CRT combined with a sequential VMAT boost in the treatment of upper thoracic esophageal cancer

Combined deep learning and radiomics in pretreatment radiation esophagitis prediction for patients with esophageal cancer underwent volumetric modulated arc therapy

PURPOSE

To develop a combined radiomics and deep learning (DL) model in predicting radiation esophagitis (RE) of a grade ≥ 2 for patients with esophageal cancer (EC) underwent volumetric modulated arc therapy (VMAT) based on computed tomography (CT) and radiation dose (RD) distribution images.

MATERIALS AND METHODS

A total of 273 EC patients underwent VMAT were retrospectively reviewed and enrolled from two centers and divided into training (n = 152), internal validation (n = 66), and external validation (n = 55) cohorts, respectively. Radiomic and dosiomic features along with DL features using convolutional neural networks were extracted and screened from CT and RD images to predict RE. The performance of these models was evaluated and compared using the area under curve (AUC) of the receiver operating characteristic curves (ROC).

RESULTS

There were 5 and 10 radiomic and dosiomic features were screened, respectively. XGBoost achieved a best AUC of 0.703, 0.694 and 0.801, 0.729 with radiomic and dosiomic features in the internal and external validation cohorts, respectively. ResNet34 achieved a best prediction AUC of 0.642, 0.657 and 0.762, 0.737 for radiomics based DL model (DLR) and RD based DL model (DLD) in the internal and external validation cohorts, respectively. Combined model of DLD + Dosiomics + clinical factors achieved a best AUC of 0.913, 0.821 and 0.805 in the training, internal, and external validation cohorts, respectively.

CONCLUSION

Although the dose was not responsible for the prediction accuracy, the combination of various feature extraction methods was a factor in improving the RE prediction accuracy. Combining DLD with dosiomic features was promising in the pretreatment prediction of RE for EC patients underwent VMAT.

Radiation pneumonitis prediction with dual-radiomics for esophageal cancer underwent radiotherapy

BACKGROUND

To integrate radiomics and dosiomics features from multiple regions in the radiation pneumonia (RP grade ≥ 2) prediction for esophageal cancer (EC) patients underwent radiotherapy (RT).

METHODS

Total of 143 EC patients in the authors' hospital (training and internal validation: 70%:30%) and 32 EC patients from another hospital (external validation) underwent RT from 2015 to 2022 were retrospectively reviewed and analyzed. Patients were dichotomized as positive (RP+) or negative (RP-) according to CTCAE V5.0. Models with radiomics and dosiomics features extracted from single region of interest (ROI), multiple ROIs and combined models were constructed and evaluated. A nomogram integrating radiomics score (Rad_score), dosiomics score (Dos_score), clinical factors, dose-volume histogram (DVH) factors, and mean lung dose (MLD) was also constructed and validated.

RESULTS

Models with Rad_score_Lung&Overlap and Dos_score_Lung&Overlap achieved a better area under curve (AUC) of 0.818 and 0.844 in the external validation in comparison with radiomics and dosiomics models with features extracted from single ROI. Combining four radiomics and dosiomics models using support vector machine (SVM) improved the AUC to 0.854 in the external validation. Nomogram integrating Rad_score, and Dos_score with clinical factors, DVH factors, and MLD further improved the RP prediction AUC to 0.937 and 0.912 in the internal and external validation, respectively.

CONCLUSION

CT-based RP prediction model integrating radiomics and dosiomics features from multiple ROIs outperformed those with features from a single ROI with increased reliability for EC patients who underwent RT.

Dose-volume comparison of intensity modulated proton therapy and volumetric modulated arc therapy for cervical esophageal cancer

Proton therapy for cervical esophageal cancer has many issues to be considered, such as the physiological curvature of the spine and the large range change from the neck to the trunk. We clarified the dosimetric characteristics of intensity modulated proton therapy (IMPT) for cervical esophageal cancer by comparing with volumetric modulated arc therapy (VMAT). Ten patients with cervical esophageal cancer were retrospectively planned for VMAT, 2-field IMPT (2F-IMPT), and 3-field IMPT (3F-IMPT). All plans were optimized to reach clinically acceptable levels. For planning target volume (PTV) coverage, 95% of the PTV should be covered by 95% of the prescription dose, unless the spinal cord limit is violated. The organs at risk included the lung, spinal cord, larynx, skin, and whole body. The prescription dose was 60 Gy relative biological effectiveness (RBE) in 30 fractions to the PTV. We compared the results according to dose-volume metrics. Significant dose reductions were achieved at lung doses, especially at low dose volumes of 20 Gy RBE or less in IMPT plans compared with VMAT plans (p < 0.05). Although the spinal cord PRV was below the tolerance level, the results were also significantly higher in VMAT plans than in IMPT plans (p < 0.001). Spinal cord PRV Dmean was significantly higher in 3F-IMPT than in 2F-IMPT (p < 0.001). In addition, it was confirmed that the integral whole body dose can be dramatically reduced in IMPT plans compared with VMAT plans. Both of 2F-IMPT and 3F-IMPT could effectively reduce spinal cord dose, as well as low integral whole body dose to a certain extent, while maintaining similar target coverage compared to VMAT. IMPT could be a promising treatment technique for patients with cervical esophageal cancer.

Cross verification of independent dose recalculation, log files based, and phantom measurement-based pretreatment quality assurance for volumetric modulated arc therapy

Independent treatment planning system (TPS) check with Mobius3D software, log files based quality assurance (QA) with MobiusFX, and phantom measurement‐based QA with ArcCHECK were performed and cross verified for head‐and‐neck (17 patients), chest (16 patients), and abdominal (19 patients) cancer patients who underwent volumetric modulated arc therapy (VMAT). Dosimetric differences and percentage gamma passing rates (%GPs) were evaluated and compared for this cross verification. For the dosimetric differences in planning target volume (PTV) coverage, there was no significant difference among TPS vs. Mobius3D, TPS vs. MobiusFX, and TPS vs. ArcCHECK. For the dosimetric differences in organs at risks (OARs), the number of metrics with an average dosimetric differences higher than ±3% for TPS vs Mobius3D, TPS vs MobiusFX, and TPS vs ArcCHECK were 1, 1, 7; 2, 1, 4; 1, 1, 5 for the patients with head‐and‐neck, abdomen, and chest cancer, respectively. The %GPs of global gamma indices for Mobius3D and MobiousFX were above 97%, while it ranged from 92% to 96% for ArcCHECK. The %GPs of individual volume‐based gamma indices were around 98% for Mobius3D and MobiousFX, except for γPTV for chest and abdominal cancer (88.9% to 92%); while it ranged from 86% to 99% for ArcCHECK. In conclusion, some differences in dosimetric metrics and gamma passing rates were observed with ArcCHECK measurement‐based QA in comparison with independent dosecheck and log files based QA. Care must be taken when considering replacing phantom measurement‐based IMRT/VMAT QA.

Prediction of response after chemoradiation for esophageal cancer using a combination of dosimetry and CT radiomics

PURPOSE

To investigate the treatment response prediction feasibility and accuracy of an integrated model combining computed tomography (CT) radiomic features and dosimetric parameters for patients with esophageal cancer (EC) who underwent concurrent chemoradiation (CRT) using machine learning.

METHODS

The radiomic features and dosimetric parameters of 94 EC patients were extracted and modeled using Support Vector Classification (SVM) and Extreme Gradient Boosting algorithm (XGBoost). The 94-sample dataset was randomly divided into a 70-sample training subset and a 24-sample independent test set while keeping the class proportions intact via stratification. A receiver operating characteristic (ROC) curve was used to assess the performance of models using radiomic features alone and using combined radiomic features and dosimetric parameters.

RESULTS

A total of 42 radiomic features and 18 dosimetric parameters plus the patients' characteristic parameters were extracted for these 94 cases (58 responders and 36 non-responders). XGBoost plus principal component analysis (PCA) achieved an accuracy and area under the curve of 0.708 and 0.541, respectively, for models with radiomic features combined with dosimetric parameters, and 0.689 and 0.479, respectively, for radiomic features alone. Image features of GlobalMean X.333.1, Coarseness, Skewness, and GlobalStd contributed most to the model. The dosimetric parameters of gross tumor volume (GTV) homogeneity index (HI), Cord Dmax, Prescription dose, Heart-Dmean, and Heart-V50 also had a strong contribution to the model.

CONCLUSIONS

The model with radiomic features combined with dosimetric parameters is promising and outperforms that with radiomic features alone in predicting the treatment response of patients with EC who underwent CRT.

KEY POINTS

• The model with radiomic features combined with dosimetric parameters is promising in predicting the treatment response of patients with EC who underwent CRT. • The model with radiomic features combined with dosimetric parameters (prediction accuracy of 0.708 and AUC of 0.689) outperforms that with radiomic features alone (best prediction accuracy of 0.625 and AUC of 0.412). • The image features of GlobalMean X.333.1, Coarseness, Skewness, and GlobalStd contributed most to the treatment response prediction model. The dosimetric parameters of GTV HI, Cord Dmax, Prescription dose, Heart-Dmean, and Heart-V50 also had a strong contribution to the model.

Planning for mARC treatments with the Eclipse treatment planning system

While modulated arc (mARC) capabilities have been available on Siemens linear accelerators for almost two years now, there was, until recently, only one treatment planning system capable of planning these treatments. The Eclipse treatment planning system now offers a module that can plan for mARC treatments. The purpose of this work was to test the module to determine whether it is capable of creating clinically acceptable plans. A total of 23 plans were created for various clinical sites and all plans delivered without anomaly. The average 3%/3 mm gamma pass rate for the plans was 98.0%, with a standard deviation of 1.7%. For a total of 14 plans, an equivalent static gantry IMRT plan was also created to compare delivery time. In all but two cases, the mARC plans delivered significantly faster than the static gantry plan. We have confirmed the successful creation of mARC plans that are deliverable with high fidelity on an ARTISTE linear accelerator, thus demonstrating the successful implementation of the Eclipse mARC module.

Correlation between gamma index passing rate and clinical dosimetric difference for pre-treatment 2D and 3D volumetric modulated arc therapy dosimetric verification

OBJECTIVE

To investigate comparatively the percentage gamma passing rate (%GP) of two-dimensional (2D) and three-dimensional (3D) pre-treatment volumetric modulated arc therapy (VMAT) dosimetric verification and their correlation and sensitivity with percentage dosimetric errors (%DE).

METHODS

%GP of 2D and 3D pre-treatment VMAT quality assurance (QA) with different acceptance criteria was obtained by ArcCHECK® (Sun Nuclear Corporation, Melbourne, FL) for 20 patients with nasopharyngeal cancer (NPC) and 20 patients with oesophageal cancer. %DE were calculated from planned dose-volume histogram (DVH) and patients' predicted DVH calculated by 3DVH® software (Sun Nuclear Corporation). Correlation and sensitivity between %GP and %DE were investigated using Pearson's correlation coefficient (r) and receiver operating characteristics (ROCs).

RESULTS

Relatively higher %DE on some DVH-based metrics were observed for both patients with NPC and oesophageal cancer. Except for 2%/2 mm criterion, the average %GPs for all patients undergoing VMAT were acceptable with average rates of 97.11% ± 1.54% and 97.39% ± 1.37% for 2D and 3D 3%/3 mm criteria, respectively. The number of correlations for 3D was higher than that for 2D (21 vs 8). However, the general correlation was still poor for all the analysed metrics (9 out of 26 for 3D 3%/3 mm criterion). The average area under the curve (AUC) of ROCs was 0.66 ± 0.12 and 0.71 ± 0.21 for 2D and 3D evaluations, respectively.

CONCLUSIONS

There is a lack of correlation between %GP and %DE for both 2D and 3D pre-treatment VMAT dosimetric evaluation. DVH-based dose metrics evaluation obtained from 3DVH will provide more useful analysis.

ADVANCES IN KNOWLEDGE

Correlation and sensitivity of %GP with %DE for VMAT QA were studied for the first time.

Dosimetric benefits of IMRT and VMAT in the treatment of middle thoracic esophageal cancer: is the conformal radiotherapy still an alternative option?

The purpose of this study is to investigate the dosimetric differences among conformal radiotherapy (CRT), intensity-modulated radiotherapy (IMRT), and volumetric-modulated radiotherapy (VMAT) in the treatment of middle thoracic esophageal cancer, and determine the most appropriate treatment modality. IMRT and one-arc VMAT plans were generated for eight middle thoracic esophageal cancer patients treated previous with CRT. The planning target volume (PTV) coverage and protections on organs at risk of three planning schemes were compared. All plans have sufficient PTV coverage and no significant differences were observed, except for the conformity and homogeneity. The lung V5, V10, and V13 in CRT were 47.9% ± 6.1%, 36.5% ± 4.6%, and 33.2% ± 4.2%, respectively, which were greatly increased to 78.2% ± 13.7% (p < 0.01), 80.8% ± 14.9% (p < 0.01), 48.4% ± 8.2% (p = 0.05) in IMRT and 58.6% ± 10.5% (p = 0.03), 67.7% ± 14.0% (p < 0.01), and 53.0% ± 10.1% (p < 0.01) in VMAT, respectively. The lung V20 (p = 0.03) in VMAT and the V30 (p = 0.04) in IMRT were lower than those in CRT. Both IMRT and VMAT achieved a better protection on heart. However, the volumes of the healthy tissue outside of PTV irradiated by a low dose were higher for IMRT and VMAT. IMRT and VMAT also had a higher MU, optimization time, and delivery time compared to CRT. In conclusion, all CRT, IMRT, and VMAT plans are able to meet the prescription and there is no clear distinction on PTV coverage. IMRT and VMAT can only decrease the volume of lung and heart receiving a high dose, but at a cost of delivering low dose to more volume of lung and normal tissues. CRT is still a feasible option for middle thoracic esophageal cancer radiotherapy, especially for the cost-effective consideration.