ESTRO 2025 - Abstract Book

S3390

Physics - Machine learning models and clinical applications

ESTRO 2025

using volumetric modulated arc therapy (VMAT) were analyzed using the modulation complexity score (MCS) and the dynamic log-files generated by the linac. Predicted and measured fluences were compared using γ -analysis in terms of mean γ - values (γ mean ) and γ - pass rate (γ % ) at the 2%(local)/2mm criterion. Three unsupervised clustering algorithms, including Agglomerative Hierarchical Clustering (AHC), K-Means (KM) and Gaussian Mixture Models (GMM), were implemented to investigate the existence of natural groupings or clusters based on plan complexity. Results: For all clustering algorithms, the silhouette scores and the dendrogram analysis provided an optimal number of clusters equal to three. The GMM clustered 65 arcs (4.9% of total arcs) into cluster 1 (blue circles) with mean values of g % , g mean and MCS of 76.7%, 0.85 and 0.112, respectively. 916 arcs (68.9% of total arcs) were grouped into cluster 2 (green circles) with mean values of g % , g mean and MCS of 86.5%, 0.58 and 0.209, respectively. Lastly, 348 arcs (26.2% of total arcs) were grouped into cluster 3 (red circles) with mean values of g % , g mean and MCS of 92.9%, 0.40 and 0.359, respectively. Cluster 1 was associated with overmodulated plans, providing a warning MCS cutoff value of 0.145 for prompt replanning. Similarly, cluster 3 was associated with PSQA optimality, providing a MCS cutoff value of 0.278, beyond which plans have an a-priori very high QA pass results and can avoid the pretreatment dosimetric verification. Head-and-neck cases reported the higher (12.0%) and the lower (4.0%) classification rates in clusters 1 and 3, respectively, suggesting a major increase of the complexity score for these plans. In Figure 1, each point represents one VMAT arc with the respective g%, gmean and MCS metric, coloured based on the assigned cluster.

Conclusion: This study demonstrated the potential of clustering analysis to unravel hidden patterns of plan complexity in dosimetric quality assurance of VMAT treatments. The results suggested that a three-clusters classification scheme has a true basis in plan complexity, supporting the hypothesis that the MCS metric strongly underlies PSQA results.

Keywords: Unsupervised; Clustering; Complexity