A prediction model for dosimetric-based lung adaptive radiotherapy

Evaluation of dose delivery based on deformed CT using a commercial software for lung cancer

This study employed a commercial software velocity to perform deformable registration and dose calculation on deformed CT images, aiming to assess the accuracy of dose delivery during the radiotherapy for lung cancers. A total of 20 patients with lung cancer were enrolled in this study. Adaptive CT (ACT) was generated by deformed the planning CT (pCT) to the CBCT of initial radiotherapy fraction, followed by contour propagation and dose recalculation. There was not significant difference between volumes of GTV and CTV calculated from the ACT and pCT. However, significant differences in dice similarity coefficient (DSC) and coverage ratio (CR) between GTV and CTV were observed, with lower values for GTV volumes below 15 cc. The mean differences in dose corresponding to 95% of the GTV, GTV-P, CTV, and CTV-P between ACT and pCT were - 0.32%, 4.52%, 2.17%, and 4.71%, respectively. For the dose corresponding to 99%, the discrepancies were - 0.18%, 8.35%, 1.92%, and 24.96%, respectively. These differences in dose primarily appeared at the edges of the target areas. Notably, a significant enhancement of dose corresponding to 1 cc for spinal cord was observed in ACT, compared with pCT. There was no statistical difference in the mean dose of lungs and heart. In general, for lung cancer patients, anatomical motion may result in both CTV and GTV moving outside the original irradiation region. The dose difference within the original target area was small, but the difference in the planning target area was considerable.

Are offline ART decisions for NSCLC impacted by the type of dose calculation algorithm?

Introduction

Decisions for plan-adaptations may be impacted by a transitioning from one dose-calculation algorithm to another. This study examines the impact on dosimetric-triggered offline adaptation in LA-NSCLC in the context of a transition from superposition/convolution dose calculation algorithm (Type-B) to linear Boltzmann equation solver dose calculation algorithms (Type-C).

Materials & Methods

Two dosimetric-triggered offline adaptive treatment workflows are compared in a retrospective planning study on 30 LA-NSCLC patients. One workflow uses a Type-B dose calculation algorithm and the other uses Type-C. Treatment plans were re-calculated on the anatomy of a mid-treatment synthetic-CT utilizing the same algorithm utilized for pre-treatment planning. Assessment for plan-adaptation was evaluated through a decision model based on target coverage and OAR constraint violation. The impact of algorithm during treatment planning was controlled for by recalculating the Type-B plan with Type-C.

Results

In the Type-B approach, 13 patients required adaptation due to OAR-constraint violations, while 15 patients required adaptation in the Type-C approach. For 8 out of 30 cases, the decision to adapt was opposite in both approaches. None of the patients in our dataset encountered CTV-target underdosage that necessitated plan-adaptation. Upon recalculating the Type-B approach with the Type-C algorithm, it was shown that 10 of the original Type-B plans revealed clinically relevant dose reductions (≥3%) on the CTV in their original plans. This re-calculation identified 21 plans in total that required ART.

Discussion

In our study, nearly one-third of the cases would have a different decision for plan-adaption when utilizing Type-C instead of Type-B. There was no substantial increase in the total number of plan-adaptations for LA-NSCLC. However, Type-C is more sensitive to altered anatomy during treatment compared to Type-B. Recalculating Type-B plans with the Type-C algorithm revealed an increase from 13 to 21 cases triggering ART.

Dosimetric comparison of four radiotherapy techniques for stage III non‑small cell lung cancer

The present study was implemented to compare the dosimetric parameters of the target dose coverage and critical structures in the treatment planning of four radiotherapy techniques [namely, three-dimensional conformal radiation therapy (3D-CRT), intensity-modulated radiation therapy (IMRT), hybrid IMRT (h-IMRT) and volumetric-modulated arc therapy (VMAT)] for stage III non-small cell lung cancer (NSCLC) qualified plans for medical physicists, therapists and physicians. A total of 40 patients confirmed to have stage IIIA or IIIB NSCLC were enrolled, and four plans were designed for each patient. The prescription dose to the planning target volume (PTV) was assigned as 60 Gy in 30 fractions. The conformity index (CI), heterogeneity index (HI) and parameters of organs at risk (OARs) were calculated. For the PTV, the CI for VMAT was found to be the highest of all the four techniques (P<0.05), whereas the HI for the h-IMRT technique was found to be the lowest (P<0.05). Concerning the OARs, for the percentage of lung volume receiving a dose >5 Gy (lung V₅), the highest value was obtained with VMAT (P<0.05), whereas for lung V₃₀ and heart V₃₀, the VMAT and IMRT techniques were found to be better compared with 3D-CRT and h-IMRT (P<0.05). For esophagus V₅₀, the maximal dose (D_max) and mean dose for the IMRT technique displayed the best results (P<0.05), and in the case of the spinal cord, the D_max with VMAT showed a significant advantage over the other techniques (P<0.05). The treatment monitor units (MUs) in IMRT were found to be the largest (P<0.05), whereas the treatment time with VMAT was the shortest (P<0.05). For smaller PTVs, VMAT was the technique that provided the optimal dose distribution and sparing of the heart. Compared with 3D-CRT alone, adding 20% IMRT to the 3D-CRT base plan was shown to improve the plan quality, and IMRT and VMAT, as techniques, had better dose coverage and sparing of OARs. Furthermore, for patients in whom the lung V5 could be kept low enough, VMAT potentially offered a good alternative to the technique to IMRT, thereby offering additional possibilities for sparing of other OARs, and decreasing the MUs and treatment time.

Development of Machine-Learning Prediction Programs for Delivering Adaptive Radiation Therapy With Tumor Geometry and Body Shape Changes in Head and Neck Volumetric Modulated Arc Therapy

Purpose

During radiation therapy for head and neck cancer using volumetric modulated arc therapy, excessive dosing or underdosing occurs as a result of the decrease in tumor volume and changes in body weight. Adaptive radiation therapy (ART) is performed when significant changes are observed; however, the decision to implement ART depends on the oncologist's subjective judgment. The purpose of this study was to present objective indicators for ART and develop a program to predict the need for ART.

Methods and Materials

The study included 47 patients in the non-ART group and 21 patients in the ART group with shape changes. Patients who received ART could not be covered with the prescribed radiation therapy dose due to shape changes. For each patient, 1112 6-dimensional lists were created, including the number of irradiations, amount of change in the clinical target volume (CTV), rate of change in CTV, mean oral cavity dose, age, and body mass index. Support vector machine and k-nearest neighbor were used for machine learning. The random number of test data to be extracted varied from 1 to 9, and a mean accuracy score was calculated. These programs could predict the need for ART if the accuracy score was high.

Results

The classification accuracy of the list, including the amount of change in the CTV and rate of change in CTV up to 20 fractions, was 0.963 and 0.967 for support vector machine and k-nearest neighbor, respectively.

Conclusions

This program predicted the need for ART with more than 90% accuracy based on shape changes over time in cone beam computed tomography analysis for up to 20 fractions. This may provide significant support for objective decisions to implement ART based on the amount of change over time during treatment.