Self-consistent tumor control probability and normal tissue complication probability models based on generalized EUDa)

Predicting radiation pneumonitis in lung cancer: a EUD-based machine learning approach for volumetric modulated arc therapy patients

Purpose

This study aims to develop an optimal machine learning model that uses lung equivalent uniform dose (lung EUD to predict radiation pneumonitis (RP) occurrence in lung cancer patients treated with volumetric modulated arc therapy (VMAT).

Methods

We analyzed a cohort of 77 patients diagnosed with locally advanced squamous cell lung cancer (LASCLC) receiving concurrent chemoradiotherapy with VMAT. Patients were categorized based on the onset of grade II or higher radiation pneumonitis (RP 2+). Dose volume histogram data, extracted from the treatment planning system, were used to compute the lung EUD values for both groups using a specialized numerical analysis code. We identified the parameter α, representing the most significant relative difference in lung EUD between the two groups. The predictive potential of variables for RP2+, including physical dose metrics, lung EUD, normal tissue complication probability (NTCP) from the Lyman-Kutcher-Burman (LKB) model, and lung EUD-calibrated NTCP for affected and whole lung, underwent both univariate and multivariate analyses. Relevant variables were then employed as inputs for machine learning models: multiple logistic regression (MLR), support vector machine (SVM), decision tree (DT), and K-nearest neighbor (KNN). Each model's performance was gauged using the area under the curve (AUC), determining the best-performing model.

Results

The optimal α-value for lung EUD was 0.3, maximizing the relative lung EUD difference between the RP 2+ and non-RP 2+ groups. A strong correlation coefficient of 0.929 (P< 0.01) was observed between lung EUD (α = 0.3) and physical dose metrics. When examining predictive capabilities, lung EUD-based NTCP for the affected lung (AUC: 0.862) and whole lung (AUC: 0.815) surpassed LKB-based NTCP for the respective lungs. The decision tree (DT) model using lung EUD-based predictors emerged as the superior model, achieving an AUC of 0.98 in both training and validation datasets.

Discussions

The likelihood of developing RP 2+ has shown a significant correlation with the advancements in RT technology. From traditional 3-D conformal RT, lung cancer treatment methodologies have transitioned to sophisticated techniques like static IMRT. Accurately deriving such a dose-effect relationship through NTCP modeling of RP incidence is statistically challenging due to the increased number of degrees-of-freedom. To the best of our knowledge, many studies have not clarified the rationale behind setting the α-value to 0.99 or 1, despite the closely aligned calculated lung EUD and lung mean dose MLD. Perfect independence among variables is rarely achievable in real-world scenarios. Four prominent machine learning algorithms were used to devise our prediction models. The inclusion of lung EUD-based factors substantially enhanced their predictive performance for RP 2+. Our results advocate for the decision tree model with lung EUD-based predictors as the optimal prediction tool for VMAT-treated lung cancer patients. Which could replace conventional dosimetric parameters, potentially simplifying complex neural network structures in prediction models.

Dosimetric analysis of radiation-induced brainstem necrosis for nasopharyngeal carcinoma treated with IMRT

Background

Radiation-induced brainstem necrosis (RIBN) is a late life-threatening complication that can appear after treatment in patients with nasopharyngeal carcinoma (NPC). However, the relationship between RIBN and radiation dose is not still well-defined.

Methods

During January 2013 and December 2017, a total of 1063 patients with NPC were treated at Sichuan cancer hospital with IMRT. A total of 479 patients were eligible for dosimetric analysis. Dosimetric parameters of the RIBN, D_max(the maximum dose), D_0.1c (maximum average dose delivered to a 0.1-cc volume), D_1cc, D_2cc, D_3cc, D_5cc, D_10cc and D_mean (mean does) were evaluated and recorded. ROC curve was used to analyze the area under curve (AUC) and cutoff points. Logistic regression for screening dose-volume parameter and logistic dose response model were used to predict the incidence of brainstem necrosis.

Results

Among the 479 patients with NPC, 6 patients were diagnosed with RIBN, the incidence of RIBN was 1.25% (6/479), and the median time to RIBN after treatment was 28.5 months (range 18–48 months). The dose of the brainstem in patients with RIBN were higher than that in patients without necrosis. ROC curve showed that the area under the curve (AUC) of D_max was the largest (0.987). Moreover, logistic stepwise regression indicated that D_max was the most important dose factor. The RIBN incidence at 5% over 5 years (TD_5/5) and 50% incidence over 5 years (TD_50/5) was 69.59 Gy and76.45 Gy, respectively.

Conclusions

Brainstem necrosis is associated with high dose irritation. D_max is the most significant predictive dosimetric factor for RIBN. D_max of brainstem should be considered as the dose limitation parameter. We suggest that the limitation dose for brainstem was D_max < 69.59 Gy.

Dose cluster model parameterization of the parotid gland in irradiation of head and neck cancer

To explore the parotid normal tissue complication probability (NTCP) modeling with percolation-based dose clusters for head-and-neck patients receiving concomitant chemotherapy and radiation therapy. Cluster models incorporating the spatial dose distribution in the parotid gland were developed to evaluate the radiation induced complication. Cluster metrics including the mean cluster size (NMCS) and the largest cluster size both normalized by the gland volume (NSLC) were evaluated and scrutinized against the benchmark NTCP. Two fitting strategies to the Lyman-Kutcher-Burman (LKB) model using the maximum likelihood method were devised: the volume parameter n fixed at 1.0 (mean dose model) and unrestricted (full LKB model). The fitted parameters TD50 and m were assessed with the LKB NTCP models with the available xerostomia data. NSLC was a better metric than NMCS with reference to the LKB model and strong correlation (r ~ 0.95) was observed between NTCP and NSLC. The mean dose model returned the parameter TD50 (39.9 Gy) and m (0.4) from the NSLC of threshold dose at around 40 Gy. Drastically different TD50 and m values were obtained from the fittings via the full LKB model, where the threshold dose would be near 27 Gy. Bootstrapping analyses further confirmed the fitting outcomes. Strong correlation with the traditional NTCP models revealed that the cluster model could achieve what NTCP models attain and may offer additional information. Parameterization of the model indicated that the model could have different predictions from current clinical recommendations. Further investigation using toxicity data is under way to validate the cluster model.

EQUIVALENT UNIFORM DOSE SENSITIVITY TO CHANGES IN ABSORBED DOSE DISTRIBUTION

Treatment planning in external beam radiation therapy (EBRT) utilizes dose volume histograms (DVHs) as optimization and evaluation tools. They present the fraction of planning target volume (PTV) receiving more than a given absorbed dose, against the absorbed dose values, and a number of radiobiological indices can be computed with their help. Equivalent uniform dose (EUD) is the absorbed dose that, uniformly imparted, would yield the same biological effect on a tumor as the dose distribution described by the DVH. Uncertainty and missing information can affect the dose distribution, therefore DVHs can be modeled as samples from a set of possible outcomes. This work studies the sensitivity of the EUD index when a small change in absorbed dose distribution takes place. EUD is treated as a functional on the set of DVHs. Defining a Lévy distance on this set and using a suitable expansion of the functional, a very simple expression for a bound on the variation of EUD when the dose distribution changes is found. This bound is easily interpreted in terms of standard treatment planning practice.