Single-Iso-Multiple-Targets (SIMT) Radiosurgery Plan Quality Control via a Novel Deep Neural Network with Spherical Convolutions

Abstract Background and Purpose Accurate prediction of normal brain dosimetric parameters is crucial for the quality control of single-center multi-target (SIMT) stereotactic radiosurgery (SRS) treatment planning. Currently, the clinical SIMT SRS planning process suffer from unreliable estimations of normal brain doses, leading to frequent plan revisions that are both time-consuming and labor-intensive. This study aimed to develop a spherical coordinate-defined deep learning model to predict dose to normal brain for SIMT SRS treatment planning. Methods By encapsulating the human brain within a sphere, 3D volumetric data of PTVs can be projected onto this geometry as a 2D spherical representation (in azimuthal and polar angles). A novel deep learning model (SCNN) was developed based on spherical convolution to predict brain dosimetric evaluators from spherical representation. Utilizing 106 SIMT cases, the model was trained to predict brain V50%, V60%, and V66.7%, corresponding to V10Gy and V12Gy, as key dosimetric indicators. The model prediction performance was evaluated using the coefficient of fitting determination (R2), mean absolute error (MAE), and mean percentage error (MPE). Results The SCNN accurately predicted normal brain dosimetric values from the modeled spherical PTV representation, with R2 scores of 0.92 ± 0.05/0.94 ± 0.10/0.93 ± 0.09 for V50%/V60%/V66.7%, respectively. MAEs values were 1.94 ± 1.61cc/1.23 ± 0.98cc/1.13 ± 0.99cc, and MPEs were 19.79 ± 20.36%/20.79 ± 21.07%/21.15 ± 22.24%, respectively. Conclusions The deep learning model provides treatment planners with accurate prediction of dose to normal brain, enabling improved consistency in treatment planning quality. This method can be extended to other brain-related analyses as an efficient data dimension reduction method.