Dosiomics Risk Model for Predicting Radiation Induced Temporal Lobe Injury and Guiding Individual Intensity-Modulated Radiation Therapy

Yang, Shanshan; OuYang, Pu‐Yun; Guo, Jin; Cai, Jiajun; Zhang, Jun; Peng, Qifeng; He, Yun; Zhang, Bao-Yu; Liu, Zhi-Qiao; Hu, Xuefeng; Chen, Yanfeng; Chen, Chunyan; Xie, Fang‐Yun

doi:10.1016/j.ijrobp.2022.11.036

Cited by 8 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…IMRT can effectively limit the high-dose exposure of the temporal lobe. The TLI probability after the first course radiotherapy was about 4.6–16% ( 5 – 7 ). However, in recurrent nasopharyngeal carcinoma, especially for patients with large tumor volume, especially those with skull base invasion or intracranial invasion, a second course of high dose irradiation would be necessary, thus TLI is inevitable ( 8 – 10 ).…”

Section: Introductionmentioning

confidence: 99%

Normal tissue complication probability model of temporal lobe injury following re-irradiation of IMRT for local recurrent nasopharyngeal carcinoma

Guan,

Peng,

Sun

et al. 2024

Front. Oncol.

View full text Add to dashboard Cite

PurposeWe tried to establish the normal tissue complication probability (NTCP) model of temporal lobe injury of recurrent nasopharyngeal carcinoma (NPC) patients after two courses of intensity modulated radiotherapy (IMRT) to provide more reliable dose-volume data reference to set the temporal lobe tolerance dose for recurrent NPC patients in the future.Methods and materialsRecurrent NPC patients were randomly divided into training data set and validation data set in a ratio of 2:1, All the temporal lobes (TLs) were re-contoured as R/L structures and named separately in the MIM system. The dose distribution of the initial IMRT plan was deformed into the second course planning CT via MIM software to get the deformed dose. Equivalent dose of TLs in 2Gy fractions was calculated via linear quadratic model, using an α/β=3 for temporal lobes. NTCP model that correlated the irradiated volume of the temporal lobe and? the clinical variables were evaluated in a multivariate prediction model using AUC analysis.ResultsFrom Jan. 2010 to Dec. 2020, 78 patients were enrolled into our study. Among which 26 (33.3%) developed TLI. The most important factors affecting TLI was the sum-dose d1.5cc of TL, while the possible clinical factors did not reach statistically significant differences in multivariate analysis. According to NTCP model, the TD5 and TD50 EQD2 dose of sum-dose d1.5cc were 65.26Gy (46.72–80.69Gy) and 125.25Gy (89.51–152.18Gy), respectively. For the accumulated EQD2 dose, the area under ROC shadow was 0.8702 (0.7577–0.9828) in model validation, p<0.001.ConclusionIn this study, a NTCP model of temporal lobe injury after a second course of IMRT for recurrent nasopharyngeal carcinoma was established. TD5 and TD50 doses of temporal lobe injury after re-RT were obtained according to the model, and the model was verified by validation set data.

show abstract

Section: Introductionmentioning

confidence: 99%

Normal tissue complication probability model of temporal lobe injury following re-irradiation of IMRT for local recurrent nasopharyngeal carcinoma

Guan,

Peng,

Sun

et al. 2024

Front. Oncol.

View full text Add to dashboard Cite

show abstract

“…11,12 Until now, few radiomics studies have been reported on predicting RTLI of patients with NPC based on the pretreatment data. Yang et al 13 extracted radiomics features with high throughput from CT, and then developed a risk model by combining threedimensional (3D) dose distributions. Bin et al 14 and Bao et al 15 established radiomics models to predict RTLI based on pretreatment MRI data, which achieved great performance.…”

Section: Introductionmentioning

confidence: 99%

A pretreatment multiparametric MRI‐based radiomics‐clinical machine learning model for predicting radiation‐induced temporal lobe injury in patients with nasopharyngeal carcinoma

Wang,

Qiu,

Zhou

et al. 2024

Head & Neck

View full text Add to dashboard Cite

BackgroundTo establish and validate a machine learning model using pretreatment multiparametric magnetic resonance imaging‐based radiomics data with clinical data to predict radiation‐induced temporal lobe injury (RTLI) in patients with nasopharyngeal carcinoma (NPC) after intensity‐modulated radiotherapy (IMRT).MethodsData from 230 patients with NPC who received IMRT (130 with RTLI and 130 without) were randomly divided into the training (n = 161) and validation cohort (n = 69) with a ratio of 7:3. Radiomics features were extracted from pretreatment apparent diffusion coefficient (ADC) map, T2‐weighted imaging (T2WI), and CE‐T1‐weighted imaging (CE‐T1WI). T‐test, spearman rank correlation, and least absolute shrinkage and selection operator (LASSO) algorithm were employed to identify significant radiomics features. Clinical features were selected with univariate and multivariate analyses. Radiomics and clinical models were constructed using multiple machine learning classifiers, and a clinical‐radiomics nomogram that combined clinical with radiomics features was developed. Receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA) were drawn to compare and verify the predictive performances of the clinical model, radiomics model, and clinical‐radiomics nomogram.ResultsA total of 5064 radiomics features were extracted, from which 52 radiomics features were selected to construct the radiomics signature. The AUC of the radiomics signature based on multiparametric MRI was 0.980 in the training cohort and 0.969 in the validation cohort, outperforming the radiomics signature only based on T2WI and CE‐T1WI (p < 0.05), which highlighted the significance of the DWI sequence in the prediction of temporal lobe injury. The area under the curve (AUC) of the clinical model was 0.895 in the training cohort and 0.905 in the validation cohort. The nomogram, which integrated radiomics and clinical features, demonstrated an impressive AUC value of 0.984 in the validation set; however, no statistically significant difference was observed compared to the radiomics model. The calibration curve and decision curve analysis of the nomogram demonstrated excellent predictive performance and clinical feasibility.ConclusionsThe clinical‐radiomics nomogram, integrating clinical features with radiomics features derived from pretreatment multiparametric MRI, exhibits compelling predictive performance for RTLI in patients diagnosed with NPC.

show abstract

“…In this study, we adopted the dosiomics approach, which involves extracting first-order statistics and 3D spatial features from radiation dose distribution, to go one step further. Studies have been exploring the role of dosiomics in risk modeling to predict radiation-induced temporal lobe injury [ 26 ], radiation pneumonitis [ 27 ], locoregional recurrences after treatment for head and neck carcinoma [ 28 ], and radiation-induced hypothyroidism [ 29 ], to name a few applications. Dosiomics features have proven promising and, in some cases, more effective than the conventionally used dose–volume histogram parameters [ 29 , 30 ].…”

Section: Introductionmentioning

confidence: 99%

Dosiomics-Based Prediction of Radiation-Induced Valvulopathy after Childhood Cancer

Chounta,

Allodji,

Vakalopoulou

et al. 2023

Cancers

View full text Add to dashboard Cite

Valvular Heart Disease (VHD) is a known late complication of radiotherapy for childhood cancer (CC), and identifying high-risk survivors correctly remains a challenge. This paper focuses on the distribution of the radiation dose absorbed by heart tissues. We propose that a dosiomics signature could provide insight into the spatial characteristics of the heart dose associated with a VHD, beyond the already-established risk induced by high doses. We analyzed data from the 7670 survivors of the French Childhood Cancer Survivors’ Study (FCCSS), 3902 of whom were treated with radiotherapy. In all, 63 (1.6%) survivors that had been treated with radiotherapy experienced a VHD, and 57 of them had heterogeneous heart doses. From the heart–dose distribution of each survivor, we extracted 93 first-order and spatial dosiomics features. We trained random forest algorithms adapted for imbalanced classification and evaluated their predictive performance compared to the performance of standard mean heart dose (MHD)-based models. Sensitivity analyses were also conducted for sub-populations of survivors with spatially heterogeneous heart doses. Our results suggest that MHD and dosiomics-based models performed equally well globally in our cohort and that, when considering the sub-population having received a spatially heterogeneous dose distribution, the predictive capability of the models is significantly improved by the use of the dosiomics features. If these findings are further validated, the dosiomics signature may be incorporated into machine learning algorithms for radiation-induced VHD risk assessment and, in turn, into the personalized refinement of follow-up guidelines.

show abstract

Dosiomics Risk Model for Predicting Radiation Induced Temporal Lobe Injury and Guiding Individual Intensity-Modulated Radiation Therapy

Cited by 8 publications

References 24 publications

Normal tissue complication probability model of temporal lobe injury following re-irradiation of IMRT for local recurrent nasopharyngeal carcinoma

Normal tissue complication probability model of temporal lobe injury following re-irradiation of IMRT for local recurrent nasopharyngeal carcinoma

A pretreatment multiparametric MRI‐based radiomics‐clinical machine learning model for predicting radiation‐induced temporal lobe injury in patients with nasopharyngeal carcinoma

Dosiomics-Based Prediction of Radiation-Induced Valvulopathy after Childhood Cancer

Contact Info

Product

Resources

About