). Our models reach accuracy comparable with or better than previously presented non-radiomic NTCP models. The benefit of our approach is obtaining the RIHT predictions before treatment planning to adjust IMRT plan to avoid the thyroid region in most susceptible patients.


Cancers ◽  
2020 ◽  
Vol 12 (9) ◽  
pp. 2716
Author(s):  
Zuzanna Nowicka ◽  
Bartłomiej Tomasik ◽  
Anna Papis-Ubych ◽  
Robert Bibik ◽  
Łukasz Graczyk ◽  
...  

We aimed to externally validate five normal tissue complication probability (NTCP) models for radiation-induced hypothyroidism (RIHT) in a prospectively recruited cohort of 108 patients with oropharyngeal cancer (OPC). NTCP scores were calculated using original published formulas. Plasma thyrotropin (TSH) level was additionally assessed in the short-term after RT. After a median of 28 months of follow-up, thirty one (28.7%) patients developed RIHT. Thyroid mean dose and thyroid volume were significant predictors of RIHT: odds ratio equal to 1.11 (95% CI 1.03–1.19) for mean thyroid dose and 0.87 (95%CI 0.81–0.93) for thyroid volume in univariate analyses. Two of the evaluated NTCP models, published by Rønjom et al. and by Boomsma et al., had satisfactory performance with accuracies of 0.87 (95%CI 0.79–0.93) and 0.84 (95%CI: 0.76–0.91), respectively. Three remaining models, by Cella et al., Bakhshandeh et al. and Vogelius et al., performed significantly worse, overestimating the risk of RIHT in this patient cohort. A short-term TSH level change relative to baseline was not indicative of RIHT development in the follow-up (OR 0.96, 95%CI: 0.65–1.42, p = 0.825). In conclusion, the models by Rønjom et al. and by Boomsma et al. demonstrated external validity and feasibility for long-term prediction of RIHT in survivors of OPC treated with Intensity-Modulated Radiation Therapy (IMRT).


Author(s):  
Niklas Benedikt Pepper ◽  
Michael Oertel ◽  
Christopher Kittel ◽  
Kai Jannes Kröger ◽  
Khaled Elsayad ◽  
...  

Abstract Purpose Mediastinal radiotherapy (RT), especially when combined with bleomycin, may result in substantial pulmonary morbidity and mortality. The use of modern RT techniques like intensity-modulated radiotherapy (IMRT) is gaining interest to spare organs at risk. Methods We evaluated 27 patients who underwent RT for Hodgkin’s lymphoma between 2009 and 2013 at our institution. For each patient, three different treatment plans for a 30-Gy involved-field RT (IFRT) were created (anterior-posterior-posterior-anterior setup [APPA], 5‑field IMRT, and 7‑field IMRT) and analyzed concerning their inherent “normal tissue complication probability” (NTCP) for pneumonitis and secondary pulmonary malignancy. Results The comparison of different radiation techniques showed a significant difference in favor of standard APPA (p < 0.01). The risk of lung toxicity was significantly higher in plans using 7‑field IMRT than in plans using 5‑field IMRT. The absolute juxtaposition showed an increase in risk for radiation pneumonitis of 1% for plans using 5‑field IMRT over APPA according to QUANTEC (Quantitative Analyses of Normal Tissue Effects in the Clinic) parameters (Burman: 0.15%) and 2.6% when using 7‑field IMRT over APPA (Burman: 0.7%) as well as 1.6% when using 7‑field IMRT over 5‑field IMRT (Burman: 0.6%). Further analysis showed an increase in risk for secondary pulmonary malignancies to be statistically significant (p < 0.01); mean induction probability for pulmonary malignoma was 0.1% higher in plans using 5‑field IMRT than APPA and 0.19% higher in plans using 7‑field IMRT than APPA as well as 0.09% higher in plans using 7‑field IMRT than 5‑field IMRT. During a median follow-up period of 65 months (95% confidence interval: 53.8–76.2 months), only one patient developed radiation-induced pneumonitis. No secondary pulmonary malignancies have been detected to date. Conclusion Radiation-induced lung toxicity is rare after treatment for Hodgkin lymphoma but may be influenced significantly by the RT technique used. In this study, APPA RT plans demonstrated a decrease in potential radiation pneumonitis and pulmonary malignancies. Biological planning using NTCP may have the potential to define personalized RT strategies


Sign in / Sign up

Export Citation Format

Share Document