Association of lung and heart dose with survival in patients with non-small cell lung cancer underwent volumetric modulated arc therapy

Risk Stratification by Combination of Heart and Lung Dose in Locally Advanced Non-Small-Cell Lung Cancer after Radiotherapy

Background/Objectives: Despite advancements in treatment for patients with unresectable locally advanced non-small cell lung cancer (LA-NSCLC), overall survival (OS) remains poor. The specific effects of varying heart and lung doses on OS in LA-NSCLC patients have not been thoroughly investigated, especially their combined impact on survival. This study aimed to examine the impact on OS of both individual and combined heart and lung doses in patients with LA-NSCLC treated with radiotherapy over a three-year follow-up period. Methods: A total of 120 patients who received definitive radiotherapy for LA-NSCLC (stage III, 92.5%) from January 2015 to January 2020 were retrospectively reviewed. The endpoint in this study was OS. Each patient was followed for a fixed period of three years. Results: Univariate Cox regression analysis showed that OS was significantly related to mean heart dose (MHD, hazard ratio [HR], 3.4 [1.8-6.3]; p < 0.001), pericardium V40 (HR, 3.2 [1.7-6.0]; p < 0.001), and total lung V20 (HR, 2.6 [1.4-5.0]; p = 0.003), and these were independent predictors for worse OS in multivariate analysis. Kaplan-Meier curve analysis with log-rank tests revealed that survival was significantly worse in patients with higher MHD (p < 0.001), pericardium V40 (p < 0.001), and total lung V20 (p = 0.002). Combining MHD and total lung V20, and pericardium V40 and total lung V20 provided enhanced risk stratification for OS (p < 0.001 for both combinations). Conclusions: The combination of heart and lung doses provided enhanced and more detailed risk stratification in prediction of OS for a fixed period of three years in LA-NSCLC patients treated with radiotherapy.

Explainable deep learning-based survival prediction for non-small cell lung cancer patients undergoing radical radiotherapy

BACKGROUND AND PURPOSE

Survival is frequently assessed using Cox proportional hazards (CPH) regression; however, CPH may be too simplistic as it assumes a linear relationship between covariables and the outcome. Alternative, non-linear machine learning (ML)-based approaches, such as random survival forests (RSFs) and, more recently, deep learning (DL) have been proposed; however, these techniques are largely black-box in nature, limiting explainability. We compared CPH, RSF and DL to predict overall survival (OS) of non-small cell lung cancer (NSCLC) patients receiving radiotherapy using pre-treatment covariables. We employed explainable techniques to provide insights into the contribution of each covariable on OS prediction.

MATERIALS AND METHODS

The dataset contained 471 stage I-IV NSCLC patients treated with radiotherapy. We built CPH, RSF and DL OS prediction models using several baseline covariable combinations. 10-fold Monte-Carlo cross-validation was employed with a split of 70%:10%:20% for training, validation and testing, respectively. We primarily evaluated performance using the concordance index (C-index) and integrated Brier score (IBS). Local interpretable model-agnostic explanation (LIME) values, adapted for use in survival analysis, were computed for each model.

RESULTS

The DL method exhibited a significantly improved C-index of 0.670 compared to the CPH and a significantly improved IBS of 0.121 compared to the CPH and RSF approaches. LIME values suggested that, for the DL method, the three most important covariables in OS prediction were stage, administration of chemotherapy and oesophageal mean radiation dose.

CONCLUSION

We show that, using pre-treatment covariables, a DL approach demonstrates superior performance over CPH and RSF for OS prediction and use explainable techniques to provide transparency and interpretability.

Dosimetric comparison of free-breathing versus respiratory motion-managed radiotherapy via four-dimensional computed tomography-based volumetric-modulated arctherapy for lung cancer

PURPOSE

The aim of this study is to use respiratory motion-managed radiotherapy (RT) to reduce side effects and to compare dosimetric factors with free-breathing planning in patients with lung cancer.

MATERIALS AND METHODS

Simulation images were obtained in 10 respiratory phases with free breathing using four-dimensional computed tomography (4D-CT) scanner. Planning target volume (PTV) was created with 5mm margins in each direction of the internal target volume delineated using the maximum intensity projection. A volumetric arc treatment (VMAT) plan was created so that the prescribed dose would cover 98% of the PTV. Target volumes for the free-breathing VMAT plan were created according to ICRU Reports 62 and the same prescribed dose was used.

RESULTS

Patients were evaluated during January 2020. Median 63Gy (59.4-64) RT was administered. Median PTV volumes were 173.53 and 494.50cm3 (P=0.008) and dose covering 95% of PTV volume was 62.97 and 60.51Gy (P=0.13) in 4D-CT based and free-breathing VMAT plans, respectively. The mean and V50 heart dose was 6.03Gy (vs. 10.36Gy, P=0.043) and 8.2% (vs. 33.9%, P=0.007), and significantly lower in 4D-CT based VMAT plans and there was also found a non-significant reduction for other risky organ doses.

CONCLUSION

Ten patients treated with respiratory motion-managed RT with 4D-CT based VMAT technique. It was observed that PTV did not increase, the target was covered with 95% accuracy, and with statistical significance in heart doses, all risky organ doses were found to be less.

Predictors of high-grade radiation pneumonitis following radiochemotherapy for locally advanced non-small cell lung cancer: analysis of clinical, radiographic and radiotherapy-related factors

Purpose:

In this study, the relation between radiation pneumonitis (RP) and a wide spectrum of clinical, radiographic and treatment-related factors was investigated. As scoring of low-grade RP can be subjective, RP grade ≥3 (RP ≥ G3) was chosen as a more objective and clinically significant endpoint for this study.

Methods and Materials:

105 consecutive patients with locally advanced non-small cell lung cancer underwent conventionally fractionated radio-(chemo-)therapy to a median dose of 64 Gy. A retrospective analysis of 25 clinical (gender, race, pulmonary function, diabetes, statin use, smoking history), radiographic (emphysema, interstitial lung disease) and radiotherapy dose- and technique-related factors was performed to identify predictors of RP ≥ G3. Following testing of all variables for statistical association with RP using univariate analysis (UVA), a forward selection algorithm was implemented for building a multivariate predictive model (MVA) with limited sample size.

Results:

Median follow-up of surviving patients was 33 months (9–132 months). RP ≥ G3 was diagnosed in 10/105 (9·5%) patients. Median survival was 28·5 months. On UVA, predictors for RP ≥ G3 were diabetes, lower lobe location, planning target volume, volumetric modulated arc therapy (VMAT), lung V5 Gy (%), lung Vspared5 Gy (mL), lung V20 Gy (%) and heart V5 Gy (% and mL). On MVA, VMAT was the only significant predictor for RP ≥ G3 (p = 0·042). Lung V5 Gy and lung V20 Gy were borderline significant for RP ≥ G3. Patients with RP ≥ 3 had a median survival of 10 months compared to 29·5 months with RP < G3 (p = 0·02).

Conclusions:

In this study, VMAT was the only factor that was significantly correlated with RP ≥ G3. Avoiding RP ≥ G3 is important as a toxicity per se and as a risk factor for poor survival. To reduce RP, caution needs to be taken to reduce low-dose lung volumes in addition to other well-established dose constraints.

Dosimetric evaluation of SBRT treatment plans of non-central lung tumours: clinical experience

Objectives:

Lung cancer is the most commonly diagnosed cancer in Canada and the leading cause of cancer-related mortality in both men and women in North America. Surgery is usually the primary treatment option for early-stage non-small cell lung cancer (NSCLC). However, for patients who may not be suitable candidates for surgery, stereotactic body radiation therapy (SBRT) is an alternative method of treatment. SBRT has proven to be an effective technique for treating NSCLC patients by focally administering high radiation dose to the tumour with acceptable risk of toxicity to surrounding healthy tissues. The goal of this comprehensive retrospective dosimetric study is to compare the dosimetric parameters between three-dimensional conformal radiation therapy (3DCRT) and volumetric-modulated arc therapy (VMAT) lung SBRT treatment plans for two prescription doses.

Methods:

We retrospectively analysed and compared lung SBRT treatment plans of 263 patients treated with either a 3DCRT non-coplanar or with 2–3 VMAT arcs technique at 48 Gy in 4 fractions (48 Gy/4) or 50 Gy in 5 fractions (50 Gy/5) prescribed to the planning target volume (PTV), typically encompassing the 80% isodose volume. All patients were treated on either a Varian 21EX or TrueBeam linear accelerator using 6-MV or 10-MV photon beams.

Results:

The mean PTV V95% and V100% for treatment plans at 48 Gy/4 are 99·4 ± 0·6% and 96·0 ± 1·0%, respectively, for 3DCRT and 99·7 ± 0·4% and 96·4 ± 3·4%, respectively, for VMAT. The corresponding mean PTV V95% and V100% at 50 Gy/5 are 99·0 ± 1·4% and 95·5 ± 2·5% for 3DCRT and 99·5 ± 0·8% and 96·1 ± 1·6% for VMAT. The CIRI and HI5/95 for the PTV at 48 Gy/4 are 1·1 ± 0·1 and 1·2 ± 0·0 for 3DCRT and 1·0 ± 0·1 and 1·2 ± 0·0 for VMAT. The corresponding CIRI and HI5/95 at 50 Gy/5 are 1·1 ± 0·1 and 1·3 ± 0·1 for 3DCRT and 1·0 ± 0·1 and 1·2 ± 0·0 for VMAT. The mean R50% and D2cm at 48 Gy/4 are 5·0 ± 0·8 and 61·2 ± 7·0% for 3DCRT and 4·9 ± 0·8 and 57·8 ± 7·9% for VMAT. The corresponding R50% and D2cm at 50 Gy/5 are 4·7 ± 0·5 and 65·5 ± 9·4% for 3DCRT and 4·7 ± 0·7 and 60·0 ± 7·2% for VMAT.

Conclusion:

The use of 3DCRT or VMAT technique for lung SBRT is an efficient and reliable method for achieving dose conformity, rapid dose fall-off and minimising doses to the organs at risk. The VMAT technique resulted in improved dose conformity, rapid dose fall-off from the PTV compared to 3DCRT, although the magnitude may not be clinically significant.