AUTHOR=Guberina Nika , Pöttgen Christoph , Santiago Alina , Levegrün Sabine , Qamhiyeh Sima , Ringbaek Toke Printz , Guberina Maja , Lübcke Wolfgang , Indenkämpen Frank , Stuschke Martin 

TITLE=Machine-learning-based prediction of the effectiveness of the delivered dose by exhale-gated radiotherapy for locally advanced lung cancer: The additional value of geometric over dosimetric parameters alone

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2023

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.870432

DOI=10.3389/fonc.2022.870432

ISSN=2234-943X

ABSTRACT=Purpose
To assess interfraction stability of effectiveness of the delivered dose distribution by exhale-gated VMAT or IMRT for locally advanced NSCLC and to determine dominant prognostic dosimetric or geometric factors.

Methods
Clinical target volume (CTVPlan) from the planning-CT was deformed to the exhale-gated daily CBCT-scans to determine CTVi, treated by the respective dose-fraction. The equivalent-uniform-dose of the CTVi was determined by the power-law (gEUDi) and cell-survival-model (EUDiSF) as effectiveness-measure for the delivered dose-distribution. Following prognostic-factors were analyzed:(I) minimum dose within the CTVi (Dmin_i), (II) the Hausdorff-distance (HDDi) between CTVi and CTVPlan, (III) doses and deformations at the point in the CTVPlan at which the global-minimum-dose over all fractions per patient occurs (PDminglobal), and (IV) deformations at the point over all CTVi-margins per patient with the largest Hausdorff-distance (HDPworst). The prognostic value and generalizability of the prognostic-factors were examined using cross-validated random-forest or multilayer-perceptron-neural-network-(MLP)-classifiers.

Results 
Altogether 218 dose-fractions (10 patients) were evaluated. There was a significant inter-patient heterogeneity between the distributions of the normalized gEUDi-values (p<0.0001,Kruskal-Wallis-tests). The accumulated gEUD over all fractions per patient fell in the narrow range between 1.004-1.023-times of the prescribed-dose, near by the median of the gEUDi-values per patient. Normalized Dmin>60% was associated with predicted gEUD-values above 95%. Dmin had the highest importance for predicting the gEUD over all analyzed prognostic-parameters by out of bag-loss-reduction using the random-forest-procedure. The cross-validated random-forest-classifier based on Dmin as the sole input had the largest Pearson-correlation-coefficient (R=0.897) in comparison to classifiers using additional input-variables. The neural-network performed better than the random-forest-classifier and the gEUD-values predicted by the MLP-classifier with Dmin as the sole input were correlated with the gEUD-values characterized by R=0.933 (95%;CI:0.913–0.948). The performance of the full MLP-model with all geometric-input parameters was slightly better (R=0.952) than that based on Dmin (p=0.0034,Z-test).

Conclusion
The accumulated dose-distributions over the treatment-series were robust against inter-fraction CTV-deformations using exhale-gating and online image-guidance. Dmin was the most important parameter for gEUD-prediction for a single fraction. All other parameters did not lead to a markedly improved generalizable prediction. Dosimetric-information, especially location and value of Dmin within the CTVi are vital information for image-guided radiation-treatment.